DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
The following FINAL Office Action is in response to Applicant’s communication filed 05/13/2026 regarding Application 19/004/441.
Status of Claim(s)
Claim(s) 1-20 is/are currently pending and are rejected as follows.
Response to Arguments – 103 Rejection
Applicant’s arguments in regards to the previously applied prior art have been fully considered but are not deemed persuasive.
Applicant argues that the combined art of Bamal in view of Ponce De Leon fail to disclose, as specified, the recited limitations of “in response to a request from a client device, generating a user account”, “causing a display of an intake interface on a the client device”, “causing generation of a prompt comprising predetermined prompt language selected”, and “causing generation of a prompt comprising…prompt text including a commend to generate new issue data…and a formatting command.”
Examiner does not find this argument persuasive. With regards to the limitations of requesting to generate a user account and displaying an intake interface on a client device, the art of Bamal discloses in Paragraph 53, “Authorized users can browse and view both open and closed work orders via user interface component,” and prior makes mention in Paragraph 46 “System…made accessible to users having suitable authorization credentials,” and further prior in Paragraph 40 “User interface component can be configured to generate user interface displays that receive user input and render output to the user in any suitable format…Input data that can be received via user interface component can include, but is not limited to, work order data…”. These actions describe acts that read on a user’s ability to have credentials that when utilized, can allow a user account to be generated that allows for access to the various work order information, and further includes additional interfaces that allow for intake on the display of an intake interface with selectable options for generating work orders. The act of logging on, or utilizing credentials would be deemed by one or ordinary skill in the art to be equivalent to requesting the generation and displaying of a user account, and is itself a request to access various interfaces available for display. Therefor the art of Bamal teaches the recited limitations of “in response to a request from a client device, generating a user account” and “causing a display of an intake interface on a the client device” as currently written in Applicant’s claims.
With regard to the recited limitations of “causing generation of a prompt comprising predetermined prompt language selected”, and “causing generation of a prompt comprising…prompt text including a commend to generate new issue data…and a formatting command,” Bamal discloses the ability to “implement prompt engineering functionality using associated trained models 312 trained with various types of training data, and can use these prompt engineering features”, “Responses 606 prompted from the generative AI model 308 can also be used by the work order generation component 210 to generate natural language content to be included in the corresponding work order”, and “Returning to FIG. 6, during the asset monitoring process, the analysis component 212 can formulate and submits prompts 604 to the generative AI model 308 designed to obtain responses 606 that can assist with monitoring the performance of industrial assets for risk conditions, formulating maintenance strategies for mitigating the risk conditions, or generating content of a work order 310. The analysis component 212 can generate these prompts 604 based on a current operating context of one or more industrial assets being monitored (as determined from real-time or historical asset data 306) as well as the training data 602 encoded in the trained models 312,” Paragraphs 56, 59, and 61 respectively. These cited portions would be deemed equivalent to one of ordinary skill in the art of Bamal teaching generating a prompt using predetermined prompt language (an example given in Paragraph 102 “…system can support industry-specific prompt engineering features that can formulate suitable prompts for submission…based on a user’s natural language request.”). These sections of Bamal also include action that would be deemed equivalent to Applicant’s cited portions of allowing the prompt to be used as part of the creation of a new work order (issue tracking) and a format command equivalent in Paragraph 106 “…with language-specific compositional or syntax information obtained as responses 606 from the generative AI model 308 to formulate a natural language response 1102 to the user's query 1106,” and Paragraph 107, “the initial request can specify the asset of interest, a type of maintenance to be performed, a technician to be assigned to the maintenance, or other such information…determine the type of information or service being requested, and refine and contextualize the initial query 1106 in a manner expected to assist the trained models 312 and the generative AI model 308 to accurately generate a suitable work order 310 or a response 1102 to the user's question.”. Therefore the prior art of Bamal in combination with Ponce De Leon continue to read on Applicant’s claims as currently presented and the previously applied 103 rejection remains applicable. Further elaboration and recitations are disclosed in the prior art rejection below.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 1-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Bamal (US 2026/030568 A1) in view of Ponce De Leon (US 8,400,467 B1)
Claim(s) 1 and 16 –
Bamal discloses the following:
A backend application operating on one or more servers coupled to a frontend application operating on a client device; (Bamal: Paragraph 23, “As used in this application, the terms “component,” “system,” “platform,” “layer,” “controller,” “terminal,” “station,” “node,” “interface” are intended to refer to a computer-related entity or an entity related to, or that is part of, an operational apparatus with one or more specific functionalities, wherein such entities can be either hardware, a combination of hardware and software, software, or software in execution. For example, a component can be, but is not limited to being, a process running on a processor, a processor, a hard disk drive, multiple storage drives (of optical or magnetic storage medium) including affixed (e.g., screwed or bolted) or removable affixed solid-state storage drives; an object; an executable; a thread of execution; a computer-executable program, and/or a computer. By way of illustration, both an application running on a server and the server can be a component. One or more components can reside within a process and/or thread of execution, and a component can be localized on one computer and/or distributed between two or more computers. Also, components as described herein can execute from various computer readable storage media having various data structures stored thereon. The components may communicate via local and/or remote processes such as in accordance with a signal having one or more data packets (e.g., data from one component interacting with another component in a local system, distributed system, and/or across a network such as the Internet with other systems via the signal). As another example, a component can be an apparatus with specific functionality provided by mechanical parts operated by electric or electronic circuitry which is operated by a software or a firmware application executed by a processor, wherein the processor can be internal or external to the apparatus and executes at least a part of the software or firmware application. As yet another example, a component can be an apparatus that provides specific functionality through electronic components without mechanical parts, the electronic components can include a processor therein to execute software or firmware that provides at least in part the functionality of the electronic components. As further yet another example, interface(s) can include input/output (I/O) components as well as associated processor, application, or Application Programming Interface (API) components. While the foregoing examples are directed to aspects of a component, the exemplified aspects or features also apply to a system, platform, interface, layer, controller, terminal, and the like.”; Paragraph 40, “User interface component 204 can be configured to generate user interface displays that receive user input and render output to the user in any suitable format (e.g., visual, audio, tactile, etc.). In some embodiments, user interface component 204 can render these interface displays on a client device (e.g., a laptop computer, tablet computer, smart phone, etc.) that is communicatively connected to the work order management system 202 (e.g., via a hardwired or wireless connection). Input data that can be received via user interface component 204 can include, but is not limited to, work order data (e.g., work order data field entries), user interface navigation input, natural language chat inputs (e.g., work order generation commands, queries regarding existing work orders or asset risks, etc.), or other such input data. Output data rendered by user interface component 204 can include, but is not limited to, information regarding closed and open work orders, risk levels associated with respective work orders, estimated costs associated with high-risk work orders, or other such output data.”; Paragraph 46, “FIG. 3 is a diagram illustrating an example architecture for automatically generating work orders 310 based on analysis of real-time or historical industrial asset performance. Work order management system 202 can be implemented on any suitable platform that allows the system 202 to be accessed via client devices (e.g., desktop computers, laptop computers, smart phones, tablet computers, wearable computing devices, etc.) and that permits the system 202 to access operational and status data generated by industrial assets within a plant facility. For example, system 202 can be installed and executed on an on-premise server device on a plant or office network of an industrial facility. Alternatively, system 202 can be executed on a cloud platform as a set of cloud-based services, allowing users at different industrial facilities to access the system 202, view work orders, receive notifications generated by the system 202, or retrieve work order analysis results. System 202 can also be executed on a public network such as the internet and made accessible to users having suitable authorization credentials. In such embodiments, the system 202 can maintain work orders for different industrial enterprises in a segregated manner, such that employees of a given industrial enterprise can only access work orders and associated analysis results associated with that enterprise. In the example depicted in FIG. 3, work order management system resides and executes on a cloud platform.”; Paragraph 53, “Authorized users can browse and view both open and closed work orders 310 via user interface component 204. FIG. 4 is an example work order display 402 that can be rendered on a client device by the user interface component 204. When a user selects a work order 310 via interaction with the work order system's primary user interface, the user interface component 204 can render a work order display 402 and populate the display 402 with information about the work order. In the example depicted in FIG. 4, the work order display 402 comprises a work order identifier 414 that uniquely identifies the selected work order 310, a section 408 that displays general information about the work order 310 (e.g. the open or closed status, a type of maintenance to be performed, a priority, an identity of the asset on which the maintenance task is to be performed, a suggested completion date for the maintenance, a name of a project with which the maintenance task is associated, etc.), and a navigation bar 406 comprising selectable controls corresponding to respective different categories of additional information that can be viewed.”)
in response to a request from a client device, generating a user account at the issue tracking platform; (Bamal: Paragraph 35, “Industrial facilities typically house and operate many industrial assets, machines, or equipment. Many of these assets require regular proactive maintenance to ensure continued optimal operation, in addition to unplanned repair operations to address unexpected downtime events, such as machine malfunctions. To manage the large number of maintenance operations carried out at a given industrial enterprise, work order management systems can be used to initiate work orders for new maintenance operations to be performed, to track the statuses of these work orders, and to keep a record of maintenance operations performed within the plant. In a typical scenario for addressing a reactive maintenance concern, when metered or observed asset performance indicators—e.g., vibration values, temperature values, product counts, a machine downtime occurrence, etc.—indicate a possible performance concern requiring investigation or maintenance, a maintenance technician or manager creates and submits a work order for the maintenance operation to the work order management system. Maintenance personnel are then assigned the task of performing the maintenance task or investigation. As the work is carried out, maintenance actions performed in connection with the schedule maintenance task are submitted and recorded with the work order, which remains open as its corresponding maintenance task is performed. The work order is then closed once the task is completed. A similar workflow can be used to schedule regular proactive or preventative maintenance on industrial assets.”; Paragraph 37, “To address these and other issues, one or more embodiments described herein provide a work order management system that automates the process of scheduling maintenance tasks and generating corresponding work orders via analysis of monitored data generated by the industrial assets. In one or more embodiments, the work order management system can monitor control, status, and/or operational data from industrial devices on the plant floor, and initiate creation of work orders based on a determination that the monitored industrial data indicates a current or predicted performance risk requiring investigation or maintenance. In some embodiments, the work order management system can leverage generative artificial intelligence (AI) or other types of AI in connection with determining when and how to schedule a maintenance task intended to mitigate asset risk. The system can also factor various types of contextual information when determining whether to create and schedule a work order, such as the cost of operator or maintenance time, scheduled plant downtimes, environmental factors (e.g., humidity), time of year, supplier issues, and other considerations.”; Paragraph 43, “Analysis component 212 can be configured to perform analysis on real-time or historical asset performance data, data obtained from an MES system or a similar high-level enterprise tracking system, contextual information, or other such data to determine when maintenance tasks are to be scheduled, what those maintenance tasks include, and which technicians are to be assigned the tasks. In some embodiments, the analysis component 212 can apply AI or generative AI-assisted analysis to this data in connection with determining when and how maintenance tasks should be scheduled and corresponding work orders generated.”; Paragraph 46, “FIG. 3 is a diagram illustrating an example architecture for automatically generating work orders 310 based on analysis of real-time or historical industrial asset performance. Work order management system 202 can be implemented on any suitable platform that allows the system 202 to be accessed via client devices (e.g., desktop computers, laptop computers, smart phones, tablet computers, wearable computing devices, etc.) and that permits the system 202 to access operational and status data generated by industrial assets within a plant facility. For example, system 202 can be installed and executed on an on-premise server device on a plant or office network of an industrial facility. Alternatively, system 202 can be executed on a cloud platform as a set of cloud-based services, allowing users at different industrial facilities to access the system 202, view work orders, receive notifications generated by the system 202, or retrieve work order analysis results. System 202 can also be executed on a public network such as the internet and made accessible to users having suitable authorization credentials. In such embodiments, the system 202 can maintain work orders for different industrial enterprises in a segregated manner, such that employees of a given industrial enterprise can only access work orders and associated analysis results associated with that enterprise. In the example depicted in FIG. 3, work order management system resides and executes on a cloud platform.”; Paragraph 53, “Authorized users can browse and view both open and closed work orders 310 via user interface component 204. FIG. 4 is an example work order display 402 that can be rendered on a client device by the user interface component 204. When a user selects a work order 310 via interaction with the work order system's primary user interface, the user interface component 204 can render a work order display 402 and populate the display 402 with information about the work order. In the example depicted in FIG. 4, the work order display 402 comprises a work order identifier 414 that uniquely identifies the selected work order 310, a section 408 that displays general information about the work order 310 (e.g. the open or closed status, a type of maintenance to be performed, a priority, an identity of the asset on which the maintenance task is to be performed, a suggested completion date for the maintenance, a name of a project with which the maintenance task is associated, etc.), and a navigation bar 406 comprising selectable controls corresponding to respective different categories of additional information that can be viewed.”)
in response to generating the user account, causing display of an intake interface on the client device; (Bamal: Paragraph 40, “User interface component 204 can be configured to generate user interface displays that receive user input and render output to the user in any suitable format (e.g., visual, audio, tactile, etc.). In some embodiments, user interface component 204 can render these interface displays on a client device (e.g., a laptop computer, tablet computer, smart phone, etc.) that is communicatively connected to the work order management system 202 (e.g., via a hardwired or wireless connection). Input data that can be received via user interface component 204 can include, but is not limited to, work order data (e.g., work order data field entries), user interface navigation input, natural language chat inputs (e.g., work order generation commands, queries regarding existing work orders or asset risks, etc.), or other such input data. Output data rendered by user interface component 204 can include, but is not limited to, information regarding closed and open work orders, risk levels associated with respective work orders, estimated costs associated with high-risk work orders, or other such output data.”; Paragraph 43, “Analysis component 212 can be configured to perform analysis on real-time or historical asset performance data, data obtained from an MES system or a similar high-level enterprise tracking system, contextual information, or other such data to determine when maintenance tasks are to be scheduled, what those maintenance tasks include, and which technicians are to be assigned the tasks. In some embodiments, the analysis component 212 can apply AI or generative AI-assisted analysis to this data in connection with determining when and how maintenance tasks should be scheduled and corresponding work orders generated.”; Paragraph 46, “FIG. 3 is a diagram illustrating an example architecture for automatically generating work orders 310 based on analysis of real-time or historical industrial asset performance. Work order management system 202 can be implemented on any suitable platform that allows the system 202 to be accessed via client devices (e.g., desktop computers, laptop computers, smart phones, tablet computers, wearable computing devices, etc.) and that permits the system 202 to access operational and status data generated by industrial assets within a plant facility. For example, system 202 can be installed and executed on an on-premise server device on a plant or office network of an industrial facility. Alternatively, system 202 can be executed on a cloud platform as a set of cloud-based services, allowing users at different industrial facilities to access the system 202, view work orders, receive notifications generated by the system 202, or retrieve work order analysis results. System 202 can also be executed on a public network such as the internet and made accessible to users having suitable authorization credentials. In such embodiments, the system 202 can maintain work orders for different industrial enterprises in a segregated manner, such that employees of a given industrial enterprise can only access work orders and associated analysis results associated with that enterprise. In the example depicted in FIG. 3, work order management system resides and executes on a cloud platform.”; Paragraph 52, “A work order 310 generated by the work order generation component 210 can contain information about the maintenance task to be performed, including but not limited to an identity of the industrial asset or machine for which maintenance is required, an aspect of the industrial asset that requires attention, a type of the maintenance to be performed, an estimated number of hours to be spent on the maintenance task, an estimated number of personnel to be assigned to the task, a description of the task, or other such information. The work order 310 is initially scheduled in the system 202 as an open work order 310 (that is, the system 202 stores the work order 310 as work order data in memory 222 and assigns an “Open” status to the work order 310) and remains open until completion of its associated maintenance tasks, at which time the system 202 assigns a “Closed” status to the work order 310.”; Paragraph 53, “Authorized users can browse and view both open and closed work orders 310 via user interface component 204. FIG. 4 is an example work order display 402 that can be rendered on a client device by the user interface component 204. When a user selects a work order 310 via interaction with the work order system's primary user interface, the user interface component 204 can render a work order display 402 and populate the display 402 with information about the work order. In the example depicted in FIG. 4, the work order display 402 comprises a work order identifier 414 that uniquely identifies the selected work order 310, a section 408 that displays general information about the work order 310 (e.g. the open or closed status, a type of maintenance to be performed, a priority, an identity of the asset on which the maintenance task is to be performed, a suggested completion date for the maintenance, a name of a project with which the maintenance task is associated, etc.), and a navigation bar 406 comprising selectable controls corresponding to respective different categories of additional information that can be viewed.”; Paragraph 111, “These generative AI-assisted techniques can allow technicians to easily generate work orders 310 using natural language text or verbal input to the system 202 (e.g., via interfaces rendered on the technicians' client devices and delivered by the user interface component 204) as the technicians are performing other tasks (e.g., upon discovering a new maintenance concern during investigation of a known issue). These approaches can also be used to easily and intuitively annotate or edit work orders using natural language voice or text input.”)
in response to receiving user input at the intake interface, analyzing the user input to determine a project type classifier; (Bamal: Paragraph 40, “User interface component 204 can be configured to generate user interface displays that receive user input and render output to the user in any suitable format (e.g., visual, audio, tactile, etc.). In some embodiments, user interface component 204 can render these interface displays on a client device (e.g., a laptop computer, tablet computer, smart phone, etc.) that is communicatively connected to the work order management system 202 (e.g., via a hardwired or wireless connection). Input data that can be received via user interface component 204 can include, but is not limited to, work order data (e.g., work order data field entries), user interface navigation input, natural language chat inputs (e.g., work order generation commands, queries regarding existing work orders or asset risks, etc.), or other such input data. Output data rendered by user interface component 204 can include, but is not limited to, information regarding closed and open work orders, risk levels associated with respective work orders, estimated costs associated with high-risk work orders, or other such output data.”; Paragraph 43, “Analysis component 212 can be configured to perform analysis on real-time or historical asset performance data, data obtained from an MES system or a similar high-level enterprise tracking system, contextual information, or other such data to determine when maintenance tasks are to be scheduled, what those maintenance tasks include, and which technicians are to be assigned the tasks. In some embodiments, the analysis component 212 can apply AI or generative AI-assisted analysis to this data in connection with determining when and how maintenance tasks should be scheduled and corresponding work orders generated.”; Paragraph 46, “FIG. 3 is a diagram illustrating an example architecture for automatically generating work orders 310 based on analysis of real-time or historical industrial asset performance. Work order management system 202 can be implemented on any suitable platform that allows the system 202 to be accessed via client devices (e.g., desktop computers, laptop computers, smart phones, tablet computers, wearable computing devices, etc.) and that permits the system 202 to access operational and status data generated by industrial assets within a plant facility. For example, system 202 can be installed and executed on an on-premise server device on a plant or office network of an industrial facility. Alternatively, system 202 can be executed on a cloud platform as a set of cloud-based services, allowing users at different industrial facilities to access the system 202, view work orders, receive notifications generated by the system 202, or retrieve work order analysis results. System 202 can also be executed on a public network such as the internet and made accessible to users having suitable authorization credentials. In such embodiments, the system 202 can maintain work orders for different industrial enterprises in a segregated manner, such that employees of a given industrial enterprise can only access work orders and associated analysis results associated with that enterprise. In the example depicted in FIG. 3, work order management system resides and executes on a cloud platform.”; Paragraph 52, “A work order 310 generated by the work order generation component 210 can contain information about the maintenance task to be performed, including but not limited to an identity of the industrial asset or machine for which maintenance is required, an aspect of the industrial asset that requires attention, a type of the maintenance to be performed, an estimated number of hours to be spent on the maintenance task, an estimated number of personnel to be assigned to the task, a description of the task, or other such information. The work order 310 is initially scheduled in the system 202 as an open work order 310 (that is, the system 202 stores the work order 310 as work order data in memory 222 and assigns an “Open” status to the work order 310) and remains open until completion of its associated maintenance tasks, at which time the system 202 assigns a “Closed” status to the work order 310.”; Paragraph 53, “Authorized users can browse and view both open and closed work orders 310 via user interface component 204. FIG. 4 is an example work order display 402 that can be rendered on a client device by the user interface component 204. When a user selects a work order 310 via interaction with the work order system's primary user interface, the user interface component 204 can render a work order display 402 and populate the display 402 with information about the work order. In the example depicted in FIG. 4, the work order display 402 comprises a work order identifier 414 that uniquely identifies the selected work order 310, a section 408 that displays general information about the work order 310 (e.g. the open or closed status, a type of maintenance to be performed, a priority, an identity of the asset on which the maintenance task is to be performed, a suggested completion date for the maintenance, a name of a project with which the maintenance task is associated, etc.), and a navigation bar 406 comprising selectable controls corresponding to respective different categories of additional information that can be viewed.”; Paragraph 111, “These generative AI-assisted techniques can allow technicians to easily generate work orders 310 using natural language text or verbal input to the system 202 (e.g., via interfaces rendered on the technicians' client devices and delivered by the user interface component 204) as the technicians are performing other tasks (e.g., upon discovering a new maintenance concern during investigation of a known issue). These approaches can also be used to easily and intuitively annotate or edit work orders using natural language voice or text input.”)
