DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Specification
The disclosure is objected to because of the following informalities:
In paragraph 0012, line 3, “The query may also include a request may ask” should read “The query may also include a request that asks”.
In paragraph 0041, lines 8-9, “The command may used to perform” should read “The command may be used to perform”.
Appropriate correction is required.
Claim Objections
Claim 19 is objected to because of the following informalities:
In Claim 19, “artifical intelligence model” should read “artificial intelligence model”.
Appropriate correction is required.
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.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1, 6 – 8, 13 – 14 and 20 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Khosla et al. (US Patent No. 12,505,135), hereinafter Khosla.
Regarding claim 1, Khosla discloses a method comprising:
in response to receiving a query, retrieving, by a processor, data from a retrieval-augmented generation (RAG) data store associated with the query (Column 5, line 62 - Column 6, line 18, "The aggregator component 104 can retrieve passages from the search systems 124 based on the natural language question and create a prompt for the LLM component 106. For example, the aggregator component 104 may analyze the natural language question by using string matching techniques (e.g., partial string matching, dense passage retrieval, etc.) to determine the meaning of the natural language question. After determining the meaning of the natural language question, the aggregator component 104 may then determine which of the search systems 124 the aggregator component 104 may retrieve passages from (e.g., retrieve from a network-based storage service QA pair system but not a network-based AI service QA pair system) based on the natural language question. Based on the retrieved passages (e.g., documents, text of the documents, pictures of the documents, or video of the documents, etc.) from the search systems 124, the aggregator component 104 may create a prompt for the LLM component 106 to answer, where the prompt from the aggregator component 104 to the LLM component 106 may contain some of the retrieved passages and a form of the natural language question. The aggregator component 104 may be a machine learning model trained on Retrieval Augmented Generation (RAG) techniques."; A natural language question reads on a query, and retrieving passages from search systems reads on retrieving data from a data store associated with the query.);
transmitting the query and the data to an artificial intelligence model (Column 3, lines 12-15, "In some embodiments, the natural language question answer service can utilize a trained large language model (LLM) to use the prompt and generate an answer to the natural language question."; Column 6, lines 2-16, "After determining the meaning of the natural language question, the aggregator component 104 may then determine which of the search systems 124 the aggregator component 104 may retrieve passages from (e.g., retrieve from a network-based storage service QA pair system but not a network-based AI service QA pair system) based on the natural language question. Based on the retrieved passages (e.g., documents, text of the documents, pictures of the documents, or video of the documents, etc.) from the search systems 124, the aggregator component 104 may create a prompt for the LLM component 106 to answer, where the prompt from the aggregator component 104 to the LLM component 106 may contain some of the retrieved passages and a form of the natural language question."; Column 6, lines 61-64, "The LLM component 106 may receive the prompt from the aggregator component 104, the user context (optionally) from user context component 105, and generate one or more answers based on the prompt and the user context."; A large language model receiving the prompt and generating one or more answers based on the prompt, where the prompt contains retrieved passages and a form of the natural language question, reads on transmitting the query and the data to an artificial intelligence model.);
processing the query with the data using the artificial intelligence model to generate a response to the query (Column 6, lines 61-64, "The LLM component 106 may receive the prompt from the aggregator component 104, the user context (optionally) from user context component 105, and generate one or more answers based on the prompt and the user context."; A large language model receiving the prompt and generating one or more answers based on the prompt reads on processing the query with the data using the artificial intelligence model to generate a response to the query.);
in response to determining that the query includes a request to perform an action, generating a command based on the request to perform the action (Column 16, lines 44-56, "Moreover, the LLM component 106 may additionally be trained to provide and/or run application programming interface (API) commands in response to a natural language question or prompt (e.g., as a form of a command line interface (CLI) command). The LLM component 106 may receive (via the natural language question answering service 102) a natural language question (or prompt) which asks for a command to be run in a network-based system which a user asking the question (or prompt) subscribes to. The LLM component 106 may gain access to the user's credentials (e.g., which services they are subscribed to, usage history, knowledge graphs of the customer, etc.) to generate an answer which can include API commands as an answer."; A large language model generating an answer that includes API commands in response to receiving a natural language question that asks for a command to be run in a network-based system reads on generating a command based on the request to perform the action in response to determining that the query includes a request to perform an action.);
and executing the command and providing the response to the query that includes a status from the executing of the command (Column 17, lines 42-55, "After determining the type and kind of API command to generate on behalf of the customer, the LLM component 106 may then send the API command to the customer with a request or prompt as to whether the API command should be executed against the network-based service. The customer may respond to the LLM component 106 (e.g., or alternatively the natural language question answering service 102) and indicate to the LLM component 106 that the API command should be executed. After receiving a request to execute the API command, the LLM component 106 may execute the API command against the network-based service and send the customer a confirmation that the API command finished successfully."; Executing the API command against the network-based service reads on executing the command, and sending the customer a confirmation that the API command finished successfully reads on providing the response to the query that includes a status from the executing of the command.).
