DETAILED ACTION
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 03/26/2026 has been entered.
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 .
Status of Claims
Claims X are canceled.
Claims X are amended.
Claims X are new.
Claims 1-20 are pending and have been examined.
This action is in reply to the papers filed on 03/26/2026 (effective filing date 04/12/2023).
Information Disclosure Statement
The information disclosure statement(s) submitted: 04/23/2024, 06/07/2024, 08/22/2024, 09/17/2024, 10/16/2024, 12/04/2024, 03/31/2025, 06/10/2025, 07/08/2025, 12/31/2025, 05/12/2026 has/have been considered by the Examiner and made of record in the application file.
Amendment
The present Office Action is based upon the original patent application filed on 04/11/2024 as modified by the amendments filed on 12/29/2025 and 03/26/2026.
Reasons For Allowance
Prior-Art Rejection withdrawn
Claims xxx are allowed. The closest prior art (See PTO-892, Notice of References Cited) does not teach the claimed:
The closest prior-art (xxx) teach the features as disclosed in Non-final Rejection (xxxx), however, these cited references do not teach and the prior-art does not teach at least the following:
Claim Rejections - 35 USC §101 - Withdrawn
Per Applicant’s amendments and arguments and considering new guidance in the MPEP, the rejections are withdrawn. Specifically, in Applicant’s Remarks (dated 03/14/2017, pgs. 8-11), Applicant traverses the 35 USC §101 rejections arguing that the amended claims recite new limitations that are not abstract, amount to significantly more, are directed to a practical application, etc… For example, Applicant argues….
In support of their arguments, Applicant cites to the following recent Fed. Cir. court cases (i.e., Alice Corp. v. CLS Bank Int’l, SRI Int’l, Inc. v. Cisco Systems, Inc., Ultramercial, Inc. v. Hulu, LLC, Berkheimer, Core Wireless, McRO, Enfish, Bascom, DDR, etc…).
Claim Rejections - 35 USC § 101
35 U.S.C. § 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. § 101 as being directed to non-statutory subject matter because the claimed invention is directed to an abstract idea without significantly more. These claims recite methods for implementing a building management system with generative AI-based automated maintenance service scheduling and modifications.
Claim 1 recites [a] method comprising: configuring, by one or more processors, a generative Al model using a plurality of first service requests for servicing building equipment and outcome data indicating outcomes of the plurality of first service requests, the outcome data comprising a plurality of examples of service actions, and corresponding successful outcomes, that resolved one or more problems or faults indicated by the plurality of first service requests, such that the generative Al model is to identify one or more patterns or trends between characteristics of the plurality of first service requests and the successful outcomes of the plurality of first service requests; receiving, by the one or more processors, a second service request for servicing an item of building equipment, the second service request comprising one or more characteristics of the item of building equipment; initiating a diagnostic conversation by prompting a user, via a user interface, to provide one or more additional items of information based at least on the one or more characteristics of the item of building equipment; receiving, via the user interface and based at least on one or more responses in the diagnostic conversation, the one or more additional items of information as unstructured data or natural language data; automatically determining, by the one or more processors using the generative Al model, one or more actions to perform on the item of building equipment, in response to the second service request, based on the one or more characteristics of the item of building equipment, the unstructured data or the natural language data, and the configuration of the generative Al model; and generating an output response to the second service request to present the one or more actions via the user interface.
The claims are being rejected according to the 2019 Revised Patent Subject Matter Eligibility Guidance (Federal Register, Vol. 84, No. 5, p. 50-57 (Jan. 7, 2019)).
Step 1: Does the Claim Fall within a Statutory Category?
Yes. Claims 1-20 recite a method and, therefore, are directed to the statutory class of a process.
Step 2A, Prong One: Is a Judicial Exception Recited?
Yes. The following tables identify the specific limitations that recite an abstract idea. The column that identifies the additional elements will be relevant to the analysis in step 2A, prong two, and step 2B.
Claim 1: Identification of Abstract Idea and Additional Elements, using Broadest Reasonable Interpretation
Claim Limitation
Abstract Idea
Additional Element
1. A method comprising:
No additional elements are positively claimed.
configuring, by one or more processors, a generative Al model using a plurality of first service requests for servicing building equipment and outcome data indicating outcomes of the plurality of first service requests, the outcome data comprising a plurality of examples of service actions, and corresponding successful outcomes, that resolved one or more problems or faults indicated by the plurality of first service requests, such that the generative Al model is to identify one or more patterns or trends between characteristics of the plurality of first service requests and the successful outcomes of the plurality of first service requests;
This limitation includes the step(s) of: configuring, by one or more processors, a generative Al model using a plurality of first service requests for servicing building equipment and outcome data indicating outcomes of the plurality of first service requests, the outcome data comprising a plurality of examples of service actions, and corresponding successful outcomes, that resolved one or more problems or faults indicated by the plurality of first service requests, such that the generative Al model is to ….
But for the one or more processors, this limitation is directed to processing known information (e.g., configuring a model) to facilitate a building management system with generative ai-based automated maintenance service scheduling and modification which may be categorized as any of the following:
mathematical concept (mathematical relationships, mathematical formulas or equations, mathematical calculations)
and/or
mental process – concepts performed in the human mind (including an observation, evaluation, judgment, opinion)
and/or
certain method of organizing human activity –
fundamental economic principles or practices (including hedging, insurance, mitigating risk), and/or
commercial or legal interactions (including agreements in the form of contracts; legal obligations; advertising, marketing or sales activities or behaviors; business relations).
configuring, by one or more processors, a generative AI model …
The “generative AI model” is not considered an ‘additional element.’
receiving, by the one or more processors, a second service request for servicing an item of building equipment, the second service request comprising one or more characteristics of the item of building equipment;
This limitation includes the step(s) of: receiving, by the one or more processors, a second service request for servicing an item of building equipment, the second service request comprising one or more characteristics of the item of building equipment.
But for the one or more processors, this limitation is directed to communicating known information (e.g., receiving a service request) to facilitate a building management system with generative ai-based automated maintenance service scheduling and modification which may be categorized as any of the following:
mathematical concept (mathematical relationships, mathematical formulas or equations, mathematical calculations)
and/or
mental process – concepts performed in the human mind (including an observation, evaluation, judgment, opinion)
and/or
certain method of organizing human activity –
fundamental economic principles or practices (including hedging, insurance, mitigating risk), and/or
commercial or legal interactions (including agreements in the form of contracts; legal obligations; advertising, marketing or sales activities or behaviors; business relations).
receiving, by the one or more processors, a second service request…
initiating a diagnostic conversation by prompting a user, via a user interface, to provide one or more additional items of information based at least on the one or more characteristics of the item of building equipment;
This limitation includes the step(s) of: initiating a diagnostic conversation by prompting a user, via a user interface, to provide one or more additional items of information based at least on the one or more characteristics of the item of building equipment.
But for the user interface, this limitation is directed to communicating known information to facilitate a building management system with generative ai-based automated maintenance service scheduling and modification which may be categorized as any of the following:
mathematical concept (mathematical relationships, mathematical formulas or equations, mathematical calculations)
and/or
mental process – concepts performed in the human mind (including an observation, evaluation, judgment, opinion)
and/or
certain method of organizing human activity –
fundamental economic principles or practices (including hedging, insurance, mitigating risk), and/or
commercial or legal interactions (including agreements in the form of contracts; legal obligations; advertising, marketing or sales activities or behaviors; business relations).
… prompting a user, via a user interface, to provide one or more additional items of information…
receiving, via the user interface and based at least on one or more responses in the diagnostic conversation, the one or more additional items of information as unstructured data or natural language data;
This limitation includes the step(s) of: receiving, via the user interface and based at least on one or more responses in the diagnostic conversation, the one or more additional items of information as unstructured data or natural language data.
But for the user interface, this limitation is directed to communicating known information to facilitate a building management system with generative ai-based automated maintenance service scheduling and modification which may be categorized as any of the following:
mathematical concept (mathematical relationships, mathematical formulas or equations, mathematical calculations)
and/or
mental process – concepts performed in the human mind (including an observation, evaluation, judgment, opinion)
and/or
certain method of organizing human activity –
fundamental economic principles or practices (including hedging, insurance, mitigating risk), and/or
commercial or legal interactions (including agreements in the form of contracts; legal obligations; advertising, marketing or sales activities or behaviors; business relations).
receiving, via the user interface and based at least on one or more responses in the diagnostic conversation, the one or more additional items of information…
automatically determining, by the one or more processors using the generative Al model, one or more actions to perform on the item of building equipment, in response to the second service request, based on the one or more characteristics of the item of building equipment, the unstructured data or the natural language data, and the configuration of the generative Al model; and
This limitation includes the step(s) of: automatically determining, by the one or more processors using the generative Al model, one or more actions to perform on the item of building equipment, in response to the second service request, based on the one or more characteristics of the item of building equipment, the unstructured data or the natural language data, and the configuration of the generative Al model.
But for the one or more processors, this limitation is directed to processing known information (e.g., determining an action) to facilitate a building management system with generative ai-based automated maintenance service scheduling and modification which may be categorized as any of the following:
mathematical concept (mathematical relationships, mathematical formulas or equations, mathematical calculations)
and/or
mental process – concepts performed in the human mind (including an observation, evaluation, judgment, opinion)
and/or
certain method of organizing human activity –
fundamental economic principles or practices (including hedging, insurance, mitigating risk), and/or
commercial or legal interactions (including agreements in the form of contracts; legal obligations; advertising, marketing or sales activities or behaviors; business relations).
automatically determining, by the one or more processors using the generative Al model, one or more actions to perform …
generating an output response to the second service request to present the one or more actions via the user interface.
This limitation includes the step(s) of: generating an output response to the second service request to present the one or more actions via the user interface.
But for the user interface, this limitation is directed to communicating known information to facilitate a building management system with generative ai-based automated maintenance service scheduling and modification which may be categorized as any of the following:
mathematical concept (mathematical relationships, mathematical formulas or equations, mathematical calculations)
and/or
mental process – concepts performed in the human mind (including an observation, evaluation, judgment, opinion)
and/or
certain method of organizing human activity –
fundamental economic principles or practices (including hedging, insurance, mitigating risk), and/or
commercial or legal interactions (including agreements in the form of contracts; legal obligations; advertising, marketing or sales activities or behaviors; business relations).
generating an output response to the second service request to present the one or more actions via the user interface
As shown above, under Step 2A, Prong One, the claims recite a judicial exception (an abstract idea). The claims are directed to the abstract idea of implementing a building management system with generative AI-based automated maintenance service scheduling and modifications, which, pursuant to MPEP 2106.04, is aptly categorized as a mathematical concept and/or mental process and/or a method of organizing human activity. Therefore, under Step 2A, Prong One, the claims recite a judicial exception.
The aforementioned claims also recite additional technical elements including: a “processor” and “user interface” to execute the method. Claims that amount to nothing more than an instruction to apply the abstract idea using a generic computer do not render an abstract idea eligible. Alice Corp., 134 S. Ct. at 2358, 110 USPQ2d at 1983. See also 134 S. Ct. at 2389, 110 USPQ2d at 1984.
Step 2A, Prong Two: Is the Abstract Idea Integrated into a Practical Application?
No. The judicial exception is not integrated into a practical application. The additional elements listed above that relate to computing components are recited at a high level of generality (i.e., as generic components performing generic computer functions such as communicating, receiving, processing, analyzing, and outputting/displaying data) such that they amount to no more than mere instructions to apply the exception using generic computing components. Simply implementing the abstract idea on a generic computer is not a practical application of the abstract idea. Additionally, the claims do not purport to improve the functioning of the computer itself. There is no technological problem that the claimed invention solves. Rather, the computer system is invoked merely as a tool. Accordingly, the additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. Therefore, these claims are directed to an abstract idea.
Furthermore, looking at the elements individually and in combination, under Step 2A, Prong Two, the claims as a whole do not integrate the judicial exception into a practical application because they fail to: improve the functioning of a computer or a technical field, apply the judicial exception in the treatment or prophylaxis of a disease, apply the judicial exception with a particular machine, effect a transformation or reduction of a particular article to a different state or thing, or apply the judicial exception beyond generally linking the use of the judicial exception to a particular technological environment. Rather, the claims merely use a computer as a tool to perform the abstract idea(s), and/or add insignificant extra-solution activity to the judicial exception, and/or generally link the use of the judicial exception to a particular technological environment.
Step 2B: Does the Claim Provide an Inventive Concept?
Next, under Step 2B, the claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements, when considered both individually and as an ordered combination, do not amount to significantly more than the abstract idea. Furthermore, looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually. Simply put, as noted above, there is no indication that the combination of elements improves the functioning of a computer (or any other technology), and their collective functions merely provide conventional computer implementation. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements relating to computing components amount to no more than applying the exception using a generic computing components. Mere instructions to apply an exception using a generic computing component cannot provide an inventive concept. Furthermore, the broadest reasonable interpretation of the claimed computer components (i.e., additional elements) includes any generic computing components that are capable of being programmed to communicate, receive, send, process, analyze, output, or display data. Furthermore, Applicant’s Specification (PGPub. 2024/0346459 [0094; 0401]) refers to a general computer system, but they do not include any technically-specific computer algorithm or code.
Additionally, pursuant to the requirement under Berkheimer, the following citations are provided to demonstrate that the additional elements, identified as extra-solution activity, amount to activities that are well-understood, routine, and conventional. See MPEP 2106.05(d).
