DETAILED ACTION
This Office Action is in response to Applicants’ Application filed on February 5, 2025. Claims 1-20 are pending and presented for examination.
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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 2/5/2025 and 3/13/2026 has considered by the examiner.
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.
Claim(s) 1-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over McCurdy et al (hereinafter, “McCurdy”, U.S. Pub. No. 2025/0117414) in view of Gilon et al (hereinafter, “Gilon”, U.S. Pub. No. 2025
As per claims 1, 8 and 15, McCurdy discloses a method and apparatus comprising:
obtaining a natural language input query related to a technical issue in a network and a natural language description of a set of configuration actions for resolving the technical issue in the network (paragraphs 0029, 0036, 0044 and 0050 discloses obtaining natural-language text strings related to technical issues that includes troubleshooting steps for resolving the user technical issue); and
generating, using a first artificial intelligence (AI) model, a multi-step configuration schema based on the natural language input query and the natural language description of the set of configuration actions (paragraph 0029 discloses a machine-learning language model for generating response useful for providing technical support and resolving the technical support issues), wherein the multi-step configuration schema includes a plurality of configuration actions, each of which is described in a natural language and in a structured form including a function and input parameters for the function (paragraphs 0029 and 0039 discloses a machine-learning language model configured to generate natural-language outputs based on natural-language inputs useful for providing technical support and resolving the technical support issues).
However, McCurdy does not explicitly disclose:
providing the multi-step configuration schema to a second AI model that connects to one or more network devices in the network and executes, on the one or more network devices, the plurality of configuration actions in the multi-step configuration schema to resolve the technical issue in the network.
Gilon discloses a resolution guidance system and method comprising:
providing the multi-step configuration schema to a second AI model that connects to one or more network devices in the network and executes, on the one or more network devices (paragraphs 0059-0060 and 0064-0065 discloses a first large language model (LLM sending input generated to a second LLM for processing the output on a device), the plurality of configuration actions in the multi-step configuration schema to resolve the technical issue in the network (paragraphs 0088 and 0089 discloses a second large language model (LLM) for resolving issues in the network).
Therefore, it would have been obvious to one of ordinary skill in the art at the time of filing to modify McCurdy by incorporating or implementing a second LLM for the purpose of processing the output of the input provided by the first LLM in order to resolve issues of a user in timely and efficient a manner.
As per claims 2, 11 and 16, McCurdy discloses the invention substantially as claims discussed above.
However, McCurdy does not explicitly disclose:
wherein the second AI model is smaller than the first AI model.
Gilon discloses a resolution guidance system and method comprising:
wherein the second AI model is smaller than the first AI model (paragraph 0085 discloses a second large language model being smaller than the large language model).
Therefore, it would have been obvious to one of ordinary skill in the art at the time of filing to modify McCurdy by incorporating or implementing a second LLM for the purpose of processing the output of the input provided by the first LLM in order to resolve issues of a user in timely and efficient a manner.
As per claims 3, 14 and 17, McCurdy discloses: wherein each of the plurality of configuration actions includes an input schema for the input parameters and an output schema for an expected output, and further comprising:
determining, for each of the plurality of configuration actions, whether data for the input parameters is present based on the input schema, wherein the data is extracted from the natural language input query or from an output from performing a preceding configuration action in the multi-step configuration schema (paragraph 0029 discloses a machine-learning language model for generating response useful for providing technical support and resolving the technical support issues and paragraphs 0029 and 0039 discloses a machine-learning language model configured to generate natural-language outputs based on natural-language inputs useful for providing technical support and resolving the technical support issues); and
based on determining that the data is missing at least one value for the input parameters, generating a follow-up query to obtain the at least one value (paragraph 0050 discloses determining any mistakes from the input and generating a natural-language text for further information).
As per claims 4 and 18, McCurdy further discloses:
executing the function to perform a configuration action on the one or more network devices in the network using the input parameters (paragraph 0029); and
generating a network trace output based on executing the function (paragraph 0029).
As per claims 5 and 19, McCurdy further discloses:
iteratively regenerating the multi-step configuration schema based on whether the network trace output matches the output schema (paragraph 0070).
As per claim 6 and 20, McCurdy discloses wherein generating the multi-step configuration schema includes:
for each configuration action, performing a retrieval augmented generation (RAG) based lookup operation to select the function in a vector datastore based on the natural language description, wherein the vector datastore stores function metadata including a plurality of function identifications, each with a corresponding function description, the input parameters, and at least one expected output field (paragraphs 0051 and 0055).