Regarding claim 6, Khosla discloses the method as claimed in claim 1.
Khosla further discloses:
wherein artificial intelligence model is a large language model (Column 3, lines 12-15, "In some embodiments, the natural language question answer service can utilize a trained large language model (LLM) to use the prompt and generate an answer to the natural language question.").
Regarding claim 7, Khosla discloses the method as claimed in claim 1.
Khosla further discloses:
further comprising transmitting the status associated with the executing of the command to a user interface (Column 5, lines 25-42, "The customer computing devices 122 in FIG. 1 can connect to the natural language question answering service 102 via the network 116. The customer computing devices 122 can send natural language questions (e.g., input from a user via a user interface (UI) of the customer computing devices 122) to the natural language question answering service 102 and receive answers from the natural language question answering service 102 based on the natural language question. The customer computing devices 122 can be configured to have at least one processor. That processor can be in communication with the memory for maintaining computer-executable instructions. The customer computing devices 122 may be physical or virtual. The customer computing devices 122 may be mobile devices, personal computers, servers, or other types of devices. The customer computing devices 122 have a display and input devices through which a user can interact with the user-interface component."; Column 17, lines 51-55, "After receiving a request to execute the API command, the LLM component 106 may execute the API command against the network-based service and send the customer a confirmation that the API command finished successfully."; A customer computing device having a display and input devices through which a user can interact with the user-interface, where a confirmation that the API command finished successfully is send the customer, reads on transmitting the status associated with the executing of the command to a user interface.).
Regarding claim 8, Khosla discloses an information handling system, comprising:
a processor (Column 5, lines 33-34, "The customer computing devices 122 can be configured to have at least one processor.");
and a memory coupled to the processor, the memory having program instructions stored thereon that upon execution (Column 8, lines 53-57, "The memory 214 may include computer program instructions that the processing unit 206 executes in order to implement one or more embodiments. The memory 214 generally includes RAM, ROM, or other persistent or non-transitory memory.") cause the processor to:
in response to receipt of a query, retrieve data from a retrieval-augmented generation (RAG) data store associated with the query (Column 5, line 62 - Column 6, line 18, "The aggregator component 104 can retrieve passages from the search systems 124 based on the natural language question and create a prompt for the LLM component 106. For example, the aggregator component 104 may analyze the natural language question by using string matching techniques (e.g., partial string matching, dense passage retrieval, etc.) to determine the meaning of the natural language question. After determining the meaning of the natural language question, the aggregator component 104 may then determine which of the search systems 124 the aggregator component 104 may retrieve passages from (e.g., retrieve from a network-based storage service QA pair system but not a network-based AI service QA pair system) based on the natural language question. Based on the retrieved passages (e.g., documents, text of the documents, pictures of the documents, or video of the documents, etc.) from the search systems 124, the aggregator component 104 may create a prompt for the LLM component 106 to answer, where the prompt from the aggregator component 104 to the LLM component 106 may contain some of the retrieved passages and a form of the natural language question. The aggregator component 104 may be a machine learning model trained on Retrieval Augmented Generation (RAG) techniques."; A natural language question reads on a query, and retrieving passages from search systems reads on retrieving data from a data store associated with the query.);
transmit the query and the data from the RAG data store to an artificial intelligence model (Column 3, lines 12-15, "In some embodiments, the natural language question answer service can utilize a trained large language model (LLM) to use the prompt and generate an answer to the natural language question."; Column 6, lines 2-16, "After determining the meaning of the natural language question, the aggregator component 104 may then determine which of the search systems 124 the aggregator component 104 may retrieve passages from (e.g., retrieve from a network-based storage service QA pair system but not a network-based AI service QA pair system) based on the natural language question. Based on the retrieved passages (e.g., documents, text of the documents, pictures of the documents, or video of the documents, etc.) from the search systems 124, the aggregator component 104 may create a prompt for the LLM component 106 to answer, where the prompt from the aggregator component 104 to the LLM component 106 may contain some of the retrieved passages and a form of the natural language question."; Column 6, lines 61-64, "The LLM component 106 may receive the prompt from the aggregator component 104, the user context (optionally) from user context component 105, and generate one or more answers based on the prompt and the user context."; A large language model receiving the prompt and generating one or more answers based on the prompt, where the prompt contains retrieved passages and a form of the natural language question, reads on transmitting the query and the data to an artificial intelligence model.);