Capturing an image (code) with an RFID reader. Ritter, US Patent No. 7734507 (Col. 3, Lines 56-67); “RFID: Riding on the Chip” by Pat Russo. Frozen Food Age. New York: Dec. 2003, vol. 52, Issue 5; page S22.
Receiving or transmitting data over a network. Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362; OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014).
Storing and retrieving information in memory. Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015); OIP Techs., 788 F.3d at 1363, 115 USPQ2d at 1092-93.
Outputting/Presenting data to a user. Mayo, 566 U.S. at 79, 101 USPQ2d at 1968; OIP Techs., Inc. v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1092-93 (Fed. Cir. 2015); MPEP 2106.05(g)(3).
Using a machine learning model to determine user segment characteristics for an ad campaign. https://whites.agency/blog/how-to-use-machine-learning-for-customer-segmentation/.
Thus, taken alone and in combination, the additional elements do not amount to significantly more than the above-identified judicial exception (the abstract idea), and are ineligible under 35 USC 101.
Independent method claims 11 and 20 also contains the identified abstract ideas, with the additional elements of a processor, which are a generic computer components, and thus not significantly more for the same reasons and rationale above.
Dependent claims 2-10 and 12-19 further describe the abstract idea. The additional elements of the dependent claims fail to integrate the abstract idea into a practical application and do not amount to significantly more than the abstract idea. Thus, as the dependent claims remain directed to a judicial exception, and as the additional elements of the claims do not amount to significantly more, the dependent claims are not patent eligible.
As such, the claims are not patent eligible.
Invention Could be Performed Manually
It is conceivable that the invention could be performed manually without the aid of machine and/or computer. For example, Applicant claims training a model, receiving a service request, and determining a response. Each of these features could be performed manually and/or with the aid of a simple generic computer to facilitate the transmission of data.
See also Leapfrog Enterprises, Inc. v. Fisher-Price, Inc., and In re Venner, which stand for the concept that automating manual activity and/or applying modern electronics to older mechanical devices to accomplish the same result is not sufficient to distinguish over the prior art. Here, applicant is merely claiming computers to facilitate and/or automate functions which used to be commonly performed by a human.
Leapfrog Enterprises, Inc. v. Fisher-Price, Inc., 485 F.3d 1157, 82 USPQ2d 1687 (Fed. Cir. 2007) "[a]pplying modern electronics to older mechanical devices has been commonplace in recent years…"). The combination is thus the adaptation of an old idea or invention using newer technology that is commonly available and understood in the art.
In In re Venner, 262 F.2d 91, 95, 120 USPQ 193, 194 (CCPA 1958), the court held that broadly providing an automatic or mechanical means to replace manual activity which accomplished the same result is not sufficient to distinguish over the prior art. MPEP 2144.04, III Automating a Manual Activity.
MPEP 2144.04 III - Automating a Manual Activity and In re Venner, 262 F.2d 91, 95, 120 USPQ 193, 194 (CCPA 1958) further stand for and provide motivation for using technology, hardware, computer, or server to automate a manual activity.
Therefore, the Office finds no improvements to another technology or field, no improvements to the function of the computer itself, and no meaningful limitations beyond generally linking the use of an abstract idea to a particular technological environment. Therefore, based on the two-part Alice Corp. analysis, there are no limitations in any of the claims that transform the exception (i.e., the abstract idea) into a patent eligible application.
Claim Rejections - Not an Ordered Combination
None of the limitations, considered as an ordered combination provide eligibility, because taken as a whole, the claims simply instruct the practitioner to implement the abstract idea with routine, conventional activity.
Claim Rejections - Preemption
Allowing the claims, as presently claimed, would preempt others from implementing a building management system with generative AI-based automated maintenance service scheduling and modifications. Furthermore, the claim language only recites the abstract idea of performing this method, there are no concrete steps articulating a particular way in which this idea is being implemented or describing how it is being performed.
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 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 of this title, 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 set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied 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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-9 and 11-20 are rejected under 35 U.S.C. 103 as being unpatentable over: McKelvy et al. 2021/0264385; in view of Hita et al. 2023/0350398; in view of DeLuca et al. 2022/0198474; in further view of Lin et al. 2022/0101148.
18/633,086 – Claim 1. (Currently Amended) McKelvy et al. 2021/0264385 teaches A method comprising: configuring, by one or more processors (McKelvy et al. 2021/0264385 [0067 - implemented using a network of computers and processors]), a generative AI model (McKelvy et al. 2021/0264385 [0062 - Artificial Intelligence (AI) Techniques of Detecting Patterns] Artificial Intelligence (AI) Techniques of Detecting Patterns Indicating Device Failure [0064 - AI technique, which can be used for detecting primary or secondary patterns indicative of normal or abnormal device behavior. Sensor data of a first plurality of equipment 101 along with their prior repair history of the plurality of the equipment 101 can be used to train multiple machine learning (ML) networks 506 (e.g., neural networks or deep neural networks) to detect patterns] FIG. 5 illustrates a diagram 500 of an AI technique, which can be used for detecting primary or secondary patterns indicative of normal or abnormal device behavior. Sensor data of a first plurality of equipment 101 along with their prior repair history of the plurality of the equipment 101 can be used to train multiple machine learning (ML) networks 506 (e.g., neural networks or deep neural networks) to detect patterns of sensor data that can be correlated to normal or abnormal device operation. Each machine learning network 506 can be trained for detecting patterns of sensor data correlated with specific malfunctions in the first plurality of equipment 101. The past maintenance reports can be used as ground truth and used to train the ML networks 506. Multiple instances of the ML networks 506 can be trained for various brands, types of equipment 101 or different parts within the equipment 101. Furthermore, instances of the ML networks 506 can be trained to detect patterns of sensor data indicative of a malfunction, wherein each instance of ML network 506 is trained to detect patterns of sensor data correlated with a malfunction. After training, the ML networks 506 can detect patterns of sensor data correlated with one or more device malfunctions and can label the sensor data accordingly, thereby generating labeled patterns of sensor data 508. The sensor data for the purpose of training the ML networks 506 may be converted into various data structure formats, including, for example, vectors, arrays, multidimensional arrays, and/or tensors.) using a plurality of first service requests for servicing building equipment and outcome data indicating outcomes of the plurality of first service requests (McKelvy et al. 2021/0264385 [0009] In some embodiments, the method further includes: generating a set of conditions based at least partly on the one or more patterns, wherein the set of conditions correlate with the anomaly; generating an equipment repair profile corresponding to the anomaly, along with a mapping of the equipment to the equipment repair profile; detecting the presence of the set of conditions in a second equipment; transmitting the equipment repair profile to an operator of the second equipment. [0011] In another embodiment, the method further includes: generating equipment repair profiles of a plurality of equipment, corresponding to anomalies detected based on the one or more patterns in the physical parameters; based at least partly on the equipment repair profiles, detecting a set of conditions shared amongst the plurality of equipment having the detected anomalies; generating a second repair profile corresponding to the set of conditions and the detected anomalies corresponding to the set of conditions; detecting presence of the set of conditions in a second plurality of equipment; and transmitting the second repair profile to one or more operators of the second plurality of equipment. [0046] UI clients 114 can also be used to receive from the operator of the equipment 101, an operation profile of the equipment 101. The operation profile can include data, such as, device identifier of equipment 101, its location identifier, its brand, type, age, hours of operation, service and/or maintenance history, and a list of the physical parameters, which the system 100 can monitor. Sensor data in combination with the operation profiles of a multitude of equipment devices 101 across an industry can be used to generate insight into diagnostics, maintenance, and overall operation efficiency of the equipment devices 101. [0061] FIG. 4 illustrates a flowchart of a method 400, which can be used in combination with the embodiment of FIG. 3 to improve the operations of the system 100. At step 402, the method includes, generating equipment repair profiles of a plurality of equipment, corresponding to anomalies detected based on the one or more patterns in the physical parameters. At step 404, the method includes, detecting, based at least partly on the equipment repair profiles, a set of conditions shared amongst the plurality of equipment having the detected anomalies. At step 406, the method includes generating a second repair profile corresponding to the set of conditions and the detected anomalies corresponding to the set of conditions. At step 408, the method includes detecting presence of the set of conditions in a second plurality of equipment. At step 410, the method includes transmitting the second repair profile to one or more operators of the second plurality of equipment.), the outcome data comprising a plurality of examples of service actions, and corresponding successful outcomes, that resolved one or more problems or faults indicated by the plurality of first service requests (McKelvy et al. 2021/0264385 [0021] In another embodiment, the operations further include: generating equipment repair profiles of a plurality of equipment, corresponding to anomalies detected based on the one or more patterns in the physical parameters; based at least partly on the equipment repair profiles, detecting a set of conditions shared amongst the plurality of equipment having the detected anomalies; generating a second repair profile corresponding to the set of conditions and the detected anomalies corresponding to the set of conditions; detecting presence of the set of conditions in a second plurality of equipment; and transmitting the second repair profile to one or more operators of the second plurality of equipment. [0046] UI clients 114 can also be used to receive from the operator of the equipment 101, an operation profile of the equipment 101. The operation profile can include data, such as, device identifier of equipment 101, its location identifier, its brand, type, age, hours of operation, service and/or maintenance history, and a list of the physical parameters, which the system 100 can monitor. Sensor data in combination with the operation profiles of a multitude of equipment devices 101 across an industry can be used to generate insight into diagnostics, maintenance, and overall operation efficiency of the equipment devices 101. [0052] In other words, the backend server 112 can detect one or more patterns in a plurality of sensor readings from a plurality of sensors 106, wherein the patterns indicate normal or abnormal equipment operation based on the stored history of the sensor data. The same algorithm is applicable to other types of sensors 106 and equipment 101. For example, a vibration sensor 106 reporting historically high vibrations, relative to other vibration sensors 106 mounted on a manufacturing equipment 101, can indicate normal operations, if the manufacturing equipment 101 has not failed or reported a problem. [0056] Additionally, the repair notification can include a course of action determined based on the sensor readings, processed clean sensor data and detected patterns in sensor data. For example, the backend server 112 can detect a pattern of increasing temperatures in a sensor 106 located near the door of a walk-in cooler that persists throughout a 24-hour period. The door is expected to be shut for an extended period of time during night hours and the temperature readings near the door are expected to drop during those hours. Other temperature sensors 106 inside the walk-in cooler do not indicate the same pattern of rising temperature and at night drop and stay constant. In this scenario, the timing of sensor readings, the location of sensor readings, and the history of the sensor reading, can indicate a malfunction or broken seal in the door of the walk-in cooler. Consequently, the repair notification can include a course of action determined based on timing, location, involved parts, and corresponding solutions. For example, a notification generated on the UI client 114 can include text phrase, “high temperatures near cooler entrance during night. Inspect proper door operation and seal.” [0064] FIG. 5 illustrates a diagram 500 of an AI technique, which can be used for detecting primary or secondary patterns indicative of normal or abnormal device behavior. Sensor data of a first plurality of equipment 101 along with their prior repair history of the plurality of the equipment 101 can be used to train multiple machine learning (ML) networks 506 (e.g., neural networks or deep neural networks) to detect patterns of sensor data that can be correlated to normal or abnormal device operation. Each machine learning network 506 can be trained for detecting patterns of sensor data correlated with specific malfunctions in the first plurality of equipment 101. The past maintenance reports can be used as ground truth and used to train the ML networks 506. Multiple instances of the ML networks 506 can be trained for various brands, types of equipment 101 or different parts within the equipment 101. Furthermore, instances of the ML networks 506 can be trained to detect patterns of sensor data indicative of a malfunction, wherein each instance of ML network 506 is trained to detect patterns of sensor data correlated with a malfunction. After training, the ML networks 506 can detect patterns of sensor data correlated with one or more device malfunctions and can label the sensor data accordingly, thereby generating labeled patterns of sensor data 508. The sensor data for the purpose of training the ML networks 506 may be converted into various data structure formats, including, for example, vectors, arrays, multidimensional arrays, and/or tensors.), such that the generative AI model is to identify one or more patterns or trends between characteristics of the plurality of first service requests and the successful outcomes of the plurality of first service requests (McKelvy et al. 2021/0264385 [0064 - Sensor data of a first plurality of equipment 101 along with their prior repair history of the plurality of the equipment 101 can be used to train multiple machine learning (ML) networks 506 (e.g., neural networks or deep neural networks) to detect patterns of sensor data that can be correlated to normal or abnormal device operation] FIG. 5 illustrates a diagram 500 of an AI technique, which can be used for detecting primary or secondary patterns indicative of normal or abnormal device behavior. Sensor data of a first plurality of equipment 101 along with their prior repair history of the plurality of the equipment 101 can be used to train multiple machine learning (ML) networks 506 (e.g., neural networks or deep neural networks) to detect patterns of sensor data that can be correlated to normal or abnormal device operation. Each machine learning network 506 can be trained for detecting patterns of sensor data correlated with specific malfunctions in the first plurality of equipment 101. The past maintenance reports can be used as ground truth and used to train the ML networks 506. Multiple instances of the ML networks 506 can be trained for various brands, types of equipment 101 or different parts within the equipment 101. Furthermore, instances of the ML networks 506 can be trained to detect patterns of sensor data indicative of a malfunction, wherein each instance of ML network 506 is trained to detect patterns of sensor data correlated with a malfunction. After training, the ML networks 506 can detect patterns of sensor data correlated with one or more device malfunctions and can label the sensor data accordingly, thereby generating labeled patterns of sensor data 508. The sensor data for the purpose of training the ML networks 506 may be converted into various data structure formats, including, for example, vectors, arrays, multidimensional arrays, and/or tensors. [0066 - method includes training a plurality of machine learning networks to detect patterns of sensor data indicative