DETAILED ACTION
A. This action is in response to the following communications: Transmittal of New Application filed 07/31/2024.
B. Claims 1-21 remains pending.
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 1,5-6 and 10 are rejected under 35 U.S.C. 101 because the claimed invention is directed to certain methods of organizing human activity without significantly more. The claim(s) 1 and 6 recite(s) “receiving user input, adding additional user input to direct a engine”, grouping of abstract ideas. The mere nominal recitation of a generic engine and generic device does not take the claim out of the “certain methods of organizing human activity” grouping. Thus, the claim recites an abstract idea.
This judicial exception is not integrated into a practical application because the claim as a whole merely describes how to generally “apply” the concept of updating user information in a computer environment. The claimed “method and device” are recited at a high level of generality and are merely invoked as tools perform an existing information update process. Even considered in combination, simply implementing the abstract idea on a generic computer with storage devices recited at a high level of generality is not a practical application of the abstract idea.The limitation adding a safety prompt on a generic user interface executed by a generic computer, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. That is, other than reciting “by a processor,” nothing in the claim element precludes the step from practically being performed in the mind. For example, but for the “by a processor” language, “in response to receiving” in the context of this claim encompasses the user manually organizing data.
The claim does not include additional elements that are sufficient to amount to the significantly more than the judicial exception because as noted previously, the method and the devices individually and in combination merely describe how to generally “apply” the concept of updating user information in a computer environment. The same applies here. (MPEP 2106.05(d). Thus, even when viewed as a whole, nothing in the claims adds significantly more (i.e. an inventive concept) to the abstract idea.
The claim is ineligible.
Claims 5 and 10 do not include elements that amount to significantly more than the abstract idea and are also rejected under the same rational.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Singh, Prabhdeep (US Pub. 2023/0360388 A1), herein referred to as “Singh” in view of Catalano, Jacob et al. (US Pub. 2024/0291779 A1), herein referred to as “Catalano”.
As for claims 1 and 6, Singh teaches. A method of interacting with a generative response engine in a safe context, comprising (par. 2-7 overview of system for training a generative AI/ML model to recognize applications, screens, and UI elements using CV and to recognize user interactions with the applications, screens, and UI elements):
receiving, from an operator application, a user prompt to perform a task (par. 143-146 generative AI model is trained to recognize user interactions and a task the user wishes to accomplish);
adding a safety prompt to the user prompt to direct a generative response engine to safe actions (par. 51-55 conductor application is added to user input through extra layer of processing with UiPath Orchestrator™ that provides orchestration capabilities to deploy, monitor, optimize, scale, and ensure security of RPA robot deployments. ).; and
providing, to the operator application, at least one action to perform based on a response obtained from the generative response engine with the user prompt and the safety prompt ( par. 51-55 and 145 deployed robots/agents to make input using validated model (safety discriminator) which implies permission including user input from interacting with mouse on user interface).
Singh does not specifically teach in detail what happens during policy enforcement; however in the same field of endeavor Catalano teaches adding a safety prompt to the user prompt upon detecting of policy violation (par. 144 an image included in user prompt message 826 is scanned for content that violates a safety policy of the interactive platform that hosts the chatbot system 300. If the chatbot system 300 detects inappropriate content, the chatbot system 300 does not generate the chatbot response message 840 using a generative AI model response 838 but instead generates the chatbot response message 840 using a canned response).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Catalano into Singh because Catalano suggests that the use of a chatbot much like Singh does in par. 59; the obvious additions to functionalities mentioned in Catalano would be an obvious inclusion since Catalano suggests that interactive platforms (e.g. Singh) (e.g., social platforms, social media platforms, interaction systems, AR platforms, applications, messaging platforms, AR applications, operating systems, gaming systems or applications, systems with which a user interacts, and the like)) may provide a way for users to interact with other users. For some users, interaction with an interactive platform may be enhanced by having a customizable chatbot to interact with. The chatbot can serve multiple uses, including providing a way for a user to generate content for posting to the interactive platform, edit existing content, and receive suggestions in a form of interactive platform postings.
