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 .
Claims 1, 3-20 are presented for examination.
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 1,3-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Claim 1 as drafted, recite a process that, under its broadest reasonable interpretation, covers steps that could reasonably be performed in the mind, including with the aid of pen and paper, but for the recitation of generic computer components. That is, the limitation “generate a model prompt to be input into a large language model, the model prompt including at least a portion of the commit message data corresponding with the start commit through the end commit” as drafted, is a process that, under its broadest reasonable interpretation, recite the abstract idea of mental processes. These limitations encompass a human mind carrying out these functions through observation, evaluation, judgment and/or opinion, or even with the aid of pen and paper. Thus, these limitations recite and fall within the “Mental Processes” grouping of abstract ideas.
This judicial exception is not integrated into a practical application. The claims recites the following additional elements “a computing system” “a processor,” “computer storage memory,” “to be input into a large language model,” “as output from the large language model,” and “obtain, via a user interface, an indication of a first commit message as a start commit and an indication of a second commit message as an end commit associated with code;” “extract commit message data only for a subset of commit messages occurring between the start commit and the end commit, wherein each commit message comprises a description associated with a corresponding modification in the code,” “obtain, as output from the large language model, a code development summary to provide for display via a user device, the code development summary summarizing the at least the portion of the commit message data for the set of commit messages associated with the code”. The additional elements “a computing system” “a processor,” “computer storage memory,” “to be input into a large language model,” “as output from the large language model,” are merely instructions to implement an abstract idea on a computer, or merely using a generic computer or computer components as a tool to perform the abstract idea. See MPEP 2106.05(f). The additional element “obtain, via a user interface, an indication of a first commit message as a start commit and an indication of a second commit message as an end commit associated with code;” “extract commit message data only for a subset of commit messages occurring between the start commit and the end commit,” “obtain, as output from the large language model, a code development summary to provide for display via a user device” does nothing more than add insignificant extra solution activity to the judicial exception, such as data gathering and outputting the results of the abstract idea, to perform a task. See MPEP 2106.05(g). Accordingly, the additional elements recited in the claims do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea, thus fail to integrate the abstract idea into a practical application.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element “a computing system” “a processor,” “computer storage memory,” “to be input into a large language model,” “as output from the large language model,” are generic computer components and instructions used as the tools to perform the abstract idea. See MPEP 2106.05(f). As to the additional element “obtain, via a user interface, an indication of a first commit message as a start commit and an indication of a second commit message as an end commit associated with code,” and “obtain, as output from the large language model, a code development summary to provide for display via a user device,” the courts have identified gathering data and displaying the output of the abstract idea is well-understood, routine, conventional activity. See MPEP 2106.05(d). Accordingly, the additional elements recited in the claims cannot provide an inventive concept. Thus, the claims are not patent eligible.
Claim 3 recites the additional element “wherein the operations further comprise receiving a user selection of the start commit and the end commit” which does nothing more than add insignificant extra solution activity to the judicial exception, such as data gathering and outputting the results of the abstract idea, to perform a task. See MPEP 2106.05(g). Accordingly, the additional elements recited in the claims do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea, thus fail to integrate the abstract idea into a practical application. The courts have identified gathering data and displaying the output of the abstract idea is well-understood, routine, conventional activity. See MPEP 2106.05(d). Accordingly, the additional elements recited in the claims cannot provide an inventive concept. Thus, the claims are not patent eligible.
Claim 4 recites the additional element “wherein the start commit corresponds with a start of a new release of the code, and the end commit corresponds with an end of the new release of the code” which further defines the data gathering set forth in the claim from which it depends, thus, are also considered to do nothing more than add insignificant extra solution activity to the judicial exception, such as data gathering and outputting the results of the abstract idea, to perform a task, which do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. See MPEP 2106.05(g). Further, the courts have identified gathering data and displaying the output of the abstract idea is well-understood, routine, conventional activity. See MPEP 2106.05(d). Accordingly, the additional elements recited in the claims cannot provide an inventive concept. Thus, the claims are not patent eligible.
Claim 5 as drafted, recite a process that, under its broadest reasonable interpretation, covers steps that could reasonably be performed in the mind, including with the aid of pen and paper, but for the recitation of generic computer components. That is, the limitation “preprocessing the commit message data for including in the model prompt, wherein the preprocessing comprises removing or filtering undesired commit message data” as drafted, is a process that, under its broadest reasonable interpretation, recite the abstract idea of mental processes. These limitations encompass a human mind carrying out these functions through observation, evaluation, judgment and/or opinion, or even with the aid of pen and paper. Thus, these limitations recite and fall within the “Mental Processes” grouping of abstract ideas.
Claim 6 as drafted, recite a process that, under its broadest reasonable interpretation, covers steps that could reasonably be performed in the mind, including with the aid of pen and paper, but for the recitation of generic computer components. That is, the limitation “wherein the at least the portion of the commit message data is determined in accordance with an input prompt size constraint associated with the large language model” as drafted, is a process that, under its broadest reasonable interpretation, recite the abstract idea of mental processes. These limitations encompass a human mind carrying out these functions through observation, evaluation, judgment and/or opinion, or even with the aid of pen and paper. Thus, these limitations recite and fall within the “Mental Processes” grouping of abstract ideas.
Claim 7 further define the “model prompt” as part of the “generating” function set forth in the claims from which they depend, thus, are also considered to recite a mental process that can be reasonably carried out through observation, evaluation, judgment and/or opinion, or even with the aid of pen and paper.
Claim 8 recites the additional element “storing the code development summary that summarizes the at least the portion of the commit message data; and in response to a request for the code development summary, providing at least a portion of the code development summary for display” which does nothing more than add insignificant extra solution activity to the judicial exception, such as data gathering and outputting the results of the abstract idea, to perform a task. See MPEP 2106.05(g). Accordingly, the additional elements recited in the claims do not integrate the abstract idea into a practical application. The courts have identified gathering data and displaying the output of the abstract idea is well-understood, routine, conventional activity. See MPEP 2106.05(d). Accordingly, the additional elements recited in the claims cannot provide an inventive concept. Thus, the claims are not patent eligible.
Claim 9 as drafted, recite a process that, under its broadest reasonable interpretation, covers steps that could reasonably be performed in the mind, including with the aid of pen and paper, but for the recitation of generic computer components. That is, the limitation “identifying a pull request identifier in a commit message of the set of commit messages” as drafted, is a process that, under its broadest reasonable interpretation, recite the abstract idea of mental processes. These limitations encompass a human mind carrying out these functions through observation, evaluation, judgment and/or opinion, or even with the aid of pen and paper. Thus, these limitations recite and fall within the “Mental Processes” grouping of abstract ideas.
This judicial exception is not integrated into a practical application. The claims recites the following additional elements “obtaining information associated with the pull request identifier; and including the information associated with the pull request identifier in the commit message data” which does nothing more than add insignificant extra solution activity to the judicial exception, such as data gathering and outputting the results of the abstract idea, to perform a task. See MPEP 2106.05(g). Further for these additional elements the courts have identified gathering data and displaying the output of the abstract idea is well-understood, routine, conventional activity. See MPEP 2106.05(d). Accordingly, the additional elements recited in the claims cannot provide an inventive concept. Thus, the claims are not patent eligible.
Claim 10 further defines “code development summary” as part of the “obtaining” function set forth in the claims from which they depend, thus, are also considered to do nothing more than add insignificant extra solution activity to the judicial exception, such as data gathering and outputting the results of the abstract idea, to perform a task, which do not integrate the abstract idea into a practical application. See MPEP 2106.05(g). Further, the courts have identified gathering data and displaying the output of the abstract idea is well-understood, routine, conventional activity. See MPEP 2106.05(d). Accordingly, the additional elements recited in the claims cannot provide an inventive concept. Thus, the claims are not patent eligible.