of a plurality of malfunctions, wherein each machine learning network is trained for detecting the patterns of sensor data indicative of a single malfunction] FIG. 6 illustrates a flowchart of a method 600 of using artificial intelligence (AI) techniques for detecting patterns of sensor data indicative of device failure. At step 602, the method includes receiving a plurality of sensor data of a first plurality of equipment. At step 604, the method includes receiving repair history associated with each equipment of the first plurality of equipment. At step 606, the method includes training a plurality of machine learning networks to detect patterns of sensor data indicative of a plurality of malfunctions, wherein each machine learning network is trained for detecting the patterns of sensor data indicative of a single malfunction. At step 608, the method includes receiving sensor data of a second plurality of equipment. At step 610, the method includes using one or more of the trained plurality of machine learning networks to detect the patterns of sensor data indicative of one or more malfunctions. At step 612, the method includes identifying one or more equipment in the second plurality of equipment having sensor data, comprising the detected patterns of sensor data. At step 614, the method includes, generating and transmitting a notification to an operator of the one or more equipment in the second plurality of equipment, wherein the notification comprises a notification of the one or more malfunction.); receiving, by the one or more processors, a second service request for servicing an item of building equipment (McKelvy et al. 2021/0264385 [0009] In some embodiments, the method further includes: generating a set of conditions based at least partly on the one or more patterns, wherein the set of conditions correlate with the anomaly; generating an equipment repair profile corresponding to the anomaly, along with a mapping of the equipment to the equipment repair profile; detecting the presence of the set of conditions in a second equipment; transmitting the equipment repair profile to an operator of the second equipment. [0010] In one embodiment, the method further includes transmitting the equipment repair profile to other operators having equipment same or similar to the second equipment. [0011] In another embodiment, the method further includes: generating equipment repair profiles of a plurality of equipment, corresponding to anomalies detected based on the one or more patterns in the physical parameters; based at least partly on the equipment repair profiles, detecting a set of conditions shared amongst the plurality of equipment having the detected anomalies; generating a second repair profile corresponding to the set of conditions and the detected anomalies corresponding to the set of conditions; detecting presence of the set of conditions in a second plurality of equipment; and transmitting the second repair profile to one or more operators of the second plurality of equipment. [0019] In some embodiments, the operations further include: generating a set of conditions based at least partly on the one or more patterns, wherein the set of conditions correlate with the anomaly; generating an equipment repair profile corresponding to the anomaly, along with a mapping of the equipment to the equipment repair profile; detecting the presence of the set of conditions in a second equipment; and transmitting the equipment repair profile to an operator of the second equipment.), the second service request comprising one or more characteristics of the item of building equipment (McKelvy et al. 2021/0264385 [0005 - receiving a profile of an equipment from an operator of the equipment, wherein the profile comprises one or more physical parameters of the equipment to be monitored and normal ranges of the physical parameters] In one aspect a method is disclosed. The method includes: receiving a profile of an equipment from an operator of the equipment, wherein the profile comprises one or more physical parameters of the equipment to be monitored and normal ranges of the physical parameters; monitoring, with one or more sensors, the one or more physical parameters of the equipment; transmitting the physical parameter values to a backend server; determining if the physical parameter values are outside the normal range and generating a notification; determining one or more patterns in the physical parameter values over a period of time; and generating a notification if the one or more patterns are indicative of an anomaly in operation of the equipment.); initiating a diagnostic conversation by prompting a user, via a user interface (McKelvy et al. 2021/0264385 [0042 – generate the UI client 114 and feed it with processed data in a format that is useful for an operator of the equipment 101 to improve its diagnostic and maintenance functions… UI client… application interface…]), to provide one or more additional items of information based at least on the one or more characteristics of the item of building equipment (McKelvy et al. 2021/0264385 [0003 - methods of providing diagnostics and maintenance for industrial and commercial equipment…][0046 - generate insight into diagnostics, maintenance, and overall operation efficiency of the equipment devices…]); receiving, via the user interface and based at least on one or more responses in the diagnostic conversation, the one or more additional items of information as unstructured data or natural language data (McKelvy et al. 2021/0264385 [0042]); automatically determining, by the one or more processors using the generative AI model (McKelvy et al. 2021/0264385 [0062 - Artificial Intelligence (AI) Techniques of Detecting Patterns] Artificial Intelligence (AI) Techniques of Detecting Patterns Indicating Device Failure [0064 - AI technique, which can be used for detecting primary or secondary patterns indicative of normal or abnormal device behavior. Sensor data of a first plurality of equipment 101 along with their prior repair history of the plurality of the equipment 101 can be used to train multiple machine learning (ML) networks 506 (e.g., neural networks or deep neural networks) to detect patterns] FIG. 5 illustrates a diagram 500 of an AI technique, which can be used for detecting primary or secondary patterns indicative of normal or abnormal device behavior. Sensor data of a first plurality of equipment 101 along with their prior repair history of the plurality of the equipment 101 can be used to train multiple machine learning (ML) networks 506 (e.g., neural networks or deep neural networks) to detect patterns of sensor data that can be correlated to normal or abnormal device operation. Each machine learning network 506 can be trained for detecting patterns of sensor data correlated with specific malfunctions in the first plurality of equipment 101. The past maintenance reports can be used as ground truth and used to train the ML networks 506. Multiple instances of the ML networks 506 can be trained for various brands, types of equipment 101 or different parts within the equipment 101. Furthermore, instances of the ML networks 506 can be trained to detect patterns of sensor data indicative of a malfunction, wherein each instance of ML network 506 is trained to detect patterns of sensor data correlated with a malfunction. After training, the ML networks 506 can detect patterns of sensor data correlated with one or more device malfunctions and can label the sensor data accordingly, thereby generating labeled patterns of sensor data 508. The sensor data for the purpose of training the ML networks 506 may be converted into various data structure formats, including, for example, vectors, arrays, multidimensional arrays, and/or tensors.), one or more actions to perform on the item of building equipment (McKelvy et al. 2021/0264385 [0035 - predictive maintenance actions] In some cases, human technicians can accumulate and transfer their knowledge of a particular brand of equipment and device and extrapolate from that knowledge to better perform repair or maintenance on other or similar devices. For example, the technician may be aware of a common failure in a particular brand of industrial refrigerator from his prior repair experiences. However, such knowledge can be limited and not shared among the industry at large. Furthermore, there is no infrastructure to collect and learn from prior repair or maintenance work of a device or industrial equipment, in a manner that the data can inform industry approaches to repair, maintenance and improving efficiency. Such data can provide technological solutions for predictive maintenance actions that can vastly improve the life cycle of industrial, commercial or consumer products by triggering timely and targeted maintenance or repair. [0056 - repair notification can include a course of action determined based on the sensor readings] Additionally, the repair notification can include a course of action determined based on the sensor readings, processed clean sensor data and detected patterns in sensor data. For example, the backend server 112 can detect a pattern of increasing temperatures in a sensor 106 located near the door of a walk-in cooler that persists throughout a 24-hour period. The door is expected to be shut for an extended period of time during night hours and the temperature readings near the door are expected to drop during those hours. Other temperature sensors 106 inside the walk-in cooler do not indicate the same pattern of rising temperature and at night drop and stay constant. In this scenario, the timing of sensor readings, the location of sensor readings, and the history of the sensor reading, can indicate a malfunction or broken seal in the door of the walk-in cooler. Consequently, the repair notification can include a course of action determined based on timing, location, involved parts, and corresponding solutions. For example, a notification generated on the UI client 114 can include text phrase, “high temperatures near cooler entrance during night. Inspect proper door operation and seal.”), in response to the second service request, based on the one or more characteristics of the item of building equipment, the unstructured data or the natural language data, and the configuration of the generative AI model (McKelvy et al. 2021/0264385 [0057] In some embodiments, the backend server 112 can detect patterns indicative of normal or abnormal equipment operation, not only from sensor data from an individual equipment 101, but from a collection of equipment 101, that may be present at the same site or at different locations. In other words, a plurality of same or similar equipment 101 can be included in the pattern detection of the backend server 112, for example, sensor data from equipment 101 having same brand and/or type can be included in pattern detection. In other examples, sensor data, as well as notification data, stored in the database 116 over a period of time can be used for pattern detection. Refrigerator XYZ brand of type UVW can show a pattern of needing a condenser part replacement after 10,000 hours of operations across various operators. Consequently, operators having the same or similar refrigerator can be sent a repair notification at or before their equipment reaches 10,000 hours of operation. [0058] In another embodiment, the detected patterns in sensor data from one or more equipment 101 can be used to generate a set of conditions whose existence in another equipment 101 of same or similar type can indicate an anomaly. For example, when an increasing trend in temperature sensor readings for a first equipment 101 is detected, the backend server 112 can generate a set of conditions indicative of an anomaly, where the set of conditions are extracted from the first equipment 101. The set of conditions can include data, such as brand, type, age, constituent parts, duration of time after which a part required maintenance, or any other data correlated with the anomaly in the first equipment 101. In some embodiments, maintenance records of the first equipment 101 stored on database 116 and/or received via operation profile of the first equipment 101 can be used to further augment the set of conditions indicative of an anomaly. In some embodiments, the set of conditions indicative of an anomaly can be generated from a plurality of first equipment 101. [0063] In some embodiments, AI techniques can be used to detect primary or secondary patterns indicative of device or equipment failure. Primary patterns can refer to patterns existing in raw or clean sensor 106 data indicative of normal or abnormal device operation. Secondary patterns can refer to patterns existing in prior maintenance records of a plurality of equipment 101, which can be indicative of normal or abnormal device operations in same or similar equipment. [0064] FIG. 5 illustrates a diagram 500 of an AI technique, which can be used for detecting primary or secondary patterns indicative of normal or abnormal device behavior. Sensor data of a first plurality of equipment 101 along with their prior repair history of the plurality of the equipment 101 can be used to train multiple machine learning (ML) networks 506 (e.g., neural networks or deep neural networks) to detect patterns of sensor data that can be correlated to normal or abnormal device operation. Each machine learning network 506 can be trained for detecting patterns of sensor data correlated with specific malfunctions in the first plurality of equipment 101. The past maintenance reports can be used as ground truth and used to train the ML networks 506. Multiple instances of the ML networks 506 can be trained for various brands, types of equipment 101 or different parts within the equipment 101. Furthermore, instances of the ML networks 506 can be trained to detect patterns of sensor data indicative of a malfunction, wherein each instance of ML network 506 is trained to detect patterns of sensor data correlated with a malfunction. After training, the ML networks 506 can detect patterns of sensor data correlated with one or more device malfunctions and can label the sensor data accordingly, thereby generating labeled patterns of sensor data 508. The sensor data for the purpose of training the ML networks 506 may be converted into various data structure formats, including, for example, vectors, arrays, multidimensional arrays, and/or tensors. [0065] Next, sensor data 510 from a second plurality of equipment 101 whose maintenance needs or repair history may be unknown are received by one or more trained ML network 512. The ML networks 512 are the same or similar to the ML networks 506 after training. The trained ML networks 512 can detect patterns of sensor data 508 in the input sensor data 510 and label them accordingly. The labels can include information that correlate with maintenance requirements of the second plurality of equipment 101. For example, labels can include, “normal device operation,” “abnormal device operation,” “part failure imminent,” or they can include part specific information, such “part MNPQ imminent failure,” or any label that may improve diagnostics and maintenance of the second plurality of equipment 101. At the same time, the backend server maintains a mapping of which specific equipment 101, the sensor data containing a detected labeled pattern originate from (e.g, via a database entry mapping a device identifier with the stored sensor barcode or QR code). The backend server 112 can therefore identify to which equipment 101, the detected labeled pattern of sensor data corresponds. [0066] FIG. 6 illustrates a flowchart of a method 600 of using artificial intelligence (AI) techniques for detecting patterns of sensor data indicative of device failure. At step 602, the method includes receiving a plurality of sensor data of a first plurality of equipment. At step 604, the method includes receiving repair history associated with each equipment of the first plurality of equipment. At step 606, the method includes training a plurality of machine learning networks to detect patterns of sensor data indicative of a plurality of malfunctions, wherein each machine learning network is trained for detecting the patterns of sensor data indicative of a single malfunction. At step 608, the method includes receiving sensor data of a second plurality of equipment. At step 610, the method includes using one or more of the trained plurality of machine learning networks to detect the patterns of sensor data indicative of one or more malfunctions. At step 612, the method includes identifying one or more equipment in the second plurality of equipment having sensor data, comprising the detected patterns of sensor data. At step 614, the method includes, generating and transmitting a notification to an operator of the one or more equipment in the second plurality of equipment, wherein the notification comprises a notification of the one or more malfunction.); and generating an output response to the second service request to present the one or more actions via the user interface (McKelvy et al. 2021/0264385 [0035 - provide technological solutions for predictive maintenance actions that can vastly improve the life cycle of industrial, commercial or consumer products by triggering timely and targeted maintenance or repair][0039 - system 100 can generate a notification to order maintenance for the equipment][0056 - the repair notification can include a course of action determined based on the sensor readings, processed clean sensor data and detected patterns in sensor data … a notification generated on the UI client 114 can include text phrase, “high temperatures near cooler entrance during night. Inspect proper door operation and seal.”]).