As for claims 2 and 7, Singh teaches. The method of claim 1, wherein the generative response engine is trained with a training dataset only safe actions, wherein unsafe actions are types of network-based interactions that pose a higher risk of creating unintended consequences compared as to information gathering (par. 48, 51-55 RPA uses trained AI/ML models and generative AI models and governance on safety is implemented through rules, policies and the like).
As for claims 3 and 8, Singh teaches. The method of claim 1, further comprising:
when the user prompt includes a screenshot illustrating a state of a client device, sending an inner monologue describing a task of the generative response engine, the screenshot, and the at least one action to a safety discriminator; and
in response to receiving an unsafe indicator from the safety discriminator, generating a second user prompt with a safety prompt to prevent the task in the inner monologue (par. 55, 92,133-143; fig. 7 and 8 screenshots used in training the model and used in user interaction to predict user intent when performing actions on user interface; the models are trained through consecutive screenshots that are input into generative AI model and continuously identify changes in same screenshots through portions of the screens inputted; inner monologue represents supervisor such as attended robot the system provides for various automations as noted in par. 41 Automations (e.g., run on a user computing system, a server, etc.) may be run by software robots, such as RPA robots, in some embodiments. For instance, attended robots, unattended robots, and/or test robots may be used. Attended robots work with users to assist them with tasks (e.g., via UiPath Assistant™). Unattended robots work independently of users and may run in the background, potentially without user knowledge. Test robots are unattended robots that run test cases against applications or RPA workflows. Test robots may be run on multiple computing systems in parallel in some embodiments.).
Singh does not specifically teach in detail what happens during policy enforcement; however in the same field of endeavor Catalano teaches adding a safety prompt to the user prompt upon detecting of policy violation (par. 144 an image included in user prompt message 826 is scanned for content that violates a safety policy of the interactive platform that hosts the chatbot system 300. If the chatbot system 300 detects inappropriate content, the chatbot system 300 does not generate the chatbot response message 840 using a generative AI model response 838 but instead generates the chatbot response message 840 using a canned response).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Catalano into Singh because Catalano suggests that the use of a chatbot much like Singh does in par. 59; the obvious additions to functionalities mentioned in Catalano would be an obvious inclusion since Catalano suggests that interactive platforms (e.g. Singh) (e.g., social platforms, social media platforms, interaction systems, AR platforms, applications, messaging platforms, AR applications, operating systems, gaming systems or applications, systems with which a user interacts, and the like)) may provide a way for users to interact with other users. For some users, interaction with an interactive platform may be enhanced by having a customizable chatbot to interact with. The chatbot can serve multiple uses, including providing a way for a user to generate content for posting to the interactive platform, edit existing content, and receive suggestions in a form of interactive platform postings.
As for claims 4 and 9, Singh teaches. The method of claim 1, further comprising:
sending an inner monologue describing a task of the generative response engine to a safety discriminator; and in response to receiving an unsafe indicator from the safety discriminator, generating a second user prompt with a safety prompt to prevent the task in the inner monologue (par. 51 RPA robots attended or unattended can have governance policies (safety discriminator) trained to implement access control and governance restrictions at the robot and/or robot design application level. This may provide an added level of security and compliance into to the automation process development pipeline in some embodiments by preventing developers from taking dependencies on unapproved software libraries that may either introduce security risks or work in a way that violates policies, regulations, privacy laws, and/or privacy policies.; par. 57-59 user interaction with various user interface that integrate RPA robots, such as chatbot, wherein the RPA robots can display on user interface approved automation governed by policies and areas that the user needs give attention if a problem arises).
Singh does not specifically teach in detail what happens during policy enforcement; however in the same field of endeavor Catalano teaches adding a safety prompt to the user prompt upon detecting of policy violation (par. 144 an image included in user prompt message 826 is scanned for content that violates a safety policy of the interactive platform that hosts the chatbot system 300. If the chatbot system 300 detects inappropriate content, the chatbot system 300 does not generate the chatbot response message 840 using a generative AI model response 838 but instead generates the chatbot response message 840 using a canned response).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Catalano into Singh because Catalano suggests that the use of a chatbot much like Singh does in par. 59; the obvious additions to functionalities mentioned in Catalano would be an obvious inclusion since Catalano suggests that interactive platforms (e.g. Singh) (e.g., social platforms, social media platforms, interaction systems, AR platforms, applications, messaging platforms, AR applications, operating systems, gaming systems or applications, systems with which a user interacts, and the like)) may provide a way for users to interact with other users. For some users, interaction with an interactive platform may be enhanced by having a customizable chatbot to interact with. The chatbot can serve multiple uses, including providing a way for a user to generate content for posting to the interactive platform, edit existing content, and receive suggestions in a form of interactive platform postings.