executing a search at the issue tracking platform to identify a set of issues managed by the issue tracking platform, the search comprising search parameters generated using data extracted from analyzing the user input: (Bamal: Paragraph 50, “When the monitoring component 208, assisted by the analysis component 212, determines that the monitored asset data 306 satisfies a condition indicative of a current or predicted asset performance issue requiring investigation or correction by maintenance personnel, system's work order generation component 210 can schedule one or more maintenance tasks predicted to correct the performance issue and generate a corresponding work order 310 for the tasks. The condition detected by the monitoring component 208 that triggers creation of a work order 310 can be, for example, a deviation of one or more data tag values that move outside a defined range of normal or expected values. In an example scenario, a baking process may require an oven temperature to stay within a defined temperature range. Accordingly, values of a data tag or automation object corresponding to this oven temperature can be collected from the industrial controller 118 that monitors and controls the baking process, and this collected data can be provided to the work order management system 202 as part of the asset data 306. The monitoring component 208 monitors this value to determine when the oven temperature deviates from this range and, in response to detecting such a deviation, instructs work order generation component 210 to generate a new open work order 310 for investigation of the temperature control issue. In some embodiments, machine-specific asset models maintained on the work order management system 202 can define which data items or performance parameters of the industrial assets are to be monitored, as well as the conditions of this data that are to trigger creation of work orders 310. In other embodiments, as will be described in more detail below, the system 202 can learn to recognize conditions of the asset data indicative of an elevated risk to an asset using machine learning, AI, generative AI, or other analytic techniques.”; Paragraph 65, “The interdependencies between industrial assets defined in the plant model 314 can be used by the analysis component 212 to identify opportunities for opportunistic maintenance scheduling, which can improve maintenance efficiency. For example, when the work order generation component 210 schedules a maintenance activity (and generates a corresponding work order 310) for a given industrial asset to mitigate a discovered risk, the analysis component 212 can also determine whether the discovered risk is likely to also affect other similar machines or components (as determined in part based on the assets defined in the plant model 314) and schedule work orders 310 to perform similar maintenance tasks on those similar assets. The analysis component 212 can also determine whether other assets that are downstream from the affected asset are likely to be impacted by the discovered risk, or by the maintenance action performed on the affected upstream asset. If so, the analysis component 212 can instruct the work order generation component 210 to include, as part of the maintenance instructions defined in the work order 310 for the affected asset, recommendations for addressing any related issues on the downstream assets. In another example, when a machine shutdown is scheduled to address a discovered high-risk issue, the analysis component 212 can identify other lower-risk issues that could also be addressed during the machine shutdown, and generate work orders 310 to address these lower-risk issues as part of the same maintenance session. In any of these examples, the analysis component 212 can reference the defined interdependencies between industrial machines or assets defined in the plant model 314 in order to identify other assets that may be affected by a machine risk (e.g., assets that are downstream from, or otherwise have a functional relationship with, the affected asset), similar assets that may be subject to a common risk, etc.”; Paragraph 66, “In some embodiments, the analysis component 212 can schedule and assign a work order 310 for a discovered asset risk based in part on a risk-reward assessment that considers the benefit of performing the work order against the risk to the affected asset. For example, machines that are especially crucial to plant operations may require the result of the analysis component's risk-reward assessment to exceed a higher benefit threshold, relative to less crucial machines, to justify any risks associated with performing the maintenance action on the machine (e.g., lost productivity or risk of damage due to improper execution of the work order).”)
causing generation of a prompt comprising: (Bamal: Paragraph 56, “Returning to FIG. 3, to facilitate intelligent automated generation of work orders 310, the monitoring component 208 is assisted by an analysis component 212 that can apply one or more types of analysis (e.g., AI, generative AI analysis or generative AI-assisted analysis, machine learning, etc.) to real-time or historical asset data 306, MES data 316 from the plant facility's MES system or another high-level plant managements system, and other contextual data in connection with determining when to schedule maintenance tasks, what these maintenance tasks entail, and which technicians are to be assigned the tasks. For example, in some embodiments, the analysis component 212 can leverage generative AI to auto-generate work orders 310 or otherwise schedule maintenance tasks based on predicted or detected asset risks. In such embodiments, the analysis component 212 can implement prompt engineering functionality using associated trained models 312 trained with various types of training data, and can use these prompt engineering features to interface with a generative AI model 308 (e.g., an LLM or another type of model) and associated neural networks.”; Paragraph 61, “Returning to FIG. 6, during the asset monitoring process, the analysis component 212 can formulate and submits prompts 604 to the generative AI model 308 designed to obtain responses 606 that can assist with monitoring the performance of industrial assets for risk conditions, formulating maintenance strategies for mitigating the risk conditions, or generating content of a work order 310. The analysis component 212 can generate these prompts 604 based on a current operating context of one or more industrial assets being monitored (as determined from real-time or historical asset data 306) as well as the training data 602 encoded in the trained models 312. The analysis component 212 can reference the trained models 312 or associated training data 602 as needed in connection with creating prompts 604 designed to obtain responses 606 from the generative AI model 308 that assist the analysis component 212 in recognizing a current or predicted risk to an industrial asset, formulating a maintenance intervention for mitigating the risk, or generating content of a work order 310 for scheduling the maintenance intervention (e.g., natural language summaries of the identified asset risk, as well as descriptions of the maintenance tasks for mitigating the risk). The analysis component 212 can generate the prompt 604 to include any relevant information that can assist the generative AI model 308 in converging on a useful responses 606 that can be used to better understand a current context of the industrial assets, including but not limited to a selected subset of the asset data itself 306, an identity of the type of industrial asset of interest (e.g., a type of machine or industrial device), an indication of the type of industrial process or application being carried out by the industrial asset of interest (e.g., a specific type of batch processing, a specific automotive manufacturing function, a sheet metal stamping application, etc.), any selected subsets of the training data 602 or MES data 316, or other such data.”)
predetermined prompt language selected based on the project type classifier; and (Bamal: Paragraph 56, “Returning to FIG. 3, to facilitate intelligent automated generation of work orders 310, the monitoring component 208 is assisted by an analysis component 212 that can apply one or more types of analysis (e.g., AI, generative AI analysis or generative AI-assisted analysis, machine learning, etc.) to real-time or historical asset data 306, MES data 316 from the plant facility's MES system or another high-level plant managements system, and other contextual data in connection with determining when to schedule maintenance tasks, what these maintenance tasks entail, and which technicians are to be assigned the tasks. For example, in some embodiments, the analysis component 212 can leverage generative AI to auto-generate work orders 310 or otherwise schedule maintenance tasks based on predicted or detected asset risks. In such embodiments, the analysis component 212 can implement prompt engineering functionality using associated trained models 312 trained with various types of training data, and can use these prompt engineering features to interface with a generative AI model 308 (e.g., an LLM or another type of model) and associated neural networks.”; Paragraph 61, “Returning to FIG. 6, during the asset monitoring process, the analysis component 212 can formulate and submits prompts 604 to the generative AI model 308 designed to obtain responses 606 that can assist with monitoring the performance of industrial assets for risk conditions, formulating maintenance strategies for mitigating the risk conditions, or generating content of a work order 310. The analysis component 212 can generate these prompts 604 based on a current operating context of one or more industrial assets being monitored (as determined from real-time or historical asset data 306) as well as the training data 602 encoded in the trained models 312. The analysis component 212 can reference the trained models 312 or associated training data 602 as needed in connection with creating prompts 604 designed to obtain responses 606 from the generative AI model 308 that assist the analysis component 212 in recognizing a current or predicted risk to an industrial asset, formulating a maintenance intervention for mitigating the risk, or generating content of a work order 310 for scheduling the maintenance intervention (e.g., natural language summaries of the identified asset risk, as well as descriptions of the maintenance tasks for mitigating the risk). The analysis component 212 can generate the prompt 604 to include any relevant information that can assist the generative AI model 308 in converging on a useful responses 606 that can be used to better understand a current context of the industrial assets, including but not limited to a selected subset of the asset data itself 306, an identity of the type of industrial asset of interest (e.g., a type of machine or industrial device), an indication of the type of industrial process or application being carried out by the industrial asset of interest (e.g., a specific type of batch processing, a specific automotive manufacturing function, a sheet metal stamping application, etc.), any selected subsets of the training data 602 or MES data 316, or other such data.”)
data extracted from the set of issues; (Bamal: Paragraph 56, “Returning to FIG. 3, to facilitate intelligent automated generation of work orders 310, the monitoring component 208 is assisted by an analysis component 212 that can apply one or more types of analysis (e.g., AI, generative AI analysis or generative AI-assisted analysis, machine learning, etc.) to real-time or historical asset data 306, MES data 316 from the plant facility's MES system or another high-level plant managements system, and other contextual data in connection with determining when to schedule maintenance tasks, what these maintenance tasks entail, and which technicians are to be assigned the tasks. For example, in some embodiments, the analysis component 212 can leverage generative AI to auto-generate work orders 310 or otherwise schedule maintenance tasks based on predicted or detected asset risks. In such embodiments, the analysis component 212 can implement prompt engineering functionality using associated trained models 312 trained with various types of training data, and can use these prompt engineering features to interface with a generative AI model 308 (e.g., an LLM or another type of model) and associated neural networks.”; Paragraph 61, “Returning to FIG. 6, during the asset monitoring process, the analysis component 212 can formulate and submits prompts 604 to the generative AI model 308 designed to obtain responses 606 that can assist with monitoring the performance of industrial assets for risk conditions, formulating maintenance strategies for mitigating the risk conditions, or generating content of a work order 310. The analysis component 212 can generate these prompts 604 based on a current operating context of one or more industrial assets being monitored (as determined from real-time or historical asset data 306) as well as the training data 602 encoded in the trained models 312. The analysis component 212 can reference the trained models 312 or associated training data 602 as needed in connection with creating prompts 604 designed to obtain responses 606 from the generative AI model 308 that assist the analysis component 212 in recognizing a current or predicted risk to an industrial asset, formulating a maintenance intervention for mitigating the risk, or generating content of a work order 310 for scheduling the maintenance intervention (e.g., natural language summaries of the identified asset risk, as well as descriptions of the maintenance tasks for mitigating the risk). The analysis component 212 can generate the prompt 604 to include any relevant information that can assist the generative AI model 308 in converging on a useful responses 606 that can be used to better understand a current context of the industrial assets, including but not limited to a selected subset of the asset data itself 306, an identity of the type of industrial asset of interest (e.g., a type of machine or industrial device), an indication of the type of industrial process or application being carried out by the industrial asset of interest (e.g., a specific type of batch processing, a specific automotive manufacturing function, a sheet metal stamping application, etc.), any selected subsets of the training data 602 or MES data 316, or other such data.”)
in response to receiving a generative response from a generative output engine, the generative response produced in response to the generative output engine receiving the prompt; (Bamal: Paragraph 64, “The work order management system 202 can consider any of the information from the trained models 312 or their associated training data 602 (e.g., technical information about industrial assets, technician skill sets, previous work orders, plant financial data, plant schedules, etc.), MES data 316 (which may include some of the training data 602 described above), prompted responses 606 from the generative AI model 308, or the plant model 314 in connection with determining whether a maintenance task should be scheduled for an industrial asset, when the task should be scheduled, and to which technicians the task should be assigned. For example, when the monitoring component 208 or analysis component 212 detect or predict, based on analysis of asset data 306, a risk condition requiring a maintenance action, the analysis component 212 can determine whether deferring the maintenance action until an upcoming planned machine shutdown would minimize a cost of the maintenance without incurring a cost associated with the risk, and if so, generate the work order 310 for the maintenance action such that corresponding maintenance tasks are scheduled to be performed during the shutdown period. To make this decision, the analysis component 212 can consider the machine's operating or shutdown schedule (as determined from the MES data 316), the cost of technicians' time during the shut down versus the cost of the technicians' time during the machine's scheduled operation, a cost associated with prolonging the asset risk until the shutdown relative to the cost of mitigating the risk sooner, or other such factors.”)
analyzing the generative response to identify a first portion of the generative response corresponding to a project definition and a second portion of the generative response corresponding to one or more issues; (Bamal: Paragraph 64, “The work order management system 202 can consider any of the information from the trained models 312 or their associated training data 602 (e.g., technical information about industrial assets, technician skill sets, previous work orders, plant financial data, plant schedules, etc.), MES data 316 (which may include some of the training data 602 described above), prompted responses 606 from the generative AI model 308, or the plant model 314 in connection with determining whether a maintenance task should be scheduled for an industrial asset, when the task should be scheduled, and to which technicians the task should be assigned. For example, when the monitoring component 208 or analysis component 212 detect or predict, based on analysis of asset data 306, a risk condition requiring a maintenance action, the analysis component 212 can determine whether deferring the maintenance action until an upcoming planned machine shutdown would minimize a cost of the maintenance without incurring a cost associated with the risk, and if so, generate the work order 310 for the maintenance action such that corresponding maintenance tasks are scheduled to be performed during the shutdown period. To make this decision, the analysis component 212 can consider the machine's operating or shutdown schedule (as determined from the MES data 316), the cost of technicians' time during the shut down versus the cost of the technicians' time during the machine's scheduled operation, a cost associated with prolonging the asset risk until the shutdown relative to the cost of mitigating the risk sooner, or other such factors.”; Paragraph 65, “The interdependencies between industrial assets defined in the plant model 314 can be used by the analysis component 212 to identify opportunities for opportunistic maintenance scheduling, which can improve maintenance efficiency. For example, when the work order generation component 210 schedules a maintenance activity (and generates a corresponding work order 310) for a given industrial asset to mitigate a discovered risk, the analysis component 212 can also determine whether the discovered risk is likely to also affect other similar machines or components (as determined in part based on the assets defined in the plant model 314) and schedule work orders 310 to perform similar maintenance tasks on those similar assets. The analysis component 212 can also determine whether other assets that are downstream from the affected asset are likely to be impacted by the discovered risk, or by the maintenance action performed on the affected upstream asset. If so, the analysis component 212 can instruct the work order generation component 210 to include, as part of the maintenance instructions defined in the work order 310 for the affected asset, recommendations for addressing any related issues on the downstream assets. In another example, when a machine shutdown is scheduled to address a discovered high-risk issue, the analysis component 212 can identify other lower-risk issues that could also be addressed during the machine shutdown, and generate work orders 310 to address these lower-risk issues as part of the same maintenance session. In any of these examples, the analysis component 212 can reference the defined interdependencies between industrial machines or assets defined in the plant model 314 in order to identify other assets that may be affected by a machine risk (e.g., assets that are downstream from, or otherwise have a functional relationship with, the affected asset), similar assets that may be subject to a common risk, etc.”; Paragraph 70, “As in previous examples, the analysis component 212 can leverage generative AI as needed to assist in determining whether values or trends in the monitored asset data 306 indicate, or are correlated with, an elevated risk of failure of an asset. For example, during monitoring of the asset data 306, the analysis component 212 may generate prompts 604 directed to the generative AI model 308 that are designed to obtain responses 606 (see FIG. 6) providing technical information about an asset whose performance or behavior is deviating from normal parameters, and can reference the information in these responses 606 in connection with determining whether a maintenance action should be performed on the asset, determining what this maintenance action should entail, and populating the content of a new work order 310 for performing this maintenance action.”; Paragraph 105, “In addition to referencing the information contained in the trained models 312 or plant model 314, the analysis component 212 can also, as needed, prompt the generative AI model 308 for responses 606 that assist in generating suitable responses 1102 or work orders 310 in response to the user's natural language request or query 1106. For example, in response to receipt of a natural language request or query 1106, the analysis component 212 can determine whether a sufficiently accurate response 1102 to the query 1106 (or a work order 310 satisfying the user's maintenance scheduling request) can be generated based on relevant information contained in the trained models 312 alone, or, alternatively, whether supplemental information from the generative AI model 308 is necessary to formulate a response 1102 having a sufficiently high probability of satisfying the user's request or query 1106 (or to generate a work order 310 having a sufficiently high probability of satisfying the request conveyed in the query 1106). If supplemental information from the generative AI model 308 is deemed necessary, the analysis component 212 can formulate prompts 604 based on analysis of the request or query 1106 and the knowledge encoded in any of the trained models 312 or plant model 314. These prompts 604 are designed to obtain responses 606 from the generative AI model 308 that can be used to formulate accurate and cohesive responses 1102 to the user's query 1106, or to generate work orders 310 that satisfy the user's natural language request.”)