McKelvy et al. 2021/0264385 may not expressly disclose the “unstructured data or the natural language data” features, however, Hita et al. 2023/0350398 teaches (Hita et al. 2023/0350398 [0004 - industrial machine diagnostic system includes a communication interface in communication with a first database storing diagnostic information related to one or more industrial machines, a second database storing user profile information, and a user device configured to transmit a natural input diagnostic request for a machine and receive an output from the communication interface.][0010 - In certain configurations a natural language processing component is configured to identify asynchronous conversations and perform topic structure identification and information extraction to match relevant conversation data to the diagnostic request data.][0058 - The system can accept various text and speech inputs and be used to provide automatic diagnostic information and recommendations. The system can be connected to any combination of a question database, live library, automated chat, or can be used assisting with manual chat. The system can also be used to help provide a hands-free diagnostic assistance where a technician verbally diagnosing a problem as they examine a machine and receives feedback based on the voice diagnostic.][Claims 1 and 11]). Before the effective filing date of the claimed invention, it would have been obvious for one of ordinary skill in the art to have modified McKelvy et al. 2021/0264385 to include the features as taught by Hita et al. 2023/0350398. One of ordinary skill in the art would have been motivated to do so to utilize well known tools and features useful for implementing a building management method/system with generative AI-based automated maintenance service scheduling and modification which should prove to improve user experience, maximize profits, and optimize revenue.
McKelvy et al. 2021/0264385 may not expressly disclose the “service requests for servicing building equipment” features, however, DeLuca et al. 2022/0198474 teaches (DeLuca et al. 2022/0198474 [0011 - computer system for aligning appropriate service requests to a technician as a provider of services, the alignment based on matching the area(s) of expertise, experience, qualifications, location, and service performance history of a respective technician to a set of service requests in which the type of service and requirements of the service are generally known from an aggregate of historical performances] Embodiments of the present invention provide a method, computer program product, and computer system for aligning appropriate service requests to a technician as a provider of services, the alignment based on matching the area(s) of expertise, experience, qualifications, location, and service performance history of a respective technician to a set of service requests in which the type of service and requirements of the service are generally known from an aggregate of historical performances. In some embodiments, a machine learning model is applied to the service performance history of a respective technician, in which the model learns a skill level and experience of the technician in a particular area of providing service to assets. [0014 - the service request may identify an asset and a problem or condition of the asset requiring service] Embodiments of the present invention include receiving a plurality of service requests. In some embodiments, service requests include information regarding the service to be performed, a location at which the service is to be performed, a requested timeframe or level of urgency, and may include conditions in which the service is to be performed. For example, the service request may identify an asset and a problem or condition of the asset requiring service. In some embodiments, the required service may be known and well defined, such as a scheduled maintenance service request of an HVAC unit. In other embodiments, the service request may include a description of symptoms and data that is sufficient to determine the service requirements. In yet other embodiments, the service request may require examination and diagnosis to determine the specific service required. In some embodiments, the location of the service request may include special access conditions for security or safety-related reasons, such that technicians responding to service requests at the location may have to complete prior background checks, interviews, agreements, or may have to possess and use specialized equipment for personal safety or safety of the location.). Before the effective filing date of the claimed invention, it would have been obvious for one of ordinary skill in the art to have modified McKelvy et al. 2021/0264385 to include the features as taught by DeLuca et al. 2022/0198474. One of ordinary skill in the art would have been motivated to do so to utilize well known tools and features useful for implementing a building management method/system with generative AI-based automated maintenance service scheduling and modification which should prove to improve user experience, maximize profits, and optimize revenue.
McKelvy et al. 2021/0264385 may not expressly disclose the “a plurality of examples of service actions, and corresponding successful outcomes, that resolved one or more problems or faults indicated by the plurality of first service requests” features, however, Lin et al. 2022/0101148 teaches these features as follows (Lin et al. 2022/0101148 [Abstract - a machine learning model is trained to predict which action will lead to a solution based on an accumulated data set including a problem and subsequent results from previous actions…] Some embodiments of the present invention are directed towards techniques for building and using machine learning enhanced trees for automated solution determination in a technical support context. Historical technical support records with associated problems, actions and results are received and clustered. A solution determination tree is constructed from the clustered actions, and a machine learning model is trained to predict which action will lead to a solution based on an accumulated data set including a problem and subsequent results from previous actions. Using the solution determination tree and the machine learning model, classes of actions are recommended based on accumulated data for an incoming support request/problem or a result resulting from a executing a previously recommended action. [0021 - a machine learning model is trained to predict which action will lead to a solution based on an accumulated data set including a problem and subsequent results from previous actions] Some embodiments of the present invention are directed to techniques for building and using machine learning enhanced trees for automated solution determination in a technical support context. Historical technical support records with associated problems, actions and results are received and clustered. A solution determination tree is constructed from the clustered actions, and a machine learning model is trained to predict which action will lead to a solution based on an accumulated data set including a problem and subsequent results from previous actions. Using the solution determination tree and the machine learning model, classes of actions are recommended based on accumulated data for an incoming support request/problem or a result resulting from a executing a previously recommended action. [0064 – a machine learning model predicts which next action or post-action (P-Action) class will lead to a successful closure of the original problem using accumulating information, such as results or responses from actions undertaken to resolve the problem] Some embodiments of the present invention include machine learning elements training on traversal paths to a solution through a tree as shown in flow 700 of FIG. 7, which includes the following traversal steps towards resolving problem 1 (PC1) 702: (i) Action 1 (AC1) 704; (ii) Result 1 (RC1) 706; (iii) P-Action (PAC1) 708; (iv) Result 2 (RC2) 710; (v) P-Action 2 (PAC2) 712; (vi) Result 3 (RC3) 714; and (vii) P-Action 3 (close) 716. Regarding flow 700, a machine learning model predicts which next action or post-action (P-Action) class will lead to a successful closure of the original problem using accumulating information, such as results or responses from actions undertaken to resolve the problem. Referring now to diagram 800 of FIG. 8, if the problem is clearly described, the machine learning model can predict the solution to the problem without traversing intermediate steps. For example, if an incoming report includes text with semantic similarity to text of problem 1 806, text of result 1 804 and text of result 2 802, the machine learning model can predict that PAC2 808 will successfully resolve the problem of the incoming report. [0056; 0062-0066]). Before the effective filing date of the claimed invention, it would have been obvious for one of ordinary skill in the art to have modified McKelvy et al. 2021/0264385 to include the features as taught by Lin et al. 2022/0101148. One of ordinary skill in the art would have been motivated to do so to utilize well known tools and features useful for implementing a building management method/system with generative AI-based automated maintenance service scheduling and modification which should prove to improve user experience, maximize profits, and optimize revenue.
18/633,086 – Claim 11. (Currently Amended) McKelvy et al. 2021/0264385 further teaches A method comprising: obtaining, by one or more processors (McKelvy et al. 2021/0264385 [0067 - implemented using a network of computers and processors]), a generative AI model configured to (McKelvy et al. 2021/0264385 [0062 - Artificial Intelligence (AI) Techniques of Detecting Patterns] Artificial Intelligence (AI) Techniques of Detecting Patterns Indicating Device Failure [0064 - AI technique, which can be used for detecting primary or secondary patterns indicative of normal or abnormal device behavior. Sensor data of a first plurality of equipment 101 along with their prior repair history of the plurality of the equipment 101 can be used to train multiple machine learning (ML) networks 506 (e.g., neural networks or deep neural networks) to detect patterns] FIG. 5 illustrates a diagram 500 of an AI technique, which can be used for detecting primary or secondary patterns indicative of normal or abnormal device behavior. Sensor data of a first plurality of equipment 101 along with their prior repair history of the plurality of the equipment 101 can be used to train multiple machine learning (ML) networks 506 (e.g., neural networks or deep neural networks) to detect patterns of sensor data that can be correlated to normal or abnormal device operation. Each machine learning network 506 can be trained for detecting patterns of sensor data correlated with specific malfunctions in the first plurality of equipment 101. The past maintenance reports can be used as ground truth and used to train the ML networks 506. Multiple instances of the ML networks 506 can be trained for various brands, types of equipment 101 or different parts within the equipment 101. Furthermore, instances of the ML networks 506 can be trained to detect patterns of sensor data indicative of a malfunction, wherein each instance of ML network 506 is trained to detect patterns of sensor data correlated with a malfunction. After training, the ML networks 506 can detect patterns of sensor data correlated with one or more device malfunctions and can label the sensor data accordingly, thereby generating labeled patterns of sensor data 508. The sensor data for the purpose of training the ML networks 506 may be converted into various data structure formats, including, for example, vectors, arrays, multidimensional arrays, and/or tensors.) identify one or more patterns or trends between characteristics of a plurality of first service requests for servicing building equipment (McKelvy et al. 2021/0264385 [0064 - Sensor data of a first plurality of equipment 101 along with their prior repair history of the plurality of the equipment 101 can be used to train multiple machine learning (ML) networks 506 (e.g., neural networks or deep neural networks) to detect patterns of sensor data that can be correlated to normal or abnormal device operation] FIG. 5 illustrates a diagram 500 of an AI technique, which can be used for detecting primary or secondary patterns indicative of normal or abnormal device behavior. Sensor data of a first plurality of equipment 101 along with their prior repair history of the plurality of the equipment 101 can be used to train multiple machine learning (ML) networks 506 (e.g., neural networks or deep neural networks) to detect patterns of sensor data that can be correlated to normal or abnormal device operation. Each machine learning network 506 can be trained for detecting patterns of sensor data correlated with specific malfunctions in the first plurality of equipment 101. The past maintenance reports can be used as ground truth and used to train the ML networks 506. Multiple instances of the ML networks 506 can be trained for various brands, types of equipment 101 or different parts within the equipment 101. Furthermore, instances of the ML networks 506 can be trained to detect patterns of sensor data indicative of a malfunction, wherein each instance of ML network 506 is trained to detect patterns of sensor data correlated with a malfunction. After training, the ML networks 506 can detect patterns of sensor data correlated with one or more device malfunctions and can label the sensor data accordingly, thereby generating labeled patterns of sensor data 508. The sensor data for the purpose of training the ML networks 506 may be converted into various data structure formats, including, for example, vectors, arrays, multidimensional arrays, and/or tensors. [0066 - method includes training a plurality of machine learning networks to detect patterns of sensor data indicative of a plurality of malfunctions, wherein each machine learning network is trained for detecting the patterns of sensor data indicative of a single malfunction] FIG. 6 illustrates a flowchart of a method 600 of using artificial intelligence (AI) techniques for detecting patterns of sensor data indicative of device failure. At step 602, the method includes receiving a plurality of sensor data of a first plurality of equipment. At step 604, the method includes receiving repair history associated with each equipment of the first plurality of equipment. At step 606, the method includes training a plurality of machine learning networks to detect patterns of sensor data indicative of a plurality of malfunctions, wherein each machine learning network is trained for detecting the patterns of sensor data indicative of a single malfunction. At step 608, the method includes receiving sensor data of a second plurality of equipment. At step 610, the method includes using one or more of the trained plurality of machine learning networks to detect the patterns of sensor data indicative of one or more malfunctions. At step 612, the method includes identifying one or more equipment in the second plurality of equipment having sensor data, comprising the detected patterns of sensor data. At step 614, the method includes, generating and transmitting a notification to an operator of the one or more equipment in the second plurality of equipment, wherein the notification comprises a notification of the one or more malfunction.) … present the one or more actions via the user interface, the output response comprising at least one of image data, video data, or audio data (McKelvy et al. 2021/0264385 [0035 - provide technological solutions for predictive maintenance actions that can vastly improve the life cycle of industrial, commercial or consumer products by triggering timely and targeted maintenance or repair][0039 - system 100 can generate a notification to order maintenance for the equipment][0056 - the repair notification can include a course of action determined based on the sensor readings, processed clean sensor data and detected patterns in sensor data … a notification generated on the UI client 114 can include text phrase, “high temperatures near cooler entrance during night. Inspect proper door operation and seal.”]).
Claim 11, has similar limitations as of Claim(s) 1, therefore it is REJECTED under the same rationale as Claim(s) 1.