As for claims 5 and 10, Singh teaches. The method of claim 1, further comprising:
when a network address included in the user prompt is associated with a denied action, generating an unavailable action prompt indicating this action is unavailable; and providing, to the operator application, a response from the generative response engine based on the unavailable action prompt (par. 51 system detects policies that are violated, if a network address (arbitrary prompt) is included in a list of violation the UiPath system can detect and take action through automation with RPA robots).
Singh does not specifically teach in detail what happens during policy enforcement; however in the same field of endeavor Catalano teaches adding a safety prompt to the user prompt upon detecting of policy violation (par. 144 an image included in user prompt message 826 is scanned for content that violates a safety policy of the interactive platform that hosts the chatbot system 300. If the chatbot system 300 detects inappropriate content, the chatbot system 300 does not generate the chatbot response message 840 using a generative AI model response 838 but instead generates the chatbot response message 840 using a canned response).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Catalano into Singh because Catalano suggests that the use of a chatbot much like Singh does in par. 59; the obvious additions to functionalities mentioned in Catalano would be an obvious inclusion since Catalano suggests that interactive platforms (e.g. Singh) (e.g., social platforms, social media platforms, interaction systems, AR platforms, applications, messaging platforms, AR applications, operating systems, gaming systems or applications, systems with which a user interacts, and the like)) may provide a way for users to interact with other users. For some users, interaction with an interactive platform may be enhanced by having a customizable chatbot to interact with. The chatbot can serve multiple uses, including providing a way for a user to generate content for posting to the interactive platform, edit existing content, and receive suggestions in a form of interactive platform postings.
As for claim 11, Singh teaches. A method of training a generative response engine to interact with an agent on a client device based on a scope identified by a user, comprising (par. 2-7 gives overview of the system for automation within a user interface as trained with models based upon prior user interaction):
collecting, by a generative response engine, a first data provided by an agent monitoring a first input from the generative response engine, wherein the first data an initial screenshot prior to the first input and a subsequent screenshot after the first input (par. 133-143; fig. 7-8 consecutive screenshots are provided to the generative AI model, monitoring continuous changes between screenshot and segmenting screenshots into boxes (lower resolution) areas to focus to specific areas of the screenshots);
generating, by the generative response engine, a second input based on a task being performed and a context collected by the generative response engine, the second input comprising a description of the second input and coordinates of the second input (par.143-146 generative AI model is trained to recognize user interaction, where the user is inputting, clicking on user interface element etc.…, and the system determines what task the user is trying to complete and assigns RPA robots to accomplish the task through automation);
obtaining supplemental information from at least one of a safety discriminator or an input discriminator based on the second input (par. 51-55 and 146 deployed RPA robots/agents to make input using the validated model and policies (safety discriminator) , which then implies permission including where the user is inputting on the user interface as monitored through screen capture);
generating, by the generative response engine, a third input based on the task being performed and the supplemental information (par. 59 is one examples of a third to the nth input based upon tasks being performed within the user interface); and
generating a training dataset including the first data provided by the first input, the second input, the supplemental information, and second data provided based on the third input; and training the generative response engine based on the training dataset (par. 55 one example is Performance of the AI/ML models may be monitored, and be trained and improved using human-validated data, such as that provided by data review center 160. Human reviewers may provide labeled data to core hyper-automation system 120 via a review application 152 on computing systems 154. For instance, human reviewers may validate that predictions by AI/ML models 132 are accurate or provide corrections otherwise. This dynamic input may then be saved as training data for retraining AI/ML models 132, and may be stored in a database such as database 140, for example. The AI center may then schedule and execute training jobs to train the new versions of the AI/ML models using the training data. Both positive and negative examples may be stored and used for retraining of AI/ML models 132. par. 60 one example of generating training dataset for the models to be trained from; End-to-end measurement and government of an automation program at any scale may be provided by hyper-automation system 100 in some embodiments. Per the above, analytics may be employed to understand the performance of automations (e.g., via UiPath Insights™). Data modeling and analytics using any combination of available business metrics and operational insights may be used for various automated processes..
