DETAILED ACTION
Claims 1-20 are pending in application.
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 .
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.
Examiner’s Notes
The Examiner cites particular sections in the references as applied to the claims below for the convenience of the applicant(s). Although the specified citations are representative of the teachings in the art and are applied to the specific limitations within the individual claim, other passages and figures may apply as well. It is respectfully requested that, in preparing responses, the applicant(s) fully consider the references in their entirety as potentially teaching all or part of the claimed invention, as well as the context of the passage as taught by the prior art or disclosed by the Examiner.
Information Disclosure Statement
The information disclosure statement filed 08/06/2025 fails to comply with 37 CFR 1.98(a)(2), which requires a legible copy of each cited foreign patent document; each non-patent literature publication or that portion which caused it to be listed; and all other information or that portion which caused it to be listed. No legible copy of the non-patent literature publication cite no. 2 (Elizabeth et al.; “Hierarchical Routing in ad hoc Mobile Networks”) was provided. It has been placed in the application file, but the information referred to therein has not been considered.
Claim Rejections - 35 USC § 112(b)
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 2, 3, 9, 10, 16, and 17 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 2 recites the limitation “its pretrained knowledge” in line 4. It is not clear which limitation the term “its” is referring to. Specifically, it is not clear if this limitation is referring to LLM’s “pretrained knowledge”, to the first language input’s “pretrained knowledge”, or to the at least one parameter value’s “pretrained knowledge”.
For the following analysis, the Examiner will consider the limitation “its pretrained knowledge” as referring to –the LLM’s pretrained knowledge—.
Claim 3 inherits the features of claim 2 and is rejected accordingly.
Claim 3 recites the limitation "the API call" in line 4 and line 5. There is insufficient antecedent basis for this limitation in the claim. It is not clear if this limitation is referring to the “application programming interface (API) call from among a plurality of API calls configured for prescriptive tasks” recited in claim 1, or to the “API call based on a first large language model (LLM)” previously recited in claim 3.
For the following analysis, the Examiner will consider the limitation “the API call” recited in lines 4 and 5 as referring to –the API call based on the first LLM—.
Claim 9 recites the limitation “its pretrained knowledge” in line 4. It is not clear which limitation the term “its” is referring to. Specifically, it is not clear if this limitation is referring to LLM’s “pretrained knowledge”, to the first language input’s “pretrained knowledge”, or to the at least one parameter value’s “pretrained knowledge”.
For the following analysis, the Examiner will consider the limitation “its pretrained knowledge” as referring to –the LLM’s pretrained knowledge—.
Claim 10 inherits the features of claim 9 and is rejected accordingly.
Claim 10 recites the limitation "the API call" in line 3 and line 5. There is insufficient antecedent basis for this limitation in the claim. It is not clear if this limitation is referring to the “application programming interface (API) call from among a plurality of API calls configured for prescriptive tasks” recited in claim 8, or to the “API call based on a first large language model (LLM)” previously recited in claim 10.
For the following analysis, the Examiner will consider the limitation “the API call” recited in lines 4 and 5 as referring to –the API call based on the first LLM—.
Claim 16 recites the limitation “its pretrained knowledge” in line 4. It is not clear which limitation the term “its” is referring to. Specifically, it is not clear if this limitation is referring to LLM’s “pretrained knowledge”, to the first language input’s “pretrained knowledge”, or to the at least one parameter value’s “pretrained knowledge”.
For the following analysis, the Examiner will consider the limitation “its pretrained knowledge” as referring to –the LLM’s pretrained knowledge—.
Claim 17 inherits the features of claim 16 and is rejected accordingly.
Claim 17 recites the limitation "the API call" in line 4 and line 5. There is insufficient antecedent basis for this limitation in the claim. It is not clear if this limitation is referring to the “application programming interface (API) call from among a plurality of API calls configured for prescriptive tasks” recited in claim 15, or to the “API call based on a first large language model (LLM)” previously recited in claim 17.
For the following analysis, the Examiner will consider the limitation “the API call” recited in lines 4 and 5 as referring to –the API call based on the first LLM—.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1, 7, 8, 14, and 15 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Cai et al. (US 2019/0349321 A1; hereinafter “Cai”).