18/633,086 – Claim 20. (Currently Amended) McKelvy et al. 2021/0264385 further teaches A method comprising: updating, by one or more processors (McKelvy et al. 2021/0264385 [0067 - implemented using a network of computers and processors]), a machine learning model using a plurality of first service requests for servicing building equipment (McKelvy et al. 2021/0264385 [0064 - Sensor data of a first plurality of equipment 101 along with their prior repair history of the plurality of the equipment 101 can be used to train multiple machine learning (ML) networks 506 (e.g., neural networks or deep neural networks) to detect patterns of sensor data that can be correlated to normal or abnormal device operation] FIG. 5 illustrates a diagram 500 of an AI technique, which can be used for detecting primary or secondary patterns indicative of normal or abnormal device behavior. Sensor data of a first plurality of equipment 101 along with their prior repair history of the plurality of the equipment 101 can be used to train multiple machine learning (ML) networks 506 (e.g., neural networks or deep neural networks) to detect patterns of sensor data that can be correlated to normal or abnormal device operation. Each machine learning network 506 can be trained for detecting patterns of sensor data correlated with specific malfunctions in the first plurality of equipment 101. The past maintenance reports can be used as ground truth and used to train the ML networks 506. Multiple instances of the ML networks 506 can be trained for various brands, types of equipment 101 or different parts within the equipment 101. Furthermore, instances of the ML networks 506 can be trained to detect patterns of sensor data indicative of a malfunction, wherein each instance of ML network 506 is trained to detect patterns of sensor data correlated with a malfunction. After training, the ML networks 506 can detect patterns of sensor data correlated with one or more device malfunctions and can label the sensor data accordingly, thereby generating labeled patterns of sensor data 508. The sensor data for the purpose of training the ML networks 506 may be converted into various data structure formats, including, for example, vectors, arrays, multidimensional arrays, and/or tensors. [0066 - method includes training a plurality of machine learning networks to detect patterns of sensor data indicative of a plurality of malfunctions, wherein each machine learning network is trained for detecting the patterns of sensor data indicative of a single malfunction] FIG. 6 illustrates a flowchart of a method 600 of using artificial intelligence (AI) techniques for detecting patterns of sensor data indicative of device failure. At step 602, the method includes receiving a plurality of sensor data of a first plurality of equipment. At step 604, the method includes receiving repair history associated with each equipment of the first plurality of equipment. At step 606, the method includes training a plurality of machine learning networks to detect patterns of sensor data indicative of a plurality of malfunctions, wherein each machine learning network is trained for detecting the patterns of sensor data indicative of a single malfunction. At step 608, the method includes receiving sensor data of a second plurality of equipment. At step 610, the method includes using one or more of the trained plurality of machine learning networks to detect the patterns of sensor data indicative of one or more malfunctions. At step 612, the method includes identifying one or more equipment in the second plurality of equipment having sensor data, comprising the detected patterns of sensor data. At step 614, the method includes, generating and transmitting a notification to an operator of the one or more equipment in the second plurality of equipment, wherein the notification comprises a notification of the one or more malfunction.) … using the machine learning model and generating an output response to the second service request to present the one or more actions via the user interface (McKelvy et al. 2021/0264385 [0035 - provide technological solutions for predictive maintenance actions that can vastly improve the life cycle of industrial, commercial or consumer products by triggering timely and targeted maintenance or repair][0039 - system 100 can generate a notification to order maintenance for the equipment][0056 - the repair notification can include a course of action determined based on the sensor readings, processed clean sensor data and detected patterns in sensor data … a notification generated on the UI client 114 can include text phrase, “high temperatures near cooler entrance during night. Inspect proper door operation and seal.”]).
Claim 20, has similar limitations as of Claim(s) 1, therefore it is REJECTED under the same rationale as Claim(s) 1.
18/633,086 – Claim 2. (Previously Presented) McKelvy et al. 2021/0264385 further teaches The method of claim 1, wherein the characteristics of the plurality of first service requests and the one or more characteristics of the second service request comprise at least one of: a type or model of the building equipment; a geographic location of the building equipment or a building associated with the building equipment; a customer associated with the building equipment; a service history of the building equipment; a problem or fault associated with the building equipment; or warranty data associated with the building equipment (McKelvy et al. 2021/0264385 [0046] UI clients 114 can also be used to receive from the operator of the equipment 101, an operation profile of the equipment 101. The operation profile can include data, such as, device identifier of equipment 101, its location identifier, its brand, type, age, hours of operation, service and/or maintenance history, and a list of the physical parameters, which the system 100 can monitor. Sensor data in combination with the operation profiles of a multitude of equipment devices 101 across an industry can be used to generate insight into diagnostics, maintenance, and overall operation efficiency of the equipment devices 101.).
18/633,086 – Claim 12. The method of claim 11, wherein the characteristics of the plurality of first service requests and the characteristics of the second service requests comprise at least one of: a type or model of the building equipment; a geographic location of the building equipment or a building associated with the building equipment; a customer associated with the building equipment; a service history of the building equipment; a problem or fault associated with the building equipment; or warranty data associated with the building equipment.
Claim 12, has similar limitations as of Claim(s) 2, therefore it is REJECTED under the same rationale as Claim(s) 2.
18/633,086 – Claim 3. (Previously Presented) McKelvy et al. 2021/0264385 further teaches The method of claim 1, wherein the outcome data indicate one or more technicians assigned to the plurality of first service requests; and automatically determining the one or more actions comprises assigning a technician to handle the second service request using the generative AI model (McKelvy et al. 2021/0264385 [0009 - transmitting the equipment repair profile to an operator of the second equipment] In some embodiments, the method further includes: generating a set of conditions based at least partly on the one or more patterns, wherein the set of conditions correlate with the anomaly; generating an equipment repair profile corresponding to the anomaly, along with a mapping of the equipment to the equipment repair profile; detecting the presence of the set of conditions in a second equipment; transmitting the equipment repair profile to an operator of the second equipment. [0011 - transmitting the second repair profile to one or more operators of the second plurality of equipment] In another embodiment, the method further includes: generating equipment repair profiles of a plurality of equipment, corresponding to anomalies detected based on the one or more patterns in the physical parameters; based at least partly on the equipment repair profiles, detecting a set of conditions shared amongst the plurality of equipment having the detected anomalies; generating a second repair profile corresponding to the set of conditions and the detected anomalies corresponding to the set of conditions; detecting presence of the set of conditions in a second plurality of equipment; and transmitting the second repair profile to one or more operators of the second plurality of equipment. [0055] In some embodiments, the sensor readings might not exceed a threshold or be outside of a range indicated in the operation profile of equipment 101. However, patterns and history of sensor readings can indicate a trajectory and approach, wherein it can be likely that the equipment 101 might fail. For example, a vibration, current or temperature sensor 106 can report readings that are gradually increasing over a period of time and the trend in sensor reading indicates a near-future propensity to exceed a threshold or range indicated in the operation profile of the equipment 101. In other instances, the detected patterns can indicate an erratic range of values of the monitored parameters beyond the noise levels of the system 100. For example, a temperature sensor 106 whose reported temperatures have been constant or near constant can start oscillating between a high temperature value and the constant value in periodic or non-periodic manner. This can indicate an upcoming equipment failure. In other words, the present reported sensor values can be compared against stored sensor data of the same sensor to determine patterns indicating [0059 - generate a repair notification] Next, the backend server 112 can scan the received sensor readings from a second equipment 101, and if presence of the set of conditions indicative of the anomaly is detected, the backend server 112 can generate a repair notification via UI clients 114. In some embodiments, the set of conditions can be used in a predictive manner, such that when presence of some of the set of conditions indicative of anomaly is detected, and one or more remaining conditions are going to be satisfied in the near future, the backend server 112, can issue a repair notification. For example, when brand and type of a second equipment 101 matches the brand and type in a set of condition indicative of anomaly, and the age of a part in the second equipment 101 is approaching an age indicated in the set of conditions within a predetermined threshold, the backend server 112 can generate a repair notification. The predetermined threshold can for example be encoded as within 90% of the value of a parameter in the set of conditions (e.g., hours of operation of the part). [0060] FIG. 3 illustrates a flow chart of a method 300 of providing automated maintenance using the systems 100 and 200. At step 302, the method includes receiving a profile of an equipment from an operator of the equipment, wherein the profile comprises one or more physical parameters of the equipment to be monitored and normal ranges of the physical parameters. At step 304, the method includes monitoring, with one or more sensors, the one or more physical parameters of the equipment. At step 306, the method includes transmitting the physical parameter values to a backend server. At step 308, the method includes determining if the physical parameter values are outside the normal range and generating a notification. At step 310, the method includes determining one or more patterns in the physical parameter values over a period of time. At step 312, the method includes generating a notification if the one or more patterns are indicative of an anomaly in operation of the equipment.).
McKelvy et al. 2021/0264385 may not expressly disclose the “technician” features, however, DeLuca et al. 2022/0198474 teaches (DeLuca et al. 2022/0198474 [0004 - aligning appropriate service requests to a technician as a provider of services] Embodiments of the present invention disclose a method, computer program product, and system for aligning appropriate service requests to a technician as a provider of services. The method provides for one or more processors to receive information about a technician, wherein the information includes an area of expertise, a skill level, documented qualifications, a set of tools and materials available to the technician, a history of previously performed service instances by the technician, and a location of the technician. The one or more processors receive a plurality of service request candidates in which respective service requests include information associated with respective service requests. The one or more processors identify a first set of service requests appropriate for the technician by comparing the information about the technician and the current location of the technician to the plurality of service request candidates. The one or more processors determine a recommended order in which the first set of service requests are performed by the technician, based on a distance between service request locations, the urgency of performing the service request, and factors associated with the respective service request; and the one or more processors present a map representation of relative locations and the recommended order of service request response for the first set of service requests to the technician. [0011 - computer system for aligning appropriate service requests to a technician as a provider of services, the alignment based on matching the area(s) of expertise, experience, qualifications, location, and service performance history of a respective technician to a set of service requests in which the type of service and requirements of the service are generally known from an aggregate of historical performances] Embodiments of the present invention provide a method, computer program product, and computer system for aligning appropriate service requests to a technician as a provider of services, the alignment based on matching the area(s) of expertise, experience, qualifications, location, and service performance history of a respective technician to a set of service requests in which the type of service and requirements of the service are generally known from an aggregate of historical performances. In some embodiments, a machine learning model is applied to the service performance history of a respective technician, in which the model learns a skill level and experience of the technician in a particular area of providing service to assets. [0014 - the service request may identify an asset and a problem or condition of the asset requiring service] Embodiments of the present invention include receiving a plurality of service requests. In some embodiments, service requests include information regarding the service to be performed, a location at which the service is to be performed, a requested timeframe or level of urgency, and may include conditions in which the service is to be performed. For example, the service request may identify an asset and a problem or condition of the asset requiring service. In some embodiments, the required service may be known and well defined, such as a scheduled maintenance service request of an HVAC unit. In other embodiments, the service request may include a description of symptoms and data that is sufficient to determine the service requirements. In yet other embodiments, the service request may require examination and diagnosis to determine the specific service required. In some embodiments, the location of the service request may include special access conditions for security or safety-related reasons, such that technicians responding to service requests at the location may have to complete prior background checks, interviews, agreements, or may have to possess and use specialized equipment for personal safety or safety of the location.). Before the effective filing date of the claimed invention, it would have been obvious for one of ordinary skill in the art to have modified McKelvy et al. 2021/0264385 to include the features as taught by DeLuca et al. 2022/0198474. One of ordinary skill in the art would have been motivated to do so to utilize well known tools and features useful for implementing a building management method/system with generative AI-based automated maintenance service scheduling and modification which should prove to improve user experience, maximize profits, and optimize revenue.
18/633,086 – Claim 13. The method of claim 11, wherein the outcome data indicate one or more technicians assigned to the plurality of first service requests; and automatically determining the one or more responses to the second service request comprises assigning a technician to handle the second service request using the generative AI model.
Claim 13, has similar limitations as of Claim(s) 3, therefore it is REJECTED under the same rationale as Claim(s) 3.
18/633,086 – Claim 4. (Previously Presented) McKelvy et al. 2021/0264385 further teaches The method of claim 1, wherein the outcome data indicate one or more types of service activities required to handle the plurality of first service requests; and automatically determining the one or more actions comprises assigning a technician to handle the second service request using the generative AI model (McKelvy et al. 2021/0264385 [0062 - Artificial Intelligence (AI) Techniques of Detecting Patterns] Artificial Intelligence (AI) Techniques of Detecting Patterns Indicating Device Failure [0064 - AI technique, which can be used for detecting primary or secondary patterns indicative of normal or abnormal device behavior. Sensor data of a first plurality of equipment 101 along with their prior repair history of the plurality of the equipment 101 can be used to train multiple machine learning (ML) networks 506 (e.g., neural networks or deep neural networks) to detect patterns] FIG. 5 illustrates a diagram 500 of an AI technique, which can be used for detecting primary or secondary patterns indicative of normal or abnormal device behavior. Sensor data of a first plurality of equipment 101 along with their prior repair history of the plurality of the equipment 101 can be used to train multiple machine learning (ML) networks 506 (e.g., neural networks or deep neural networks) to detect patterns of sensor data that can be correlated to normal or abnormal device operation. Each machine learning network 506 can be trained for detecting patterns of sensor data correlated with specific malfunctions in the first plurality of equipment 101. The past maintenance reports can be used as ground truth and used to train the ML networks 506. Multiple instances of the ML networks 506 can be trained for various brands, types of equipment 101 or different parts within the equipment 101. Furthermore, instances of the ML networks 506 can be trained to detect patterns of sensor data indicative of a malfunction, wherein each instance of ML network 506 is trained to detect patterns of sensor data correlated with a malfunction. After training, the ML networks 506 can detect patterns of sensor data correlated with one or more device malfunctions and can label the sensor data accordingly, thereby generating labeled patterns of sensor data 508. The sensor data for the purpose of training the ML networks 506 may be converted into various data structure formats, including, for example, vectors, arrays, multidimensional arrays, and/or tensors.) based on capabilities of one or more technicians with respect to the one or more types of service activities (McKelvy et al. 2021/0264385 [0056 - repair notification can include a course of action determined based on] Additionally, the repair notification can include a course of action determined based on the sensor readings, processed clean sensor data and detected patterns in sensor data. For example, the backend server 112 can detect a pattern of increasing temperatures in a sensor 106 located near the door of a walk-in cooler that persists throughout a 24-hour period. The door is expected to be shut for an extended period of time during night hours and the temperature readings near the door are expected to drop during those hours. Other temperature sensors 106 inside the walk-in cooler do not indicate the same pattern of rising temperature and at night drop and stay constant. In this scenario, the timing of sensor readings, the location of sensor readings, and the history of the sensor reading, can indicate a malfunction or broken seal in the door of the walk-in cooler. Consequently, the repair notification can include a course of action determined based on timing, location, involved parts, and corresponding solutions. For example, a notification generated on the UI client 114 can include text phrase, “high temperatures near cooler entrance during night. Inspect proper door operation and seal.”).