Bamal does not explicitly disclose the following, however, in analogous art of task planning and management, Ponce De Leon discloses the following:
causing generation of a project comprising the one or more issues hierarchically arranged within the project; (Ponce De Leon: Column 4 line 59 – Column 5 line 6, “GPM fundamentally differs from CPM scheduling systems by providing evolving dates, floats, resource profiles and cost curves in real time to a user, while the user is constructing the schedule. With GPM, the planning and scheduling steps are consolidated, which increases network construction efficiency and accuracy. Moreover, combining GPM with an interactive display creates a kinetic linkage between the visual representation of the plan and the abstract cognition of users generating the plan. Users may perform resource leveling, schedule optimization, and time/cost tradeoffs interactively on the display and simultaneously with network construction. GPM algorithms also allow users to switch from constructing network schedules forward from release dates to backwards from target dates and vice versa.”; Column 7 lines 49 – 67, “The object processor 108 may create any number of objects within the constraints of storage capacity. The object processor 108 may also create a number of object types. For example, the object processor 108 may create objects representative of activities, milestones, benchmarks, embedded nodes, logic relationships, data dates, and project ends, or project start and end dates. These objects may be classified as planning objects as they affect the logic and dependency relationships in the schedule. The object processor 108 may also create objects classified as aesthetic objects as they may be used to increase the understandability and/or aesthetic presentation of the schedule. Examples of aesthetic objects include text, annotations, which is different from text in that annotations are embedded within the object, images, resource-axis, which define the vertical axis of the resource profile graphs, and information objects, which may be used to connect to a file from an external application, for example, a user may embed a document into the schedule by storing the path of the document with the information object.”; Column 17 lines 50 – 67, “An exemplary collaborative and full wall planning session 1700 is illustrated at FIG. 17. With reference to FIG. 17, the system may provide the following advantages to a full wall planning session: high resolution graphical interface 1702 that enhances the interaction between all stakeholders 1704; ability to graphically create and link network dependencies 1706; graphical nature allows network to be clearly understood and easy to create and edit; identify the resources needed to complete the project; graphical display of resources 1708 to allow for the best placement of tasks and stakeholders 1704 to plan for their level of effort; facilitation of a quick and interactive project planning and scheduling session; ability to test alternative approaches and evaluate performance; easily identify the critical path for a project; ability to add information text, annotations and information objects to enrich plan; ability to determine what action is necessary to keep project on schedule; and monitor percent complete and show the real possibility of meeting the deadline.”)
and causing display of a project interface comprising one or more graphical objects, each corresponding to an issue of the one or more issues. (Ponce De Leon: Column 4 line 59 – Column 5 line 6, “GPM fundamentally differs from CPM scheduling systems by providing evolving dates, floats, resource profiles and cost curves in real time to a user, while the user is constructing the schedule. With GPM, the planning and scheduling steps are consolidated, which increases network construction efficiency and accuracy. Moreover, combining GPM with an interactive display creates a kinetic linkage between the visual representation of the plan and the abstract cognition of users generating the plan. Users may perform resource leveling, schedule optimization, and time/cost tradeoffs interactively on the display and simultaneously with network construction. GPM algorithms also allow users to switch from constructing network schedules forward from release dates to backwards from target dates and vice versa.”; Column 7 lines 49 – 67, “The object processor 108 may create any number of objects within the constraints of storage capacity. The object processor 108 may also create a number of object types. For example, the object processor 108 may create objects representative of activities, milestones, benchmarks, embedded nodes, logic relationships, data dates, and project ends, or project start and end dates. These objects may be classified as planning objects as they affect the logic and dependency relationships in the schedule. The object processor 108 may also create objects classified as aesthetic objects as they may be used to increase the understandability and/or aesthetic presentation of the schedule. Examples of aesthetic objects include text, annotations, which is different from text in that annotations are embedded within the object, images, resource-axis, which define the vertical axis of the resource profile graphs, and information objects, which may be used to connect to a file from an external application, for example, a user may embed a document into the schedule by storing the path of the document with the information object.”; Column 17 lines 50 – 67, “An exemplary collaborative and full wall planning session 1700 is illustrated at FIG. 17. With reference to FIG. 17, the system may provide the following advantages to a full wall planning session: high resolution graphical interface 1702 that enhances the interaction between all stakeholders 1704; ability to graphically create and link network dependencies 1706; graphical nature allows network to be clearly understood and easy to create and edit; identify the resources needed to complete the project; graphical display of resources 1708 to allow for the best placement of tasks and stakeholders 1704 to plan for their level of effort; facilitation of a quick and interactive project planning and scheduling session; ability to test alternative approaches and evaluate performance; easily identify the critical path for a project; ability to add information text, annotations and information objects to enrich plan; ability to determine what action is necessary to keep project on schedule; and monitor percent complete and show the real possibility of meeting the deadline.”)
Bamal discloses a method of using generative prompts to track, manage, and create tasks and issues. Ponce De Leon discloses a method for a graphical platform for tracking tasks across a larger project. At the time of Applicant’s filed invention, one of ordinary skill in the art would have deemed it obvious to combine the methods of Bamal with the teachings of Ponce De Leon in order to increase the efficiency of scheduling and planning as disclosed by Ponce De Leon (Ponce De Leon: Column 4 line 59 – Column 5 line 5, “GPM algorithms also allow users to switch from constructing network schedules forward from release dates to backwards from target dates and vice versa.”)
Claim(s) 2 –
Bamal in view of Ponce De Leon disclose the limitations of claim 1
Bamal further discloses the following:
the prompt is a first prompt and the generative response is a first generative response; (Bamal: Paragraph 56, “Returning to FIG. 3, to facilitate intelligent automated generation of work orders 310, the monitoring component 208 is assisted by an analysis component 212 that can apply one or more types of analysis (e.g., AI, generative AI analysis or generative AI-assisted analysis, machine learning, etc.) to real-time or historical asset data 306, MES data 316 from the plant facility's MES system or another high-level plant managements system, and other contextual data in connection with determining when to schedule maintenance tasks, what these maintenance tasks entail, and which technicians are to be assigned the tasks. For example, in some embodiments, the analysis component 212 can leverage generative AI to auto-generate work orders 310 or otherwise schedule maintenance tasks based on predicted or detected asset risks. In such embodiments, the analysis component 212 can implement prompt engineering functionality using associated trained models 312 trained with various types of training data, and can use these prompt engineering features to interface with a generative AI model 308 (e.g., an LLM or another type of model) and associated neural networks.”; Paragraph 59, “Similarly, when an asset risk is detected, the analysis component 212 can determine a suitable set of maintenance tasks for mitigating the detected or predicted risk based on the training data 602 encoded in the models 312, as well as responses 606 prompted from the generative AI model 308. Responses 606 prompted from the generative AI model 308 can also be used by the work order generation component 210 to generate natural language content to be included in the corresponding work order 310 (e.g., natural language descriptions of the asset risk rendered in the Summary box 404 of the work order display 402, natural language descriptions of the maintenance tasks rendered in the Instructions box 410 or list 502, etc.).”)
the intake interface comprises a text-based input field; (Bamal: Paragraph 102, “Some embodiments of the work order management system 202 can also incorporate a generative AI chat interface that allows a user to interact with the system 202 via natural language chat exchanges. In such embodiments, the system 202 can support industry-specific prompt engineering features that can formulate suitable prompts 604 for submission to the generative AI model 308 based on a user's natural language requests or queries. FIG. 11 is a diagram illustrating exchange of generative AI dialog messages between a user and the work order management system 202. Embodiments of the system 202 that support a generative AI-based chat interactions can render (via user interface component 204) a chat interface through which a user can exchange natural language prompts or chat conversations with the system 202. This chat interface can include a data entry field for entering a user's natural language request or query 1106 as a text string, or can support other input formats for a user's request or query 1106 (e.g., spoken-word audio input).”)
in response to receiving text input to the text-based input field, generating a second prompt for submission to the generative output engine, the second prompt including the text input; (Bamal: Paragraph 103, “In general, the work order management system 202 can receive and process a user's natural language requests or queries 1106, which can comprise questions about existing open or closed work orders 310, questions about asset risks, requests to create new work orders 310 for performing maintenance tasks, or other such prompts. The system 202 can use prompt engineering services to process natural language requests or queries 1106 submitted by the user via the chat interface (or via a spoken word interface). These prompt engineering services can leverage knowledge encoded in the trained modules 312 (as learned from training data 602), together with responses 606 prompted from the generative AI model 308, to accurately ascertain the user's needs and respond to the user's request or query 1106.”; Paragraph 108, “The analysis component 212 can use a range of approaches for processing a natural language request or query 1106 submitted by the user, and for formulating prompts 604 to the generative AI model 308 designed to yield responses 606 that assist in responding to the user's request or query 1106. According to an example approach, the analysis component 212 can access an archive of chat exchanges between the analysis component 212 and other users and identify chat sessions that were initiated by user queries having similarities to the initial query 1106 submitted by the present user. Upon identifying these archived chat sessions, the analysis component 212 can analyze these past chat sessions to determine types of information that were ultimately generated as a result of these sessions (e.g., work orders 310 having features or elements that are a function of specific keywords of the user's query, a specific type of information about a work order 310 or set of work orders 310 that was ultimately determined to be sought by the user, etc.), and either generate an output (e.g., a work order 310 or a natural language response 1102 to the user's query 1106) based on the outcomes of these past chat sessions and adapted to the user's initial request or query 1106, or, if necessary, generate a prompt 604 for submission to the generative AI model 308 designed to obtain a response 606 comprising the necessary type of information.”)
and the search at the issue tracking platform is generated using a second generative response from the generative output engine received in response to providing the second prompt to the generative output engine. (Bamal: Paragraph 50, “When the monitoring component 208, assisted by the analysis component 212, determines that the monitored asset data 306 satisfies a condition indicative of a current or predicted asset performance issue requiring investigation or correction by maintenance personnel, system's work order generation component 210 can schedule one or more maintenance tasks predicted to correct the performance issue and generate a corresponding work order 310 for the tasks. The condition detected by the monitoring component 208 that triggers creation of a work order 310 can be, for example, a deviation of one or more data tag values that move outside a defined range of normal or expected values. In an example scenario, a baking process may require an oven temperature to stay within a defined temperature range. Accordingly, values of a data tag or automation object corresponding to this oven temperature can be collected from the industrial controller 118 that monitors and controls the baking process, and this collected data can be provided to the work order management system 202 as part of the asset data 306. The monitoring component 208 monitors this value to determine when the oven temperature deviates from this range and, in response to detecting such a deviation, instructs work order generation component 210 to generate a new open work order 310 for investigation of the temperature control issue. In some embodiments, machine-specific asset models maintained on the work order management system 202 can define which data items or performance parameters of the industrial assets are to be monitored, as well as the conditions of this data that are to trigger creation of work orders 310. In other embodiments, as will be described in more detail below, the system 202 can learn to recognize conditions of the asset data indicative of an elevated risk to an asset using machine learning, AI, generative AI, or other analytic techniques.”; Paragraph 65, “The interdependencies between industrial assets defined in the plant model 314 can be used by the analysis component 212 to identify opportunities for opportunistic maintenance scheduling, which can improve maintenance efficiency. For example, when the work order generation component 210 schedules a maintenance activity (and generates a corresponding work order 310) for a given industrial asset to mitigate a discovered risk, the analysis component 212 can also determine whether the discovered risk is likely to also affect other similar machines or components (as determined in part based on the assets defined in the plant model 314) and schedule work orders 310 to perform similar maintenance tasks on those similar assets. The analysis component 212 can also determine whether other assets that are downstream from the affected asset are likely to be impacted by the discovered risk, or by the maintenance action performed on the affected upstream asset. If so, the analysis component 212 can instruct the work order generation component 210 to include, as part of the maintenance instructions defined in the work order 310 for the affected asset, recommendations for addressing any related issues on the downstream assets. In another example, when a machine shutdown is scheduled to address a discovered high-risk issue, the analysis component 212 can identify other lower-risk issues that could also be addressed during the machine shutdown, and generate work orders 310 to address these lower-risk issues as part of the same maintenance session. In any of these examples, the analysis component 212 can reference the defined interdependencies between industrial machines or assets defined in the plant model 314 in order to identify other assets that may be affected by a machine risk (e.g., assets that are downstream from, or otherwise have a functional relationship with, the affected asset), similar assets that may be subject to a common risk, etc.”; Paragraph 66, “In some embodiments, the analysis component 212 can schedule and assign a work order 310 for a discovered asset risk based in part on a risk-reward assessment that considers the benefit of performing the work order against the risk to the affected asset. For example, machines that are especially crucial to plant operations may require the result of the analysis component's risk-reward assessment to exceed a higher benefit threshold, relative to less crucial machines, to justify any risks associated with performing the maintenance action on the machine (e.g., lost productivity or risk of damage due to improper execution of the work order).”; Paragraph 110, “In another example approach, the analysis component 212 can enhance the user's query 1106 with additional information from the trained models 312 (or the training data 602 used to train the models 312) that contextualizes the user's request, and integrate this additional information with the user's query 1106 to yield the prompt 604 submitted to the generative AI model 308. The types of additional contextual information added to the query 1106 can depend on the nature of the query 1106 and can include, but are not limited to, technical information about an industrial asset known to be relevant to the user's query 1106, information about past maintenance tasks as obtained from closed work orders 310, information regarding monitored operational trends in the asset of interest, or other such information.”; Paragraph 120, “At 1304, asset data comprising operational, status, or performance data generated by industrial assets in service within the plant facility are analyzed for conditions indicative of a performance issue requiring performance of a maintenance task, where this analysis is performed using the one or more models trained at step 1302. In some embodiments, this analysis of the asset data can leverage generative AI to assist in determining whether values or trends in the monitored asset data are indicative of an actionable performance problem. For example, the system performing the analysis can formulate prompts directed to a generative AI model that are designed to obtain responses that can assist the system in interpreting values or trends in the asset data and determining whether these values or trends are indicative of a current or predicted performance concern in any of the monitored industrial assets”)
Claim(s) 3 –
Bamal in view of Ponce De Leon disclose the limitations of claims 1 and 2
Bamal further discloses the following:
the user input further comprises a user role; and (Bamal: Paragraph 77, “To assist with this work order assignment analysis, the analysis component 212 can reference relevant subsets of the plant facility's MES data 316 that identify the technicians associated with the plant facility as well as the respective technicians' work schedules and skill sets. For example, if the MES system maintains information regarding the roles and availability schedules of plant personnel, the MES interface component 214 can retrieve this information as MES data 316, and the analysis component 212 can analyze this data 316 to determine identities of technicians who are qualified to attend to the maintenance task and whose schedules indicate that the technicians are available to work on the task within the time frame defined by the work order 310. In general, the analysis component 212 can match the work order's maintenance tasks to a selected subset of technicians based on best fit criteria that considers the technicians' relative levels of experience or skill in performing the maintenance tasks, relevant skill sets, work schedules, availability bandwidths, or other factors (some or all of which can be obtained from the plant's MES system as MES data 316).”; Paragraph 79, “The analysis component 212 can generate and tracks each technician's KPIs 802 based on MES data 316 obtained from the plant's MES system (or another high-level business or management system used by the plant) by the MES interface component 214, including the identities of the technicians registered to perform maintenance within the facility, the work schedules of those technicians, information regarding the technician's skill sets (e.g., certifications, training, technical roles, etc.), or other such information. Additionally, for each technician, the analysis component 212 can monitor the content of closed or past work orders 310 that had been assigned to the technician to determine the degrees of experience the technician has had in performing various types of maintenance or working on specific machines or assets (e.g., replacing specific types of parts or machine components, recovering a specified machine from a downtime conditions, cleaning, inspections, etc.), translate these degrees of experience to corresponding KPI values indicating the technician's relative degrees of experience in these maintenance tasks, and assign these KPI values to the technician.”; Paragraph 81, “Using technician KPIs 802 or other metrics of respective technicians' skill sets and levels of maintenance experiences, the analysis component 212 can assess which technicians perform best on certain types of maintenance jobs and assign work orders 310 accordingly. If it is known that a work order 310 being generated by the work order generation component 210 requires certain specific skills (PLC programming, robot path teaching, etc.), the analysis component 212 can instruct the work order generation component 210 to assign the work order 310 to a technician having the necessary skills and experience. In some embodiments, the analysis component 212 can also determine whether a work order 310 in the process of being generated carries a level of risk that exceeds a defined threshold (e.g., due to the relative importance of the affected asset and the expected loss in productivity if the maintenance is not performed correctly, or due to a higher safety risk associated with the work order 310), and if so, assign the work order 310 to a technician whose KPIs 801 indicate a relatively high level of experience, or to a higher number of technicians than would typically be assigned in order to reduce the risk to high-value assets.”)
the search at the issue tracking platform is executed using the project type classifier and the user role. (Bamal: Paragraph 83, “The analysis component 212 can also consider expected degrees of difficulty when scheduling and assigning work orders 310. For example, the analysis component can determine a relative degree of difficulty associated with a work order 310 being generated and, if the degree of difficulty exceeds a threshold, schedule the work order's maintenance tasks to be spread over different days to reduce the amount of daily effort required to complete the work order 310. When determining the degree of difficulty associated with a work order 310, the analysis component 212 can consider the experience level of the technicians assigned to the work order 310 (e.g., as determined from the technician KPIs 802). The analysis component 212 may also divide tasks of a work order 310 among different technicians based on the technicians' current or expected locations relative to the affected asset (which can be determined based in part on asset layout or location information defined in the plant model 314), skill levels relative to each task defined by the work order 310, etc.”; Paragraph 117, “At 1210, the system selects one or more technicians to be assigned the one or more maintenance tasks based on analysis of the maintenance tasks determined at step 1208 and information regarding the set of technicians associated with the plant facility. The information about the technicians can comprise, for example, identities of the technicians registered to perform maintenance within the facility, the work schedules of those technicians, information regarding the technician's skill sets, or other such information. The system can also generate information about technicians' levels of experience in addressing various types of maintenance tasks (or levels of experience in working on a specific asset within the plant) based on analysis of closed or past work orders that had been assigned to the respective technicians and assign maintenance tasks to selected technicians based on this information regarding the technicians' relative levels of relevant work experience.”)
Claim(s) 4 –
Bamal in view of Ponce De Leon disclose the limitations of claims 1
Bamal further discloses the following:
wherein the data extracted from the set of issues comprises, for each issue of the set of issues, a respective title, a respective issue description, a respective defined project workflow, one or more hierarchical relationships, or combinations thereof. (Bamal: Paragraph 52, “A work order 310 generated by the work order generation component 210 can contain information about the maintenance task to be performed, including but not limited to an identity of the industrial asset or machine for which maintenance is required, an aspect of the industrial asset that requires attention, a type of the maintenance to be performed, an estimated number of hours to be spent on the maintenance task, an estimated number of personnel to be assigned to the task, a description of the task, or other such information. The work order 310 is initially scheduled in the system 202 as an open work order 310 (that is, the system 202 stores the work order 310 as work order data in memory 222 and assigns an “Open” status to the work order 310) and remains open until completion of its associated maintenance tasks, at which time the system 202 assigns a “Closed” status to the work order 310.”; Paragraph 53, “Authorized users can browse and view both open and closed work orders 310 via user interface component 204. FIG. 4 is an example work order display 402 that can be rendered on a client device by the user interface component 204. When a user selects a work order 310 via interaction with the work order system's primary user interface, the user interface component 204 can render a work order display 402 and populate the display 402 with information about the work order. In the example depicted in FIG. 4, the work order display 402 comprises a work order identifier 414 that uniquely identifies the selected work order 310, a section 408 that displays general information about the work order 310 (e.g. the open or closed status, a type of maintenance to be performed, a priority, an identity of the asset on which the maintenance task is to be performed, a suggested completion date for the maintenance, a name of a project with which the maintenance task is associated, etc.), and a navigation bar 406 comprising selectable controls corresponding to respective different categories of additional information that can be viewed.”)