Claim 11 as drafted, recite a process that, under its broadest reasonable interpretation, covers steps that could reasonably be performed in the mind, including with the aid of pen and paper, but for the recitation of generic computer components. That is, the limitation “automatically selecting a set of commit messages corresponding with a code based on at least one criteria” as drafted, is a process that, under its broadest reasonable interpretation, recite the abstract idea of mental processes. These limitations encompass a human mind carrying out these functions through observation, evaluation, judgment and/or opinion, or even with the aid of pen and paper. Thus, these limitations recite and fall within the “Mental Processes” grouping of abstract ideas.
This judicial exception is not integrated into a practical application. The claims recites the following additional elements “being generated via a trained large language model” “via a graphical user interface,” and “providing a request to generate a code development summary in association with the set of commit messages selected based on the at least one criteria, the request including at least a portion of the set of commit messages that occur between a start commit message and an end commit message,” “obtaining the code development summary representing the set of commit messages corresponding with the code,” and “causing display, via a graphical user interface, of the code development summary in association with the code”. The additional elements “being generated via a trained large language model” “via a graphical user interface,” are merely instructions to implement an abstract idea on a computer, or merely using a generic computer or computer components as a tool to perform the abstract idea. See MPEP 2106.05(f). The additional element “providing a request to generate a code development summary...the request including at least a portion of the set of commit messages that occur between a start commit message and an end commit message,” and “causing display, via a graphical user interface, of the code development summary in association with the code” does nothing more than add insignificant extra solution activity to the judicial exception, such as data gathering and outputting the results of the abstract idea, to perform a task. See MPEP 2106.05(g). Accordingly, the additional elements recited in the claims do not integrate the abstract idea into a practical application.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above, the additional elements “being generated via a trained large language model” “via a graphical user interface,” are generic computer components and instructions used as the tools to perform the abstract idea. See MPEP 2106.05(f). As to the extra solution elements, the courts have identified gathering data and displaying the output of the abstract idea is well-understood, routine, conventional activity. See MPEP 2106.05(d). Accordingly, the additional elements recited in the claims cannot provide an inventive concept. Thus, the claims are not patent eligible.
Claim 12 as drafted, recite a process that, under its broadest reasonable interpretation, covers steps that could reasonably be performed in the mind, including with the aid of pen and paper, but for the recitation of generic computer components. That is, the limitation “preprocessing a plurality of commit messages corresponding with the code to remove one or more commit messages; wherein the set of commit messages is selected from the preprocessed plurality of commit messages” as drafted, is a process that, under its broadest reasonable interpretation, recite the abstract idea of mental processes. These limitations encompass a human mind carrying out these functions through observation, evaluation, judgment and/or opinion, or even with the aid of pen and paper. Thus, these limitations recite and fall within the “Mental Processes” grouping of abstract ideas.
Claims 13-14 further define the “request” function set forth in the claims from which they depend, thus, are also considered to recite a mental process that can be reasonably carried out through observation, evaluation, judgment and/or opinion, or even with the aid of pen and paper.
Claim 15 as drafted, recite a process that, under its broadest reasonable interpretation, covers steps that could reasonably be performed in the mind, including with the aid of pen and paper, but for the recitation of generic computer components. That is, the limitation “generating the request that includes the at least the portion of the set of commit messages that occur between the start commit message and the end commit message” as drafted, is a process that, under its broadest reasonable interpretation, recite the abstract idea of mental processes. These limitations encompass a human mind carrying out these functions through observation, evaluation, judgment and/or opinion, or even with the aid of pen and paper. Thus, these limitations recite and fall within the “Mental Processes” grouping of abstract ideas.
This judicial exception is not integrated into a practical application. The claims recites the following additional elements “inputting the request into the trained large language model to generate the code development summary representing the set of commit messages,” which are merely instructions to implement an abstract idea on a computer, or merely using a generic computer or computer components as a tool to perform the abstract idea. See MPEP 2106.05(f). Accordingly, the additional elements recited in the claims do not integrate the abstract idea into a practical application, and cannot provide an inventive concept. Thus, the claims are not patent eligible.
Claim 16 as drafted, recite a process that, under its broadest reasonable interpretation, covers steps that could reasonably be performed in the mind, including with the aid of pen and paper, but for the recitation of generic computer components. That is, the limitation “generating, using the trained large language model, a code development summary that summarizes the code modification data associated with the code in accordance with the target audience and the subset of the commit messages” as drafted, is a process that, under its broadest reasonable interpretation, recite the abstract idea of mental processes. These limitations encompass a human mind carrying out these functions through observation, evaluation, judgment and/or opinion, or even with the aid of pen and paper. Thus, these limitations recite and fall within the “Mental Processes” grouping of abstract ideas.
This judicial exception is not integrated into a practical application. The claims recites the following additional elements “one or more computer storage media” “one or more processors” “at a trained large language model” “using the trained large language model,” and “obtaining, at a trained large language model, a model prompt that includes an indication of a target audience for viewing a summary related to code development and code modification data associated with code, wherein the code modification data comprises a description associated with a corresponding modification in the code, and wherein the model prompt includes a subset of commit messages that occur between a start commit message and an end commit message,” “providing the code development summary to a data store for subsequent presentation”. The additional elements “one or more computer storage media” “one or more processors” “at a trained large language model” “using the trained large language model,” are merely instructions to implement an abstract idea on a computer, or merely using a generic computer or computer components as a tool to perform the abstract idea. See MPEP 2106.05(f). The additional element “obtaining, at a trained large language model, a model prompt that includes an indication of a target audience...and wherein the model prompt includes a subset of commit messages that occur between a start commit message and an end commit message,” “providing the code development summary to a data store for subsequent presentation” does nothing more than add insignificant extra solution activity to the judicial exception, such as data gathering and outputting the results of the abstract idea, to perform a task. See MPEP 2106.05(g). Accordingly, the additional elements recited in the claims do not integrate the abstract idea into a practical application.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above, the additional element “one or more computer storage media” “one or more processors” “at a trained large language model” “using the trained large language model,” are generic computer components and instructions used as the tools to perform the abstract idea. See MPEP 2106.05(f). As to the extra solution elements, the courts have identified gathering data and displaying the output of the abstract idea is well-understood, routine, conventional activity. See MPEP 2106.05(d). Accordingly, the additional elements recited in the claims cannot provide an inventive concept. Thus, the claims are not patent eligible.
Claim 17 further defines “model prompt” as part of the “obtaining” function set forth in the claims from which they depend, thus, are also considered to do nothing more than add insignificant extra solution activity to the judicial exception, such as data gathering and outputting the results of the abstract idea, to perform a task, which do not integrate the abstract idea into a practical application. See MPEP 2106.05(g). Further, the courts have identified gathering data and displaying the output of the abstract idea is well-understood, routine, conventional activity. See MPEP 2106.05(d). Accordingly, the additional elements recited in the claims cannot provide an inventive concept. Thus, the claims are not patent eligible.
Claims 18-19 further defines “target audience” as part of the “obtaining” function set forth in the claims from which they depend, thus, are also considered to do nothing more than add insignificant extra solution activity to the judicial exception, such as data gathering and outputting the results of the abstract idea, to perform a task, which do not integrate the abstract idea into a practical application. See MPEP 2106.05(g). Further, the courts have identified gathering data and displaying the output of the abstract idea is well-understood, routine, conventional activity. See MPEP 2106.05(d). Accordingly, the additional elements recited in the claims cannot provide an inventive concept. Thus, the claims are not patent eligible.