process the query with the data using the artificial intelligence model to generate a response to the query (Column 6, lines 61-64, "The LLM component 106 may receive the prompt from the aggregator component 104, the user context (optionally) from user context component 105, and generate one or more answers based on the prompt and the user context."; A large language model receiving the prompt and generating one or more answers based on the prompt reads on processing the query with the data using the artificial intelligence model to generate a response to the query.);
in response to determining that the query includes a request to perform an action, generate a command based on the request to perform the action (Column 16, lines 44-56, "Moreover, the LLM component 106 may additionally be trained to provide and/or run application programming interface (API) commands in response to a natural language question or prompt (e.g., as a form of a command line interface (CLI) command). The LLM component 106 may receive (via the natural language question answering service 102) a natural language question (or prompt) which asks for a command to be run in a network-based system which a user asking the question (or prompt) subscribes to. The LLM component 106 may gain access to the user's credentials (e.g., which services they are subscribed to, usage history, knowledge graphs of the customer, etc.) to generate an answer which can include API commands as an answer."; A large language model generating an answer that includes API commands in response to receiving a natural language question that asks for a command to be run in a network-based system reads on generating a command based on the request to perform the action in response to determining that the query includes a request to perform an action.);
and execute the command and provide the response that includes a status from the execution of the command (Column 17, lines 42-55, "After determining the type and kind of API command to generate on behalf of the customer, the LLM component 106 may then send the API command to the customer with a request or prompt as to whether the API command should be executed against the network-based service. The customer may respond to the LLM component 106 (e.g., or alternatively the natural language question answering service 102) and indicate to the LLM component 106 that the API command should be executed. After receiving a request to execute the API command, the LLM component 106 may execute the API command against the network-based service and send the customer a confirmation that the API command finished successfully."; Executing the API command against the network-based service reads on executing the command, and sending the customer a confirmation that the API command finished successfully reads on providing the response to the query that includes a status from the executing of the command.).
Regarding claim 13, arguments analogous to claim 7 are applicable.
Regarding claim 14, arguments analogous to claim 1 are applicable. In addition, Khosla discloses a non-transitory computer-readable medium to store instructions that are executable to perform operations (Column 8, lines 53-57, "The memory 214 may include computer program instructions that the processing unit 206 executes in order to implement one or more embodiments. The memory 214 generally includes RAM, ROM, or other persistent or non-transitory memory.") comprising the steps of claim 1.
Regarding claim 20, arguments analogous to claim 7 are applicable.
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.
Claims 2, 4, 9, 11, 15 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Khosla in view of D'Urso et al. ("A Novel LLM Architecture for Intelligent System Configuration"), hereinafter D'Urso.
Regarding claim 2, Khosla discloses the method as claimed in claim 1, but does not specifically disclose: wherein the query is related to a system configuration of an information handling system.
D'Urso teaches:
wherein the query is related to a system configuration of an information handling system (Abstract, lines 1-15, "This paper presents a comparative analysis of novel LLM-based architectures designed specifically for system configuration purposes. Generative Artificial Intelligence (Gen AI) has rapidly evolved, offering transformative capabilities in content generation across various domains. Large Language Models (LLMs) stand at the forefront of this evolution, revolutionizing natural language understanding and enabling sophisticated conversational systems. Leveraging the potential of LLMs, our study introduces a novel system architecture centered around an intelligent chatbot tailored to assist learners in complex network configurations. By integrating Generative Pre-trained Transformer-based models with Retrieval Augmented Generation (RAG) and Function Calling features, our architecture aims to provide a co-pilot-like experience, guiding users through understanding requirements and generating configuration scripts."; A chatbot for assisting learners in network configurations implemented with a large language model using retrieval augmented generation reads on the query being related to a system configuration of an information handling system.).