As per claim 7, McCurdy discloses wherein the plurality of configuration actions include at least one of a command line interface function, a data modeling language function, or an application programming interface call and wherein generating the multi-step configuration schema includes:
augmenting the multi-step configuration schema with one or more instructions for processing an output from the function (paragraphs 0014 and 0044); and
refining the multi-step configuration schema by mapping the output from the function to at least one subsequent configuration action of the multi-step configuration schema and by mapping one or more dependencies between the plurality of configuration actions in the multi- step configuration schema (paragraphs 0029 and 0039).
As per claim 9, McCurdy discloses wherein each step in the multi-step configuration schema is further augmented with an expected output field, and further comprising:
generating the response to the troubleshooting query based on matching an output from executing the function in a step of the multi-step configuration schema with the expected output field for the step (paragraph 0029).
As per claim 10, McCurdy further discloses:
generating a trace file based on executing a plurality of functions in the multi-step configuration schema (paragraph 0029); and
adding the trace file to the response for the troubleshooting query (paragraph 0029).
As per claim 12, McCurdy discloses the invention substantially as claims discussed above.
However, McCurdy does not explicitly discloses wherein determining the multi-step configuration schema includes:
selecting, by the second AI model, the multi-step configuration schema from a plurality of multi-step configuration schemas generated by the first AI model, based on the troubleshooting query.
Gilon discloses a resolution guidance system and method comprising:
selecting, by the second AI model, the multi-step configuration schema from a plurality of multi-step configuration schemas generated by the first AI model, based on the troubleshooting query (paragraphs 0088 and 0089 discloses a second large language model (LLM) for resolving issues in the network).
Therefore, it would have been obvious to one of ordinary skill in the art at the time of filing to modify McCurdy by incorporating or implementing a second LLM for the purpose of processing the output of the input provided by the first LLM in order to resolve issues of a user in timely and efficient a manner.
As per claim 13, McCurdy discloses wherein executing the multi-step configuration schema includes:
executing a first operation in the multi-step configuration schema to generate an output (paragraph 0029); and
executing second operation in the multi-step configuration schema based on the output from the first operation (paragraph 0029).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Chawla et al (U.S. Pat. No. 12,524,412) discloses retrieval of structured tabular data in a retrieval-augmented generation (RAG) platform. A natural language query is received through a query agent object rendered within a canvas including interconnected agent objects. A dataset agent object is identified based at least in part on metadata filtering using the natural language query and short metadata. A structured query conforming to structured query language syntax is generated using a large language model (LLM) and executed on the structured data. A response including the result set and dataset agent identifier is generated and transmitted to a downstream agent object for further processing.
Vaughn et al (U.S. Pub. No. 2019/0347117) discloses a system and method for aiding a user in troubleshooting a problem includes extracting one or more entities and actions from a problem statement received from a user computing device, wherein, in response to the extracting: mapping, the one or more entities and actions to one or more images related to the one or more entities and actions, and ordering, the one or more entities and actions into a user action sequence, creating a pictorial sequence of user-taken actions to correct the problem, comparing the pictorial sequence of user-taken actions to correct the problem with a correct pictorial sequence to correct the problem, to identify a correct action that the user failed to perform, and isolating a portion of the correct pictorial sequence that corresponds to the correct action that the user failed to perform, for displaying to the user on the user computing system.
Davlos et (U.S. Pub. No. 2014/0310222) discloses troubleshooting a technical problem on a user device using a network-based remediation platform. Receiving problem statements relating to technical problems associated with a user device, activating a domain of cases, assigning a score for the cases based on a scoring algorithm, and determining one or more remediation actions to suggest based on the score.
Wu et al (U.S. Pub. No. 2024/0235955) discloses a network management system (NMS) that includes one or more processors coupled to memory storing network data. The one or more processors are configured to receive a query identifying a site and determine, based on the network data, a first set of troubleshooting issues for a wide area network (WAN) deployment at the site, a second set of troubleshooting issues for a wireless deployment at the site, and a third set of troubleshooting issues for a wired deployment at the site. The one or more processors are configured to determine, based on a user experience metric, a first troubleshooting issue from the first set of troubleshooting issues for the WAN deployment, a second troubleshooting issue from the second set of troubleshooting issues for the wireless deployment, and a third troubleshooting issue from the third set of troubleshooting issues for the wired deployment.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to LASHONDA T JACOBS-BURTON whose telephone number is (571)272-4004. The examiner can normally be reached M-F 8:30 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, Ario Etienne can be reached at 571-272-4001. 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.
/LASHONDA JACOBS-BURTON/Primary Examiner, Art Unit 2457
ljb
July 18, 2026
Prosecution Insights