Claim 20 recites the additional element “providing the code development summary for display based on a request to view the code development summary” which does nothing more than add insignificant extra solution activity to the judicial exception, such as data gathering and outputting the results of the abstract idea, to perform a task. See MPEP 2106.05(g). Accordingly, the additional elements recited in the claims do not integrate the abstract idea into a practical application. The courts have identified gathering data and displaying the output of the abstract idea is well-understood, routine, conventional activity. See MPEP 2106.05(d). Accordingly, the additional elements recited in the claims cannot provide an inventive concept. Thus, the claims are not patent eligible.
Claim Rejections - 35 USC § 112
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 1 and 3-10 are rejected under 35 U.S.C. 112(b) as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor regards as the invention.
Regarding Claim 1, the claim recites in the final “obtain” limitation “the code development summary summarizing the at least the portion of the commit message data for the set of commit messages associated with the code.” There is insufficient antecedent basis for the limitation “the set of commit messages” in the claim. By way of the present amendment, the earlier “extract” limitation was amended to recite “extract commit message data only for a subset of commit messages occurring between the start commit and the end commit,” such that the claim now introduces “a subset of commit messages” rather than “a set of commit messages.” Consequently, it cannot be determined whether “the set of commit messages” refers to the previously recited “subset of commit messages,” to some broader set of commit messages from which the subset is drawn, or to a different grouping of commit messages altogether. Because the metes and bounds of the claim cannot be determined with reasonable certainty, the claim is indefinite. See Nautilus, Inc. v. Biosig Instruments, Inc., 572 U.S. 898 (2014).
Claims 3-10 are rejected under 35 U.S.C. 112(b) as depending from a rejected base claim and failing to resolve the indefiniteness noted above with respect to claim 1. Appropriate correction, for example amending “the set of commit messages” to recite “the subset of commit messages,” or otherwise reconciling the recited groupings, is required. Examiner notes that this rejection is directed to the form of the claim language and not to the patentability of any underlying subject matter.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 1 and 6-10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Hutchins (US 20210326536A1) in view of Smith (US 9557968B1), further in view of Farrier (US 11662997B2), further in view of Mosquera (US 11030071B2).
Regarding Claim 1, Hutchins (US 20210326536A1) teaches
A computing system comprising: a processor; and computer storage memory having computer-executable instructions stored thereon which, when executed by the processor, configure the computing system to perform operations comprising:
generate a model prompt to be input into a large language model (Claim 8, "making a call to an artificial intelligence (AI) platform, wherein the call contains the text block concatenated from the texts extracted from the main body of the content and specifies a summarization component of the AI platform, a sentiment analyzer component of the AI platform, and a summarization range") Examiner Comments: The call to the AI platform acts as a model prompt to the large language model, including a text portion for summarization.
obtain, as output from the large language model, a code development summary summarizing the at least the portion of the commit message data for the set of commit messages associated with the code (Claim 8, "wherein the text block is processed by the summarization component of the AI platform according to the summarization range so as to produce a summary of the text block in the summarization range") Examiner Comments: The AI platform outputs a summary of the text block portion, reading on obtaining a code development summary as output from the large language model.
Hutchins did not specifically teach
obtain, via a user interface, an indication of a first commit message as a start commit and an indication of a second commit message as an end commit associated with code;
extract commit message data only for a subset of commit messages occurring between the start commit and the end commit, wherein each commit message comprises a description associated with a corresponding modification in the code;
the model prompt including at least a portion of the commit message data corresponding with the start commit through the end commit;
a code development summary to provide for display via a user device.
However, Smith (US 9557968B1) teaches
obtain, via a user interface, an indication of a first commit message as a start commit and an indication of a second commit message as an end commit associated with code (Col 6: ln 46-56, "in 600 a merge base of a first code branch and a second code branch is determined. In 602, a first code branch commit is selected. For example, data for the first code branch is received and a most recent first commit data is selected") Examiner Comments: Smith teaches determining a merge base commit that bounds the start of a range and selecting a most recent commit that bounds the end of the range for a code branch, and, as further shown at the Abstract, "a user interface determiner for determining a display of the first set of commits and the second set of commits," so that the two boundary commits and the resulting commits are obtained and presented through a user interface, which reads on obtaining, via a user interface, an indication of a first commit as a start commit and an indication of a second commit as an end commit associated with code.
extract commit message data only for a subset of commit messages occurring between the start commit and the end commit (Col 6: ln 60-66, "the first code branch commit is added to a first branch data ... so the first branch data comprises a first set of commits in a first code branch that are not common to a second code branch") Examiner Comments: Smith teaches walking the commit history from the most recent commit back to the merge base and collecting into the branch data only the subset of commits located between those two boundaries, that is, the first set of commits not common to the second branch (see also Claim 3, Col 10: ln 51-54, "the version control system provides the system for comparing code branches with a subset of the first set of commits and a subset of the second set of commits"), which reads on extracting commit message data only for a subset of commit messages occurring between the start commit and the end commit.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Hutchins in view of Smith in order to apply the summarization taught by Hutchins to a specific, bounded set of commits identified between two selected points in a code history, because Smith recognizes that it can be difficult for a developer to keep track of the changes happening to the main code repository while working on a checked out branch (Smith, Col 1: ln 16-18).
Hutchins and Smith did not specifically teach
wherein each commit message comprises a description associated with a corresponding modification in the code;
the model prompt including at least a portion of the commit message data.
However, Farrier (US 11662997B2) teaches
wherein each commit message comprises a description associated with a corresponding modification in the code (Col 6: ln 17-25, "The term 'commit message' refers to the messages submitted by one or more developers during a commit, and the central repository in which the messages are stored. Typically when a developer commits a change to a central code repository, they do so with a brief, timestamped commit message explaining the change") Examiner Comments: Farrier explicitly defines commit messages as descriptions associated with code modifications, where each commit message explains the corresponding change.
the model prompt including at least a portion of the commit message data (Col 2: ln 10-30, "analyzing the commit message and calculating one or more parameters of the commit message, training a machine learning classifier with the set of data comprising the type of commit, the set of areas modified, the causing commit, and the commit message") Examiner Comments: Farrier processes commit message data as input for machine learning analysis, reading on including at least a portion of the commit message data for processing.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Hutchins and Smith in view of Farrier in order to to use the commit messages within the subset identified by Smith, each understood in view of Farrier to describe its corresponding code modification, as the text supplied to the large language model of Hutchins for summarization, because doing so provides the model with concise, developer-authored descriptions of the code changes and thereby yields a more accurate and meaningful code development summary (Farrier [Summary]).
Hutchins, Smith and Farrier did not specifically teach
a code development summary to provide for display via a user device.
However, Mosquera (US 11030071B2) teaches
a code development summary to provide for display via a user device (Col 12: ln 10-67, "FIG. 9A shows an exemplary dashboard 900 with statistics and metrics collected by the continuous deployment platform and its integrations to provide actionable insights regarding the software development lifecycle") Examiner Comments: Mosquera teaches providing the resulting code development information for display on a dashboard presented at a user device, reading on providing the summary for display via a user device.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Hutchins, Smith and Farrier in view of Mosquera in order to provide the generated code development summary for display on the dashboard of Mosquera at a user device so that developers and other stakeholders could review the summarized commit information together with the other software development metrics in a single, centralized interface, thereby increasing the efficiency and convenience with which the summarized code changes are reviewed (Mosquera [Summary]).
Regarding Claim 6, Hutchins, Smith, Farrier and Mosquera teach
The computing system of Claim 1.