Singh does not specifically teach in detail what happens during policy enforcement; however in the same field of endeavor Catalano teaches adding a safety prompt to the user prompt upon detecting of policy violation (par. 144 an image included in user prompt message 826 is scanned for content that violates a safety policy of the interactive platform that hosts the chatbot system 300. If the chatbot system 300 detects inappropriate content, the chatbot system 300 does not generate the chatbot response message 840 using a generative AI model response 838 but instead generates the chatbot response message 840 using a canned response).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Catalano into Singh because Catalano suggests that the use of a chatbot much like Singh does in par. 59; the obvious additions to functionalities mentioned in Catalano would be an obvious inclusion since Catalano suggests that interactive platforms (e.g. Singh) (e.g., social platforms, social media platforms, interaction systems, AR platforms, applications, messaging platforms, AR applications, operating systems, gaming systems or applications, systems with which a user interacts, and the like)) may provide a way for users to interact with other users. For some users, interaction with an interactive platform may be enhanced by having a customizable chatbot to interact with. The chatbot can serve multiple uses, including providing a way for a user to generate content for posting to the interactive platform, edit existing content, and receive suggestions in a form of interactive platform postings.
As for claim 12, Singh teaches. The method of claim 11, wherein the generative response engine stores the context comprising the initial screenshot at a first resolution, previous screenshots at the first resolution, and the subsequent screenshot, and wherein the generative response engine is configured to identify features in images at the first resolution (par. 25 a feedback loop process that continuously or periodically compares the current screenshot to the previous screenshot to identify changes. Locations where visual changes occur on the screen may be identified and optical character recognition (OCR) may be performed on the location where the change occurred. Results of the OCR may then be compared to the content of a keyboard queue (e.g., as determined by key hooking) to determine whether a match exists. The locations where the change occurred may be determined by comparing a box of pixels from the current screenshot to a box of pixels in the same location from a previous screenshot; par. 145 boxes drawn on screen, which as identified by par. 25 is plurality of pixels would be in various resolutions depending on size of box drawn).
As for claim 13, Singh teaches. The method of claim 12, further comprising: separating the subsequent screenshot into a plurality of fragments at the first resolution; and determining whether to generate the second input using a fragment of the subsequent screenshot or the subsequent screenshot at the first resolution (par. 25 a feedback loop process that continuously or periodically compares the current screenshot to the previous screenshot to identify changes. Locations where visual changes occur on the screen may be identified and optical character recognition (OCR) may be performed on the location where the change occurred. Results of the OCR may then be compared to the content of a keyboard queue (e.g., as determined by key hooking) to determine whether a match exists. The locations where the change occurred may be determined by comparing a box of pixels from the current screenshot to a box of pixels in the same location from a previous screenshot; par. 145 boxes drawn on screen, which as identified by par. 25 is plurality of pixels would be in various resolutions depending on size of box drawn).
As for claim 14, Singh teaches. The method of claim 13, wherein the fragment of the subsequent screenshot and a type of input associated with the second input are provided to the input discriminator, and wherein the supplemental information includes a hint identifying a potential change to the second input based on the type of input (par. 129 collection of models with action suggestions).
As for claim 15, Singh teaches. The method of claim 14, wherein the type of input corresponds to at least one of a primary click, a secondary click for generating contextual options, or a click that is modified based on a key press event (par. 21 training of the generative AI/ML model may be performed without other system inputs such as system-level information (e.g., key presses, mouse clicks, locations, operating system operations, etc.) or application-level information (e.g., information from an application programming interface (API) from a software application executing on a computing system), such as that provided by the driver of UiPath Studio™).