With respect to claim 1, Cai teaches: A computer-implemented method comprising:
receiving at least one natural language input via a software application (see e.g. paragraph 46: “virtual agent 180 (chat bot) that can interact with the communication platform users. The virtual agent 180 (chat bot) can provide a flexible user experience with cognitive natural language interaction”; and paragraph 44: “inquiries received at virtual agent 180 using natural language processor 120”);
determining that the at least one natural language input matches an application programming interface (API) call (see e.g. Fig. 15: “Phyton Flask RestAPI”) from among a plurality of API calls (see e.g. paragraph 188: “use a Neural Network Classification model to classify each of the client interactions as either relevant or irrelevant. The machine learning model was built using a python hosted RESTFUL API service”; and paragraph 189: “receiving an interaction data set including… an interaction description text including the natural language message data; inputting the interaction data set into a machine learning classification model including a multilayer perceptron to generate a relevant interaction score”) configured for prescriptive tasks (see e.g. paragraph 51: “configured to generate a prescriptive solution for the IT incident using the natural language processor and a prescriptive model”);
identifying at least one parameter value of the API call from the at least one natural language input (see e.g. paragraph 190: “Data arrives via post call to the Python REST API”; and paragraph 191: “Key features are then parsed out of the inputted JSON”) and transmitting the API call to a prescriptive artificial intelligence (AI) model (see e.g. Fig. 15: “Machine Learning Model”; paragraph 183: “platform 100 involves cognitive automation by combining machine learning and deep learning (as part of predictive/prescriptive models 126 and operational risk model 124) with natural language processor 120 to provide output at an interactive virtual agent 180”; and paragraph 192: “following variables are then passed through the machine learning model”; and paragraphs 193-197);
executing the prescriptive AI model on the at least one parameter value to generate a natural language response (see e.g. paragraph 51: “process received the IT incident using the natural language processor 120 and generate a prescriptive solution for the IT incident using the knowledge base and the prescriptive models 126”; and paragraph 189: “inputting the interaction data set into a machine learning classification model including a multilayer perceptron to generate a relevant interaction score”); and
displaying the natural language response via a graphical user interface (GUI) of the software application (see e.g. paragraph 51: “output the prescriptive solution to a virtual agent 180”; and paragraph 178: “output the prescriptive solution for display at an interface application 130 with a visual element indicating the prescriptive solution. In some embodiments, the processor 104 is configured to output the prescriptive solution to the virtual agent 180”).
Cai discloses a virtual agent 180 that receives natural-language user inquires and provides natural-language prescriptive solutions as responses to the inquires utilizing prescriptive machine learning models. These user interactions with the machine learning models are implemented via RestAPIs that provide variables/parameters to the machine learning models for processing.
With respect to claim 7, Cai teaches: The computer-implemented method of claim 1, wherein the determining comprises matching the at least one natural language input to the API call from among the plurality of API calls based on execution of a large language model (LLM) on the at least one natural language input (see e.g. paragraph 44: “The agent platform 100 can receive a large amount of data relating to Information Technology (IT) incidents, security events, change requests, and so on, from different entities 150 (e.g. network entities, network endpoints). The agent platform 100 can process the data to generate summary reports, risk profiles, regulatory issues, and so on, in response to inquiries received at virtual agent 180 using natural language processor 120”).
With respect to claims 8 and 14: Claims 8 and 14 are directed to a computer system comprising a processor set and a set of one or more computer-readable storage media storing program instructions for causing the processor set to perform computer operations corresponding to the method disclosed in claims 1 and 7, respectively; please see the rejections directed to claims 1 and 7 above which also cover the limitations recited in claims 8 and 14. Note that, Cai also discloses an agent platform 100 comprising a processor 104 and data storage 110 storing program instructions to perform the method disclosed in claims 1 and 7 (see e.g. Fig. 1).
With respect to claim 15: Claim 15 is directed to a computer program product comprising a set of one or more computer-readable storage media storing program instructions for causing a processor set to perform computer operations corresponding to the method disclosed in claim 1; please see the rejection directed to claim 1 above which also covers the limitations recited in claim 15. Note that, Cai also discloses a computer readable medium storing software instructions to perform the method disclosed in claim 1 (see e.g. paragraph 234).
Claim Rejections - 35 USC § 103
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.
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 2-6, 9-13, and 16-20 are rejected under 35 U.S.C. 103 as being unpatentable over Cai in view of Kachuee et al. (US 12,626,698 B1; hereinafter “Kachuee”).