Hutchins further teaches wherein the at least the portion of the commit message data is determined in accordance with an input prompt size constraint associated with the large language model (Claim 4, "wherein the call contains the adjusted summarization range, wherein the text block is processed by the summarization component of the AI platform according to the adjusted summarization range so as to produce a modified summary of the text block in the adjusted summarization range") Examiner Comments: The summarization range constrains the input size for the AI processing, reading on an input prompt size constraint.
Regarding Claim 7, Hutchins, Smith, Farrier and Mosquera teach
The computing system of Claim 1.
Hutchins further teaches wherein the model prompt includes an indication of a type of audience for which the code development summary is to be generated (Claim 7, "wherein the call further specifies a knowledge base or taxonomy for processing the text block concatenated by the summarizer from the texts extracted from the main body of the content") Examiner Comments: The specified knowledge base or taxonomy indicates a context akin to an audience type for tailored summarization.
Regarding Claim 8, Hutchins, Smith, Farrier and Mosquera teach
The computing system of Claim 1.
Mosquera further teaches wherein the operations further comprise: storing the code development summary that summarizes the at least the portion of the commit message data; and in response to a request for the code development summary, providing at least a portion of the code development summary for display (Mosquera, Col 12: ln 10-67, "FIG. 9A shows an exemplary dashboard 900 with statistics and metrics collected by the continuous deployment platform and its integrations to provide actionable insights regarding the software development lifecycle") Examiner Comments: Mosquera stores and displays summaries of code changes via dashboards in response to requests.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Hutchins, Smith and Farrier in view of Mosquera in order to provide the generated code development summary for display on the dashboard of Mosquera at a user device so that developers and other stakeholders could review the summarized commit information together with the other software development metrics in a single, centralized interface, thereby increasing the efficiency and convenience with which the summarized code changes are reviewed (Mosquera [Summary]).
Regarding Claim 9, Hutchins, Smith, Farrier and Mosquera teach
The computing system of Claim 1.
Mosquera further teaches wherein the operations further comprise: identifying a pull request identifier in a commit message of the set of commit messages; obtaining information associated with the pull request identifier; and including the information associated with the pull request identifier in the commit message data (Mosquera, Col 14: ln 38-50, "The intelligent chatbot creates and sends a message indicating that the compliance with SLA has decreased and therefore presents a risk. It also shows the latest pull request that caused the SLA to decrease") Examiner Comments: Mosquera identifies and obtains pull request information linked to commits and includes it in the presented data.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Hutchins, Smith and Farrier in view of Mosquera in order to provide the generated code development summary for display on the dashboard of Mosquera at a user device so that developers and other stakeholders could review the summarized commit information together with the other software development metrics in a single, centralized interface, thereby increasing the efficiency and convenience with which the summarized code changes are reviewed (Mosquera [Summary]).
Regarding Claim 10, Hutchins, Smith, Farrier and Mosquera teach
The computing system of Claim 1.
Mosquera further teaches wherein the code development summary includes at least one link to a pull request associated with the at least the portion of the commit message data (Mosquera, Col 14: ln 38-50, "It also shows the latest pull request that caused the SLA to decrease") Examiner Comments: The display includes references to pull requests in the summary.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Hutchins, Smith and Farrier in view of Mosquera in order to provide the generated code development summary for display on the dashboard of Mosquera at a user device so that developers and other stakeholders could review the summarized commit information together with the other software development metrics in a single, centralized interface, thereby increasing the efficiency and convenience with which the summarized code changes are reviewed (Mosquera [Summary]).
Claim(s) 3-5 is/are rejected under 35 U.S.C. 103 as being unpatentable over Hutchins (US 20210326536A1) in view of Smith (US 9557968B1), further in view of Farrier (US 11662997B2), further in view of Mosquera (US 11030071B2), and further in view of Fox (US 9141378).
Regarding Claim 3, Hutchins, Smith, Farrier and Mosquera teach
The computing system of Claim 1.
Hutchins, Smith, Farrier and Mosquera did not specifically teach
wherein the operations further comprise receiving a user selection of the start commit and the end commit.
However, Fox (US 9141378) teaches
wherein the operations further comprise receiving a user selection of the start commit and the end commit (Col 18: ln 53-64, "the artifacts to be evaluated can be input by a user as part of a request") Examiner Comments: Fox teaches that a user inputs the artifacts (including the scope of commits) to be evaluated as part of a request, reading on receiving a user selection of the start and end commits.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Hutchins, Smith, Farrier and Mosquera in view of Fox in order to provide a reliable interpretation about artifact quality based on the entire lifecycle history of the artifact such that the interpretation can be consistent across multiple artifacts, so that the relative qualities of artifacts can be consistently compared (Fox [Summary]).
Regarding Claim 4, Hutchins, Smith, Farrier and Mosquera teach
The computing system of Claim 1.
Hutchins, Smith, Farrier and Mosquera did not specifically teach
wherein the start commit corresponds with a start of a new release of the code, and the end commit corresponds with an end of the new release of the code.
However, Fox (US 9141378) teaches
wherein the start commit corresponds with a start of a new release of the code, and the end commit corresponds with an end of the new release of the code (Col 1: ln 64 to Col 2: ln 11, "the processor further determines a stability of the artifact from a periodicity of releases of the artifact in the source code management information and a volume and severity of issues reported for the artifact in the issue tracking information") Examiner Comments: Fox teaches tracking periodicity of releases, which entails tracking commits from the start to the end of releases, reading on the start and end commits corresponding to the start and end of a new release.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Hutchins, Smith, Farrier and Mosquera in view of Fox in order to provide a reliable interpretation about artifact quality based on the entire lifecycle history of the artifact such that the interpretation can be consistent across multiple artifacts, so that the relative qualities of artifacts can be consistently compared (Fox [Summary]).
Regarding Claim 5, Hutchins, Smith, Farrier and Mosquera teach
The computing system of Claim 1.
Hutchins, Smith, Farrier and Mosquera did not specifically teach
wherein the operations further comprise preprocessing the commit message data for including in the model prompt, wherein the preprocessing comprises removing or filtering undesired commit message data.
However, Fox (US 9141378) teaches
wherein the operations further comprise preprocessing the commit message data for including in the model prompt, wherein the preprocessing comprises removing or filtering undesired commit message data (Col 1: ln 64 to Col 2: ln 11, "the artifact is determined to be stable when the artifact has regular periodic releases and fewer than a first predetermined number of severe issues, and the artifact is determined to be not stable when the artifact has more than a second predetermined number of severe issues") Examiner Comments: Fox teaches filtering data based on severity thresholds, which maps to preprocessing by filtering undesired data from commit histories.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Hutchins, Smith, Farrier and Mosquera in view of Fox in order to provide a reliable interpretation about artifact quality based on the entire lifecycle history of the artifact such that the interpretation can be consistent across multiple artifacts, so that the relative qualities of artifacts can be consistently compared (Fox [Summary]).
Claim(s) 11-15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Hutchins (US 20210326536A1) in view of Amit (US 20220122025A1), further in view of Mosquera (US 11030071B2), further in view of Farrier (US 11662997B2), and further in view of Smith (US 9557968B1).
Regarding Claim 11, Hutchins (US 20210326536A1) teaches
A computer-implemented method comprising:
providing a request to generate a code development summary in association with the set of commit messages selected based on the at least one criteria (Claim 8, "making a call to an artificial intelligence (AI) platform, wherein the call contains the text block concatenated from the texts extracted from the main body of the content and specifies a summarization component of the AI platform, a sentiment analyzer component of the AI platform, and a summarization range") Examiner Comments: The call to the AI platform is a request to generate a summary of the provided text.
in response to the request, obtaining the code development summary representing the set of commit messages corresponding with the code, the code development summary being generated via a trained large language model (Claim 8, "wherein the text block is processed by the summarization component of the AI platform according to the summarization range so as to produce a summary of the text block in the summarization range") Examiner Comments: Hutchins obtains a summary generated by the AI platform in response to the call, reading on obtaining the code development summary generated via a trained large language model.