As for claim 16, Singh teaches. The method of claim 14, wherein the input discriminator is configured to determine a confidence that the coordinates of the second input miss a target associated with the task (par. 115-118 use of weights are used during training to determine effective training data).
As for claim 17, Singh teaches. The method of claim 11, further comprising: providing, to the safety discriminator, the description of the second input, wherein the description corresponds to an inner monologue that is trained based on a monologue of the training dataset, wherein the supplemental information comprises additional content to supplement the task, wherein the additional content provides further guidance to the generative response engine that maintains a scope (par. 55, 92,133-143; fig. 7 and 8 screenshots used in training the model and used in user interaction to predict user intent when performing actions on user interface; the models are trained through consecutive screenshots that are input into generative AI model and continuously identify changes in same screenshots through portions of the screens inputted; inner monologue represents supervisor such as attended robot the system provides for various automations as noted in par. 41 Automations (e.g., run on a user computing system, a server, etc.) may be run by software robots, such as RPA robots, in some embodiments. For instance, attended robots, unattended robots, and/or test robots may be used. Attended robots work with users to assist them with tasks (e.g., via UiPath Assistant™). Unattended robots work independently of users and may run in the background, potentially without user knowledge. Test robots are unattended robots that run test cases against applications or RPA workflows. Test robots may be run on multiple computing systems in parallel in some embodiments.).
Singh does not specifically teach in detail what happens during policy enforcement; however in the same field of endeavor Catalano teaches adding a safety prompt to the user prompt upon detecting of policy violation (par. 144 an image included in user prompt message 826 is scanned for content that violates a safety policy of the interactive platform that hosts the chatbot system 300. If the chatbot system 300 detects inappropriate content, the chatbot system 300 does not generate the chatbot response message 840 using a generative AI model response 838 but instead generates the chatbot response message 840 using a canned response).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Catalano into Singh because Catalano suggests that the use of a chatbot much like Singh does in par. 59; the obvious additions to functionalities mentioned in Catalano would be an obvious inclusion since Catalano suggests that interactive platforms (e.g. Singh) (e.g., social platforms, social media platforms, interaction systems, AR platforms, applications, messaging platforms, AR applications, operating systems, gaming systems or applications, systems with which a user interacts, and the like)) may provide a way for users to interact with other users. For some users, interaction with an interactive platform may be enhanced by having a customizable chatbot to interact with. The chatbot can serve multiple uses, including providing a way for a user to generate content for posting to the interactive platform, edit existing content, and receive suggestions in a form of interactive platform postings.
.
As for claim 18, Singh teaches. The method of claim 17, wherein the scope identifies a surface area for input into at a client computer (par. 26 example of surface areas of a computing client featuring windows, elements, application and the like which are used as training data for the AI/ML model).
As for claim 19. The method of claim 11, wherein the context comprises a plurality of timestep image pairs having a first resolution, a current screenshot corresponding to a current state of a client and separated into a plurality of fragments having the first resolution, previous inputs metadata corresponding to a human input device, and an inner monologue of the generative response engine, and wherein each timestep image pair includes including a screenshot before an input and a screenshot after the input (par. 28 training of the generative AI/ML model may be supplemented with information from “automation boxes”, which are implemented via hardware or software and observe what information is coming from an input device, such as a mouse or the keyboard. In certain embodiments, a camera may be used to track where the user is looking on the screen. The information from automation boxes and/or cameras may be time stamped and used in conjunction with the graphical elements, applications, and screens detected by the generative AI/ML model to assist in its training and better understand what the user is doing at the time).
As for claim 20, Singh teaches. The method of claim 11, further comprising: identifying the generative response engine is unable to continue the task; sending an instruction to the agent to request supervised input; and receiving recorded data from the agent that includes human input to advance the task (par. 35 Long-running workflows for RPA in some embodiments are master projects that support service orchestration, human intervention, and long-running transactions in unattended environments. Human intervention comes into play when certain processes require human inputs to handle exceptions, approvals, or validation before proceeding to the next step in the activity).