Claim(s) 5 –
Bamal in view of Ponce De Leon disclose the limitations of claims 1
Bamal does not explicitly disclose the following, however, in analogous art of task planning and management, Ponce De Leon discloses the following:
the intake interface comprises a sequence of interfaces that are selected according to a defined set of parameters; (Ponce De Leon: Column 5 line 34 – Column 6 line 11, “The system may also provide default schedule attributes. The system may provide a number of project type options that the user may select, wherein each of the project type options comprise their own set of attributes that are typical for that project type. Exemplary project types may include constructing a building or highway, teaching project planning skills, writing a novel, analyzing and presenting evidence in a legal proceeding, planning a military campaign, or any other time-based project type. The system may also be designed for particular fields of use and may contain graphical information and selectable options representative of that field. The intuitive nature of the system makes it usable by a broad range of users, whether skilled in project planning or not. The GUI 102 may contain one or more interface tools, including menus, dialog boxes, toolbars, etc. In the example shown at FIG. 2, the GUI 102 displays the calendar attributes, including year 212, month 214 and day 216. The GUI 102 may also display grid lines 218, a histogram 220 and line graphs 222 for representing resources and/or cost information, discussed below, as well as a graphical legend 224 to explain what is represented by the schedule. The GUI 102 may display other graphical and/or textual information representing aspects of the project and/or schedule. The GUI 102 may also utilize colors, color shades and/or hatching patterns to distinguish different aspects of the project and/or schedule.”)
each interface of the sequence of interfaces comprises a set of options displayed in accordance with the defined set of parameters; and (Ponce De Leon: Column 12 lines 5 – 47, “The system may provide project resources based on a number of predefined characteristics. These characteristics may include resource type, category, cost, and color, color shading and/or hatching pattern to be assigned to the resource for display. The resource type may be user definable. Examples of resource type in the construction industry include carpenter, backhoe, concrete, etc. Other resource types in other industries may be defined by the user. The user may include any level of specificity in defining resource types. For example, the user may define a carpenter with specific training, a backhoe with specific lift capacity, and specific grade of concrete, etc. The system may also provide a listing of resource types for the user to select, which may be divided at any level of granularity and may be categorized based on industry. The system may also provide the user with a list of resource categories for the user to select, e.g. labor, equipment, material, commodity, professional, etc. For example, carpenter may fall under the category "labor," backhoe may fall under the category "equipment," and concrete may fall under the category "material." The system may offer any number of resource categories for the user to select and associate with the resource type. The user may also customize resource categories. The system may also provide the user with a palette of colors to select to associate with the resources. The system may also provide the user with a selection of hatching patterns to associate with the resources.”)
a selected option for a currently displayed interface of the sequence of interfaces is used to select a subsequent set of options displayed in a subsequent interface. (Ponce De Leon: Column 12 lines 5 – 47, “The system may provide project resources based on a number of predefined characteristics. These characteristics may include resource type, category, cost, and color, color shading and/or hatching pattern to be assigned to the resource for display. The resource type may be user definable. Examples of resource type in the construction industry include carpenter, backhoe, concrete, etc. Other resource types in other industries may be defined by the user. The user may include any level of specificity in defining resource types. For example, the user may define a carpenter with specific training, a backhoe with specific lift capacity, and specific grade of concrete, etc. The system may also provide a listing of resource types for the user to select, which may be divided at any level of granularity and may be categorized based on industry. The system may also provide the user with a list of resource categories for the user to select, e.g. labor, equipment, material, commodity, professional, etc. For example, carpenter may fall under the category "labor," backhoe may fall under the category "equipment," and concrete may fall under the category "material." The system may offer any number of resource categories for the user to select and associate with the resource type. The user may also customize resource categories. The system may also provide the user with a palette of colors to select to associate with the resources. The system may also provide the user with a selection of hatching patterns to associate with the resources.”)
Bamal discloses a method of using generative prompts to track, manage, and create tasks and issues. Ponce De Leon discloses a method for a graphical platform for tracking tasks across a larger project. At the time of Applicant’s filed invention, one of ordinary skill in the art would have deemed it obvious to combine the methods of Bamal with the teachings of Ponce De Leon in order to increase the efficiency of scheduling and planning as disclosed by Ponce De Leon (Ponce De Leon: Column 4 line 59 – Column 5 line 5, “GPM algorithms also allow users to switch from constructing network schedules forward from release dates to backwards from target dates and vice versa.”)
Claim(s) 6 and 19 –
Bamal in view of Ponce De Leon disclose the limitations of claims 1 and 16
Bamal further discloses the following:
wherein the predetermined prompt language comprises instructions to generate at least a portion of the generative response in a structured data format. (Bamal: Paragraph 29, “FIG. 1 is a block diagram of an example industrial control environment 100. In this example, a number of industrial controllers 118 are deployed throughout an industrial plant environment to monitor and control respective industrial systems or processes relating to product manufacture, machining, motion control, batch processing, material handling, or other such industrial functions. Industrial controllers 118 typically execute respective control programs to facilitate monitoring and control of industrial devices 120 making up the controlled industrial assets or systems (e.g., industrial machines). One or more industrial controllers 118 may also comprise a soft controller executed on a personal computer or other hardware platform, or on a cloud platform. Some hybrid devices may also combine controller functionality with other functions (e.g., visualization). The control programs executed by industrial controllers 118 can comprise any conceivable type of code used to process input signals read from the industrial devices 120 and to control output signals generated by the industrial controllers, including but not limited to ladder logic, sequential function charts, function block diagrams, or structured text.”; Paragraph 40, “User interface component 204 can be configured to generate user interface displays that receive user input and render output to the user in any suitable format (e.g., visual, audio, tactile, etc.). In some embodiments, user interface component 204 can render these interface displays on a client device (e.g., a laptop computer, tablet computer, smart phone, etc.) that is communicatively connected to the work order management system 202 (e.g., via a hardwired or wireless connection). Input data that can be received via user interface component 204 can include, but is not limited to, work order data (e.g., work order data field entries), user interface navigation input, natural language chat inputs (e.g., work order generation commands, queries regarding existing work orders or asset risks, etc.), or other such input data. Output data rendered by user interface component 204 can include, but is not limited to, information regarding closed and open work orders, risk levels associated with respective work orders, estimated costs associated with high-risk work orders, or other such output data.”; Paragraph 126, “Generally, program modules include routines, programs, components, data structures, etc., that perform particular tasks or implement particular abstract data types. Moreover, those skilled in the art will appreciate that the inventive methods can be practiced with other computer system configurations, including single-processor or multiprocessor computer systems, minicomputers, mainframe computers, Internet of Things (IoT) devices, distributed computing systems, as well as personal computers, hand-held computing devices, microprocessor-based or programmable consumer electronics, and the like, each of which can be operatively coupled to one or more associated devices.”)
Claim(s) 7 –
Bamal in view of Ponce De Leon disclose the limitations of claims 1, 6, 16, an 19
Bamal further discloses the following:
wherein analyzing the generative response comprises identifying the one or more issues and corresponding issue data from the structure data format. (Bamal: Paragraph 29, “FIG. 1 is a block diagram of an example industrial control environment 100. In this example, a number of industrial controllers 118 are deployed throughout an industrial plant environment to monitor and control respective industrial systems or processes relating to product manufacture, machining, motion control, batch processing, material handling, or other such industrial functions. Industrial controllers 118 typically execute respective control programs to facilitate monitoring and control of industrial devices 120 making up the controlled industrial assets or systems (e.g., industrial machines). One or more industrial controllers 118 may also comprise a soft controller executed on a personal computer or other hardware platform, or on a cloud platform. Some hybrid devices may also combine controller functionality with other functions (e.g., visualization). The control programs executed by industrial controllers 118 can comprise any conceivable type of code used to process input signals read from the industrial devices 120 and to control output signals generated by the industrial controllers, including but not limited to ladder logic, sequential function charts, function block diagrams, or structured text.”; Paragraph 40, “User interface component 204 can be configured to generate user interface displays that receive user input and render output to the user in any suitable format (e.g., visual, audio, tactile, etc.). In some embodiments, user interface component 204 can render these interface displays on a client device (e.g., a laptop computer, tablet computer, smart phone, etc.) that is communicatively connected to the work order management system 202 (e.g., via a hardwired or wireless connection). Input data that can be received via user interface component 204 can include, but is not limited to, work order data (e.g., work order data field entries), user interface navigation input, natural language chat inputs (e.g., work order generation commands, queries regarding existing work orders or asset risks, etc.), or other such input data. Output data rendered by user interface component 204 can include, but is not limited to, information regarding closed and open work orders, risk levels associated with respective work orders, estimated costs associated with high-risk work orders, or other such output data.”; Paragraph 126, “Generally, program modules include routines, programs, components, data structures, etc., that perform particular tasks or implement particular abstract data types. Moreover, those skilled in the art will appreciate that the inventive methods can be practiced with other computer system configurations, including single-processor or multiprocessor computer systems, minicomputers, mainframe computers, Internet of Things (IoT) devices, distributed computing systems, as well as personal computers, hand-held computing devices, microprocessor-based or programmable consumer electronics, and the like, each of which can be operatively coupled to one or more associated devices.”)
Claim(s) 8 –
Bamal in view of Ponce De Leon disclose the limitations of claims 1 and 6-7
Bamal further discloses the following:
causing generation of the project comprises causing generation of the one or more issues at the issue tracking platform, the one or more issues associated with the user account; (Bamal: Paragraph 35, “Industrial facilities typically house and operate many industrial assets, machines, or equipment. Many of these assets require regular proactive maintenance to ensure continued optimal operation, in addition to unplanned repair operations to address unexpected downtime events, such as machine malfunctions. To manage the large number of maintenance operations carried out at a given industrial enterprise, work order management systems can be used to initiate work orders for new maintenance operations to be performed, to track the statuses of these work orders, and to keep a record of maintenance operations performed within the plant. In a typical scenario for addressing a reactive maintenance concern, when metered or observed asset performance indicators—e.g., vibration values, temperature values, product counts, a machine downtime occurrence, etc.—indicate a possible performance concern requiring investigation or maintenance, a maintenance technician or manager creates and submits a work order for the maintenance operation to the work order management system. Maintenance personnel are then assigned the task of performing the maintenance task or investigation. As the work is carried out, maintenance actions performed in connection with the schedule maintenance task are submitted and recorded with the work order, which remains open as its corresponding maintenance task is performed. The work order is then closed once the task is completed. A similar workflow can be used to schedule regular proactive or preventative maintenance on industrial assets.”; Paragraph 78, “In some embodiments, the analysis component 212 can track technician key performance indicators (KPIs) for each technician and use these technician KPIs to determine maintenance task assignments. FIG. 8 is a diagram illustrating tracking of technician KPIs 802. In general, a technician's KPIs 802 can represent quantitative measures of the technician's range of skill sets, experience in performing certain types of maintenance tasks or working on specific types of industrial assets, and past levels of success in performing various types of maintenance tasks. In some embodiments, multiple different technician KPIs 802 can be generated and tracked for each technician, with each KPI 802 representing a measure of a specific type of skill or experience (e.g., a level of controller programming experience, a level of industrial robot teaching or programming experience, a level of past success in carrying out a specific type of asset maintenance, etc.). Technician KPIs 802 can also include indications of the technicians' availabilities to perform maintenance tasks.”; Paragraph 84, “In some embodiments, the work order management system 202 can deliver notifications to relevant plant personnel when a new work order 310 is generated and scheduled, alerting those employees that the new work order 310 has been created. FIG. 9 is a diagram illustrating delivery of maintenance notifications 902 to a technician's client device 904. In response to creation of a work order 310 using any of the techniques described above, the user interface component 204 can deliver a notification 902 to the client devices 904 of technicians whom the analysis component 212 or the work order generation component 210 have designated to carry out the work order 310. The notification 902 can include any of the information described above as being rendered on the work order displays 402 illustrated in FIGS. 4 and 5, including a description of the work to be performed (e.g., a list of maintenance tasks as rendered in the Instructions box 410), the industrial asset or machine on which the maintenance is to be performed, a time at which the maintenance is scheduled, the identities of other technicians who have been assigned the work order 310, or other such information. Once created, the work order 310 can be managed through its lifecycle within the domain of the work order management system 202. This can include updating the status of the work order 310 within the system 202 as the work order's maintenance tasks are performed and ultimately closing the work order 310 upon completion of the maintenance tasks. At any time, authorized users can invoke the work order display 402 on their client devices 904 via the user interface component 204 to view detailed information about the work order 310, as well as status information for the respective maintenance tasks defined in the work order 310.”)
and the one or more issues are processed in accordance with an issue workflow. (Bamal: Paragraph 35, “Industrial facilities typically house and operate many industrial assets, machines, or equipment. Many of these assets require regular proactive maintenance to ensure continued optimal operation, in addition to unplanned repair operations to address unexpected downtime events, such as machine malfunctions. To manage the large number of maintenance operations carried out at a given industrial enterprise, work order management systems can be used to initiate work orders for new maintenance operations to be performed, to track the statuses of these work orders, and to keep a record of maintenance operations performed within the plant. In a typical scenario for addressing a reactive maintenance concern, when metered or observed asset performance indicators—e.g., vibration values, temperature values, product counts, a machine downtime occurrence, etc.—indicate a possible performance concern requiring investigation or maintenance, a maintenance technician or manager creates and submits a work order for the maintenance operation to the work order management system. Maintenance personnel are then assigned the task of performing the maintenance task or investigation. As the work is carried out, maintenance actions performed in connection with the schedule maintenance task are submitted and recorded with the work order, which remains open as its corresponding maintenance task is performed. The work order is then closed once the task is completed. A similar workflow can be used to schedule regular proactive or preventative maintenance on industrial assets.”; Paragraph 78, “In some embodiments, the analysis component 212 can track technician key performance indicators (KPIs) for each technician and use these technician KPIs to determine maintenance task assignments. FIG. 8 is a diagram illustrating tracking of technician KPIs 802. In general, a technician's KPIs 802 can represent quantitative measures of the technician's range of skill sets, experience in performing certain types of maintenance tasks or working on specific types of industrial assets, and past levels of success in performing various types of maintenance tasks. In some embodiments, multiple different technician KPIs 802 can be generated and tracked for each technician, with each KPI 802 representing a measure of a specific type of skill or experience (e.g., a level of controller programming experience, a level of industrial robot teaching or programming experience, a level of past success in carrying out a specific type of asset maintenance, etc.). Technician KPIs 802 can also include indications of the technicians' availabilities to perform maintenance tasks.”; Paragraph 84, “In some embodiments, the work order management system 202 can deliver notifications to relevant plant personnel when a new work order 310 is generated and scheduled, alerting those employees that the new work order 310 has been created. FIG. 9 is a diagram illustrating delivery of maintenance notifications 902 to a technician's client device 904. In response to creation of a work order 310 using any of the techniques described above, the user interface component 204 can deliver a notification 902 to the client devices 904 of technicians whom the analysis component 212 or the work order generation component 210 have designated to carry out the work order 310. The notification 902 can include any of the information described above as being rendered on the work order displays 402 illustrated in FIGS. 4 and 5, including a description of the work to be performed (e.g., a list of maintenance tasks as rendered in the Instructions box 410), the industrial asset or machine on which the maintenance is to be performed, a time at which the maintenance is scheduled, the identities of other technicians who have been assigned the work order 310, or other such information. Once created, the work order 310 can be managed through its lifecycle within the domain of the work order management system 202. This can include updating the status of the work order 310 within the system 202 as the work order's maintenance tasks are performed and ultimately closing the work order 310 upon completion of the maintenance tasks. At any time, authorized users can invoke the work order display 402 on their client devices 904 via the user interface component 204 to view detailed information about the work order 310, as well as status information for the respective maintenance tasks defined in the work order 310.”; Paragraph 89, “The Risk Level section 1004 summarizes work order performance for a specified period of time (e.g., the past week, the past day, the past month, etc.). In the illustrated example, Risk Level section 1004 categorizes the examined work orders 310 into three risk types-low risk, medium risk, and high risk-based on the degree to which performance of the work orders deviated from expected or typical performance. The categorization of a work order as being a low, medium, or high risk is determined based on the value of an anomaly score calculated by the system 202 for that work order. In an example implementation, work orders 310 having anomaly scores between 0 and 0.33 may be categorized as low risk, work orders 310 having anomaly scores between 0.34 and 0.66 may be categorized as medium risk, and work orders 310 having anomaly scores between 0.67 and 1 may be categorized as high risk. Under the Work Orders column, Risk Level section 1004 can display the total number of work orders that have been assigned to each of the three risk levels. This offers viewers a high-level summary of how many maintenance jobs were performed in a manner that deviated from expectations for those types of jobs, and the degree to which the work orders 310 were different from expected performance in one or more particulars (e.g., time spent on the job, number of personnel who worked on the job, materials or parts used on the job, etc.).”)
Claim(s) 9 –
Bamal discloses the following:
receiving a request to generate a user account at the issue tracking platform; (Bamal: Paragraph 46, “FIG. 3 is a diagram illustrating an example architecture for automatically generating work orders 310 based on analysis of real-time or historical industrial asset performance. Work order management system 202 can be implemented on any suitable platform that allows the system 202 to be accessed via client devices (e.g., desktop computers, laptop computers, smart phones, tablet computers, wearable computing devices, etc.) and that permits the system 202 to access operational and status data generated by industrial assets within a plant facility. For example, system 202 can be installed and executed on an on-premise server device on a plant or office network of an industrial facility. Alternatively, system 202 can be executed on a cloud platform as a set of cloud-based services, allowing users at different industrial facilities to access the system 202, view work orders, receive notifications generated by the system 202, or retrieve work order analysis results. System 202 can also be executed on a public network such as the internet and made accessible to users having suitable authorization credentials. In such embodiments, the system 202 can maintain work orders for different industrial enterprises in a segregated manner, such that employees of a given industrial enterprise can only access work orders and associated analysis results associated with that enterprise. In the example depicted in FIG. 3, work order management system resides and executes on a cloud platform.”)