Hutchins did not specifically teach
automatically selecting a set of commit messages corresponding with a code based on at least one criteria;
the request including at least a portion of the set of commit messages that occur between a start commit message and an end commit message;
causing display, via a graphical user interface, of the code development summary in association with the code;
commit messages.
However, Amit (US 20220122025A1) teaches
automatically selecting a set of commit messages corresponding with a code based on at least one criteria (Para 0145, "If a bot filter is selected, then processor 50 filters out any task profiles 60B whose respective bot flag 128 is set") Examiner Comments: Amit teaches automatically selecting, by filtering, a set of commit-related data based on at least one criteria such as bot flags or merged commit flags, which reads on automatically selecting commit messages based on criteria.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Hutchins in view of Amit in order to automatically select only the relevant set of commit messages for summarization and to exclude undesired entries, such as bot-generated commits or already-merged commits, that would otherwise introduce noise into the summary. Removing such irrelevant entries before summarization would predictably improve the relevance and accuracy of the resulting code development summary and reduce the amount of data processed by the model, and would have been achieved through the routine application of the known filtering of Amit to the known summarization of Hutchins with a reasonable expectation of success (Amit, Para 0145).
Hutchins and Amit did not specifically teach
causing display, via a graphical user interface, of the code development summary in association with the code.
However, Mosquera (US 11030071B2) teaches
causing display, via a graphical user interface, of the code development summary in association with the code (Col 12: ln 10-67, "FIG. 9A shows an exemplary dashboard 900 with statistics and metrics collected by the continuous deployment platform and its integrations to provide actionable insights regarding the software development lifecycle") Examiner Comments: Mosquera displays code development information via a graphical dashboard interface.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Hutchins and Amit in view of Mosquera in order to to provide the generated code development summary for display on the dashboard of Mosquera at a user device so that developers and other stakeholders could review the summarized commit information together with the other software development metrics in a single, centralized interface, thereby increasing the efficiency and convenience with which the summarized code changes are reviewed (Mosquera [Summary]).
Hutchins, Amit and Mosquera did not specifically teach
commit messages.
However, Farrier (US 11662997B2) teaches
commit messages (Col 6: ln 17-25, "The term 'commit message' refers to the messages submitted by one or more developers during a commit, and the central repository in which the messages are stored. Typically when a developer commits a change to a central code repository, they do so with a brief, timestamped commit message explaining the change") Examiner Comments: Farrier explicitly defines commit messages as descriptions of code modifications.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Hutchins, Amit and Mosquera in view of Farrier in order to use the commit messages within the subset identified by Smith, each understood in view of Farrier to describe its corresponding code modification, as the text supplied to the large language model of Hutchins for summarization, because doing so provides the model with concise, developer-authored descriptions of the code changes and thereby yields a more accurate and meaningful code development summary (Farrier [Summary]).
Hutchins, Amit, Mosquera and Farrier did not specifically teach
the request including at least a portion of the set of commit messages that occur between a start commit message and an end commit message.
However, Smith (US 9557968B1) teaches
the request including at least a portion of the set of commit messages that occur between a start commit message and an end commit message (Col 6: ln 46-56, "in 600 a merge base of a first code branch and a second code branch is determined. In 602, a first code branch commit is selected. For example, data for the first code branch is received and a most recent first commit data is selected") Examiner Comments: Smith teaches determining a merge base commit as a start boundary and a most recent commit as an end boundary and collecting the subset of commits between them (Col 6: ln 60-66, "the first code branch commit is added to a first branch data ... so the first branch data comprises a first set of commits in a first code branch that are not common to a second code branch"), reading on the portion of the set of commit messages that occur between a start commit message and an end commit message.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Hutchins, Amit, Mosquera and Farrier in view of Smith in order to include in the request only the subset of commit messages located between two selected commits, because Smith recognizes that it can be difficult for a developer to keep track of the changes happening to the main code repository while working on a checked out branch (Smith, Col 1: ln 16-18).
Regarding Claim 12, Hutchins, Amit, Mosquera, Farrier and Smith teach
The method of Claim 11.
Amit further teaches, further comprising: preprocessing a plurality of commit messages corresponding with the code to remove one or more commit messages (Amit, Para 0145, "If a bot filter is selected, then processor 50 filters out any task profiles 60B whose respective bot flag 128 is set") Examiner Comments: Amit preprocesses by filtering out (removing) commit-related data associated with bots, reading on preprocessing to remove undesired commit messages.
wherein the set of commit messages is selected from the preprocessed plurality of commit messages (Amit, Para 0145, "If a merged commit filter is selected, then processor 50 filters out any task profiles 60B whose respective merged commit flag 130 is set") Examiner Comments: After filtering, the remaining set of commit data is selected from the preprocessed plurality, reading on selecting from the preprocessed commit messages.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Hutchins in view of Amit in order to automatically select only the relevant set of commit messages for summarization and to exclude undesired entries, such as bot-generated commits or already-merged commits, that would otherwise introduce noise into the summary. Removing such irrelevant entries before summarization would predictably improve the relevance and accuracy of the resulting code development summary and reduce the amount of data processed by the model, and would have been achieved through the routine application of the known filtering of Amit to the known summarization of Hutchins with a reasonable expectation of success (Amit, Para 0145).
Regarding Claim 13, Hutchins, Amit, Mosquera, Farrier and Smith teach
The method of Claim 11.
Mosquera further teaches
wherein the request is automatically provided based on a new commit associated with the code (Mosquera, Col 7: ln 25-37, "A code update may be received in a development environment ... The code update may be a code commit from a developer and request to merge into a production branch of code in a repository") Examiner Comments: Requests are triggered by new commits in the continuous deployment environment.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Hutchins and Amit in view of Mosquera in order to to provide the generated code development summary for display on the dashboard of Mosquera at a user device so that developers and other stakeholders could review the summarized commit information together with the other software development metrics in a single, centralized interface, thereby increasing the efficiency and convenience with which the summarized code changes are reviewed (Mosquera [Summary]).
Regarding Claim 14, Hutchins, Amit, Mosquera, Farrier and Smith teach
The method of Claim 11.
Farrier further teaches
wherein the request is automatically provided in response to a user selection, via the graphical user interface, of the set of commit messages (Farrier, Col 6: ln 17-25, "The term 'commit message' refers to the messages submitted by one or more developers during a commit, and the central repository in which the messages are stored. Typically when a developer commits a change to a central code repository, they do so with a brief, timestamped commit message explaining the change") Examiner Comments: When combined with Mosquera graphical dashboard interface, the user can interact with commit-related data to trigger requests.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Hutchins, Amit and Mosquera in view of Farrier in order to use the commit messages within the subset identified by Smith, each understood in view of Farrier to describe its corresponding code modification, as the text supplied to the large language model of Hutchins for summarization, because doing so provides the model with concise, developer-authored descriptions of the code changes and thereby yields a more accurate and meaningful code development summary (Farrier [Summary]).
Regarding Claim 15, Hutchins, Amit, Mosquera, Farrier and Smith teach
The method of Claim 11.
Hutchins further teaches generating the request; and inputting the request into the trained large language model to generate the code development summary representing the set of commit messages (Claim 8, "making a call to an artificial intelligence (AI) platform, wherein the call contains the text block concatenated from the texts extracted from the main body of the content and specifies a summarization component of the AI platform, a sentiment analyzer component of the AI platform, and a summarization range") Examiner Comments: The call includes the text set for input to the AI model for summarization.