Claim(s) 21 is/are rejected under 35 U.S.C. 103 as being unpatentable over Singh, Prabhdeep (US Pub. 2023/0360388 A1), herein referred to as “Singh” in view of Catalano, Jacob et al. (US Pub. 2024/0291779 A1), herein referred to as “Catalano” in further view of Freeman, Mallory et al. (US Pub. 2022/0126326 A1), herein referred to as “Freeman”.
As for claim 21, Singh teaches. The method of claim 20, wherein the recorded data in cleaned to remove duplicate information corresponding to each timestep and included in the training dataset (par. 45 data for training is timestamp data; and par. 85 can remove data from queue to server which implies removal of duplicate information to save processing at server side).
In the event that Singh does not teach remove duplicate information corresponding to timestamp; Freeman in the same field of endeavor teaches wherein the recorded data in cleaned to remove duplicate information corresponding to each timestep and included in the training dataset (par. 45 data for training is timestamp data (par. 58,83 and 87 removing duplicate information that pertains to sensor information from camera and time stamp images).
It would have been obvious to one ordinary skill in the art before the effective filing date to combine Freeman into Singh as modified by Catalano since Freeman suggests in paragraph 145 Many different arrangements of the various components depicted, as well as components not shown, are possible without departing from the scope of the claims below. Embodiments of the disclosure have been described with the intent to be illustrative rather than restrictive. Alternative embodiments will become apparent to readers of this disclosure after and because of reading it. Alternative means of implementing the aforementioned can be completed without departing from the scope of the claims below. Certain features and sub-combinations are of utility and may be employed without reference to other features and sub-combinations and are contemplated within the scope of the claims.
(Note :) It is noted that any citation to specific, pages, columns, lines, or figures in the prior art references and any interpretation of the references should not be considered to be limiting in any way. A reference is relevant for all it contains and may be relied upon for all that it would have reasonably suggested to one having ordinary skill in the art. In re Heck, 699 F.2d 1331, 1332-33, 216 USPQ 1038, 1039 (Fed. Cir. 1983) (quoting In re Lemelson, 397 F.2d 1006,1009, 158 USPQ 275, 277 (CCPA 1968)).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
PROMPT ENGINEERING FOR ARTIFICIAL INTELLIGENCE ASSISTED INDUSTRIAL AUTOMATION SYSTEM DESIGN
Document ID
US 20250005224 A1
Date Published
2025-01-02
Abstract
Technology disclosed herein includes a prompt engineering service that integrates artificial intelligence with the programming systems of an industrial automation environment to design a system of the industrial automation environment. The interface service leverages the capabilities of a large language model (LLM) trained on industrial automation workflows to provide accurate and relevant system design information. For example, the interface service receives system configuration data and generates a first prompt requesting a category associated with the system configuration data. The interface service uses the first prompt to generate a response from the LLM. The interface service generates a second prompt requesting a user interface message for offering assistance to configure the system based on the category. The interface service uses the second prompt to generate the user interface message and displays the message in a user interface.
ENHANCING ACCURACY AND REDUCING HALLUCINATIONS IN GENERATIVE AI OUTPUTS THROUGH CONTEXTUAL INTEGRATION AND MULTI-AI-MODEL INTERACTIONS
Document ID
US 20250173541 A1
Date Published
2025-05-29
Abstract
A computer-implemented method, system, and computer program product for leveraging artificial intelligence to improve operations. An artificial intelligence assistant is created to assist a user in leveraging artificial intelligence to service a request from a user. Furthermore, a request is received from the user, where the request is a request to chat with a context. Context refers to experiences that are utilized by the user for interacting (e.g., chatting) with artificial intelligence, which is used to minimize artificial intelligence hallucinations since such context is used by the artificial intelligence model to output a response thereby providing more confidence that the output response of the artificial intelligence model is more accurate. The request is then serviced by leveraging the artificial intelligence using the context. In this manner, artificial intelligence hallucinations are minimized.
Inquires
Any inquiry concerning this communication should be directed to NICHOLAS AUGUSTINE at telephone number (571)270-1056.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
PNG
media_image1.png
213
559
media_image1.png
Greyscale
/NICHOLAS AUGUSTINE/Primary Examiner, Art Unit 2178 August 17, 2026
Prosecution Insights