DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claims 1-20 have been submitted for examination and are pending further prosecution by the United States Patent & Trademark Office.
Allowable Subject Matter
With respect to independent claim 1, the prior art of record does not teach or suggest, either solely or in combination, the limitations "providing as a first input to a language model: at least a first subset of the first set of the code change context; and a query instructing the language model to generate a response to the first code change explanation request based on the first subset of the first set of the code change context; receiving a first natural language output from the language model responsive to the first input; generating a first code change explanation response based on the first natural language output received from the language model;" when considered in combination with the other limitations of claim 1.
With respect to independent claim 11, the prior art of record does not teach or suggest, either solely or in combination, the limitations "providing, as a first input to a language model: at least a first subset of the first set of the code change context; and a query instructing the language model to generate a response to the first code change explanation request based on the first subset of the first set of the code change context; receiving a first natural language output from the language model responsive to the first input; generating a first code change explanation response based on the first natural language output received from the language model;" when considered in combination with the other limitations of claim 11.
With respect to independent claim 16, the prior art of record does not teach or suggest, either solely or in combination, the limitations "providing, as a first input to a language model: at least a first subset of the first set of the code change context; and a query instructing the language model to generate a response to the first code change explanation request based on the first subset of the first set of the code change context; receiving a first natural language output from the language model responsive to the first input; generating a first code change explanation response based on the first natural language output received from the language model;" when considered in combination with the other limitations of claim 16.
However, claims 1-3, 5-7, 9, 11-14 and 16-20 are rejected under 35 U.S.C. 101 as being directed to an abstract idea (see below).
Claims 4, 8, 10 and 15 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Specification
The abstract of the disclosure is objected to because of an informality. It is suggested that Applicant amend the abstract as follows:
-- A system and method for automatically generating a change history of source code using a generative artificial intelligence ("AI") system. In examples, a generative AI system receives a request inquiring about one or more changes made to software code of a software service or application. In response to receiving the request, the generative AI system navigates one or more information sources to collect code change context relevant to history of the code change(s). The generative AI system generates an instruction corresponding to the received request, where the instruction and the code change context are provided as input to a language model (LM) (e.g., a generative AI model). Based on the inquiry of the request, the LM processes the input, generates, and provides a corresponding output. The generative AI system then uses the output to generate and provide an explanation about the code change(s) to a requestor of the request. --
Applicant is reminded of the proper language and format for an abstract of the disclosure.
The abstract should be in narrative form and generally limited to a single paragraph on a separate sheet within the range of 50 to 150 words. It is important that the abstract not exceed 150 words in length since the space provided for the abstract on the computer tape used by the printer is limited. The form and legal phraseology often used in patent claims, such as "means" and "said," should be avoided. The abstract should describe the disclosure sufficiently to assist readers in deciding whether there is a need for consulting the full patent text for details.
The language should be clear and concise and should not repeat information given in the title. It should avoid using phrases which can be implied, such as, "The disclosure concerns," "The disclosure defined by this invention," "The disclosure describes," etc.
When re-submitted, the new abstract must be in a separate sheet, apart from other sheets.
Correction is required. See MPEP § 608.01(b).
Claim Objections
The following claims are objected to because of antecedence issues. It is suggested Applicants amend these claims as follows:
Claim 5
-- a pull request associated with a [[the]] commit included in the pull request database; --
-- an issue associated with a [[the]] pull request included in the issue database; --
-- a work item associated with a [[the]] pull request included in the work item database; --
Claim 13
-- a pull request associated with a [[the]] commit included in the pull request database; --
-- an issue associated with a [[the]] pull request included in the issue database; --
-- a work item associated with a [[the]] pull request included in the work item database; --
Claim 20
-- a pull request associated with a [[the]] commit included in the pull request database; --
-- an issue associated with a [[the]] pull request included in the issue database; --
-- a work item associated with a [[the]] pull request included in the work item database; --
Claims 6-8 and 14 are also objected to due to their dependence on objected base claim(s).
Appropriate correction is required.
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 1-3, 5-7, 9, 11-14 and 16-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. Claim 1 recites a system for providing a code change explanation response to a requestor of a code change explanation request. Given its broadest reasonable interpretation, claim 1 would fall under the category of mental processes as the claim features limitations performable as mental steps, but without additional elements that integrate the abstract idea into a practical application or amount to significantly more than the abstract idea. An analysis of claim 1 according to the 2019 Revised Patent Subject Matter Eligibility test follows:
Step 1: Is the claim directed to a process, machine, manufacture or composition of matter?