Smith further teaches
the at least the portion of the set of commit messages that occur between the start commit message and the end commit message (Col 6: ln 60-66, "the first code branch commit is added to a first branch data ... so the first branch data comprises a first set of commits in a first code branch that are not common to a second code branch") Examiner Comments: Smith collects only the subset of commits located between the merge base start boundary and the most recent end boundary, reading on the portion of the set of commit messages that occur between the start commit message and the end commit message.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Hutchins, Amit, Mosquera and Farrier in view of Smith in order to include in the request only the subset of commit messages located between two selected commits, because Smith recognizes that it can be difficult for a developer to keep track of the changes happening to the main code repository while working on a checked out branch (Smith, Col 1: ln 16-18).
Claim(s) 16-18 and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Hutchins (US 20210326536A1) in view of Mosquera (US 11030071B2), further in view of Farrier (US 11662997B2), and further in view of Smith (US 9557968B1).
Regarding Claim 16, Hutchins (US 20210326536A1) teaches
One or more computer storage media having computer-executable instructions embodied thereon that, when executed by one or more processors, cause the one or more processors to perform a method, the method comprising: obtaining, at a trained large language model, a model prompt that includes an indication of a target audience for viewing a summary related to code development and code modification data associated with code (Claim 7, "wherein the call further specifies a knowledge base or taxonomy for processing the text block concatenated by the summarizer from the texts extracted from the main body of the content") Examiner Comments: The specified knowledge base or taxonomy specifies context for tailored summarization, reading on an indication of a target audience for viewing a summary.
generating, using the trained large language model, a code development summary that summarizes the code modification data associated with the code in accordance with the target audience (Claim 1, "wherein the text block is processed by the summarization component of the AI platform according to the summarization range so as to produce a summary of the text block in the summarization range") Examiner Comments: The AI platform generates a summary per the specified context or taxonomy.
Hutchins did not specifically teach
wherein the code modification data comprises a description associated with a corresponding modification in the code;
wherein the model prompt includes a subset of commit messages that occur between a start commit message and an end commit message;
in accordance with the target audience and the subset of the commit messages;
providing the code development summary to a data store for subsequent presentation.
However, Mosquera (US 11030071B2) teaches
providing the code development summary to a data store for subsequent presentation (Col 12: ln 10-67, "FIG. 9A shows an exemplary dashboard 900 with statistics and metrics collected by the continuous deployment platform and its integrations to provide actionable insights regarding the software development lifecycle") Examiner Comments: Mosquera stores and displays code development information via dashboards for subsequent presentation.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Hutchins and Mosquera in order to provide the generated code development summary for display on the dashboard of Mosquera at a user device so that developers and other stakeholders could review the summarized commit information together with the other software development metrics in a single, centralized interface, thereby increasing the efficiency and convenience with which the summarized code changes are reviewed (Mosquera [Summary]).
Hutchins and Mosquera did not specifically teach
wherein the code modification data comprises a description associated with a corresponding modification in the code.
However, Farrier (US 11662997B2) teaches
wherein the code modification data comprises a description associated with a corresponding modification in the code (Col 6: ln 17-25, "The term 'commit message' refers to the messages submitted by one or more developers during a commit, and the central repository in which the messages are stored. Typically when a developer commits a change to a central code repository, they do so with a brief, timestamped commit message explaining the change") Examiner Comments: Farrier teaches that code modification data (commit messages) comprises descriptions of corresponding code modifications.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Hutchins and Mosquera in view of Farrier in order to to use the commit messages within the subset identified by Smith, each understood in view of Farrier to describe its corresponding code modification, as the text supplied to the large language model of Hutchins for summarization, because doing so provides the model with concise, developer-authored descriptions of the code changes and thereby yields a more accurate and meaningful code development summary (Farrier [Summary]).
Hutchins, Mosquera and Farrier did not specifically teach
wherein the model prompt includes a subset of commit messages that occur between a start commit message and an end commit message, and generating the code development summary in accordance with the subset of the commit messages.
However, Smith (US 9557968B1) teaches
wherein the model prompt includes a subset of commit messages that occur between a start commit message and an end commit message (Col 6: ln 46-56, "in 600 a merge base of a first code branch and a second code branch is determined. In 602, a first code branch commit is selected. For example, data for the first code branch is received and a most recent first commit data is selected") Examiner Comments: Smith teaches determining a merge base commit as a start boundary and a most recent commit as an end boundary and collecting the subset of commits between them (Col 6: ln 60-66, "the first code branch commit is added to a first branch data ... so the first branch data comprises a first set of commits in a first code branch that are not common to a second code branch"), which when included in the model prompt reads on a subset of commit messages that occur between a start commit message and an end commit message.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Hutchins, Mosquera and Farrier in view of Smith in order to provide a developer with an efficient mechanism for identifying and reviewing only the specific set of commits located between two selected points in the code history, because Smith recognizes that it can be difficult for a developer to keep track of the changes happening to the main code repository while working on a checked out branch (Smith, Col 1: ln 16-18).
Regarding Claim 17, Hutchins, Mosquera, Farrier and Smith teach
The media of Claim 16.
Hutchin further teaches, wherein the model prompt further includes an output attribute to indicate a desired format or style for the code development summary (Hutchins, Claim 4, "wherein the call contains the adjusted summarization range") Examiner Comments: The summarization range indicates the desired output format.
Regarding Claim 18, Hutchins, Mosquera, Farrier and Smith teach
The media of Claim 16.
Hutchins further teaches wherein the target audience comprises a particular consumer audience or a particular code developer audience (Hutchins, Claim 7, "wherein the call further specifies a knowledge base or taxonomy for processing the text block concatenated by the summarizer from the texts extracted from the main body of the content") Examiner Comments: The specified knowledge base or taxonomy can specify different audience contexts such as consumer or developer audiences.
Regarding Claim 20, Hutchins, Mosquera, Farrier and Smith teach
The media of Claim 16.
Mosquera further teaches wherein the method further comprises providing the code development summary for display based on a request to view the code development summary (Mosquera, Col 12: ln 10-67, "FIG. 9A shows an exemplary dashboard 900 with statistics and metrics collected by the continuous deployment platform and its integrations to provide actionable insights regarding the software development lifecycle") Examiner Comments: Mosquera displays summary information on request via the dashboard.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Hutchins and Mosquera in order to provide the generated code development summary for display on the dashboard of Mosquera at a user device so that developers and other stakeholders could review the summarized commit information together with the other software development metrics in a single, centralized interface, thereby increasing the efficiency and convenience with which the summarized code changes are reviewed (Mosquera [Summary]).
Claim(s) 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Hutchins (US 20210326536A1) in view of Mosquera (US 11030071B2), Farrier (US 11662997B2), and Smith (US 9557968B1), further in view of Brinbaum (US 8688434B1).
Regarding Claim 19, Hutchins, Mosquera, Farrier and Smith teach
The media of Claim 16.
Hutchins, Mosquera, Farrier and Smith did not specifically teach
wherein the target audience is user specified or automatically determined based on a user desiring to view the code development summary.