D'Urso is considered to be analogous to the claimed invention because it is in the same field of retrieval augmented generation machine learning models. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Khosla to incorporate the teachings of D'Urso to implement a chatbot for assisting learners in network configurations. Doing so would allow for leveraging the potential of large language models to assist learners in complex network configurations (D'Urso; Abstract, lines 1-9).
Regarding claim 4, Khosla discloses the method as claimed in claim 1, but does not specifically disclose: wherein the RAG data store includes system configuration related data.
D'Urso teaches:
wherein the RAG data store includes system configuration related data (Abstract, lines 1-15, "This paper presents a comparative analysis of novel LLM-based architectures designed specifically for system configuration purposes. Generative Artificial Intelligence (Gen AI) has rapidly evolved, offering transformative capabilities in content generation across various domains. Large Language Models (LLMs) stand at the forefront of this evolution, revolutionizing natural language understanding and enabling sophisticated conversational systems. Leveraging the potential of LLMs, our study introduces a novel system architecture centered around an intelligent chatbot tailored to assist learners in complex network configurations. By integrating Generative Pre-trained Transformer-based models with Retrieval Augmented Generation (RAG) and Function Calling features, our architecture aims to provide a co-pilot-like experience, guiding users through understanding requirements and generating configuration scripts."; Section VI-B, lines 11-17, "Notably, this scenario can be extended to encompass ”known” network configuration protocols, such as DHCP, by incorporating proprietary documents for RAG purposes. This adaptive approach underscores the versatility of the chatbot system in accommodating various configuration contexts and leveraging external resources for enhanced performance."; A chatbot for assisting learners in network configurations implemented with a large language model using retrieval augmented generation, where retrieval augmented generation incorporates proprietary documents of known network configuration protocols, reads on the RAG data store includes system configuration related data.).
D'Urso is considered to be analogous to the claimed invention because it is in the same field of retrieval augmented generation machine learning models. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Khosla to incorporate the teachings of D'Urso to implement a chatbot for assisting learners in network configurations implemented with a large language model using retrieval augmented generation, where retrieval augmented generation incorporates proprietary documents of known network configuration protocols. Doing so would allow for leveraging the potential of large language models to assist learners in complex network configurations (D'Urso; Abstract, lines 1-9).
Regarding claim 9, arguments analogous to claim 2 are applicable.
Regarding claim 11, arguments analogous to claim 4 are applicable.
Regarding claim 15, arguments analogous to claim 2 are applicable.
Regarding claim 17, arguments analogous to claim 4 are applicable.
Claims 3, 10 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Khosla in view of Sayyed et al. (US Patent Application Publication No. 2023/0100899), hereinafter Sayyed.
Regarding claim 3, Khosla discloses the method as claimed in claim 1, but does not specifically disclose: wherein the query is related to a basic input/output system (BIOS) of an information handling system.
Sayyed teaches:
wherein the query is related to a basic input/output system (BIOS) of an information handling system (Paragraph 0036, lines 17-20, "A user 302 may interact with an application 304 of an information handling system at operating system runtime to select one or more BIOS firmware modules for activation.").
Sayyed is considered to be analogous to the claimed invention because it is in the same field of basic input output system (BIOS) management. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Khosla to incorporate the teachings of Sayyed to have the query be related to a basic input/output system (BIOS) of an information handling system under the rationale of a simple substitution of one known element for another to obtain predictable results, where a user interacting with the basic input output system (BIOS) of an information handling system of Sayyed is substituted for the query of Khosla.
Regarding claim 10, arguments analogous to claim 3 are applicable.
Regarding claim 16, arguments analogous to claim 3 are applicable.
Claims 5, 12 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Khosla in view of Srivastava et al. (US Patent Application Publication No. 2026/0087020), hereinafter Srivastava.
Regarding claim 5, Khosla discloses the method as claimed in claim 1, but does not specifically disclose: wherein the processing of the query further includes processing data from a telemetry data store.