in response to the receiving the request, causing display of an intake interface comprising a first set of selectable options; (Bamal: Paragraph 40, “User interface component 204 can be configured to generate user interface displays that receive user input and render output to the user in any suitable format (e.g., visual, audio, tactile, etc.). In some embodiments, user interface component 204 can render these interface displays on a client device (e.g., a laptop computer, tablet computer, smart phone, etc.) that is communicatively connected to the work order management system 202 (e.g., via a hardwired or wireless connection). Input data that can be received via user interface component 204 can include, but is not limited to, work order data (e.g., work order data field entries), user interface navigation input, natural language chat inputs (e.g., work order generation commands, queries regarding existing work orders or asset risks, etc.), or other such input data. Output data rendered by user interface component 204 can include, but is not limited to, information regarding closed and open work orders, risk levels associated with respective work orders, estimated costs associated with high-risk work orders, or other such output data.”; Paragraph 43, “Analysis component 212 can be configured to perform analysis on real-time or historical asset performance data, data obtained from an MES system or a similar high-level enterprise tracking system, contextual information, or other such data to determine when maintenance tasks are to be scheduled, what those maintenance tasks include, and which technicians are to be assigned the tasks. In some embodiments, the analysis component 212 can apply AI or generative AI-assisted analysis to this data in connection with determining when and how maintenance tasks should be scheduled and corresponding work orders generated.”; Paragraph 46, “FIG. 3 is a diagram illustrating an example architecture for automatically generating work orders 310 based on analysis of real-time or historical industrial asset performance. Work order management system 202 can be implemented on any suitable platform that allows the system 202 to be accessed via client devices (e.g., desktop computers, laptop computers, smart phones, tablet computers, wearable computing devices, etc.) and that permits the system 202 to access operational and status data generated by industrial assets within a plant facility. For example, system 202 can be installed and executed on an on-premise server device on a plant or office network of an industrial facility. Alternatively, system 202 can be executed on a cloud platform as a set of cloud-based services, allowing users at different industrial facilities to access the system 202, view work orders, receive notifications generated by the system 202, or retrieve work order analysis results. System 202 can also be executed on a public network such as the internet and made accessible to users having suitable authorization credentials. In such embodiments, the system 202 can maintain work orders for different industrial enterprises in a segregated manner, such that employees of a given industrial enterprise can only access work orders and associated analysis results associated with that enterprise. In the example depicted in FIG. 3, work order management system resides and executes on a cloud platform.”; Paragraph 52, “A work order 310 generated by the work order generation component 210 can contain information about the maintenance task to be performed, including but not limited to an identity of the industrial asset or machine for which maintenance is required, an aspect of the industrial asset that requires attention, a type of the maintenance to be performed, an estimated number of hours to be spent on the maintenance task, an estimated number of personnel to be assigned to the task, a description of the task, or other such information. The work order 310 is initially scheduled in the system 202 as an open work order 310 (that is, the system 202 stores the work order 310 as work order data in memory 222 and assigns an “Open” status to the work order 310) and remains open until completion of its associated maintenance tasks, at which time the system 202 assigns a “Closed” status to the work order 310.”; Paragraph 53, “Authorized users can browse and view both open and closed work orders 310 via user interface component 204. FIG. 4 is an example work order display 402 that can be rendered on a client device by the user interface component 204. When a user selects a work order 310 via interaction with the work order system's primary user interface, the user interface component 204 can render a work order display 402 and populate the display 402 with information about the work order. In the example depicted in FIG. 4, the work order display 402 comprises a work order identifier 414 that uniquely identifies the selected work order 310, a section 408 that displays general information about the work order 310 (e.g. the open or closed status, a type of maintenance to be performed, a priority, an identity of the asset on which the maintenance task is to be performed, a suggested completion date for the maintenance, a name of a project with which the maintenance task is associated, etc.), and a navigation bar 406 comprising selectable controls corresponding to respective different categories of additional information that can be viewed.”; Paragraph 111, “These generative AI-assisted techniques can allow technicians to easily generate work orders 310 using natural language text or verbal input to the system 202 (e.g., via interfaces rendered on the technicians' client devices and delivered by the user interface component 204) as the technicians are performing other tasks (e.g., upon discovering a new maintenance concern during investigation of a known issue). These approaches can also be used to easily and intuitively annotate or edit work orders using natural language voice or text input.”)
in response to detecting a selection of a second selectable option from the second set of selectable options, executing a structured search request on the issue tracking platform, the structured search request generated using data determined from the first selectable option and the second selectable option; (Bamal: Paragraph 50, “When the monitoring component 208, assisted by the analysis component 212, determines that the monitored asset data 306 satisfies a condition indicative of a current or predicted asset performance issue requiring investigation or correction by maintenance personnel, system's work order generation component 210 can schedule one or more maintenance tasks predicted to correct the performance issue and generate a corresponding work order 310 for the tasks. The condition detected by the monitoring component 208 that triggers creation of a work order 310 can be, for example, a deviation of one or more data tag values that move outside a defined range of normal or expected values. In an example scenario, a baking process may require an oven temperature to stay within a defined temperature range. Accordingly, values of a data tag or automation object corresponding to this oven temperature can be collected from the industrial controller 118 that monitors and controls the baking process, and this collected data can be provided to the work order management system 202 as part of the asset data 306. The monitoring component 208 monitors this value to determine when the oven temperature deviates from this range and, in response to detecting such a deviation, instructs work order generation component 210 to generate a new open work order 310 for investigation of the temperature control issue. In some embodiments, machine-specific asset models maintained on the work order management system 202 can define which data items or performance parameters of the industrial assets are to be monitored, as well as the conditions of this data that are to trigger creation of work orders 310. In other embodiments, as will be described in more detail below, the system 202 can learn to recognize conditions of the asset data indicative of an elevated risk to an asset using machine learning, AI, generative AI, or other analytic techniques.”; Paragraph 65, “The interdependencies between industrial assets defined in the plant model 314 can be used by the analysis component 212 to identify opportunities for opportunistic maintenance scheduling, which can improve maintenance efficiency. For example, when the work order generation component 210 schedules a maintenance activity (and generates a corresponding work order 310) for a given industrial asset to mitigate a discovered risk, the analysis component 212 can also determine whether the discovered risk is likely to also affect other similar machines or components (as determined in part based on the assets defined in the plant model 314) and schedule work orders 310 to perform similar maintenance tasks on those similar assets. The analysis component 212 can also determine whether other assets that are downstream from the affected asset are likely to be impacted by the discovered risk, or by the maintenance action performed on the affected upstream asset. If so, the analysis component 212 can instruct the work order generation component 210 to include, as part of the maintenance instructions defined in the work order 310 for the affected asset, recommendations for addressing any related issues on the downstream assets. In another example, when a machine shutdown is scheduled to address a discovered high-risk issue, the analysis component 212 can identify other lower-risk issues that could also be addressed during the machine shutdown, and generate work orders 310 to address these lower-risk issues as part of the same maintenance session. In any of these examples, the analysis component 212 can reference the defined interdependencies between industrial machines or assets defined in the plant model 314 in order to identify other assets that may be affected by a machine risk (e.g., assets that are downstream from, or otherwise have a functional relationship with, the affected asset), similar assets that may be subject to a common risk, etc.”; Paragraph 66, “In some embodiments, the analysis component 212 can schedule and assign a work order 310 for a discovered asset risk based in part on a risk-reward assessment that considers the benefit of performing the work order against the risk to the affected asset. For example, machines that are especially crucial to plant operations may require the result of the analysis component's risk-reward assessment to exceed a higher benefit threshold, relative to less crucial machines, to justify any risks associated with performing the maintenance action on the machine (e.g., lost productivity or risk of damage due to improper execution of the work order).”)
subsequent to receiving a set of issues in response to executing the structured search request: (Bamal: Paragraph 50, “When the monitoring component 208, assisted by the analysis component 212, determines that the monitored asset data 306 satisfies a condition indicative of a current or predicted asset performance issue requiring investigation or correction by maintenance personnel, system's work order generation component 210 can schedule one or more maintenance tasks predicted to correct the performance issue and generate a corresponding work order 310 for the tasks. The condition detected by the monitoring component 208 that triggers creation of a work order 310 can be, for example, a deviation of one or more data tag values that move outside a defined range of normal or expected values. In an example scenario, a baking process may require an oven temperature to stay within a defined temperature range. Accordingly, values of a data tag or automation object corresponding to this oven temperature can be collected from the industrial controller 118 that monitors and controls the baking process, and this collected data can be provided to the work order management system 202 as part of the asset data 306. The monitoring component 208 monitors this value to determine when the oven temperature deviates from this range and, in response to detecting such a deviation, instructs work order generation component 210 to generate a new open work order 310 for investigation of the temperature control issue. In some embodiments, machine-specific asset models maintained on the work order management system 202 can define which data items or performance parameters of the industrial assets are to be monitored, as well as the conditions of this data that are to trigger creation of work orders 310. In other embodiments, as will be described in more detail below, the system 202 can learn to recognize conditions of the asset data indicative of an elevated risk to an asset using machine learning, AI, generative AI, or other analytic techniques.”; Paragraph 65, “The interdependencies between industrial assets defined in the plant model 314 can be used by the analysis component 212 to identify opportunities for opportunistic maintenance scheduling, which can improve maintenance efficiency. For example, when the work order generation component 210 schedules a maintenance activity (and generates a corresponding work order 310) for a given industrial asset to mitigate a discovered risk, the analysis component 212 can also determine whether the discovered risk is likely to also affect other similar machines or components (as determined in part based on the assets defined in the plant model 314) and schedule work orders 310 to perform similar maintenance tasks on those similar assets. The analysis component 212 can also determine whether other assets that are downstream from the affected asset are likely to be impacted by the discovered risk, or by the maintenance action performed on the affected upstream asset. If so, the analysis component 212 can instruct the work order generation component 210 to include, as part of the maintenance instructions defined in the work order 310 for the affected asset, recommendations for addressing any related issues on the downstream assets. In another example, when a machine shutdown is scheduled to address a discovered high-risk issue, the analysis component 212 can identify other lower-risk issues that could also be addressed during the machine shutdown, and generate work orders 310 to address these lower-risk issues as part of the same maintenance session. In any of these examples, the analysis component 212 can reference the defined interdependencies between industrial machines or assets defined in the plant model 314 in order to identify other assets that may be affected by a machine risk (e.g., assets that are downstream from, or otherwise have a functional relationship with, the affected asset), similar assets that may be subject to a common risk, etc.”; Paragraph 66, “In some embodiments, the analysis component 212 can schedule and assign a work order 310 for a discovered asset risk based in part on a risk-reward assessment that considers the benefit of performing the work order against the risk to the affected asset. For example, machines that are especially crucial to plant operations may require the result of the analysis component's risk-reward assessment to exceed a higher benefit threshold, relative to less crucial machines, to justify any risks associated with performing the maintenance action on the machine (e.g., lost productivity or risk of damage due to improper execution of the work order).”)
causing generation of a prompt comprising: (Bamal: Paragraph 56, “Returning to FIG. 3, to facilitate intelligent automated generation of work orders 310, the monitoring component 208 is assisted by an analysis component 212 that can apply one or more types of analysis (e.g., AI, generative AI analysis or generative AI-assisted analysis, machine learning, etc.) to real-time or historical asset data 306, MES data 316 from the plant facility's MES system or another high-level plant managements system, and other contextual data in connection with determining when to schedule maintenance tasks, what these maintenance tasks entail, and which technicians are to be assigned the tasks. For example, in some embodiments, the analysis component 212 can leverage generative AI to auto-generate work orders 310 or otherwise schedule maintenance tasks based on predicted or detected asset risks. In such embodiments, the analysis component 212 can implement prompt engineering functionality using associated trained models 312 trained with various types of training data, and can use these prompt engineering features to interface with a generative AI model 308 (e.g., an LLM or another type of model) and associated neural networks.”; Paragraph 61, “Returning to FIG. 6, during the asset monitoring process, the analysis component 212 can formulate and submits prompts 604 to the generative AI model 308 designed to obtain responses 606 that can assist with monitoring the performance of industrial assets for risk conditions, formulating maintenance strategies for mitigating the risk conditions, or generating content of a work order 310. The analysis component 212 can generate these prompts 604 based on a current operating context of one or more industrial assets being monitored (as determined from real-time or historical asset data 306) as well as the training data 602 encoded in the trained models 312. The analysis component 212 can reference the trained models 312 or associated training data 602 as needed in connection with creating prompts 604 designed to obtain responses 606 from the generative AI model 308 that assist the analysis component 212 in recognizing a current or predicted risk to an industrial asset, formulating a maintenance intervention for mitigating the risk, or generating content of a work order 310 for scheduling the maintenance intervention (e.g., natural language summaries of the identified asset risk, as well as descriptions of the maintenance tasks for mitigating the risk). The analysis component 212 can generate the prompt 604 to include any relevant information that can assist the generative AI model 308 in converging on a useful responses 606 that can be used to better understand a current context of the industrial assets, including but not limited to a selected subset of the asset data itself 306, an identity of the type of industrial asset of interest (e.g., a type of machine or industrial device), an indication of the type of industrial process or application being carried out by the industrial asset of interest (e.g., a specific type of batch processing, a specific automotive manufacturing function, a sheet metal stamping application, etc.), any selected subsets of the training data 602 or MES data 316, or other such data.”)
issue data extracted from the set of issues; and prompt text including a command to generate new issue data for one or more new issues and a formatting command; (Bamal: Paragraph 56, “Returning to FIG. 3, to facilitate intelligent automated generation of work orders 310, the monitoring component 208 is assisted by an analysis component 212 that can apply one or more types of analysis (e.g., AI, generative AI analysis or generative AI-assisted analysis, machine learning, etc.) to real-time or historical asset data 306, MES data 316 from the plant facility's MES system or another high-level plant managements system, and other contextual data in connection with determining when to schedule maintenance tasks, what these maintenance tasks entail, and which technicians are to be assigned the tasks. For example, in some embodiments, the analysis component 212 can leverage generative AI to auto-generate work orders 310 or otherwise schedule maintenance tasks based on predicted or detected asset risks. In such embodiments, the analysis component 212 can implement prompt engineering functionality using associated trained models 312 trained with various types of training data, and can use these prompt engineering features to interface with a generative AI model 308 (e.g., an LLM or another type of model) and associated neural networks.”; Paragraph 70, “As in previous examples, the analysis component 212 can leverage generative AI as needed to assist in determining whether values or trends in the monitored asset data 306 indicate, or are correlated with, an elevated risk of failure of an asset. For example, during monitoring of the asset data 306, the analysis component 212 may generate prompts 604 directed to the generative AI model 308 that are designed to obtain responses 606 (see FIG. 6) providing technical information about an asset whose performance or behavior is deviating from normal parameters, and can reference the information in these responses 606 in connection with determining whether a maintenance action should be performed on the asset, determining what this maintenance action should entail, and populating the content of a new work order 310 for performing this maintenance action.”; Paragraph 99, “The analysis component 212 can formulate recommendations for addressing a discovered asset risk based on such factors as the nature of the risk; the type of industrial asset, device, or process that is subject to the risk (e.g., a sheet metal stamping press, a mixer, a conveyor, a die cast machine, an industrial controller, a motor drive, etc.); a function of the industrial asset within the plant's operations and/or the asset's relationship with other assets (as determined, for example, based on information in the plant model 314 about the organization of the plant's assets); technical information about the asset (as obtained, for example, from the training data 602 or from responses 606 prompted from the generative AI model 308 by the analysis component 212); or other such information. In some embodiments, the analysis component 212 can formulate the language of these risk-mitigation recommendations with the assistance of generative AI model 308, and display these natural language recommendations on display 1002 or another interface display. The analysis component 212 can also proactively generate work orders 310 to perform the recommended risk-mitigation actions upon discovery of these asset risks, populating the work orders 310 with information about the recommended maintenance tasks (which can be generated with the assistance of the generative AI model 308).”)
providing the prompt to a generative output engine; (Bamal: Paragraph 56, “Returning to FIG. 3, to facilitate intelligent automated generation of work orders 310, the monitoring component 208 is assisted by an analysis component 212 that can apply one or more types of analysis (e.g., AI, generative AI analysis or generative AI-assisted analysis, machine learning, etc.) to real-time or historical asset data 306, MES data 316 from the plant facility's MES system or another high-level plant managements system, and other contextual data in connection with determining when to schedule maintenance tasks, what these maintenance tasks entail, and which technicians are to be assigned the tasks. For example, in some embodiments, the analysis component 212 can leverage generative AI to auto-generate work orders 310 or otherwise schedule maintenance tasks based on predicted or detected asset risks. In such embodiments, the analysis component 212 can implement prompt engineering functionality using associated trained models 312 trained with various types of training data, and can use these prompt engineering features to interface with a generative AI model 308 (e.g., an LLM or another type of model) and associated neural networks.”; Paragraph 70, “As in previous examples, the analysis component 212 can leverage generative AI as needed to assist in determining whether values or trends in the monitored asset data 306 indicate, or are correlated with, an elevated risk of failure of an asset. For example, during monitoring of the asset data 306, the analysis component 212 may generate prompts 604 directed to the generative AI model 308 that are designed to obtain responses 606 (see FIG. 6) providing technical information about an asset whose performance or behavior is deviating from normal parameters, and can reference the information in these responses 606 in connection with determining whether a maintenance action should be performed on the asset, determining what this maintenance action should entail, and populating the content of a new work order 310 for performing this maintenance action.”; Paragraph 99, “The analysis component 212 can formulate recommendations for addressing a discovered asset risk based on such factors as the nature of the risk; the type of industrial asset, device, or process that is subject to the risk (e.g., a sheet metal stamping press, a mixer, a conveyor, a die cast machine, an industrial controller, a motor drive, etc.); a function of the industrial asset within the plant's operations and/or the asset's relationship with other assets (as determined, for example, based on information in the plant model 314 about the organization of the plant's assets); technical information about the asset (as obtained, for example, from the training data 602 or from responses 606 prompted from the generative AI model 308 by the analysis component 212); or other such information. In some embodiments, the analysis component 212 can formulate the language of these risk-mitigation recommendations with the assistance of generative AI model 308, and display these natural language recommendations on display 1002 or another interface display. The analysis component 212 can also proactively generate work orders 310 to perform the recommended risk-mitigation actions upon discovery of these asset risks, populating the work orders 310 with information about the recommended maintenance tasks (which can be generated with the assistance of the generative AI model 308).”)
receiving a generative response from the generative output engine, the generative response produced by the generative output engine in response to the prompt and formatted in accordance with the formatting command; (Bamal: Paragraph 56, “Returning to FIG. 3, to facilitate intelligent automated generation of work orders 310, the monitoring component 208 is assisted by an analysis component 212 that can apply one or more types of analysis (e.g., AI, generative AI analysis or generative AI-assisted analysis, machine learning, etc.) to real-time or historical asset data 306, MES data 316 from the plant facility's MES system or another high-level plant managements system, and other contextual data in connection with determining when to schedule maintenance tasks, what these maintenance tasks entail, and which technicians are to be assigned the tasks. For example, in some embodiments, the analysis component 212 can leverage generative AI to auto-generate work orders 310 or otherwise schedule maintenance tasks based on predicted or detected asset risks. In such embodiments, the analysis component 212 can implement prompt engineering functionality using associated trained models 312 trained with various types of training data, and can use these prompt engineering features to interface with a generative AI model 308 (e.g., an LLM or another type of model) and associated neural networks.”; Paragraph 70, “As in previous examples, the analysis component 212 can leverage generative AI as needed to assist in determining whether values or trends in the monitored asset data 306 indicate, or are correlated with, an elevated risk of failure of an asset. For example, during monitoring of the asset data 306, the analysis component 212 may generate prompts 604 directed to the generative AI model 308 that are designed to obtain responses 606 (see FIG. 6) providing technical information about an asset whose performance or behavior is deviating from normal parameters, and can reference the information in these responses 606 in connection with determining whether a maintenance action should be performed on the asset, determining what this maintenance action should entail, and populating the content of a new work order 310 for performing this maintenance action.”; Paragraph 99, “The analysis component 212 can formulate recommendations for addressing a discovered asset risk based on such factors as the nature of the risk; the type of industrial asset, device, or process that is subject to the risk (e.g., a sheet metal stamping press, a mixer, a conveyor, a die cast machine, an industrial controller, a motor drive, etc.); a function of the industrial asset within the plant's operations and/or the asset's relationship with other assets (as determined, for example, based on information in the plant model 314 about the organization of the plant's assets); technical information about the asset (as obtained, for example, from the training data 602 or from responses 606 prompted from the generative AI model 308 by the analysis component 212); or other such information. In some embodiments, the analysis component 212 can formulate the language of these risk-mitigation recommendations with the assistance of generative AI model 308, and display these natural language recommendations on display 1002 or another interface display. The analysis component 212 can also proactively generate work orders 310 to perform the recommended risk-mitigation actions upon discovery of these asset risks, populating the work orders 310 with information about the recommended maintenance tasks (which can be generated with the assistance of the generative AI model 308).”; Paragraph 107, “In another example scenario, a user wishing to generate a work order 310 for carrying out a specific maintenance task, or who has a question about an existing work order 310, can submit an initial natural language request or query 1106 that broadly defines the maintenance task to be scheduled or the information being requested. In the case of generating a work order 310 using generative AI, the initial request can specify the asset of interest, a type of maintenance to be performed, a technician to be assigned to the maintenance, or other such information. For queries regarding a work order 310, the initial query 1106 may specify information that can assist the system 202 in identifying the work order 310 and the nature of the information requested. The analysis component 212 can parse this initial request or query 1106 to determine the type of information or service being requested, and refine and contextualize the initial query 1106 in a manner expected to assist the trained models 312 and the generative AI model 308 to accurately generate a suitable work order 310 or a response 1102 to the user's question. If the analysis component 212 determines that additional information from the user would yield a response having a higher probability of satisfying the user's initial request, the analysis component 212 can formulate and render one or more query responses 1102 that prompt the user for more refined information that will allow the analysis component 212 to more accurately respond to the user's request. Through iterations of such chat exchanges, the analysis component 212 can collaborate with the user in exploring potential response variations likely to satisfy the user's needs.”; Paragraph 108, “The analysis component 212 can use a range of approaches for processing a natural language request or query 1106 submitted by the user, and for formulating prompts 604 to the generative AI model 308 designed to yield responses 606 that assist in responding to the user's request or query 1106. According to an example approach, the analysis component 212 can access an archive of chat exchanges between the analysis component 212 and other users and identify chat sessions that were initiated by user queries having similarities to the initial query 1106 submitted by the present user. Upon identifying these archived chat sessions, the analysis component 212 can analyze these past chat sessions to determine types of information that were ultimately generated as a result of these sessions (e.g., work orders 310 having features or elements that are a function of specific keywords of the user's query, a specific type of information about a work order 310 or set of work orders 310 that was ultimately determined to be sought by the user, etc.), and either generate an output (e.g., a work order 310 or a natural language response 1102 to the user's query 1106) based on the outcomes of these past chat sessions and adapted to the user's initial request or query 1106, or, if necessary, generate a prompt 604 for submission to the generative AI model 308 designed to obtain a response 606 comprising the necessary type of information.”)