However, Brinbaum (US 8688434B1) teaches
wherein the target audience is user specified or automatically determined based on a user desiring to view the code development summary (Col 3: ln 24-43, "An end-user or operator may enter commands (e.g., to customize narrative stories to an intended audience, etc.) and information (e.g., to key in data and/or information to be used in generating narrative stories, to indicate the logical location of that information in a network or file system, etc.) into the processing device 20 through input devices such as a keyboard 54 and/or a pointing device 56") Examiner Comments: Brinbaum teaches that the system allows customization of narrative stories to an intended audience specified by the user.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Hutchins, Mosquera, Farrier and Smith in view of Brinbaum so that the target audience of the code development summary is user specified or automatically determined based on the user who desires to view the summary, thereby allowing the same underlying code changes to be summarized at a level of detail and with terminology appropriate to different viewers, such as developers or non-technical stakeholders. Adapting the output to an intended audience in this manner predictably improves the relevance and usefulness of the generated summary for its recipient, and amounts to applying the known audience-customization technique of Brinbaum to the known summary generation of the combined system with a reasonable expectation of success (Brinbaum [Summary]).
Response to arguments
Applicant argues "Applicant submits the claims are directed to a technical solution to a technical problem. In contrast, as stated in the Application, 'using an LLM to generate code development summaries facilitates reducing computing resource consumption, such as computer memory and latency. In particular, code development summaries can be accurately generated without requiring training and/or fine-tuning of the model for the particular code or for a particular model output, such as the generated code development summary. Utilizing pre-trained models reduces computing resources consumed for performing training.'"
Examiner respectfully disagrees. While Applicant asserts that the claims are directed to a technical solution that reduces computing resource consumption by utilizing pre-trained models without fine-tuning, the Examiner notes that the claims as drafted do not recite such specific technical improvements. The claims recite obtaining commit message data, generating a model prompt, and obtaining a summary from a large language model. These steps, at their core, describe the abstract idea of collecting data and using a generic AI tool to summarize it. The mere use of a large language model, without more, is akin to applying a judicial exception using generic computer components. The specification’s discussion of resource savings from avoiding fine-tuning describes an advantage of a particular implementation, but this advantage is not reflected in the claim language itself. The claims do not recite any limitation directed to avoiding fine-tuning, reducing parameters, or constraining computational resources in a manner that would constitute a technical improvement. Accordingly, the claims remain directed to an abstract idea without significantly more, and the 101 rejection is maintained.
Applicant argues "the cited references fail to teach or suggest 'obtain, via a user interface, an indication of a start commit and an indication of an end commit associated with code,' as in claim 1. Applicant submits the cited references, Mosquera, Hutchins, and Farrier fail to teach this claim aspect, nor were they cited to for doing so. Moreover, the Fox reference also fails to teach this claim aspect. Although Fox discusses code changes committed, there is no teaching or suggestion of 'obtain, via a user interface, an indication of a start commit and an indication of end commit associated with code,' as recited in claim 1."
Examiner respectfully disagrees. Fox teaches at Col 18: ln 53-64 that "the artifacts to be evaluated can be input by a user as part of a request." Fox further teaches at Col 2: ln 17-24 that "the processor further obtains an indication of artifacts for which a history is to be interpreted, identifies a software repository of a software project to which each of the artifacts belongs, and obtains an indication of where the source code management storage system for each artifact is located." These passages establish that Fox’s system receives user input specifying the artifacts (and their associated history) to be evaluated. The "history of code changes committed" (Col 1: ln 40-59) includes a range of commits from start to end for those artifacts. When a user inputs the artifacts to be evaluated as part of a request, this constitutes obtaining, via a user interface, indications that define the scope of commit history to be analyzed (i.e., a start point and an end point). Furthermore, Fox’s system evaluates artifact quality based on "periodicity of releases" (Col 1: ln 64-Col 2: ln 11), which inherently requires defining start and end boundaries for each release period. The combination of Fox’s user-driven artifact selection with the dashboard GUI taught by Mosquera (Col 12: ln 10-67, showing an exemplary dashboard with statistics and metrics), provides the user interface element through which such indications are obtained. One of ordinary skill in the art would find it obvious to incorporate Fox’s user-specified artifact evaluation scope into Mosquera’s graphical dashboard interface, thereby obtaining via a user interface the indications of start and end commits.
Applicant argues "the cited references fail to teach or suggest 'extract commit message data for a set of commit messages corresponding with the start commit through the end commit, wherein each commit message comprises a description associated with a corresponding modification in the code,' as recited in claim 1. The Office appears to refer to the Mosquera reference for this claim aspect. Although Mosquera mentions a code commit, Applicant submits that such a code commit mentioned in Mosquera is not extracting commit message data for a set of commit messages corresponding with the start commit through the end commit."
Examiner respectfully disagrees. The Examiner notes that Mosquera alone was not cited to teach this entire limitation. Rather, the combination of Mosquera, Farrier, and Fox together teach this limitation. Specifically, Fox teaches at Col 1: ln 40-59 that the system gathers "source code management information having a history of code changes committed against another plurality of artifacts" and "checks a combined history of the issue tracking information and the source code management information for a history of issues filed against an artifact and a history of commits and corresponding source code changes committed against the artifact." This teaches extracting a history of commits and corresponding source code changes for specified artifacts within a defined scope. Farrier (Col 6: ln 17-25) explicitly teaches that commit messages are "messages submitted by one or more developers during a commit" and that "when a developer commits a change to a central code repository, they do so with a brief, timestamped commit message explaining the change." The combination of Fox’s teaching of extracting commit history within a user-specified scope and Farrier’s teaching that commits include descriptive messages reads on the claimed limitation of extracting commit message data for a set of commit messages corresponding with the start commit through the end commit, wherein each commit message comprises a description associated with a corresponding modification in the code. In response to Applicant’s arguments against the references individually, one cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986).
Applicant argues "the cited references fail to teach or suggest 'generate a model prompt to be input into a large language model, the model prompt including at least a portion of the commit message data corresponding with the start commit through the end commit,' as recited in claim 1. The Office appears to refer to the Farrier reference to ostensibly teach a model prompt including commit message data for processing with an LLM. In Farrier, the technology is directed to using a machine learning classifier to calculate a probability that the commit will cause a failure in the source code repository... Farrier, however, is void of any generation of a prompt to input into a LLM that includes commit message data, as in claim 1. Instead, Farrier describes analyzing commit messages to determine parameters and train a classifier."
Examiner respectfully disagrees. The Examiner notes that Farrier was not solely relied upon to teach the entirety of this limitation. Rather, Hutchins (US 20210326536A1) was cited to teach the generation of a model prompt to be input into an AI platform. Specifically, Hutchins teaches at Claim 8 "making a call to an artificial intelligence (AI) platform, wherein the call contains the text block concatenated from the texts extracted from the main body of the content and specifies a summarization component of the AI platform... and a summarization range." This call to the AI platform constitutes a model prompt containing text data for summarization by the AI model. The limitation that the model prompt includes "commit message data corresponding with the start commit through the end commit" is addressed by the combination: Fox teaches extracting commit history within a defined range, Farrier teaches that commits include descriptive messages, and Hutchins teaches constructing a prompt with text data for AI summarization. The combination of these references teaches generating a model prompt that includes commit message data corresponding with the start commit through the end commit for input into a large language model.
Applicant argues "dependent claim 9 recites identifying a pull request identifier in a commit message of the set of commit messages; obtaining information associated with the pull request identifier; and including the information associated with the pull request identifier in the commit message data. Applicant submits the cited references fail to teach or suggest obtaining and using information associated with a pull request, as recited in claim 9."
Examiner respectfully disagrees. Mosquera teaches at Col 14: ln 38-50 that "the intelligent chatbot creates and sends a message indicating that the compliance with SLA has decreased and therefore presents a risk. It also shows the latest pull request that caused the SLA to decrease." This passage teaches a system that identifies and obtains pull request information linked to code changes, and includes (displays) the pull request information in association with commit-related data. Mosquera’s system identifies pull requests associated with SLA changes and presents this information, which reads on identifying a pull request identifier, obtaining information associated with it, and including it in the data presented.