McKelvy et al. 2021/0264385 may not expressly disclose the “technician” features, however, DeLuca et al. 2022/0198474 teaches (DeLuca et al. 2022/0198474 [0004 - aligning appropriate service requests to a technician as a provider of services] Embodiments of the present invention disclose a method, computer program product, and system for aligning appropriate service requests to a technician as a provider of services. The method provides for one or more processors to receive information about a technician, wherein the information includes an area of expertise, a skill level, documented qualifications, a set of tools and materials available to the technician, a history of previously performed service instances by the technician, and a location of the technician. The one or more processors receive a plurality of service request candidates in which respective service requests include information associated with respective service requests. The one or more processors identify a first set of service requests appropriate for the technician by comparing the information about the technician and the current location of the technician to the plurality of service request candidates. The one or more processors determine a recommended order in which the first set of service requests are performed by the technician, based on a distance between service request locations, the urgency of performing the service request, and factors associated with the respective service request; and the one or more processors present a map representation of relative locations and the recommended order of service request response for the first set of service requests to the technician. [0011 - computer system for aligning appropriate service requests to a technician as a provider of services, the alignment based on matching the area(s) of expertise, experience, qualifications, location, and service performance history of a respective technician to a set of service requests in which the type of service and requirements of the service are generally known from an aggregate of historical performances] Embodiments of the present invention provide a method, computer program product, and computer system for aligning appropriate service requests to a technician as a provider of services, the alignment based on matching the area(s) of expertise, experience, qualifications, location, and service performance history of a respective technician to a set of service requests in which the type of service and requirements of the service are generally known from an aggregate of historical performances. In some embodiments, a machine learning model is applied to the service performance history of a respective technician, in which the model learns a skill level and experience of the technician in a particular area of providing service to assets. [0014 - the service request may identify an asset and a problem or condition of the asset requiring service] Embodiments of the present invention include receiving a plurality of service requests. In some embodiments, service requests include information regarding the service to be performed, a location at which the service is to be performed, a requested timeframe or level of urgency, and may include conditions in which the service is to be performed. For example, the service request may identify an asset and a problem or condition of the asset requiring service. In some embodiments, the required service may be known and well defined, such as a scheduled maintenance service request of an HVAC unit. In other embodiments, the service request may include a description of symptoms and data that is sufficient to determine the service requirements. In yet other embodiments, the service request may require examination and diagnosis to determine the specific service required. In some embodiments, the location of the service request may include special access conditions for security or safety-related reasons, such that technicians responding to service requests at the location may have to complete prior background checks, interviews, agreements, or may have to possess and use specialized equipment for personal safety or safety of the location.). Before the effective filing date of the claimed invention, it would have been obvious for one of ordinary skill in the art to have modified McKelvy et al. 2021/0264385 to include the features as taught by DeLuca et al. 2022/0198474. One of ordinary skill in the art would have been motivated to do so to utilize well known tools and features useful for implementing a building management method/system with generative AI-based automated maintenance service scheduling and modification which should prove to improve user experience, maximize profits, and optimize revenue.
18/633,086 – Claim 14. The method of claim 11, wherein the outcome data indicate one or more types of service activities required to handle the plurality of first service requests; and automatically determining the one or more responses to the second service request comprises assigning a technician to handle the second service request using the generative AI model based on capabilities of one or more technicians with respect to the one or more types of service activities.
Claim 14, has similar limitations as of Claim(s) 4, therefore it is REJECTED under the same rationale as Claim(s) 4.
18/633,086 – Claim 5. (Previously Presented) McKelvy et al. 2021/0264385 further teaches The method of claim 1, wherein the outcome data indicate one or more amounts of time required to perform one or more service events for the building equipment responsive the plurality of first service requests; and automatically determining the one or actions comprises scheduling a service activity to handle the second service request using the generative AI model (McKelvy et al. 2021/0264385 [0062 - Artificial Intelligence (AI) Techniques of Detecting Patterns] Artificial Intelligence (AI) Techniques of Detecting Patterns Indicating Device Failure [0064 - AI technique, which can be used for detecting primary or secondary patterns indicative of normal or abnormal device behavior. Sensor data of a first plurality of equipment 101 along with their prior repair history of the plurality of the equipment 101 can be used to train multiple machine learning (ML) networks 506 (e.g., neural networks or deep neural networks) to detect patterns] FIG. 5 illustrates a diagram 500 of an AI technique, which can be used for detecting primary or secondary patterns indicative of normal or abnormal device behavior. Sensor data of a first plurality of equipment 101 along with their prior repair history of the plurality of the equipment 101 can be used to train multiple machine learning (ML) networks 506 (e.g., neural networks or deep neural networks) to detect patterns of sensor data that can be correlated to normal or abnormal device operation. Each machine learning network 506 can be trained for detecting patterns of sensor data correlated with specific malfunctions in the first plurality of equipment 101. The past maintenance reports can be used as ground truth and used to train the ML networks 506. Multiple instances of the ML networks 506 can be trained for various brands, types of equipment 101 or different parts within the equipment 101. Furthermore, instances of the ML networks 506 can be trained to detect patterns of sensor data indicative of a malfunction, wherein each instance of ML network 506 is trained to detect patterns of sensor data correlated with a malfunction. After training, the ML networks 506 can detect patterns of sensor data correlated with one or more device malfunctions and can label the sensor data accordingly, thereby generating labeled patterns of sensor data 508. The sensor data for the purpose of training the ML networks 506 may be converted into various data structure formats, including, for example, vectors, arrays, multidimensional arrays, and/or tensors.) based on a predicted amount of time required to perform the service activity to handle the second service request (McKelvy et al. 2021/0264385 [0035] In some cases, human technicians can accumulate and transfer their knowledge of a particular brand of equipment and device and extrapolate from that knowledge to better perform repair or maintenance on other or similar devices. For example, the technician may be aware of a common failure in a particular brand of industrial refrigerator from his prior repair experiences. However, such knowledge can be limited and not shared among the industry at large. Furthermore, there is no infrastructure to collect and learn from prior repair or maintenance work of a device or industrial equipment, in a manner that the data can inform industry approaches to repair, maintenance and improving efficiency. Such data can provide technological solutions for predictive maintenance actions that can vastly improve the life cycle of industrial, commercial or consumer products by triggering timely and targeted maintenance or repair.).
McKelvy et al. 2021/0264385 may not expressly disclose the “time and scheduling” features, however, DeLuca et al. 2022/0198474 teaches (DeLuca et al. 2022/0198474 [0046-0049 - time][0004 - aligning appropriate service requests to a technician as a provider of services] Embodiments of the present invention disclose a method, computer program product, and system for aligning appropriate service requests to a technician as a provider of services. The method provides for one or more processors to receive information about a technician, wherein the information includes an area of expertise, a skill level, documented qualifications, a set of tools and materials available to the technician, a history of previously performed service instances by the technician, and a location of the technician. The one or more processors receive a plurality of service request candidates in which respective service requests include information associated with respective service requests. The one or more processors identify a first set of service requests appropriate for the technician by comparing the information about the technician and the current location of the technician to the plurality of service request candidates. The one or more processors determine a recommended order in which the first set of service requests are performed by the technician, based on a distance between service request locations, the urgency of performing the service request, and factors associated with the respective service request; and the one or more processors present a map representation of relative locations and the recommended order of service request response for the first set of service requests to the technician. [0011 - computer system for aligning appropriate service requests to a technician as a provider of services, the alignment based on matching the area(s) of expertise, experience, qualifications, location, and service performance history of a respective technician to a set of service requests in which the type of service and requirements of the service are generally known from an aggregate of historical performances] Embodiments of the present invention provide a method, computer program product, and computer system for aligning appropriate service requests to a technician as a provider of services, the alignment based on matching the area(s) of expertise, experience, qualifications, location, and service performance history of a respective technician to a set of service requests in which the type of service and requirements of the service are generally known from an aggregate of historical performances. In some embodiments, a machine learning model is applied to the service performance history of a respective technician, in which the model learns a skill level and experience of the technician in a particular area of providing service to assets. [0014 - the service request may identify an asset and a problem or condition of the asset requiring service] Embodiments of the present invention include receiving a plurality of service requests. In some embodiments, service requests include information regarding the service to be performed, a location at which the service is to be performed, a requested timeframe or level of urgency, and may include conditions in which the service is to be performed. For example, the service request may identify an asset and a problem or condition of the asset requiring service. In some embodiments, the required service may be known and well defined, such as a scheduled maintenance service request of an HVAC unit. In other embodiments, the service request may include a description of symptoms and data that is sufficient to determine the service requirements. In yet other embodiments, the service request may require examination and diagnosis to determine the specific service required. In some embodiments, the location of the service request may include special access conditions for security or safety-related reasons, such that technicians responding to service requests at the location may have to complete prior background checks, interviews, agreements, or may have to possess and use specialized equipment for personal safety or safety of the location.). Before the effective filing date of the claimed invention, it would have been obvious for one of ordinary skill in the art to have modified McKelvy et al. 2021/0264385 to include the features as taught by DeLuca et al. 2022/0198474. One of ordinary skill in the art would have been motivated to do so to utilize well known tools and features useful for implementing a building management method/system with generative AI-based automated maintenance service scheduling and modification which should prove to improve user experience, maximize profits, and optimize revenue.
18/633,086 – Claim 15. The method of claim 11, wherein the outcome data indicate one or more amounts of time required to perform one or more service events for the building equipment responsive the plurality of first service requests; and automatically determining the one or more responses to the second service request comprises scheduling a service activity to handle the second service request using the generative AI model based on a predicted amount of time required to perform the service activity to handle the second service request.
Claim 15, has similar limitations as of Claim(s) 5, therefore it is REJECTED under the same rationale as Claim(s) 5.
18/633,086 – Claim 6. (Previously Presented) McKelvy et al. 2021/0264385 further teaches The method of claim 1, wherein the outcome data indicate one or more service vehicles used to service the building equipment responsive to the plurality of first service requests; and automatically determining the one or more actions comprises scheduling a service vehicle to handle the second service request using the generative AI model (McKelvy et al. 2021/0264385 [0062 - Artificial Intelligence (AI) Techniques of Detecting Patterns] Artificial Intelligence (AI) Techniques of Detecting Patterns Indicating Device Failure [0064 - AI technique, which can be used for detecting primary or secondary patterns indicative of normal or abnormal device behavior. Sensor data of a first plurality of equipment 101 along with their prior repair history of the plurality of the equipment 101 can be used to train multiple machine learning (ML) networks 506 (e.g., neural networks or deep neural networks) to detect patterns] FIG. 5 illustrates a diagram 500 of an AI technique, which can be used for detecting primary or secondary patterns indicative of normal or abnormal device behavior. Sensor data of a first plurality of equipment 101 along with their prior repair history of the plurality of the equipment 101 can be used to train multiple machine learning (ML) networks 506 (e.g., neural networks or deep neural networks) to detect patterns of sensor data that can be correlated to normal or abnormal device operation. Each machine learning network 506 can be trained for detecting patterns of sensor data correlated with specific malfunctions in the first plurality of equipment 101. The past maintenance reports can be used as ground truth and used to train the ML networks 506. Multiple instances of the ML networks 506 can be trained for various brands, types of equipment 101 or different parts within the equipment 101. Furthermore, instances of the ML networks 506 can be trained to detect patterns of sensor data indicative of a malfunction, wherein each instance of ML network 506 is trained to detect patterns of sensor data correlated with a malfunction. After training, the ML networks 506 can detect patterns of sensor data correlated with one or more device malfunctions and can label the sensor data accordingly, thereby generating labeled patterns of sensor data 508. The sensor data for the purpose of training the ML networks 506 may be converted into various data structure formats, including, for example, vectors, arrays, multidimensional arrays, and/or tensors.).