Yes, claim 1 is directed to a system and, therefore, a machine.
Step 2A Prong 1: Does the claim recite an Abstract Idea, Law of Nature, or Natural Phenomenon?
Yes, claim 1 recites an abstract idea as the following limitations are performable as mental processes: receiving an indication of a first code change explanation request in relation to a code change to a portion of a software code file; - A first developer can ask a second developer why a particular function in a source code file was changed; executing a first search for code change context relevant to the first code change explanation request; - The second developer can identify information that may help answer the first developer's query; collecting, from one or more information sources, a first set of the code change context relevant to the first code change explanation request; - The second developer can collect data from an information source, such as a printed pull request from a pull request database, pertaining to the changed function; generating a first code change explanation response - After analyzing the data from the information source, the second developer can provide to the first developer an answer as to why the particular function was changed.
Step 2A Prong 2: Does the Claim Recite Additional Elements That Integrate The Judicial Exception Into A Practical Application?
Claim 1 recites the following additional elements: A system, a processing system, and memory comprising computer executable instructions: -- However, these additional elements simply amount to using a computer as a tool to perform the abstract idea and, therefore, do not integrate the abstract idea into a practical application.
Claim 1 also recites the following additional elements: providing as a first input to a language model: at least a first subset of the first set of the code change context; and a query instructing the language model to generate a response to the first code change explanation request based on the first subset of the first set of the code change context; receiving a first natural language output from the language model responsive to the first input. - However, since no detail is provided regarding how the language model generates a first natural language output based upon the first input, these additional elements simply amount to employing a generic machine learning technique to generate a prediction. Thus, the additional elements amount to using generic instructions for implementing the abstract idea on a computer. Consequently, these additional elements do not integrate the judicial exception into a practical application.
Claim 1 also recites the following additional element generating a first code change explanation response based on the first natural language output received from the language model. - However, simply generating a response based on the natural language output of the language model amounts to an insignificant post-solution activity in the form of data outputting. Therefore, the additional element does not integrate the judicial exception into a practical application.
Step 2B: Does the Claim Recite Additional Elements That Amount To Significantly More Than The Judicial Exception?
Claim 1 recites the following additional elements: A system, a processing system; and memory comprising computer executable instructions: -- However, these additional elements simply amount to using a computer as a tool to perform the abstract idea and, therefore, are not significantly more than the abstract idea.
Claim 1 also recites the following additional elements: providing as a first input to a language model: at least a first subset of the first set of the code change context; and a query instructing the language model to generate a response to the first code change explanation request based on the first subset of the first set of the code change context; receiving a first natural language output from the language model responsive to the first input. - However, since no detail is provided regarding how the language model generates a first natural language output based upon the first input, these additional elements simply amount to employing a generic machine learning technique to generate a prediction. Thus, the additional elements amount to using generic instructions for implementing the abstract idea on a computer. Consequently, these additional elements are not significantly more than the abstract idea.
Claim 1 also recites the following additional element generating a first code change explanation response based on the first natural language output received from the language model. - However, simply generating a response based on the natural language output of a language model amounts to an insignificant post-solution activity in the form of data outputting, which is a well-understood, routine and conventional activity (see WO 2025072919 A1; [0061]). Therefore, the additional element is not significantly more than the abstract idea.
Claim 11, which recites a method for performing the system of claim 1, is rejected for the same reasons given for claim 1 as the claims recite analogous limitations.
Claim 16, which recites a device for performing the system of claim 1, is rejected for the same reasons given for claim 1 as the claims recite analogous limitations. While claim 16 further recites the additional elements of a device, a processing system, and memory comprising computer executable instructions, these additional elements do not integrate the abstract idea into a practical application or amount to significantly more than the abstract idea as they simply amount to using a computer as a tool to perform the abstract idea.
Claims 2, 12 and 17 are also directed to the abstract idea as the claims simply recite an additional iteration of the request/response operations recited by independent claims 1, 11 and 16, respectively, without further additional elements that integrate the abstract idea into a practical application or amount to significantly more than the abstract idea.
Claims 3 and 18 are also directed to the abstract idea as the claims simply recite a minor variation of the steps performed by their respective base claims without reciting further additional elements that integrate the abstract idea into a practical application or amount to significantly more than the abstract idea.