Applicant argues "independent claim 11 recites 'automatically selecting a set of commit messages corresponding with a code based on at least one criteria.' The cited references fail to teach this claim aspect, nor are they cited to for doing so. Further, with reference to Amit, Amit states '[i]f a merged commit filter is selected, the processor 50 filters out any task profiles 60B whose respective merged commit flag 130 is set...' As such, although Amit mentions a merged commit filter, such a filter is to filter out task profiles, and not selecting commit messages corresponding with code based on a criteria, as in claim 11."
Examiner respectfully disagrees. Amit teaches at Para 0145 that "if a bot filter is selected, then processor 50 filters out any task profiles 60B whose respective bot flag 128 is set" and "if a merged commit filter is selected, then processor 50 filters out any task profiles 60B whose respective merged commit flag 130 is set." Applicant contends that Amit’s filtering is directed to task profiles rather than commit messages. However, the Examiner notes that Amit’s task profiles are directly associated with code commits. Amit teaches at Para 0030-0031 that the system analyzes commits in source code repositories and creates task profiles based on commit data. The task profiles represent and are derived from commit-related data, including commit messages, commit types, and associated metadata. Therefore, when Amit’s processor filters out task profiles based on criteria such as bot flags or merged commit flags, it is effectively selecting (through exclusion of undesired entries) a set of commit-related data corresponding with code based on at least one criteria. Under the broadest reasonable interpretation, filtering commit-associated task profiles based on criteria reads on automatically selecting a set of commit messages corresponding with a code based on at least one criteria. The filtering criteria (bot flag, merged commit flag) determine which commit-related data is selected for further processing, which is the essence of the claimed limitation.
Applicant further argues "the cited references fail to teach or suggest providing a request to generate a code development summary in association with the commit messages selected based on the criteria, as in claim 11. Instead, Mosquera merely discusses code commits from a developer, but not using a selected set of commit messages for providing a request to generate a code development summary, as in claim 11."
Examiner respectfully disagrees. The rejection is based on the combination of Amit, Mosquera, Hutchins, and Farrier. Amit teaches automatically selecting commit data based on criteria. Mosquera teaches receiving code commits and triggering processing workflows (Col 7: ln 25-37). Hutchins teaches generating a summarization request (a call) to an AI platform to produce a summary of text data (Claim 8). The combination of these references teaches that after Amit’s criteria-based selection of commit data, the selected data is used (as taught by Hutchins) to provide a request (a call to the AI platform) to generate a code development summary. One of ordinary skill in the art would have been motivated to combine Amit’s commit filtering with Hutchins’ AI-based summarization to generate more accurate and relevant summaries by excluding noise from irrelevant commits such as bot-generated or merged commits. Again, one cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981).
Applicant argues "the cited references fail to teach or suggest 'obtaining, at a trained large language model, a model prompt that includes an indication of a target audience for viewing a summary related to code development and code modification data associated with code, wherein the code modification data comprises a description associated with a corresponding modification in the code,' as recited in claim 16. The Office Action appears to rely on Hutchins for ostensibly teaching this claim aspect. Hutchins refers to a call that further specifies 'a knowledge base or taxonomy for processing the text block concatenated by the summarizer from the texts extracted from the main body of the content.' A knowledge base or taxonomy, as in Hutchins, however, is very different from obtaining a trained LLM a model prompt that includes an indication of a target audience for viewing a summary related to code development and code modification data associated with the code, as in claim 16."
Examiner respectfully disagrees. Hutchins teaches at Claim 7 that the call to the AI platform "further specifies a knowledge base or taxonomy for processing the text block." Hutchins further teaches at Para 0029 that "NLP text mining engine 235 is operable to programmatically examine the input text and determine, according to a controlled vocabulary (a taxonomy—a scheme of classification), a best topic for the document and attach the topic to the document. For instance, a news article discusses that a president is going to visit a country. NLP text mining engine 235 is operable to programmatically examine the article, determine that this article concerns foreign affair and/or diplomacy, and add 'foreign affair' and/or 'diplomacy' as metadata." A taxonomy or knowledge base specified in the prompt to the AI platform functions as an indication of the context and perspective from which the summary should be generated. Under the broadest reasonable interpretation, specifying a taxonomy or knowledge base in a prompt to an AI model serves the same functional purpose as specifying a target audience—it tailors the summarization output to a particular viewpoint, level of detail, or domain of interest. Just as specifying a target audience indicates to the model what kind of summary the viewer needs, specifying a taxonomy indicates what classification scheme and level of granularity the AI should apply when generating the summary. Furthermore, the amended limitation adds "for viewing a summary related to code development," which further narrows the target audience context. However, when combined with Farrier’s teaching of commit message analysis in code development environments and Mosquera’s teaching of code development dashboards, the combination teaches a prompt that includes both an audience-context indication (Hutchins’ taxonomy) and code modification data (Farrier’s commit messages) in a code development setting (Mosquera’s platform). Accordingly, the combined teachings of Hutchins, Mosquera, and Farrier teach the claimed limitation.
Examiner Comments
Claim 16 is directed to "one or more computer storage media having computer-executable instructions embodied thereon." The specification at paragraph [00128] explicitly states that "Computer storage media does not comprise a propagated data signal." In view of this disclosure, the claimed "computer storage media" is interpreted as limited to non-transitory embodiments, excluding transitory propagating signals. Therefore, claim 16 is directed to statutory subject matter under 35 U.S.C. § 101 and is not being rejected on this basis.
Response to Arguments
Applicant’s arguments with respect to claims 1, 3-20 have been considered but are moot because the arguments do not apply to the previous cited sections of the references used in the previous office action. The current office action is now citing additional references to address the newly added claimed limitations.
Applicant argues “using an LLM to generate code development summaries facilitates reducing computing resource consumption, such as computer memory and latency. In particular, code development summaries can be accurately generated without requiring training and/or fine-tuning of the model.”
Examiner respectfully disagrees. While Applicant asserts that the claims are directed to a technical solution that reduces computing resource consumption by utilizing pre-trained models without fine-tuning, the claims as drafted do not recite such specific technical improvements. The claims recite obtaining an indication of a start commit and an end commit, extracting a subset of commit messages between them, generating a model prompt, and obtaining a summary from a large language model. These steps, at their core, describe the abstract idea of collecting data and using a generic artificial intelligence tool to summarize it. The specification’s discussion of resource savings from avoiding fine-tuning describes an advantage of a particular implementation, but this advantage is not reflected in the claim language. The claims do not recite any limitation directed to avoiding fine-tuning, reducing parameters, or constraining computational resources in a manner that would constitute a technical improvement. Accordingly, the claims remain directed to an abstract idea without significantly more.
Applicant argues “Applicant has amended independent claim 1, for example, to obtain the code development summary to provide for display via a user device, which further supports a practical application.”
Examiner respectfully disagrees. The amended limitation “to provide for display via a user device” recites nothing more than outputting the result of the abstract idea for display. Outputting or displaying the result of a judicial exception is insignificant extra-solution activity that does not integrate the exception into a practical application, and is a well-understood, routine, and conventional activity. See MPEP 2106.05(g) and 2106.05(d). Displaying the generated summary neither improves the functioning of a computer nor effects a particular treatment or transformation, and therefore does not impose a meaningful limit on the abstract idea.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AMIR SOLTANZADEH whose telephone number is (571)272-3451. The examiner can normally be reached M-F, 9am - 5pm ET.
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, Wei Mui can be reached at (571) 272-3708. 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.
/AMIR SOLTANZADEH/Examiner, Art Unit 2191 /WEI Y MUI/Supervisory Patent Examiner, Art Unit 2191
Prosecution Insights