Srivastava teaches:
wherein the processing of the query further includes processing data from a telemetry data store (Paragraph 0020, lines 1-7, "In an example, for parsing the user query and one of the one or more data repositories and the one or more additional data repositories, a retrieval-augmented generation (RAG) model may be invoked to fetch particular data, required to respond to the user query, from at least one data repository of the one or more data repositories or the one or more additional repositories."; Paragraph 0035, lines 1-11, "Upon determining that one or more additional data repositories from the plurality of data repositories are to be searched, the query resolution engine 108 may parse the user query and the one or more additional data repositories to retrieve additional data having a context similar to the context of the user query. For instance, in the afore-mentioned example of the query, based on the contextual data, it may be determined that a data repository storing configuration data related to the assets and another data repository storing telemetry data related to the assets should be searched for refining the preliminary response."; Retrieving additional data having a context similar to the context of the user query from a data repository storing telemetry data reads on processing data from a telemetry data store.).
Srivastava is considered to be analogous to the claimed invention because it is in the same field of retrieval augmented generation machine learning models. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Khosla to incorporate the teachings of Srivastava to retrieve additional data having a context similar to the context of the user query from a data repository storing telemetry data. Doing so would allow for efficiently and accurately resolving domain-specific user queries (Srivastava; Paragraph 0013, lines 1-19).
Regarding claim 12, arguments analogous to claim 5 are applicable.
Regarding claim 18, arguments analogous to claim 5 are applicable.
Claim 19 is rejected under 35 U.S.C. 103 as being unpatentable over Khosla in view of George et al. (US Patent Application Publication No. 2026/0073184), hereinafter George.
Regarding claim 19, Khosla discloses the non-transitory computer-readable medium as claimed in claim 14, but does not specifically disclose: wherein the artificial intelligence model is a small language model.
George teaches:
wherein the artificial intelligence model is a small language model (Paragraph 0004, lines 1-14, "According to an embodiment, a method of question answering using enhanced retrieval-augmented generation may include receiving, by a computing system, a user query, pre-processing, by the computing system, the user query to determine whether the user query is associated with malicious intent, retrieving, by the computing system, relevant data from a knowledge base by using a keyword index and a semantic index in response to determining that the user query is not associated with malicious intent, prompting, by the computing system, a large language model to generate an answer to the user query based on only the relevant data retrieved from the knowledge base, and receiving, by the computing system, the answer to the user query from the large language model in response to the prompt."; Paragraph 0009, lines 1-4, "In some embodiments, prompting the large language model to generate the answer to the user query may include generating answer highlights in the relevant data using a small language model (SLM).").
George is considered to be analogous to the claimed invention because it is in the same field of retrieval augmented generation machine learning models. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Khosla to incorporate the teachings of George to use a small language model to generate an answer to a user query that includes answer highlights in the relevant data. Doing so would allow for finding answer highlights very quickly and efficiently (George; Paragraph 0134, lines 1-12).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Pappakrishnan et al. (US Patent No. 12,524,416) teaches an enhanced retrieval-augmented generation (RAG) architecture to achieve higher accuracy and reliability in RAG-based large language model (LLM) applications.
Xie et al. (US Patent Application Publication No. 2026/0127164) teaches a query processing system that uses a knowledge graph for retrieval-augmented generation (RAG) in leveraging a large language model (LLM) to convert user queries to data queries.
Palladino et al. (US Patent Application Publication No. 2026/0072966) teaches a method for performing retrieval augmented generation (RAG) for artificial intelligence (AI) queries through a web gateway.
Mui et al. (US Patent Application Publication No. 2025/0278415) teaches a retrieval augmented generation (RAG) based query reformulation pipeline for a Query and Answer (QA) system.
Qin (US Patent Application Publication No. 2024/0346256) teaches a method for using retrieval augmented artificial intelligence to generate a response to a query.
Lee et al. ("Development of an RAG-Based LLM Chatbot for Enhancing Technical Support Service") teaches a method for implementing a domain-specific retrieval-augmented generation large language model chatbot for software technical support.
Zhang et al ("RAG4ITOps: A Supervised Fine-Tunable and Comprehensive RAG Framework for IT Operations and Maintenance") teaches a framework based on retrieval augmented generation to facilitate the business process of establishing question answering systems for IT operations and maintenance.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to James Boggs whose telephone number is (571)272-2968. The examiner can normally be reached M-F 8:00 AM - 5:00 PM.
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, Daniel Washburn can be reached at (571)272-5551. 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.
/JAMES BOGGS/Examiner, Art Unit 2657
Prosecution Insights