analyzing the generative response to identify a plurality of issue data sets; ; (Bamal: Paragraph 64, “The work order management system 202 can consider any of the information from the trained models 312 or their associated training data 602 (e.g., technical information about industrial assets, technician skill sets, previous work orders, plant financial data, plant schedules, etc.), MES data 316 (which may include some of the training data 602 described above), prompted responses 606 from the generative AI model 308, or the plant model 314 in connection with determining whether a maintenance task should be scheduled for an industrial asset, when the task should be scheduled, and to which technicians the task should be assigned. For example, when the monitoring component 208 or analysis component 212 detect or predict, based on analysis of asset data 306, a risk condition requiring a maintenance action, the analysis component 212 can determine whether deferring the maintenance action until an upcoming planned machine shutdown would minimize a cost of the maintenance without incurring a cost associated with the risk, and if so, generate the work order 310 for the maintenance action such that corresponding maintenance tasks are scheduled to be performed during the shutdown period. To make this decision, the analysis component 212 can consider the machine's operating or shutdown schedule (as determined from the MES data 316), the cost of technicians' time during the shut down versus the cost of the technicians' time during the machine's scheduled operation, a cost associated with prolonging the asset risk until the shutdown relative to the cost of mitigating the risk sooner, or other such factors.”; Paragraph 65, “The interdependencies between industrial assets defined in the plant model 314 can be used by the analysis component 212 to identify opportunities for opportunistic maintenance scheduling, which can improve maintenance efficiency. For example, when the work order generation component 210 schedules a maintenance activity (and generates a corresponding work order 310) for a given industrial asset to mitigate a discovered risk, the analysis component 212 can also determine whether the discovered risk is likely to also affect other similar machines or components (as determined in part based on the assets defined in the plant model 314) and schedule work orders 310 to perform similar maintenance tasks on those similar assets. The analysis component 212 can also determine whether other assets that are downstream from the affected asset are likely to be impacted by the discovered risk, or by the maintenance action performed on the affected upstream asset. If so, the analysis component 212 can instruct the work order generation component 210 to include, as part of the maintenance instructions defined in the work order 310 for the affected asset, recommendations for addressing any related issues on the downstream assets. In another example, when a machine shutdown is scheduled to address a discovered high-risk issue, the analysis component 212 can identify other lower-risk issues that could also be addressed during the machine shutdown, and generate work orders 310 to address these lower-risk issues as part of the same maintenance session. In any of these examples, the analysis component 212 can reference the defined interdependencies between industrial machines or assets defined in the plant model 314 in order to identify other assets that may be affected by a machine risk (e.g., assets that are downstream from, or otherwise have a functional relationship with, the affected asset), similar assets that may be subject to a common risk, etc.”; Paragraph 70, “As in previous examples, the analysis component 212 can leverage generative AI as needed to assist in determining whether values or trends in the monitored asset data 306 indicate, or are correlated with, an elevated risk of failure of an asset. For example, during monitoring of the asset data 306, the analysis component 212 may generate prompts 604 directed to the generative AI model 308 that are designed to obtain responses 606 (see FIG. 6) providing technical information about an asset whose performance or behavior is deviating from normal parameters, and can reference the information in these responses 606 in connection with determining whether a maintenance action should be performed on the asset, determining what this maintenance action should entail, and populating the content of a new work order 310 for performing this maintenance action.”; Paragraph 105, “In addition to referencing the information contained in the trained models 312 or plant model 314, the analysis component 212 can also, as needed, prompt the generative AI model 308 for responses 606 that assist in generating suitable responses 1102 or work orders 310 in response to the user's natural language request or query 1106. For example, in response to receipt of a natural language request or query 1106, the analysis component 212 can determine whether a sufficiently accurate response 1102 to the query 1106 (or a work order 310 satisfying the user's maintenance scheduling request) can be generated based on relevant information contained in the trained models 312 alone, or, alternatively, whether supplemental information from the generative AI model 308 is necessary to formulate a response 1102 having a sufficiently high probability of satisfying the user's request or query 1106 (or to generate a work order 310 having a sufficiently high probability of satisfying the request conveyed in the query 1106). If supplemental information from the generative AI model 308 is deemed necessary, the analysis component 212 can formulate prompts 604 based on analysis of the request or query 1106 and the knowledge encoded in any of the trained models 312 or plant model 314. These prompts 604 are designed to obtain responses 606 from the generative AI model 308 that can be used to formulate accurate and cohesive responses 1102 to the user's query 1106, or to generate work orders 310 that satisfy the user's natural language request.”)
Bamal does not explicitly disclose the following, however, in analogous art of task planning and management, Ponce De Leon discloses the following:
in response to detecting a selection of a first selectable option from the first set of selectable options, causing display of a second set of selectable options at the intake interface, the second set of selectable options determined using the first selectable option and a defined set of parameters; (Ponce De Leon: Column 12 lines 5 – 47, “The system may provide project resources based on a number of predefined characteristics. These characteristics may include resource type, category, cost, and color, color shading and/or hatching pattern to be assigned to the resource for display. The resource type may be user definable. Examples of resource type in the construction industry include carpenter, backhoe, concrete, etc. Other resource types in other industries may be defined by the user. The user may include any level of specificity in defining resource types. For example, the user may define a carpenter with specific training, a backhoe with specific lift capacity, and specific grade of concrete, etc. The system may also provide a listing of resource types for the user to select, which may be divided at any level of granularity and may be categorized based on industry. The system may also provide the user with a list of resource categories for the user to select, e.g. labor, equipment, material, commodity, professional, etc. For example, carpenter may fall under the category "labor," backhoe may fall under the category "equipment," and concrete may fall under the category "material." The system may offer any number of resource categories for the user to select and associate with the resource type. The user may also customize resource categories. The system may also provide the user with a palette of colors to select to associate with the resources. The system may also provide the user with a selection of hatching patterns to associate with the resources.”)
subsequent to identifying the plurality of issue data sets, causing creation of a project and causing creation of a set of new issues, the set of new issues assigned to the project and including data extracted from the plurality of issue data sets; and (Ponce De Leon: Column 4 line 59 – Column 5 line 6, “GPM fundamentally differs from CPM scheduling systems by providing evolving dates, floats, resource profiles and cost curves in real time to a user, while the user is constructing the schedule. With GPM, the planning and scheduling steps are consolidated, which increases network construction efficiency and accuracy. Moreover, combining GPM with an interactive display creates a kinetic linkage between the visual representation of the plan and the abstract cognition of users generating the plan. Users may perform resource leveling, schedule optimization, and time/cost tradeoffs interactively on the display and simultaneously with network construction. GPM algorithms also allow users to switch from constructing network schedules forward from release dates to backwards from target dates and vice versa.”; Column 7 lines 49 – 67, “The object processor 108 may create any number of objects within the constraints of storage capacity. The object processor 108 may also create a number of object types. For example, the object processor 108 may create objects representative of activities, milestones, benchmarks, embedded nodes, logic relationships, data dates, and project ends, or project start and end dates. These objects may be classified as planning objects as they affect the logic and dependency relationships in the schedule. The object processor 108 may also create objects classified as aesthetic objects as they may be used to increase the understandability and/or aesthetic presentation of the schedule. Examples of aesthetic objects include text, annotations, which is different from text in that annotations are embedded within the object, images, resource-axis, which define the vertical axis of the resource profile graphs, and information objects, which may be used to connect to a file from an external application, for example, a user may embed a document into the schedule by storing the path of the document with the information object.”; Column 17 lines 50 – 67, “An exemplary collaborative and full wall planning session 1700 is illustrated at FIG. 17. With reference to FIG. 17, the system may provide the following advantages to a full wall planning session: high resolution graphical interface 1702 that enhances the interaction between all stakeholders 1704; ability to graphically create and link network dependencies 1706; graphical nature allows network to be clearly understood and easy to create and edit; identify the resources needed to complete the project; graphical display of resources 1708 to allow for the best placement of tasks and stakeholders 1704 to plan for their level of effort; facilitation of a quick and interactive project planning and scheduling session; ability to test alternative approaches and evaluate performance; easily identify the critical path for a project; ability to add information text, annotations and information objects to enrich plan; ability to determine what action is necessary to keep project on schedule; and monitor percent complete and show the real possibility of meeting the deadline.”)
causing display of a project interface comprising issue objects based on the set of new issues. (Ponce De Leon: Column 4 line 59 – Column 5 line 6, “GPM fundamentally differs from CPM scheduling systems by providing evolving dates, floats, resource profiles and cost curves in real time to a user, while the user is constructing the schedule. With GPM, the planning and scheduling steps are consolidated, which increases network construction efficiency and accuracy. Moreover, combining GPM with an interactive display creates a kinetic linkage between the visual representation of the plan and the abstract cognition of users generating the plan. Users may perform resource leveling, schedule optimization, and time/cost tradeoffs interactively on the display and simultaneously with network construction. GPM algorithms also allow users to switch from constructing network schedules forward from release dates to backwards from target dates and vice versa.”; Column 7 lines 49 – 67, “The object processor 108 may create any number of objects within the constraints of storage capacity. The object processor 108 may also create a number of object types. For example, the object processor 108 may create objects representative of activities, milestones, benchmarks, embedded nodes, logic relationships, data dates, and project ends, or project start and end dates. These objects may be classified as planning objects as they affect the logic and dependency relationships in the schedule. The object processor 108 may also create objects classified as aesthetic objects as they may be used to increase the understandability and/or aesthetic presentation of the schedule. Examples of aesthetic objects include text, annotations, which is different from text in that annotations are embedded within the object, images, resource-axis, which define the vertical axis of the resource profile graphs, and information objects, which may be used to connect to a file from an external application, for example, a user may embed a document into the schedule by storing the path of the document with the information object.”; Column 17 lines 50 – 67, “An exemplary collaborative and full wall planning session 1700 is illustrated at FIG. 17. With reference to FIG. 17, the system may provide the following advantages to a full wall planning session: high resolution graphical interface 1702 that enhances the interaction between all stakeholders 1704; ability to graphically create and link network dependencies 1706; graphical nature allows network to be clearly understood and easy to create and edit; identify the resources needed to complete the project; graphical display of resources 1708 to allow for the best placement of tasks and stakeholders 1704 to plan for their level of effort; facilitation of a quick and interactive project planning and scheduling session; ability to test alternative approaches and evaluate performance; easily identify the critical path for a project; ability to add information text, annotations and information objects to enrich plan; ability to determine what action is necessary to keep project on schedule; and monitor percent complete and show the real possibility of meeting the deadline.”)
Bamal discloses a method of using generative prompts to track, manage, and create tasks and issues. Ponce De Leon discloses a method for a graphical platform for tracking tasks across a larger project. At the time of Applicant’s filed invention, one of ordinary skill in the art would have deemed it obvious to combine the methods of Bamal with the teachings of Ponce De Leon in order to increase the efficiency of scheduling and planning as disclosed by Ponce De Leon (Ponce De Leon: Column 4 line 59 – Column 5 line 5, “GPM algorithms also allow users to switch from constructing network schedules forward from release dates to backwards from target dates and vice versa.”)
Claim(s) 10 –
Bamal in view of Ponce De Leon disclose the limitations of claim 9
Bamal further discloses the following:
the set of new issues is associated with the user account; and (Bamal: Paragraph 77, “To assist with this work order assignment analysis, the analysis component 212 can reference relevant subsets of the plant facility's MES data 316 that identify the technicians associated with the plant facility as well as the respective technicians' work schedules and skill sets. For example, if the MES system maintains information regarding the roles and availability schedules of plant personnel, the MES interface component 214 can retrieve this information as MES data 316, and the analysis component 212 can analyze this data 316 to determine identities of technicians who are qualified to attend to the maintenance task and whose schedules indicate that the technicians are available to work on the task within the time frame defined by the work order 310. In general, the analysis component 212 can match the work order's maintenance tasks to a selected subset of technicians based on best fit criteria that considers the technicians' relative levels of experience or skill in performing the maintenance tasks, relevant skill sets, work schedules, availability bandwidths, or other factors (some or all of which can be obtained from the plant's MES system as MES data 316).”; Paragraph 79, “The analysis component 212 can generate and tracks each technician's KPIs 802 based on MES data 316 obtained from the plant's MES system (or another high-level business or management system used by the plant) by the MES interface component 214, including the identities of the technicians registered to perform maintenance within the facility, the work schedules of those technicians, information regarding the technician's skill sets (e.g., certifications, training, technical roles, etc.), or other such information. Additionally, for each technician, the analysis component 212 can monitor the content of closed or past work orders 310 that had been assigned to the technician to determine the degrees of experience the technician has had in performing various types of maintenance or working on specific machines or assets (e.g., replacing specific types of parts or machine components, recovering a specified machine from a downtime conditions, cleaning, inspections, etc.), translate these degrees of experience to corresponding KPI values indicating the technician's relative degrees of experience in these maintenance tasks, and assign these KPI values to the technician.”; Paragraph 81, “Using technician KPIs 802 or other metrics of respective technicians' skill sets and levels of maintenance experiences, the analysis component 212 can assess which technicians perform best on certain types of maintenance jobs and assign work orders 310 accordingly. If it is known that a work order 310 being generated by the work order generation component 210 requires certain specific skills (PLC programming, robot path teaching, etc.), the analysis component 212 can instruct the work order generation component 210 to assign the work order 310 to a technician having the necessary skills and experience. In some embodiments, the analysis component 212 can also determine whether a work order 310 in the process of being generated carries a level of risk that exceeds a defined threshold (e.g., due to the relative importance of the affected asset and the expected loss in productivity if the maintenance is not performed correctly, or due to a higher safety risk associated with the work order 310), and if so, assign the work order 310 to a technician whose KPIs 801 indicate a relatively high level of experience, or to a higher number of technicians than would typically be assigned in order to reduce the risk to high-value assets.”)
the set of new issues is processed in accordance with an issue workflow defined for each issue of the set of new issues. (Bamal: Paragraph 52, “A work order 310 generated by the work order generation component 210 can contain information about the maintenance task to be performed, including but not limited to an identity of the industrial asset or machine for which maintenance is required, an aspect of the industrial asset that requires attention, a type of the maintenance to be performed, an estimated number of hours to be spent on the maintenance task, an estimated number of personnel to be assigned to the task, a description of the task, or other such information. The work order 310 is initially scheduled in the system 202 as an open work order 310 (that is, the system 202 stores the work order 310 as work order data in memory 222 and assigns an “Open” status to the work order 310) and remains open until completion of its associated maintenance tasks, at which time the system 202 assigns a “Closed” status to the work order 310.”; Paragraph 53, “Authorized users can browse and view both open and closed work orders 310 via user interface component 204. FIG. 4 is an example work order display 402 that can be rendered on a client device by the user interface component 204. When a user selects a work order 310 via interaction with the work order system's primary user interface, the user interface component 204 can render a work order display 402 and populate the display 402 with information about the work order. In the example depicted in FIG. 4, the work order display 402 comprises a work order identifier 414 that uniquely identifies the selected work order 310, a section 408 that displays general information about the work order 310 (e.g. the open or closed status, a type of maintenance to be performed, a priority, an identity of the asset on which the maintenance task is to be performed, a suggested completion date for the maintenance, a name of a project with which the maintenance task is associated, etc.), and a navigation bar 406 comprising selectable controls corresponding to respective different categories of additional information that can be viewed.”)
Claim(s) 11 –
Bamal in view of Ponce De Leon disclose the limitations of claim 9
Bamal further discloses the following:
wherein the plurality of issue data sets comprise, for each issue of the set of new issues, a respective title, a respective issue description, a respective defined project workflow, one or more hierarchical relationships, or combinations thereof. (Bamal: Paragraph 52, “A work order 310 generated by the work order generation component 210 can contain information about the maintenance task to be performed, including but not limited to an identity of the industrial asset or machine for which maintenance is required, an aspect of the industrial asset that requires attention, a type of the maintenance to be performed, an estimated number of hours to be spent on the maintenance task, an estimated number of personnel to be assigned to the task, a description of the task, or other such information. The work order 310 is initially scheduled in the system 202 as an open work order 310 (that is, the system 202 stores the work order 310 as work order data in memory 222 and assigns an “Open” status to the work order 310) and remains open until completion of its associated maintenance tasks, at which time the system 202 assigns a “Closed” status to the work order 310.”; Paragraph 53, “Authorized users can browse and view both open and closed work orders 310 via user interface component 204. FIG. 4 is an example work order display 402 that can be rendered on a client device by the user interface component 204. When a user selects a work order 310 via interaction with the work order system's primary user interface, the user interface component 204 can render a work order display 402 and populate the display 402 with information about the work order. In the example depicted in FIG. 4, the work order display 402 comprises a work order identifier 414 that uniquely identifies the selected work order 310, a section 408 that displays general information about the work order 310 (e.g. the open or closed status, a type of maintenance to be performed, a priority, an identity of the asset on which the maintenance task is to be performed, a suggested completion date for the maintenance, a name of a project with which the maintenance task is associated, etc.), and a navigation bar 406 comprising selectable controls corresponding to respective different categories of additional information that can be viewed.”)