With respect to claim 2, Cai teaches: The computer-implemented method of claim 1,
Cai does not but Kachuee teaches:
comprising determining that a first natural language input does not match any of the plurality of API calls (see e.g. Kachuee, from column 27, line 65 to column 28, line 1: “determine one or more APIs that are to process with respect to the user input or the current task (e.g., determine one or more API calls to cause the APIs to process) given the information”; column 32, lines 34-39: “determine whether additional information is needed in order to complete the current task (e.g., if an ambiguity exists in the user input data 227 or the current task, if the current task is to resolve an identified ambiguity, if an API argument is missing from the user input or other available data, etc.)”), and in response, executing a large language model (LLM) on the at least one parameter value to generate additional dialog based on its pretrained knowledge and outputting the additional dialog via the GUI of the software application (see e.g. Kachuee, column 32, lines 39-46: “in which case the shortlister language model 440 may send data representing a request for such additional information to the response arbitration component 260. In some embodiments, the action plan data 242 may represent the request for additional information, and the action plan execution component 245 may be configured to send corresponding action data 247 to the personalized context component 265”; and column 2, lines 28-31: “input to the LLM may be in the form of a prompt. A prompt may be a natural language input, for example, an instruction, for the LLM to generate an output according to the prompt”).
Cai and Kachuee are analogous art because they are in the same field of endeavor: natural language processing for task execution. Therefore, it would have been obvious to one with ordinary skill in the art before the effective filing date of the claimed invention to modify Cai with the teachings of Kachuee. The motivation/suggestion would be to handle ambiguous user inputs; thus improving the overall robustness of the system.
With respect to claim 3, Cai as modified teaches: The computer-implemented method of claim 2, wherein the determining comprises determining that the first natural language input corresponds to an API call based on a first large language model (LLM) that interprets an intent behind the first natural language input (see e.g. Cai, paragraph 87: “the backend can sends this message to the cognitive engine which extracts the intent of the user to find resolution”), and
Cai does not but Kachuee teaches:
slot filling the API call based on a second LLM that extracts the at least one parameter value from the first natural language input to configure the API call (see e.g. Kachuee, column 4, lines 4-11: “determine a set of APIs capable of performing a task with respect to the first spoken user input; generating a second prompt to identify at least one API, from the set of APIs, to perform the task, the second prompt including the user profile data; processing, using a second LLM, the second prompt to select, from the set of APIs, a first API to perform the task; based on the second LLM selecting the first API”; and column 30, lines 10-16: “the NER component identifies “slots” (each corresponding to one or more particular words in text data) that may be useful for later processing. The NER component may also label each slot with a type (e.g., noun, place, city, artist name, song name, etc.). Thereafter, the ER component links a slot of text data to a specific entity known to the system”).
Cai and Kachuee are analogous art because they are in the same field of endeavor: natural language processing for task execution. Therefore, it would have been obvious to one with ordinary skill in the art before the effective filing date of the claimed invention to modify Cai with the teachings of Kachuee. The motivation/suggestion would be to improve natural language processing by utilizing multiple LLMs (see e.g. Kachuee, column 2, lines 6-27).
With respect to claim 4, Cai teaches: The computer-implemented method of claim 1, comprising… executing the prescriptive AI model on the required parameter value to generate the natural language response (see e.g. Cai, paragraph 51: “process received the IT incident using the natural language processor 120 and generate a prescriptive solution for the IT incident using the knowledge base and the prescriptive models 126”; and paragraph 189: “inputting the interaction data set into a machine learning classification model including a multilayer perceptron to generate a relevant interaction score”).