McKelvy et al. 2021/0264385 may not expressly disclose the “scheduling a vehicle” features, however, DeLuca et al. 2022/0198474 teaches (DeLuca et al. 2022/0198474 [0033 - determine whether a special tool required for a particular service request is present in the vehicle for a technician designated to perform the service request] Tool inventory tracker 160 is a repository of tools that are allocated to each technician and tracks whether the tools are with the technician. In some embodiments, tool inventory tracker 160 tracks the location of one or more toolboxes allocated to a respective technician, by a transmitting device attached to the toolboxes. In some embodiments, tool inventory tracker 160 tracks the location of special tools that are used for certain service request tasks, such as special calibration tools or diagnostic tools. Tool inventory tracker 160 provides location information of tools to service alignment program 200 to determine whether a special tool required for a particular service request is present in the vehicle for a technician designated to perform the service request, based on a transmitting device attached to the special tool or a smart-tool feature of the special tool. Based on the location of a special tool used for a particular service request, service alignment program 200 may alter the order of performing service requests of the respective technician and may navigate the technician to obtain the special tool prior to performing the service request. [0037 - service truck] For example, service alignment program 200 receives information about technician A from technician information 140. The information acknowledges that technician A has expertise in HVAC maintenance, repair, and installations. The information indicates that the technician has 10 years of experience, and has an expert or master skill level. The information further includes that the technician works out of the south side of city XYZ and has worked previously at 3 government and one military facility. Technician A is certified on HVAC calibration tools and has such a tool in his possession (service truck), based on additional information from tool inventory tracker 160. [0004 - aligning appropriate service requests to a technician as a provider of services] Embodiments of the present invention disclose a method, computer program product, and system for aligning appropriate service requests to a technician as a provider of services. The method provides for one or more processors to receive information about a technician, wherein the information includes an area of expertise, a skill level, documented qualifications, a set of tools and materials available to the technician, a history of previously performed service instances by the technician, and a location of the technician. The one or more processors receive a plurality of service request candidates in which respective service requests include information associated with respective service requests. The one or more processors identify a first set of service requests appropriate for the technician by comparing the information about the technician and the current location of the technician to the plurality of service request candidates. The one or more processors determine a recommended order in which the first set of service requests are performed by the technician, based on a distance between service request locations, the urgency of performing the service request, and factors associated with the respective service request; and the one or more processors present a map representation of relative locations and the recommended order of service request response for the first set of service requests to the technician. [0011 - computer system for aligning appropriate service requests to a technician as a provider of services, the alignment based on matching the area(s) of expertise, experience, qualifications, location, and service performance history of a respective technician to a set of service requests in which the type of service and requirements of the service are generally known from an aggregate of historical performances] Embodiments of the present invention provide a method, computer program product, and computer system for aligning appropriate service requests to a technician as a provider of services, the alignment based on matching the area(s) of expertise, experience, qualifications, location, and service performance history of a respective technician to a set of service requests in which the type of service and requirements of the service are generally known from an aggregate of historical performances. In some embodiments, a machine learning model is applied to the service performance history of a respective technician, in which the model learns a skill level and experience of the technician in a particular area of providing service to assets. [0014 - the service request may identify an asset and a problem or condition of the asset requiring service] Embodiments of the present invention include receiving a plurality of service requests. In some embodiments, service requests include information regarding the service to be performed, a location at which the service is to be performed, a requested timeframe or level of urgency, and may include conditions in which the service is to be performed. For example, the service request may identify an asset and a problem or condition of the asset requiring service. In some embodiments, the required service may be known and well defined, such as a scheduled maintenance service request of an HVAC unit. In other embodiments, the service request may include a description of symptoms and data that is sufficient to determine the service requirements. In yet other embodiments, the service request may require examination and diagnosis to determine the specific service required. In some embodiments, the location of the service request may include special access conditions for security or safety-related reasons, such that technicians responding to service requests at the location may have to complete prior background checks, interviews, agreements, or may have to possess and use specialized equipment for personal safety or safety of the location.). Before the effective filing date of the claimed invention, it would have been obvious for one of ordinary skill in the art to have modified McKelvy et al. 2021/0264385 to include the features as taught by DeLuca et al. 2022/0198474. One of ordinary skill in the art would have been motivated to do so to utilize well known tools and features useful for implementing a building management method/system with generative AI-based automated maintenance service scheduling and modification which should prove to improve user experience, maximize profits, and optimize revenue.
18/633,086 – Claim 16. The method of claim 11, wherein the outcome data indicate one or more service vehicles used to service the building equipment responsive to the plurality of first service requests; and automatically determining the one or more responses to the second service request comprises scheduling a service vehicle to handle the second service request using the generative AI model.
Claim 16, has similar limitations as of Claim(s) 6, therefore it is REJECTED under the same rationale as Claim(s) 6.
18/633,086 – Claim 7. (Previously Presented) McKelvy et al. 2021/0264385 further teaches The method of claim 1, wherein the outcome data indicate one or more replacement parts of the building equipment used to service the building equipment responsive to the plurality of first service requests; and automatically determining the one or more actions comprises provisioning one or more replacement parts to handle the second service request using the generative AI model (McKelvy et al. 2021/0264385 [0022 - part needed repair or replacement] In some embodiments, the set of conditions comprise one or more of a brand of the equipment, or part identification of a previously repaired or replaced part, and a duration of time after which the part needed repair or replacement. [0057 - pattern of needing a condenser part replacement after 10,000 hours of operations] In some embodiments, the backend server 112 can detect patterns indicative of normal or abnormal equipment operation, not only from sensor data from an individual equipment 101, but from a collection of equipment 101, that may be present at the same site or at different locations. In other words, a plurality of same or similar equipment 101 can be included in the pattern detection of the backend server 112, for example, sensor data from equipment 101 having same brand and/or type can be included in pattern detection. In other examples, sensor data, as well as notification data, stored in the database 116 over a period of time can be used for pattern detection. Refrigerator XYZ brand of type UVW can show a pattern of needing a condenser part replacement after 10,000 hours of operations across various operators. Consequently, operators having the same or similar refrigerator can be sent a repair notification at or before their equipment reaches 10,000 hours of operation.).
18/633,086 – Claim 17. The method of claim 11, wherein the outcome data indicate one or more replacement parts of the building equipment used to service the building equipment responsive to the plurality of first service requests; and automatically determining the one or more responses to the second service request comprises provisioning one or more replacement parts to handle the second service request using the generative AI model.
Claim 17, has similar limitations as of Claim(s) 7, therefore it is REJECTED under the same rationale as Claim(s) 7.
18/633,086 – Claim 8. (Previously Presented) McKelvy et al. 2021/0264385 further teaches The method of claim 1, wherein the outcome data indicate one or more tools used to service the building equipment responsive to the plurality of first service requests; and automatically determining the one or more actions comprises provisioning one or more tools to handle the second service request using the generative AI model (McKelvy et al. 2021/0264385 [0034 - onboard diagnostic tools to assist human technicians] Industrial and commercial equipment are important parts of the economy. Often this equipment relies on periodic inspection by human technicians to detect and perform maintenance and/or repairs. Sometimes, such equipment can include or are retrofitted with onboard diagnostic tools to assist human technicians in diagnostics, maintenance or repair. In many cases, however, important maintenance or repair may be delayed, postponed or not performed until an equipment failure disrupts the normal operation of the equipment. Additionally, equipment maintenance is generally performed for devices in isolation and technological insights which can be gained from individual repairs and extrapolated across same or similar equipment in an industry are routinely lost.).
DeLuca et al. 2022/0198474 also teaches the claimed “tool” features as follows (DeLuca et al. 2022/0198474 [0019 - receives information about technicians from technician information 140, tool availability and technician training on tools from tool inventory tracker ] Service alignment program 200 receives information about technicians from technician information 140, tool availability and technician training on tools from tool inventory tracker 160, and information associated with requests for service from service request information 130. Service alignment program 200 determines the area of expertise for a given request for service as well as the level of skill and qualifications required to perform the service and other factors associated with the particular request for service, such as location, site conditions, special tool requirements, and urgency. Service alignment program 200 optimizes the alignment of candidate service requests to the respective capabilities of the service technicians. Service alignment program 200 performs the optimization by comparing the service request information and requirements to the technician information and performs a best-match assignment of a set of service requests to respective technicians that are appropriate for the capabilities and performance history of the technician. [0033 - Tool inventory tracker 160 is a repository of tools that are allocated to each technician and tracks whether the tools are with the technician] Tool inventory tracker 160 is a repository of tools that are allocated to each technician and tracks whether the tools are with the technician. In some embodiments, tool inventory tracker 160 tracks the location of one or more toolboxes allocated to a respective technician, by a transmitting device attached to the toolboxes. In some embodiments, tool inventory tracker 160 tracks the location of special tools that are used for certain service request tasks, such as special calibration tools or diagnostic tools. Tool inventory tracker 160 provides location information of tools to service alignment program 200 to determine whether a special tool required for a particular service request is present in the vehicle for a technician designated to perform the service request, based on a transmitting device attached to the special tool or a smart-tool feature of the special tool. Based on the location of a special tool used for a particular service request, service alignment program 200 may alter the order of performing service requests of the respective technician and may navigate the technician to obtain the special tool prior to performing the service request. [0004 - aligning appropriate service requests to a technician as a provider of services] Embodiments of the present invention disclose a method, computer program product, and system for aligning appropriate service requests to a technician as a provider of services. The method provides for one or more processors to receive information about a technician, wherein the information includes an area of expertise, a skill level, documented qualifications, a set of tools and materials available to the technician, a history of previously performed service instances by the technician, and a location of the technician. The one or more processors receive a plurality of service request candidates in which respective service requests include information associated with respective service requests. The one or more processors identify a first set of service requests appropriate for the technician by comparing the information about the technician and the current location of the technician to the plurality of service request candidates. The one or more processors determine a recommended order in which the first set of service requests are performed by the technician, based on a distance between service request locations, the urgency of performing the service request, and factors associated with the respective service request; and the one or more processors present a map representation of relative locations and the recommended order of service request response for the first set of service requests to the technician. [0011 - computer system for aligning appropriate service requests to a technician as a provider of services, the alignment based on matching the area(s) of expertise, experience, qualifications, location, and service performance history of a respective technician to a set of service requests in which the type of service and requirements of the service are generally known from an aggregate of historical performances] Embodiments of the present invention provide a method, computer program product, and computer system for aligning appropriate service requests to a technician as a provider of services, the alignment based on matching the area(s) of expertise, experience, qualifications, location, and service performance history of a respective technician to a set of service requests in which the type of service and requirements of the service are generally known from an aggregate of historical performances. In some embodiments, a machine learning model is applied to the service performance history of a respective technician, in which the model learns a skill level and experience of the technician in a particular area of providing service to assets. [0014 - the service request may identify an asset and a problem or condition of the asset requiring service] Embodiments of the present invention include receiving a plurality of service requests. In some embodiments, service requests include information regarding the service to be performed, a location at which the service is to be performed, a requested timeframe or level of urgency, and may include conditions in which the service is to be performed. For example, the service request may identify an asset and a problem or condition of the asset requiring service. In some embodiments, the required service may be known and well defined, such as a scheduled maintenance service request of an HVAC unit. In other embodiments, the service request may include a description of symptoms and data that is sufficient to determine the service requirements. In yet other embodiments, the service request may require examination and diagnosis to determine the specific service required. In some embodiments, the location of the service request may include special access conditions for security or safety-related reasons, such that technicians responding to service requests at the location may have to complete prior background checks, interviews, agreements, or may have to possess and use specialized equipment for personal safety or safety of the location.). Before the effective filing date of the claimed invention, it would have been obvious for one of ordinary skill in the art to have modified McKelvy et al. 2021/0264385 to include the features as taught by DeLuca et al. 2022/0198474. One of ordinary skill in the art would have been motivated to do so to utilize well known tools and features useful for implementing a building management method/system with generative AI-based automated maintenance service scheduling and modification which should prove to improve user experience, maximize profits, and optimize revenue.
18/633,086 – Claim 18. The method of claim 11, wherein the outcome data indicate one or more tools used to service the building equipment responsive to the plurality of first service requests; and automatically determining the one or more responses to the second service request comprises provisioning one or more tools to handle the second service request using the generative AI model.
Claim 18, has similar limitations as of Claim(s) 8, therefore it is REJECTED under the same rationale as Claim(s) 8.
18/633,086 – Claim 9. (Previously Presented) McKelvy et al. 2021/0264385 further teaches The method of claim 1, wherein the outcome data indicate whether a plurality of service activities performed in response to the plurality of first service requests were successful in resolving one or more problems or faults indicated by the plurality of first service requests (McKelvy et al. 2021/0264385 [0035] In some cases, human technicians can accumulate and transfer their knowledge of a particular brand of equipment and device and extrapolate from that knowledge to better perform repair or maintenance on other or similar devices. For example, the technician may be aware of a common failure in a particular brand of industrial refrigerator from his prior repair experiences. However, such knowledge can be limited and not shared among the industry at large. Furthermore, there is no infrastructure to collect and learn from prior repair or maintenance work of a device or industrial equipment, in a manner that the data can inform industry approaches to repair, maintenance and improving efficiency. Such data can provide technological solutions for predictive maintenance actions that can vastly improve the life cycle of industrial, commercial or consumer products by triggering timely and targeted maintenance or repair. [0056] Additionally, the repair notification can include a course of action determined based on the sensor readings, processed clean sensor data and detected patterns in sensor data. For example, the backend server 112 can detect a pattern of increasing temperatures in a sensor 106 located near the door of a walk-in cooler that persists throughout a 24-hour period. The door is expected to be shut for an extended period of time during night hours and the temperature readings near the door are expected to drop during those hours. Other temperature sensors 106 inside the walk-in cooler do not indicate the same pattern of rising temperature and at night drop and stay constant. In this scenario, the timing of sensor readings, the location of sensor readings, and the history of the sensor reading, can indicate a malfunction or broken seal in the door of the walk-in cooler. Consequently, the repair notification can include a course of action determined based on timing, location, involved parts, and corresponding solutions. For example, a notification generated on the UI client 114 can include text phrase, “high temperatures near cooler entrance during night. Inspect proper door operation and seal.”); and automatically determining the one or more actions comprises determining a service activity to perform in response to the second service request using the generative AI model (McKelvy et al. 2021/0264385 [0062 - Artificial Intelligence (AI) Techniques of Detecting Patterns] Artificial Intelligence (AI) Techniques of Detecting Patterns Indicating Device Failure [0064 - AI technique, which can be used for detecting primary or secondary patterns indicative of normal or abnormal device behavior. Sensor data of a first plurality of equipment 101 along with their prior repair history of the plurality of the equipment 101 can be used to train multiple machine learning (ML) networks 506 (e.g., neural networks or deep neural networks) to detect patterns] FIG. 5 illustrates a diagram 500 of an AI technique, which can be used for detecting primary or secondary patterns indicative of normal or abnormal device behavior. Sensor data of a first plurality of equipment 101 along with their prior repair history of the plurality of the equipment 101 can be used to train multiple machine learning (ML) networks 506 (e.g., neural networks or deep neural networks) to detect patterns of sensor data that can be correlated to normal or abnormal device operation. Each machine learning network 506 can be trained for detecting patterns of sensor data correlated with specific malfunctions in the first plurality of equipment 101. The past maintenance reports can be used as ground truth and used to train the ML networks 506. Multiple instances of the ML networks 506 can be trained for various brands, types of equipment 101 or different parts within the equipment 101. Furthermore, instances of the ML networks 506 can be trained to detect patterns of sensor data indicative of a malfunction, wherein each instance of ML network 506 is trained to detect patterns of sensor data correlated with a malfunction. After training, the ML networks 506 can detect patterns of sensor data correlated with one or more device malfunctions and can label the sensor data accordingly, thereby generating labeled patterns of sensor data 508. The sensor data for the purpose of training the ML networks 506 may be converted into various data structure formats, including, for example, vectors, arrays, multidimensional arrays, and/or tensors.).