Claim(s) 12 –
Bamal in view of Ponce De Leon disclose the limitations of claim 9
Bamal further discloses the following:
the first set of selectable options comprises options related to defined user roles configured at the issue tracking platform; and (Bamal: Paragraph 77, “To assist with this work order assignment analysis, the analysis component 212 can reference relevant subsets of the plant facility's MES data 316 that identify the technicians associated with the plant facility as well as the respective technicians' work schedules and skill sets. For example, if the MES system maintains information regarding the roles and availability schedules of plant personnel, the MES interface component 214 can retrieve this information as MES data 316, and the analysis component 212 can analyze this data 316 to determine identities of technicians who are qualified to attend to the maintenance task and whose schedules indicate that the technicians are available to work on the task within the time frame defined by the work order 310. In general, the analysis component 212 can match the work order's maintenance tasks to a selected subset of technicians based on best fit criteria that considers the technicians' relative levels of experience or skill in performing the maintenance tasks, relevant skill sets, work schedules, availability bandwidths, or other factors (some or all of which can be obtained from the plant's MES system as MES data 316).”; Paragraph 79, “The analysis component 212 can generate and tracks each technician's KPIs 802 based on MES data 316 obtained from the plant's MES system (or another high-level business or management system used by the plant) by the MES interface component 214, including the identities of the technicians registered to perform maintenance within the facility, the work schedules of those technicians, information regarding the technician's skill sets (e.g., certifications, training, technical roles, etc.), or other such information. Additionally, for each technician, the analysis component 212 can monitor the content of closed or past work orders 310 that had been assigned to the technician to determine the degrees of experience the technician has had in performing various types of maintenance or working on specific machines or assets (e.g., replacing specific types of parts or machine components, recovering a specified machine from a downtime conditions, cleaning, inspections, etc.), translate these degrees of experience to corresponding KPI values indicating the technician's relative degrees of experience in these maintenance tasks, and assign these KPI values to the technician.”; Paragraph 81, “Using technician KPIs 802 or other metrics of respective technicians' skill sets and levels of maintenance experiences, the analysis component 212 can assess which technicians perform best on certain types of maintenance jobs and assign work orders 310 accordingly. If it is known that a work order 310 being generated by the work order generation component 210 requires certain specific skills (PLC programming, robot path teaching, etc.), the analysis component 212 can instruct the work order generation component 210 to assign the work order 310 to a technician having the necessary skills and experience. In some embodiments, the analysis component 212 can also determine whether a work order 310 in the process of being generated carries a level of risk that exceeds a defined threshold (e.g., due to the relative importance of the affected asset and the expected loss in productivity if the maintenance is not performed correctly, or due to a higher safety risk associated with the work order 310), and if so, assign the work order 310 to a technician whose KPIs 801 indicate a relatively high level of experience, or to a higher number of technicians than would typically be assigned in order to reduce the risk to high-value assets.”)
the second set of selectable options comprises options related to project type classifiers configured at the issue tracking platform. (Bamal: Paragraph 40, “User interface component 204 can be configured to generate user interface displays that receive user input and render output to the user in any suitable format (e.g., visual, audio, tactile, etc.). In some embodiments, user interface component 204 can render these interface displays on a client device (e.g., a laptop computer, tablet computer, smart phone, etc.) that is communicatively connected to the work order management system 202 (e.g., via a hardwired or wireless connection). Input data that can be received via user interface component 204 can include, but is not limited to, work order data (e.g., work order data field entries), user interface navigation input, natural language chat inputs (e.g., work order generation commands, queries regarding existing work orders or asset risks, etc.), or other such input data. Output data rendered by user interface component 204 can include, but is not limited to, information regarding closed and open work orders, risk levels associated with respective work orders, estimated costs associated with high-risk work orders, or other such output data.”; Paragraph 43, “Analysis component 212 can be configured to perform analysis on real-time or historical asset performance data, data obtained from an MES system or a similar high-level enterprise tracking system, contextual information, or other such data to determine when maintenance tasks are to be scheduled, what those maintenance tasks include, and which technicians are to be assigned the tasks. In some embodiments, the analysis component 212 can apply AI or generative AI-assisted analysis to this data in connection with determining when and how maintenance tasks should be scheduled and corresponding work orders generated.”; Paragraph 46, “FIG. 3 is a diagram illustrating an example architecture for automatically generating work orders 310 based on analysis of real-time or historical industrial asset performance. Work order management system 202 can be implemented on any suitable platform that allows the system 202 to be accessed via client devices (e.g., desktop computers, laptop computers, smart phones, tablet computers, wearable computing devices, etc.) and that permits the system 202 to access operational and status data generated by industrial assets within a plant facility. For example, system 202 can be installed and executed on an on-premise server device on a plant or office network of an industrial facility. Alternatively, system 202 can be executed on a cloud platform as a set of cloud-based services, allowing users at different industrial facilities to access the system 202, view work orders, receive notifications generated by the system 202, or retrieve work order analysis results. System 202 can also be executed on a public network such as the internet and made accessible to users having suitable authorization credentials. In such embodiments, the system 202 can maintain work orders for different industrial enterprises in a segregated manner, such that employees of a given industrial enterprise can only access work orders and associated analysis results associated with that enterprise. In the example depicted in FIG. 3, work order management system resides and executes on a cloud platform.”; Paragraph 52, “A work order 310 generated by the work order generation component 210 can contain information about the maintenance task to be performed, including but not limited to an identity of the industrial asset or machine for which maintenance is required, an aspect of the industrial asset that requires attention, a type of the maintenance to be performed, an estimated number of hours to be spent on the maintenance task, an estimated number of personnel to be assigned to the task, a description of the task, or other such information. The work order 310 is initially scheduled in the system 202 as an open work order 310 (that is, the system 202 stores the work order 310 as work order data in memory 222 and assigns an “Open” status to the work order 310) and remains open until completion of its associated maintenance tasks, at which time the system 202 assigns a “Closed” status to the work order 310.”; Paragraph 53, “Authorized users can browse and view both open and closed work orders 310 via user interface component 204. FIG. 4 is an example work order display 402 that can be rendered on a client device by the user interface component 204. When a user selects a work order 310 via interaction with the work order system's primary user interface, the user interface component 204 can render a work order display 402 and populate the display 402 with information about the work order. In the example depicted in FIG. 4, the work order display 402 comprises a work order identifier 414 that uniquely identifies the selected work order 310, a section 408 that displays general information about the work order 310 (e.g. the open or closed status, a type of maintenance to be performed, a priority, an identity of the asset on which the maintenance task is to be performed, a suggested completion date for the maintenance, a name of a project with which the maintenance task is associated, etc.), and a navigation bar 406 comprising selectable controls corresponding to respective different categories of additional information that can be viewed.”; Paragraph 111, “These generative AI-assisted techniques can allow technicians to easily generate work orders 310 using natural language text or verbal input to the system 202 (e.g., via interfaces rendered on the technicians' client devices and delivered by the user interface component 204) as the technicians are performing other tasks (e.g., upon discovering a new maintenance concern during investigation of a known issue). These approaches can also be used to easily and intuitively annotate or edit work orders using natural language voice or text input.”)
Claim(s) 13 –
Bamal in view of Ponce De Leon disclose the limitations of claims 9 and 12
Bamal further discloses the following:
In response to detecting a selection of the second selectable option from the second set of selectable options causing the intake interface to display a text-based input field; (Bamal: Paragraph 102, “Some embodiments of the work order management system 202 can also incorporate a generative AI chat interface that allows a user to interact with the system 202 via natural language chat exchanges. In such embodiments, the system 202 can support industry-specific prompt engineering features that can formulate suitable prompts 604 for submission to the generative AI model 308 based on a user's natural language requests or queries. FIG. 11 is a diagram illustrating exchange of generative AI dialog messages between a user and the work order management system 202. Embodiments of the system 202 that support a generative AI-based chat interactions can render (via user interface component 204) a chat interface through which a user can exchange natural language prompts or chat conversations with the system 202. This chat interface can include a data entry field for entering a user's natural language request or query 1106 as a text string, or can support other input formats for a user's request or query 1106 (e.g., spoken-word audio input).”)
in response to receiving text input to the text-based input field, generating a second prompt for submission to a generative output engine using the text input; (Bamal: Paragraph 50, “When the monitoring component 208, assisted by the analysis component 212, determines that the monitored asset data 306 satisfies a condition indicative of a current or predicted asset performance issue requiring investigation or correction by maintenance personnel, system's work order generation component 210 can schedule one or more maintenance tasks predicted to correct the performance issue and generate a corresponding work order 310 for the tasks. The condition detected by the monitoring component 208 that triggers creation of a work order 310 can be, for example, a deviation of one or more data tag values that move outside a defined range of normal or expected values. In an example scenario, a baking process may require an oven temperature to stay within a defined temperature range. Accordingly, values of a data tag or automation object corresponding to this oven temperature can be collected from the industrial controller 118 that monitors and controls the baking process, and this collected data can be provided to the work order management system 202 as part of the asset data 306. The monitoring component 208 monitors this value to determine when the oven temperature deviates from this range and, in response to detecting such a deviation, instructs work order generation component 210 to generate a new open work order 310 for investigation of the temperature control issue. In some embodiments, machine-specific asset models maintained on the work order management system 202 can define which data items or performance parameters of the industrial assets are to be monitored, as well as the conditions of this data that are to trigger creation of work orders 310. In other embodiments, as will be described in more detail below, the system 202 can learn to recognize conditions of the asset data indicative of an elevated risk to an asset using machine learning, AI, generative AI, or other analytic techniques.”; Paragraph 65, “The interdependencies between industrial assets defined in the plant model 314 can be used by the analysis component 212 to identify opportunities for opportunistic maintenance scheduling, which can improve maintenance efficiency. For example, when the work order generation component 210 schedules a maintenance activity (and generates a corresponding work order 310) for a given industrial asset to mitigate a discovered risk, the analysis component 212 can also determine whether the discovered risk is likely to also affect other similar machines or components (as determined in part based on the assets defined in the plant model 314) and schedule work orders 310 to perform similar maintenance tasks on those similar assets. The analysis component 212 can also determine whether other assets that are downstream from the affected asset are likely to be impacted by the discovered risk, or by the maintenance action performed on the affected upstream asset. If so, the analysis component 212 can instruct the work order generation component 210 to include, as part of the maintenance instructions defined in the work order 310 for the affected asset, recommendations for addressing any related issues on the downstream assets. In another example, when a machine shutdown is scheduled to address a discovered high-risk issue, the analysis component 212 can identify other lower-risk issues that could also be addressed during the machine shutdown, and generate work orders 310 to address these lower-risk issues as part of the same maintenance session. In any of these examples, the analysis component 212 can reference the defined interdependencies between industrial machines or assets defined in the plant model 314 in order to identify other assets that may be affected by a machine risk (e.g., assets that are downstream from, or otherwise have a functional relationship with, the affected asset), similar assets that may be subject to a common risk, etc.”; Paragraph 66, “In some embodiments, the analysis component 212 can schedule and assign a work order 310 for a discovered asset risk based in part on a risk-reward assessment that considers the benefit of performing the work order against the risk to the affected asset. For example, machines that are especially crucial to plant operations may require the result of the analysis component's risk-reward assessment to exceed a higher benefit threshold, relative to less crucial machines, to justify any risks associated with performing the maintenance action on the machine (e.g., lost productivity or risk of damage due to improper execution of the work order).”)
and the structured search request is generated using a second generative response from the generative output engine received in response to submission of the second prompt to the generative output engine. (Bamal: Paragraph 50, “When the monitoring component 208, assisted by the analysis component 212, determines that the monitored asset data 306 satisfies a condition indicative of a current or predicted asset performance issue requiring investigation or correction by maintenance personnel, system's work order generation component 210 can schedule one or more maintenance tasks predicted to correct the performance issue and generate a corresponding work order 310 for the tasks. The condition detected by the monitoring component 208 that triggers creation of a work order 310 can be, for example, a deviation of one or more data tag values that move outside a defined range of normal or expected values. In an example scenario, a baking process may require an oven temperature to stay within a defined temperature range. Accordingly, values of a data tag or automation object corresponding to this oven temperature can be collected from the industrial controller 118 that monitors and controls the baking process, and this collected data can be provided to the work order management system 202 as part of the asset data 306. The monitoring component 208 monitors this value to determine when the oven temperature deviates from this range and, in response to detecting such a deviation, instructs work order generation component 210 to generate a new open work order 310 for investigation of the temperature control issue. In some embodiments, machine-specific asset models maintained on the work order management system 202 can define which data items or performance parameters of the industrial assets are to be monitored, as well as the conditions of this data that are to trigger creation of work orders 310. In other embodiments, as will be described in more detail below, the system 202 can learn to recognize conditions of the asset data indicative of an elevated risk to an asset using machine learning, AI, generative AI, or other analytic techniques.”; Paragraph 65, “The interdependencies between industrial assets defined in the plant model 314 can be used by the analysis component 212 to identify opportunities for opportunistic maintenance scheduling, which can improve maintenance efficiency. For example, when the work order generation component 210 schedules a maintenance activity (and generates a corresponding work order 310) for a given industrial asset to mitigate a discovered risk, the analysis component 212 can also determine whether the discovered risk is likely to also affect other similar machines or components (as determined in part based on the assets defined in the plant model 314) and schedule work orders 310 to perform similar maintenance tasks on those similar assets. The analysis component 212 can also determine whether other assets that are downstream from the affected asset are likely to be impacted by the discovered risk, or by the maintenance action performed on the affected upstream asset. If so, the analysis component 212 can instruct the work order generation component 210 to include, as part of the maintenance instructions defined in the work order 310 for the affected asset, recommendations for addressing any related issues on the downstream assets. In another example, when a machine shutdown is scheduled to address a discovered high-risk issue, the analysis component 212 can identify other lower-risk issues that could also be addressed during the machine shutdown, and generate work orders 310 to address these lower-risk issues as part of the same maintenance session. In any of these examples, the analysis component 212 can reference the defined interdependencies between industrial machines or assets defined in the plant model 314 in order to identify other assets that may be affected by a machine risk (e.g., assets that are downstream from, or otherwise have a functional relationship with, the affected asset), similar assets that may be subject to a common risk, etc.”; Paragraph 66, “In some embodiments, the analysis component 212 can schedule and assign a work order 310 for a discovered asset risk based in part on a risk-reward assessment that considers the benefit of performing the work order against the risk to the affected asset. For example, machines that are especially crucial to plant operations may require the result of the analysis component's risk-reward assessment to exceed a higher benefit threshold, relative to less crucial machines, to justify any risks associated with performing the maintenance action on the machine (e.g., lost productivity or risk of damage due to improper execution of the work order).”; Paragraph 110, “In another example approach, the analysis component 212 can enhance the user's query 1106 with additional information from the trained models 312 (or the training data 602 used to train the models 312) that contextualizes the user's request, and integrate this additional information with the user's query 1106 to yield the prompt 604 submitted to the generative AI model 308. The types of additional contextual information added to the query 1106 can depend on the nature of the query 1106 and can include, but are not limited to, technical information about an industrial asset known to be relevant to the user's query 1106, information about past maintenance tasks as obtained from closed work orders 310, information regarding monitored operational trends in the asset of interest, or other such information.”; Paragraph 120, “At 1304, asset data comprising operational, status, or performance data generated by industrial assets in service within the plant facility are analyzed for conditions indicative of a performance issue requiring performance of a maintenance task, where this analysis is performed using the one or more models trained at step 1302. In some embodiments, this analysis of the asset data can leverage generative AI to assist in determining whether values or trends in the monitored asset data are indicative of an actionable performance problem. For example, the system performing the analysis can formulate prompts directed to a generative AI model that are designed to obtain responses that can assist the system in interpreting values or trends in the asset data and determining whether these values or trends are indicative of a current or predicted performance concern in any of the monitored industrial assets”)
Claim(s) 14 –
Bamal in view of Ponce De Leon disclose the limitations of claim 9
Bamal further discloses the following:
generating a second prompt for submission to the generative output engine using the first selectable option and the second selectable option; (Bamal: Paragraph 50, “When the monitoring component 208, assisted by the analysis component 212, determines that the monitored asset data 306 satisfies a condition indicative of a current or predicted asset performance issue requiring investigation or correction by maintenance personnel, system's work order generation component 210 can schedule one or more maintenance tasks predicted to correct the performance issue and generate a corresponding work order 310 for the tasks. The condition detected by the monitoring component 208 that triggers creation of a work order 310 can be, for example, a deviation of one or more data tag values that move outside a defined range of normal or expected values. In an example scenario, a baking process may require an oven temperature to stay within a defined temperature range. Accordingly, values of a data tag or automation object corresponding to this oven temperature can be collected from the industrial controller 118 that monitors and controls the baking process, and this collected data can be provided to the work order management system 202 as part of the asset data 306. The monitoring component 208 monitors this value to determine when the oven temperature deviates from this range and, in response to detecting such a deviation, instructs work order generation component 210 to generate a new open work order 310 for investigation of the temperature control issue. In some embodiments, machine-specific asset models maintained on the work order management system 202 can define which data items or performance parameters of the industrial assets are to be monitored, as well as the conditions of this data that are to trigger creation of work orders 310. In other embodiments, as will be described in more detail below, the system 202 can learn to recognize conditions of the asset data indicative of an elevated risk to an asset using machine learning, AI, generative AI, or other analytic techniques.”; Paragraph 65, “The interdependencies between industrial assets defined in the plant model 314 can be used by the analysis component 212 to identify opportunities for opportunistic maintenance scheduling, which can improve maintenance efficiency. For example, when the work order generation component 210 schedules a maintenance activity (and generates a corresponding work order 310) for a given industrial asset to mitigate a discovered risk, the analysis component 212 can also determine whether the discovered risk is likely to also affect other similar machines or components (as determined in part based on the assets defined in the plant model 314) and schedule work orders 310 to perform similar maintenance tasks on those similar assets. The analysis component 212 can also determine whether other assets that are downstream from the affected asset are likely to be impacted by the discovered risk, or by the maintenance action performed on the affected upstream asset. If so, the analysis component 212 can instruct the work order generation component 210 to include, as part of the maintenance instructions defined in the work order 310 for the affected asset, recommendations for addressing any related issues on the downstream assets. In another example, when a machine shutdown is scheduled to address a discovered high-risk issue, the analysis component 212 can identify other lower-risk issues that could also be addressed during the machine shutdown, and generate work orders 310 to address these lower-risk issues as part of the same maintenance session. In any of these examples, the analysis component 212 can reference the defined interdependencies between industrial machines or assets defined in the plant model 314 in order to identify other assets that may be affected by a machine risk (e.g., assets that are downstream from, or otherwise have a functional relationship with, the affected asset), similar assets that may be subject to a common risk, etc.”; Paragraph 66, “In some embodiments, the analysis component 212 can schedule and assign a work order 310 for a discovered asset risk based in part on a risk-reward assessment that considers the benefit of performing the work order against the risk to the affected asset. For example, machines that are especially crucial to plant operations may require the result of the analysis component's risk-reward assessment to exceed a higher benefit threshold, relative to less crucial machines, to justify any risks associated with performing the maintenance action on the machine (e.g., lost productivity or risk of damage due to improper execution of the work order).”; Paragraph 110, “In another example approach, the analysis component 212 can enhance the user's query 1106 with additional information from the trained models 312 (or the training data 602 used to train the models 312) that contextualizes the user's request, and integrate this additional information with the user's query 1106 to yield the prompt 604 submitted to the generative AI model 308. The types of additional contextual information added to the query 1106 can depend on the nature of the query 1106 and can include, but are not limited to, technical information about an industrial asset known to be relevant to the user's query 1106, information about past maintenance tasks as obtained from closed work orders 310, information regarding monitored operational trends in the asset of interest, or other such information.”; Paragraph 120, “At 1304, asset data comprising operational, status, or performance data generated by industrial assets in service within the plant facility are analyzed for conditions indicative of a performance issue requiring performance of a maintenance task, where this analysis is performed using the one or more models trained at step 1302. In some embodiments, this analysis of the asset data can leverage generative AI to assist in determining whether values or trends in the monitored asset data are indicative of an actionable performance problem. For example, the system performing the analysis can formulate prompts directed to a generative AI model that are designed to obtain responses that can assist the system in interpreting values or trends in the asset data and determining whether these values or trends are indicative of a current or predicted performance concern in any of the monitored industrial assets”)
causing display, in the intake interface, of a user prompt and a text-based input field, the user prompt generated using a second generative response from the generative output engine; (Bamal: Paragraph 102, “Some embodiments of the work order management system 202 can also incorporate a generative AI chat interface that allows a user to interact with the system 202 via natural language chat exchanges. In such embodiments, the system 202 can support industry-specific prompt engineering features that can formulate suitable prompts 604 for submission to the generative AI model 308 based on a user's natural language requests or queries. FIG. 11 is a diagram illustrating exchange of generative AI dialog messages between a user and the work order management system 202. Embodiments of the system 202 that support a generative AI-based chat interactions can render (via user interface component 204) a chat interface through which a user can exchange natural language prompts or chat conversations with the system 202. This chat interface can include a data entry field for entering a user's natural language request or query 1106 as a text string, or can support other input formats for a user's request or query 1106 (e.g., spoken-word audio input).”)