Cai does not but Kachuee teaches:
identifying a required parameter value of the API call that is missing from the at least one natural language input (see e.g. Kachuee, column 32, lines 34-39: “determine whether additional information is needed in order to complete the current task (e.g., if an ambiguity exists in the user input data 227 or the current task, if the current task is to resolve an identified ambiguity, if an API argument is missing from the user input or other available data, etc.)”), and in response, identifying the required parameter value from prior conversation state stored within a memory (see e.g. Kachuee, column 32, lines 39-60: “in which case the shortlister language model 440 may send data representing a request for such additional information to the response arbitration component 260. In some embodiments, the action plan data 242 may represent the request for additional information, and the action plan execution component 245 may be configured to send corresponding action data 247 to the personalized context component 265… The system 200 may send a request to the personalized context component 265 to “identify user pizza preference” and the personalized context component 265 may process as described herein above to return personalized context data resolving the ambiguity (e.g., the user's pizza preference may be determined to be a cheese pizza or a pepperoni pizza)”; and column 34, lines 61-63: “context data 542 may correspond to various contextual information associated with the user input (e.g., dialog history data, historical user input data”) and
Cai and Kachuee are analogous art because they are in the same field of endeavor: natural language processing for task execution. Therefore, it would have been obvious to one with ordinary skill in the art before the effective filing date of the claimed invention to modify Cai with the teachings of Kachuee. The motivation/suggestion would be to handle ambiguous user inputs; thus improving the overall robustness of the system.
With respect to claim 5, Cai teaches: The computer-implemented method of claim 1,
Cai does not but Kachuee teaches:
comprising identifying a required parameter value of the API call that is missing from a first natural language input (see e.g. Kachuee, column 32, lines 34-39: “determine whether additional information is needed in order to complete the current task (e.g., if an ambiguity exists in the user input data 227 or the current task, if the current task is to resolve an identified ambiguity, if an API argument is missing from the user input or other available data, etc.)”), and in response, executing a large language model (LLM) on the first natural language input to generate additional dialog and outputting the additional dialog via the GUI of the software application (see e.g. Kachuee, column 32, lines 39-46: “in which case the shortlister language model 440 may send data representing a request for such additional information to the response arbitration component 260. In some embodiments, the action plan data 242 may represent the request for additional information, and the action plan execution component 245 may be configured to send corresponding action data 247 to the personalized context component 265”; and column 2, lines 28-31: “input to the LLM may be in the form of a prompt. A prompt may be a natural language input, for example, an instruction, for the LLM to generate an output according to the prompt”).
Cai and Kachuee are analogous art because they are in the same field of endeavor: natural language processing for task execution. Therefore, it would have been obvious to one with ordinary skill in the art before the effective filing date of the claimed invention to modify Cai with the teachings of Kachuee. The motivation/suggestion would be to handle ambiguous user inputs; thus improving the overall robustness of the system.
With respect to claim 6, Cai teaches: The computer-implemented method of claim 5, comprising receiving a second natural language input via the software application (see e.g. Cai, paragraph 39: “queries and requests from employees and/or customers… numerous requests may be submitted”; and paragraph 44: “inquiries received at virtual agent 180 using natural language processor 120”) and aggregating the first natural language input with the second natural language input to generate an aggregated input (see e.g. Cai, paragraph 39: “catalogue queries and requests… requests may be stockpiled”), wherein the identifying comprises identifying the required parameter value from the aggregated input (see e.g. Cai, paragraph 39: “Historical requests may be stockpiled for analysis to identify potential solutions that were useful to resolve prior requests”; and paragraph 51: “process received the IT incident using the natural language processor 120 and generate a prescriptive solution for the IT incident using the knowledge base and the prescriptive models 126”).
With respect to claims 9-13: Claims 9-13 are directed to a computer system comprising a processor set and a set of one or more computer-readable storage media storing program instructions for causing the processor set to perform computer operations corresponding to the method disclosed in claims 2-6, respectively; please see the rejections directed to claims 2-6 above which also cover the limitations recited in claims 9-13.
With respect to claims 16-20: Claims 16-20 are directed to a computer program product comprising a set of one or more computer-readable storage media storing program instructions for causing a processor set to perform computer operations corresponding to the method disclosed in claims 2-6, respectively; please see the rejections directed to claims 2-6 above which also cover the limitations recited in claims 16-20.
CONCLUSION
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Khullar et al. (US 2025/0284888 A1) discloses a chat interface where users can query information from various entities in available API sets and request actions that can be automated via the APIs (see paragraph 24).
Liu et al. (US 2025/0258723 A1) discloses an input prompt that identifies API(s) responsive to a natural language user instruction, wherein the input prompt is processed using the second trained LLM to generate one or more execution steps for fulfilling a corresponding API task (see paragraph 19).
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Umut Onat whose telephone number is (571)270-1735. The examiner can normally be reached M-Th 9:00-7:30.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Kevin L Young can be reached at (571) 270-3180. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/UMUT ONAT/Primary Examiner, Art Unit 2194
Prosecution Insights