Claims 5 and 13 are also directed to the abstract idea as the claims simply elaborate upon limitations found abstract in independent claims 1 and 11, respectively, without reciting further additional elements that integrate the abstract idea into a practical application or amount to significantly more than the abstract idea.
Claims 6 and 14 are also directed to the abstract idea as the second developer can manually collect at least "a pull request description included in the pull request;" by reading said description. Since the claims do not recite additional elements that integrate the abstract idea into a practical application or amount to significantly more than the abstract idea, the claims are ineligible.
Claim 7 recites the additional element of "wherein executing the first search comprises using at least one code navigation tool to access the code change context, the at least one code navigation tool including: ...a pull request interface;". However, using a pull request interface to search for a pull request, which can be located manually, simply amounts to using generic computing instructions to implement the abstract idea as the pull request interface is recited at a high level of generality. Therefore, the additional element does not integrate the abstract idea into a practical application or amount to significantly more than the abstract idea.
Claim 9 recites the additional element of "wherein the language model is a generative artificial intelligence (AI) model". However, the additional element still amounts to employing a generic machine learning technique to generate a prediction as no detail is recited regarding how the generative AI model generates a first natural language output based upon the first input. Therefore, the additional element does not integrate the abstract idea into a practical application or amount to significantly more than the abstract idea.
Claim 19 is also directed to the abstract idea as the following limitations are performable as mental processes: receiving feedback from the requester about the first code change explanation response; -- the first developer can provide feedback to the second developer regarding the answer as to why the particular function was changed; providing the second code change explanation response to the requestor. - the second developer can provide an updated answer as to why the particular function was changed to the first developer. Claim 19 also recites the following additional elements: providing the feedback to the language model; receiving a second natural language output from the language model responsive to the feedback; - However, since no detail is provided regarding how the language model generates the second natural language output based upon the feedback, these additional elements simply amount to employing a generic machine learning technique to generate a prediction. Thus, the additional elements amount to using generic instructions for implementing the abstract idea on a computer. Consequently, these additional elements do not integrate the judicial exception into a practical application or amount to significantly more than the abstract idea. Claim 19 also recites the additional element generating a second code change explanation response based on the second natural language output received from the language model. - However, simply generating a response based on a natural language output of a language model amounts to an insignificant post-solution activity in the form of data outputting. Therefore, the additional element does not integrate the judicial exception into a practical application. This additional element is also a well-understood, routine and conventional activity (see WO 2025072919 A1; [0061]) and, therefore, is not significantly more than the abstract idea.
Claim 20 is also directed to the abstract idea as the limitation "wherein: executing the first search comprises collecting the code change context from one or more information sources, the one or more information sources including: ...a pull request database;" simply elaborates upon limitations found abstract in base claim 16 without reciting additional elements. With respect to the limitation "the code change context comprises natural language text of one or more of: ...a pull request description included in the pull request;", the second developer can manually collect this natural language text by reading said description. Since the claim does not recite additional elements that integrate the abstract idea into a practical application or amount to significantly more than the abstract idea, the claim is ineligible.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. US 12487875 B1 discloses a computer-implemented method in an incident management system for automatically generating a remediation for an incident associated with a computer system, whereby a notification of the incident associated with the computer system is received, such as from a conversational agent based on a chat conversation, an error message is extracted from the notification, recent code changes are collected and matched to natural language representations of the error message by generating prompts to a large language model (LLM) to explain the code change, explain the error, and query the LLM as to whether the change is related to the error, and if so, automatically generate instructions that can be applied to the computer system to remediate or correct the incident. US 20240004638 A1 discloses a method and system for detecting whether a commit in a code repository contains code for fixing a software vulnerability, said method and system enabling the semantic meaning of a code change to be understood and used to classify the purpose of the code change. The NPL document "Toward Better Understanding and Documentation of Rationale for Code Changes" explores the rationale for code changes. The NPL document "Large-scale intent analysis for identifying large-review-effort code changes" presents the first study to leverage change intent to characterize and identify Large-Review-Effort (LRE) changes—changes with large review effort.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to GEOFFREY R ST LEGER whose telephone number is (571)270-7720. The examiner can normally be reached M-F (IFP) ~9:00-5:00 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, Hyung S Sough can be reached at 571-272-6799. 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.
/GEOFFREY R ST LEGER/Primary Examiner, Art Unit 2192