and the structured search request is generated using a user input to the text-based input field. (Bamal: Paragraph 50, “When the monitoring component 208, assisted by the analysis component 212, determines that the monitored asset data 306 satisfies a condition indicative of a current or predicted asset performance issue requiring investigation or correction by maintenance personnel, system's work order generation component 210 can schedule one or more maintenance tasks predicted to correct the performance issue and generate a corresponding work order 310 for the tasks. The condition detected by the monitoring component 208 that triggers creation of a work order 310 can be, for example, a deviation of one or more data tag values that move outside a defined range of normal or expected values. In an example scenario, a baking process may require an oven temperature to stay within a defined temperature range. Accordingly, values of a data tag or automation object corresponding to this oven temperature can be collected from the industrial controller 118 that monitors and controls the baking process, and this collected data can be provided to the work order management system 202 as part of the asset data 306. The monitoring component 208 monitors this value to determine when the oven temperature deviates from this range and, in response to detecting such a deviation, instructs work order generation component 210 to generate a new open work order 310 for investigation of the temperature control issue. In some embodiments, machine-specific asset models maintained on the work order management system 202 can define which data items or performance parameters of the industrial assets are to be monitored, as well as the conditions of this data that are to trigger creation of work orders 310. In other embodiments, as will be described in more detail below, the system 202 can learn to recognize conditions of the asset data indicative of an elevated risk to an asset using machine learning, AI, generative AI, or other analytic techniques.”; Paragraph 65, “The interdependencies between industrial assets defined in the plant model 314 can be used by the analysis component 212 to identify opportunities for opportunistic maintenance scheduling, which can improve maintenance efficiency. For example, when the work order generation component 210 schedules a maintenance activity (and generates a corresponding work order 310) for a given industrial asset to mitigate a discovered risk, the analysis component 212 can also determine whether the discovered risk is likely to also affect other similar machines or components (as determined in part based on the assets defined in the plant model 314) and schedule work orders 310 to perform similar maintenance tasks on those similar assets. The analysis component 212 can also determine whether other assets that are downstream from the affected asset are likely to be impacted by the discovered risk, or by the maintenance action performed on the affected upstream asset. If so, the analysis component 212 can instruct the work order generation component 210 to include, as part of the maintenance instructions defined in the work order 310 for the affected asset, recommendations for addressing any related issues on the downstream assets. In another example, when a machine shutdown is scheduled to address a discovered high-risk issue, the analysis component 212 can identify other lower-risk issues that could also be addressed during the machine shutdown, and generate work orders 310 to address these lower-risk issues as part of the same maintenance session. In any of these examples, the analysis component 212 can reference the defined interdependencies between industrial machines or assets defined in the plant model 314 in order to identify other assets that may be affected by a machine risk (e.g., assets that are downstream from, or otherwise have a functional relationship with, the affected asset), similar assets that may be subject to a common risk, etc.”; Paragraph 66, “In some embodiments, the analysis component 212 can schedule and assign a work order 310 for a discovered asset risk based in part on a risk-reward assessment that considers the benefit of performing the work order against the risk to the affected asset. For example, machines that are especially crucial to plant operations may require the result of the analysis component's risk-reward assessment to exceed a higher benefit threshold, relative to less crucial machines, to justify any risks associated with performing the maintenance action on the machine (e.g., lost productivity or risk of damage due to improper execution of the work order).”; Paragraph 110, “In another example approach, the analysis component 212 can enhance the user's query 1106 with additional information from the trained models 312 (or the training data 602 used to train the models 312) that contextualizes the user's request, and integrate this additional information with the user's query 1106 to yield the prompt 604 submitted to the generative AI model 308. The types of additional contextual information added to the query 1106 can depend on the nature of the query 1106 and can include, but are not limited to, technical information about an industrial asset known to be relevant to the user's query 1106, information about past maintenance tasks as obtained from closed work orders 310, information regarding monitored operational trends in the asset of interest, or other such information.”; Paragraph 120, “At 1304, asset data comprising operational, status, or performance data generated by industrial assets in service within the plant facility are analyzed for conditions indicative of a performance issue requiring performance of a maintenance task, where this analysis is performed using the one or more models trained at step 1302. In some embodiments, this analysis of the asset data can leverage generative AI to assist in determining whether values or trends in the monitored asset data are indicative of an actionable performance problem. For example, the system performing the analysis can formulate prompts directed to a generative AI model that are designed to obtain responses that can assist the system in interpreting values or trends in the asset data and determining whether these values or trends are indicative of a current or predicted performance concern in any of the monitored industrial assets”)
Claim(s) 15 –
Bamal in view of Ponce De Leon disclose the limitations of claim 9
Bamal further discloses the following:
wherein the formatting command comprises instructions to generate at least a portion of the generative response as a structured data format. (Bamal: Paragraph 29, “FIG. 1 is a block diagram of an example industrial control environment 100. In this example, a number of industrial controllers 118 are deployed throughout an industrial plant environment to monitor and control respective industrial systems or processes relating to product manufacture, machining, motion control, batch processing, material handling, or other such industrial functions. Industrial controllers 118 typically execute respective control programs to facilitate monitoring and control of industrial devices 120 making up the controlled industrial assets or systems (e.g., industrial machines). One or more industrial controllers 118 may also comprise a soft controller executed on a personal computer or other hardware platform, or on a cloud platform. Some hybrid devices may also combine controller functionality with other functions (e.g., visualization). The control programs executed by industrial controllers 118 can comprise any conceivable type of code used to process input signals read from the industrial devices 120 and to control output signals generated by the industrial controllers, including but not limited to ladder logic, sequential function charts, function block diagrams, or structured text.”; Paragraph 40, “User interface component 204 can be configured to generate user interface displays that receive user input and render output to the user in any suitable format (e.g., visual, audio, tactile, etc.). In some embodiments, user interface component 204 can render these interface displays on a client device (e.g., a laptop computer, tablet computer, smart phone, etc.) that is communicatively connected to the work order management system 202 (e.g., via a hardwired or wireless connection). Input data that can be received via user interface component 204 can include, but is not limited to, work order data (e.g., work order data field entries), user interface navigation input, natural language chat inputs (e.g., work order generation commands, queries regarding existing work orders or asset risks, etc.), or other such input data. Output data rendered by user interface component 204 can include, but is not limited to, information regarding closed and open work orders, risk levels associated with respective work orders, estimated costs associated with high-risk work orders, or other such output data.”; Paragraph 126, “Generally, program modules include routines, programs, components, data structures, etc., that perform particular tasks or implement particular abstract data types. Moreover, those skilled in the art will appreciate that the inventive methods can be practiced with other computer system configurations, including single-processor or multiprocessor computer systems, minicomputers, mainframe computers, Internet of Things (IoT) devices, distributed computing systems, as well as personal computers, hand-held computing devices, microprocessor-based or programmable consumer electronics, and the like, each of which can be operatively coupled to one or more associated devices.”)
Claim(s) 17 –
Bamal in view of Ponce De Leon disclose the limitations of claim 16
Bamal further discloses the following:
the intake interface comprises a text-based input field; in response to receiving text input to the text-based input field, (Bamal: Paragraph 102, “Some embodiments of the work order management system 202 can also incorporate a generative AI chat interface that allows a user to interact with the system 202 via natural language chat exchanges. In such embodiments, the system 202 can support industry-specific prompt engineering features that can formulate suitable prompts 604 for submission to the generative AI model 308 based on a user's natural language requests or queries. FIG. 11 is a diagram illustrating exchange of generative AI dialog messages between a user and the work order management system 202. Embodiments of the system 202 that support a generative AI-based chat interactions can render (via user interface component 204) a chat interface through which a user can exchange natural language prompts or chat conversations with the system 202. This chat interface can include a data entry field for entering a user's natural language request or query 1106 as a text string, or can support other input formats for a user's request or query 1106 (e.g., spoken-word audio input).”)
generating a second prompt for submission to the generative output engine using the text input; and (Bamal: Paragraph 103, “In general, the work order management system 202 can receive and process a user's natural language requests or queries 1106, which can comprise questions about existing open or closed work orders 310, questions about asset risks, requests to create new work orders 310 for performing maintenance tasks, or other such prompts. The system 202 can use prompt engineering services to process natural language requests or queries 1106 submitted by the user via the chat interface (or via a spoken word interface). These prompt engineering services can leverage knowledge encoded in the trained modules 312 (as learned from training data 602), together with responses 606 prompted from the generative AI model 308, to accurately ascertain the user's needs and respond to the user's request or query 1106.”; Paragraph 108, “The analysis component 212 can use a range of approaches for processing a natural language request or query 1106 submitted by the user, and for formulating prompts 604 to the generative AI model 308 designed to yield responses 606 that assist in responding to the user's request or query 1106. According to an example approach, the analysis component 212 can access an archive of chat exchanges between the analysis component 212 and other users and identify chat sessions that were initiated by user queries having similarities to the initial query 1106 submitted by the present user. Upon identifying these archived chat sessions, the analysis component 212 can analyze these past chat sessions to determine types of information that were ultimately generated as a result of these sessions (e.g., work orders 310 having features or elements that are a function of specific keywords of the user's query, a specific type of information about a work order 310 or set of work orders 310 that was ultimately determined to be sought by the user, etc.), and either generate an output (e.g., a work order 310 or a natural language response 1102 to the user's query 1106) based on the outcomes of these past chat sessions and adapted to the user's initial request or query 1106, or, if necessary, generate a prompt 604 for submission to the generative AI model 308 designed to obtain a response 606 comprising the necessary type of information.”)
update the intake interface using a generative response returned in response to providing the second prompt to the generative output engine. (Bamal: Paragraph 84, “In some embodiments, the work order management system 202 can deliver notifications to relevant plant personnel when a new work order 310 is generated and scheduled, alerting those employees that the new work order 310 has been created. FIG. 9 is a diagram illustrating delivery of maintenance notifications 902 to a technician's client device 904. In response to creation of a work order 310 using any of the techniques described above, the user interface component 204 can deliver a notification 902 to the client devices 904 of technicians whom the analysis component 212 or the work order generation component 210 have designated to carry out the work order 310. The notification 902 can include any of the information described above as being rendered on the work order displays 402 illustrated in FIGS. 4 and 5, including a description of the work to be performed (e.g., a list of maintenance tasks as rendered in the Instructions box 410), the industrial asset or machine on which the maintenance is to be performed, a time at which the maintenance is scheduled, the identities of other technicians who have been assigned the work order 310, or other such information. Once created, the work order 310 can be managed through its lifecycle within the domain of the work order management system 202. This can include updating the status of the work order 310 within the system 202 as the work order's maintenance tasks are performed and ultimately closing the work order 310 upon completion of the maintenance tasks. At any time, authorized users can invoke the work order display 402 on their client devices 904 via the user interface component 204 to view detailed information about the work order 310, as well as status information for the respective maintenance tasks defined in the work order 310.”; Paragraph 97, “The insights gleaned by embodiments of the work order management system 202 can afford maintenance and manufacturing personnel the ability to find areas of their operations that are underperforming or overperforming. The system 202 can also identify root causes or recommend paths to resolving maintenance inefficiencies identified by the statistical and machine learning analysis applied to past work orders 310. This allows maintenance teams to improve their processes and ultimately reduce maintenance or manufacturing costs. The work order management system 202 can also regularly re-evaluate the work orders 310 as new work orders 310 are submitted, completed, and closed, so that the algorithms used to generate risk scores and recommended countermeasures are regularly updated with new training data.”; Paragraph 118, “At 1212, a work order for performing the one or more maintenance tasks determined at step 1208 is generated by the system. In some embodiments, the system can generate content of the work order (e.g., descriptions of the discovered asset risk detected at step 1206 as well as the maintenance tasks determined at step 1208 for mitigating the risks) based on information obtained or analyzed in previous steps, and can also generate a portion of the content with the assistance of the generative AI model. At 1214, the work order management system updates a work schedule to assign the one or more technicians selected at step 1210 to the work order.”; Paragraph 120, “At 1304, asset data comprising operational, status, or performance data generated by industrial assets in service within the plant facility are analyzed for conditions indicative of a performance issue requiring performance of a maintenance task, where this analysis is performed using the one or more models trained at step 1302. In some embodiments, this analysis of the asset data can leverage generative AI to assist in determining whether values or trends in the monitored asset data are indicative of an actionable performance problem. For example, the system performing the analysis can formulate prompts directed to a generative AI model that are designed to obtain responses that can assist the system in interpreting values or trends in the asset data and determining whether these values or trends are indicative of a current or predicted performance concern in any of the monitored industrial assets.”)
Claim(s) 18 –
Bamal in view of Ponce De Leon disclose the limitations of claims 16-17
Bamal further discloses the following:
wherein the search at the issue tracking platform backend application is generated using a second generative response from the generative output engine received in response to providing the second prompt to the generative output engine. (Bamal: Paragraph 50, “When the monitoring component 208, assisted by the analysis component 212, determines that the monitored asset data 306 satisfies a condition indicative of a current or predicted asset performance issue requiring investigation or correction by maintenance personnel, system's work order generation component 210 can schedule one or more maintenance tasks predicted to correct the performance issue and generate a corresponding work order 310 for the tasks. The condition detected by the monitoring component 208 that triggers creation of a work order 310 can be, for example, a deviation of one or more data tag values that move outside a defined range of normal or expected values. In an example scenario, a baking process may require an oven temperature to stay within a defined temperature range. Accordingly, values of a data tag or automation object corresponding to this oven temperature can be collected from the industrial controller 118 that monitors and controls the baking process, and this collected data can be provided to the work order management system 202 as part of the asset data 306. The monitoring component 208 monitors this value to determine when the oven temperature deviates from this range and, in response to detecting such a deviation, instructs work order generation component 210 to generate a new open work order 310 for investigation of the temperature control issue. In some embodiments, machine-specific asset models maintained on the work order management system 202 can define which data items or performance parameters of the industrial assets are to be monitored, as well as the conditions of this data that are to trigger creation of work orders 310. In other embodiments, as will be described in more detail below, the system 202 can learn to recognize conditions of the asset data indicative of an elevated risk to an asset using machine learning, AI, generative AI, or other analytic techniques.”; Paragraph 65, “The interdependencies between industrial assets defined in the plant model 314 can be used by the analysis component 212 to identify opportunities for opportunistic maintenance scheduling, which can improve maintenance efficiency. For example, when the work order generation component 210 schedules a maintenance activity (and generates a corresponding work order 310) for a given industrial asset to mitigate a discovered risk, the analysis component 212 can also determine whether the discovered risk is likely to also affect other similar machines or components (as determined in part based on the assets defined in the plant model 314) and schedule work orders 310 to perform similar maintenance tasks on those similar assets. The analysis component 212 can also determine whether other assets that are downstream from the affected asset are likely to be impacted by the discovered risk, or by the maintenance action performed on the affected upstream asset. If so, the analysis component 212 can instruct the work order generation component 210 to include, as part of the maintenance instructions defined in the work order 310 for the affected asset, recommendations for addressing any related issues on the downstream assets. In another example, when a machine shutdown is scheduled to address a discovered high-risk issue, the analysis component 212 can identify other lower-risk issues that could also be addressed during the machine shutdown, and generate work orders 310 to address these lower-risk issues as part of the same maintenance session. In any of these examples, the analysis component 212 can reference the defined interdependencies between industrial machines or assets defined in the plant model 314 in order to identify other assets that may be affected by a machine risk (e.g., assets that are downstream from, or otherwise have a functional relationship with, the affected asset), similar assets that may be subject to a common risk, etc.”; Paragraph 66, “In some embodiments, the analysis component 212 can schedule and assign a work order 310 for a discovered asset risk based in part on a risk-reward assessment that considers the benefit of performing the work order against the risk to the affected asset. For example, machines that are especially crucial to plant operations may require the result of the analysis component's risk-reward assessment to exceed a higher benefit threshold, relative to less crucial machines, to justify any risks associated with performing the maintenance action on the machine (e.g., lost productivity or risk of damage due to improper execution of the work order).”; Paragraph 110, “In another example approach, the analysis component 212 can enhance the user's query 1106 with additional information from the trained models 312 (or the training data 602 used to train the models 312) that contextualizes the user's request, and integrate this additional information with the user's query 1106 to yield the prompt 604 submitted to the generative AI model 308. The types of additional contextual information added to the query 1106 can depend on the nature of the query 1106 and can include, but are not limited to, technical information about an industrial asset known to be relevant to the user's query 1106, information about past maintenance tasks as obtained from closed work orders 310, information regarding monitored operational trends in the asset of interest, or other such information.”; Paragraph 120, “At 1304, asset data comprising operational, status, or performance data generated by industrial assets in service within the plant facility are analyzed for conditions indicative of a performance issue requiring performance of a maintenance task, where this analysis is performed using the one or more models trained at step 1302. In some embodiments, this analysis of the asset data can leverage generative AI to assist in determining whether values or trends in the monitored asset data are indicative of an actionable performance problem. For example, the system performing the analysis can formulate prompts directed to a generative AI model that are designed to obtain responses that can assist the system in interpreting values or trends in the asset data and determining whether these values or trends are indicative of a current or predicted performance concern in any of the monitored industrial assets”)
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Philip N Warner whose telephone number is (571)270-7407. The examiner can normally be reached Monday-Friday 7am-4:00pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Jerry O’Connor can be reached at 571-272-6787. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/Philip N Warner/Examiner, Art Unit 3624
/Jerry O'Connor/Supervisory Patent Examiner,Group Art Unit 3624
Prosecution Insights