18/633,086 – Claim 19. The method of claim 11, wherein the outcome data indicate whether a plurality of service activities performed in response to the plurality of first service requests were successful in resolving one or more problems or faults indicated by the plurality of first service requests; and automatically determining the one or more responses to the second service request comprises determining a service activity to perform in response to the second service request using the generative AI model.
Claim 19, has similar limitations as of Claim(s) 9, therefore it is REJECTED under the same rationale as Claim(s) 9.
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over: McKelvy et al. 2021/0264385; in view of Hita et al. 2023/0350398; in view of DeLuca et al. 2022/0198474; in further view of Lin et al. 2022/0101148; in further view of Ryan et al. 2019/0379589.
18/633,086 – Claim 10. (Previously Presented) McKelvy et al. 2021/0264385 further teaches The method of claim 1, wherein automatically determining the one or more actions comprises: predicting a root cause of a problem indicated by the second service request; and determining a service activity predicted to resolve the root cause of the problem indicated by the second service request (McKelvy et al. 2021/0264385 [0048] In some embodiments, the operation profile of the equipment 101 can include one or more threshold or ranges in which the equipment 101 is deemed to function normally, and sensor readings outside those threshold and ranges can indicate an equipment failure or a need for repair. For example, the sensors 106 can be deployed in walk-in coolers where a temperature range of 35-41 degrees Fahrenheit would indicate normal operations and temperatures outside that range would indicate potential problem with the cooler. The operation profile of the equipment 101 received at the backend server 112 can include data indicating this range.).
McKelvy et al. 2021/0264385 may not expressly disclose the “root cause” features, however, Ryan et al. 2019/0379589 teaches (Ryan et al. 2019/0379589 [0003 - performance monitoring, problem detection, and root cause analysis are performed] Conventionally, performance monitoring, problem detection, and root cause analysis are performed in a manual fashion after a failure has occurred. This approach is taken across various application areas, such as manufacturing, vehicle maintenance, airplane maintenance, healthcare, building maintenance, road and other infrastructure maintenance. This manual approach is very expensive, time-consuming and requires a human expert with the knowledge of the given system to debug the problem after the failure. At the same time, the number of monitors is increasing, as the Internet of Things (IoT) is now connecting things to the network, which would not conventionally be connected or monitored. The manual approach to performance monitoring with the failure and debug cycle is not feasible. At the same time, it would be desirable to decrease the cost even in current manual approaches by introducing machine learning methodologies for pattern detection to enable new approaches to detecting and forecasting faults before they occur and to find patterns in time-series that can be used to pin point the causes of failures. [0065 - Patterns can then be further correlated with the network at the time for root cause analysis] FIG. 4 is a graph 40 of performance monitoring (PM) and associated alarms over time. The data of graph 40 may be used for predicting alarms before they happen. Pattern detection may be trained with traffic measurements and labeled as patterns (e.g., windows A.sub.1, labeled 42, followed by windows A.sub.2, labeled 44). These changes 46 (e.g., from window A.sub.1 to window A.sub.2) in PM activity may be analyzed in pattern detection analysis to predict a start of congestion in the future, corresponding to alarm A.sub.3, which may be a critical alarm 48. One set of data (e.g., queue sizes) can be used for measurements, while another (e.g., end-to-end performance) can be used to generate labels. Patterns can then be further correlated with the network at the time for root cause analysis.). Before the effective filing date of the claimed invention, it would have been obvious for one of ordinary skill in the art to have modified McKelvy et al. 2021/0264385 to include the features as taught by Ryan et al. 2019/0379589. One of ordinary skill in the art would have been motivated to do so to utilize well known tools and features useful for implementing a building management method/system with generative AI-based automated maintenance service scheduling and modification which should prove to improve user experience, maximize profits, and optimize revenue.
Examiner’s Response to Arguments
Per Applicants’ amendments/arguments, the rejections are withdrawn.
Applicant's arguments have been considered but are moot in view of the new ground(s) of rejection.
Applicants’ amendments have necessitated the new grounds of rejection noted above.
Examiner’s Response: Claim Rejections – 35 USC § 103
Per Applicants’ amendments/arguments, the rejections are withdrawn. See notes above for additional reasoning and rationale for dropping prior-art rejection including Applicant’s amendments and arguments and unique combination of features and elements not taught by the prior-art without hindsight reasoning.
Applicant's arguments have been considered but are moot in view of the new ground(s) of rejection.
Applicants’ amendments have necessitated the new grounds of rejection noted above.
Regarding Claim X, on page(s) 8-9 of Applicant’s Remarks / After Final Amendments (dated 07/15/2011), Applicant(s) argues that the cited reference(s) (Ellis and Vandermolen) fails to teach, describe, or suggest the amended features. Specifically, Applicant(s) argues that cited reference(s) do not teach, describe, or suggest the following: . With respect, Applicant’s arguments are deemed unpersuasive and the amended feature(s) remain rejected as follows.
With respect, Applicant’s arguments are deemed unpersuasive and the amended feature(s) remain rejected as follows.
Examiner’s Response: Claim Rejections – 35 USC §101
Per Applicants’ amendments/arguments, the rejections are withdrawn. See notes above for additional reasoning and rationale for dropping 35 USC 101 rejection including Applicant’s amendments, arguments, lack of abstract idea, and practical integration.
Applicant's arguments have been considered but are moot in view of the new ground(s) of rejection.
Applicants’ amendments have necessitated the new grounds of rejection noted above.
Regarding Claims 1-20, on page(s) 9-15 of Applicant’s Remarks (dated 03/26/2026), Applicants traverse the 35 USC §101 rejections arguing the following: the claims are not abstract, the claims are integrated into a practical application, and the claims are significantly more than any alleged abstract idea by reciting an improvement to building equipment servicing technology. With respect, the Office disagrees with Applicant’s arguments and maintains the rejection as noted above and herein.
Subject Matter Eligibility – 35 U.S.C. § 101
Step 2A, Prong One Analysis
The claim recites configuring a generative AI model using a plurality of service requests for servicing building equipment, initiating a diagnostic conversation, receiving additional information as unstructured data or natural language data, determining actions to perform, generating an output response, etc… When given the broadest reasonable interpretation, these limitations describe the collection and analysis of information and the application of mathematical relationships or algorithms to adjust model parameters. Such concepts fall within the enumerated groupings of abstract ideas, namely mental processes (concepts performed in the human mind) and/or mathematical concepts (mathematical relationships, formulas, or calculations) and/or certain methods of organizing human activities (hedging, insurance, mitigating risk, commercial interactions).
The recitation of a “generative AI model” and “service requests” and “processors” “user interface” does not alter this characterization, as they are claimed at a high level of generality and do not reflect a specific improvement to the functioning of a computer or other technology. Therefore, the claim recites a judicial exception.
Step 2A, Prong Two Analysis
The additional elements, including generic computer components (e.g., processor and/or user interface) for receiving, processing, and storing data, are recited at a level of generality that amounts to no more than applying the abstract idea on a generic computer. The specification describes these components performing their conventional functions without any specialized hardware, unconventional arrangement, or improvement to computer functionality.
As such, the claim does not integrate the judicial exception into a practical application because it does not effect a transformation, improve the functioning of a computer, or apply the exception in a meaningful way beyond linking it to a generic computing environment. Accordingly, the claim is directed to an abstract idea and fails to satisfy Step 2A.
Step 2B Analysis
Under Step 2B, the claim is examined to determine whether any additional elements, individually or in combination, amount to significantly more than the judicial exception. The additional elements in the claim—such as generic processors, memory, and network interfaces—are recited at a high level of generality and perform well-understood, routine, and conventional functions (e.g., receiving data, executing algorithms, and storing results) as described in the specification.
Implementing the abstract idea of configuring a generative AI model using service requests on such generic computer components does not add a meaningful limitation beyond the judicial exception itself. There is no indication in the claim or specification of any unconventional hardware, specialized AI training architecture, or other non-routine technical feature that would transform the nature of the claim into a patent-eligible application. The ordered combination of elements merely applies the abstract idea using generic computing technology in its ordinary capacity.
Accordingly, the claim does not include an inventive concept sufficient to amount to significantly more than the judicial exception. The claim is therefore ineligible under 35 U.S.C. § 101.
Desjardins. The applicant’s argument that the claimed improvements represent “concrete enhancements to building-management systems and building equipment servicing” is not sufficient to satisfy Step 2A, Prong Two of the Alice/Mayo framework. Under the USPTO’s updated MPEP guidance following Ex parte Desjardins, claims must integrate a judicial exception into a practical application by showing a technological improvement to the functioning of a computer or other technology or technical field.
The claimed improvements are generic operational benefits that could be achieved in any building management or maintenance context without requiring the specific claimed elements. They do not demonstrate a non-abstract, concrete improvement to the functioning of the system, as required by the USPTO’s Desjardins guidance. The claimed elements are generic building-management system components or maintenance procedures performed on generic equipment, and the applicant’s description of ‘concrete enhancements’ is too broad and generic to satisfy Step 2A, Prong Two.
1. No technological improvement to the claimed system. The claimed enhancements do not demonstrate a non-abstract, concrete improvement to the way the system operates. Instead, they are generic operational benefits that could be achieved in any building management or maintenance context without requiring the specific claimed elements. Such benefits are not the kind of “technical improvement” that Desjardins require; they are merely functional advantages that do not alter the underlying technical process in a way that would make it patent-eligible.
2. Generic computer components and abstract idea. The claimed elements are generic building-management system components or maintenance procedures performed on generic equipment. They do not add a specific, non-abstract technical feature that transforms the system’s operation. Under Desjardins, improvements must be tied to measurable, concrete changes in system performance—such as reduced storage requirements, lower system complexity, or mitigation of a known technical problem—that are not obvious in the prior art. The applicant’s description lacks such specific, measurable technical effects.
4. Conclusion. Because the claimed improvements do not show a technological improvement to the functioning of the building-management system or equipment servicing, they fail to integrate the judicial exception into a practical application. The claim remains directed to an abstract idea and is not eligible under Step 2A, Prong Two.
Any comments considered necessary by applicant must be submitted no later than the payment of the issue fee and, to avoid processing delays, should preferably accompany the issue fee. Such submissions should be clearly labeled “Comments on Statement of Reasons for Allowance.”
Conclusion
PERTINENT PRIOR ART – Patent Literature
The prior-art made of record and considered pertinent to applicant's disclosure.
Kale 2022/0026879 [0076 - module 175 of unsupervised machine learning is used to train or refine an artificial neural network 125 to facilitate anomaly detection 173. The unsupervised machine learning module 175 is configured to adjust the ANN (e.g., SNN 208) based on classification, clustering, or recognized pattern]
Siebel et al. 2018/0191867 [0493 - recognize patterns and trends of fraud or malfunction to assist with long-term fraud and malfunction prevention; directly assign prioritized leads to field investigation teams to confirm and address cases of loss; use validated field investigation results to improve machine learning models]
Shinde et al. 2021/0262689 [0036 - automatically perform one or more actions to prevent and/or fix the predicted faults … a work order ticket may be automatically generated to fix a piece of equipment causing a predicted fault…][0201 - fault prediction and diagnosis system … may perform one or more actions … compare the cost savings to a threshold … and may take one or more actions based on the comparison (e.g., automatically generate a ticket to fix the predicted fault if doing so would save money or preemptively silence a number of alarms associated with the predicted fault if attempting to fix the predicted fault would cost more than allowing the fault to occur, etc.). … a work order ticket may include instructions for an individual to repair and/or otherwise interact with a piece of equipment to achieve a desired outcome … instructs maintenance personnel to repair a defective blower fan in a HVAC system to solve a low zone temperature fault.]
PERTINENT PRIOR ART – Non-Patent Literature (NPL)
The NPL prior-art made of record and considered pertinent to applicant's disclosure.
Bandi, Ajay, Pydi Venkata Satya Ramesh Adapa, and Yudu Eswar Vinay Pratap Kumar Kuchi. 2023. "The Power of Generative AI: A Review of Requirements, Models, Input–Output Formats, Evaluation Metrics, and Challenges" Future Internet 15, no. 8: 260. https://doi.org/10.3390/fi15080260
THIS ACTION IS MADE FINAL
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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 extension fee 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 date of this final action.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MATTHEW T. SITTNER whose telephone number is (571) 270-7137 and email: matthew.sittner@uspto.gov. The examiner can normally be reached on Monday-Friday, 8:00am - 5:00pm (Mountain Time Zone). Please schedule interview requests via email: matthew.sittner@uspto.gov
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Sarah M. Monfeldt can be reached on (571) 270-1833.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/MATTHEW T SITTNER/
Primary Examiner, Art Unit 3629b
Prosecution Insights