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 .
DETAILED ACTION
This action is in response to the application filed on 04/26/2024.
Claims 1-20 are pending.
Examiner’s Note
Please note that Examiner cites particular columns and line numbers in the references as applied to the claims below for the convenience of the applicant. Although the specified citations are representative of the teachings in the art and are applied to the specific limitations within the individual claim, other passages and figures may apply as well. It is respectfully requested that, in preparing responses, the applicant fully consider the references in entirely as potentially teaching all or part of the claimed invention, as well as the context of the passage as taught by the prior art or disclosed by the examiner.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier.
Such claim limitation(s) is/are:
a first one or more models configured to output at least one of the first context information or the second context information, or
a second model configured to output the review information in claim 12,
wherein the one or more models include a model configured to output the review information in claim 16 and
wherein the one or more models include a large language model configured to generate and output the review information in claim 17.
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
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 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter.
Claim 1, this claim is within at least one of the four categories of patent eligible subject matter as it is directing to a system claim under Step 1.
1. A system for automated code review using artificial intelligence (AI), the system comprising:
one or more memories; and
one or more processors, communicatively coupled to the one or more memories, configured to:
obtain a pull request indicating a proposed change to a subset of executable code from a set of executable code;
determine, using one or more AI models, first context information associated with the proposed change and second context information associated with at least one of the subset of executable code, the set of executable code, or a context of the subset of executable code within the set of executable code;
generate an embedding vector representing at least one of the first context information or the second context information;
determine, using the embedding vector and an embedding space, a scrutiny level for review of the pull request based on at least one of the first context information or the second context information;
obtain, via the one or more AI models and using the scrutiny level, review information associated with the pull request; and
perform, based on the review information, an action to modify the proposed change or to commit the proposed change to the set of executable code.
Regarding claim 1, the limitations “determine,…, first context information associated with the proposed change and second context information associated with at least one of the subset of executable code, the set of executable code, or a context of the subset of executable code within the set of executable code; generate an embedding vector representing at least one of the first context information or the second context information; determine, using the embedding vector and an embedding space, a scrutiny level for review of the pull request based on at least one of the first context information or the second context information” as drafted, are functions that, under its broadest reasonable interpretation, recite the abstract idea of a mental process. For example, a person is capable of determining the context information with the proposed change to the code using pen and paper and decide how thoroughly to review the code. In the same manner, a person is capable of generating embedding vectors for the context information with aid of pen and paper to be utilized in reviewing the code to determine the scrutiny level of the code review. Therefore, these limitations encompass a human mind carrying out the function through observation, evaluation judgment and/or opinion, or even with the aid of pen and paper. Thus, these limitations recite and falls within the “Mental Processes” grouping of abstract ideas under Step 2A, Prong 1.
Under Step 2A, Prong 2, the additional elements “one or more memories; and one or more processors, communicatively coupled to the one or more memories, configured to,” and “using one or more AI models” and “perform, based on the review information, an action to modify the proposed change or to commit the proposed change to the set of executable code” are recited at a high-level of generality such that it amounts no more than mere instructions for executing / applying / running AI model which merely using generic computing equipment to execute / apply the modified proposed changes to perform the abstract idea. See MPEP 2106.05(f). For the additional elements “obtain a pull request indicating a proposed change to a subset of executable code from a set of executable code” “obtain, via the one or more AI models and using the scrutiny level, review information associated with the pull request” do nothing more than to add insignificant extra solution activity to the judicial exception of merely storing / gathering data. See MPEP § 2106.05(g).
Under Step 2B, 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 elements of “one or more memories; and one or more processors, communicatively coupled to the one or more memories, configured to,” and “using one or more AI models” and “perform, based on the review information, an action to modify the proposed change or to commit the proposed change to the set of executable code” amount to no more than mere instructions, or generic computer and/or computer components to carry out the exception, thus, cannot amount to an inventive concept. For the additional elements “obtain a pull request indicating a proposed change to a subset of executable code from a set of executable code” “obtain, via the one or more AI models and using the scrutiny level, review information associated with the pull request” the courts have identified functions such as gathering and storing data as well-understood, routine, conventional activity (Berkheimer v. HP, Inc., 881 F.3d 1360, 1368, 125 USPQ2d 1649, 1654 (Fed. Cir. 2018)), thus do not amount to significantly more than the judicial exception. See MPEP 2106.05(d). Accordingly, the claims are not patent eligible under 35 USC 101.
2. The system of claim 1, wherein the review information includes at least one of: natural language text indicating a review of the proposed change, or proposed executable code to be included in the proposed change.
The limitations for this claim further recite an additional mental process under Step 2A, Prong 1.
3. The system of claim 1, wherein the one or more AI models include at least one of: a first model configured to output the first context information, a second model configured to output the second context information, or a third model configured to output the review information.
The limitations, a first/second/or third model, amount to no more than mere instructions to apply the exception using generic computer and/or mere computer components to carry out the exception under Step 2A, Prong 2. For the limitations, configured to output the first context information… configured to output the second context information, or… configured to output the review information, are merely pre and post activities solutions by data gathering and displaying / outputting the review information under step 2A, Prong 2. See MPEP § 2106.05(g).
4. The system of claim 1, wherein the scrutiny level indicates a level of review to be applied by the one or more AI models when reviewing the pull request.
The limitation amount to no more than mere instructions to apply the exception using generic computer and/or mere computer components to carry out the exception under Step 2A, Prong 2.
5. The system of claim 1, wherein the scrutiny level is indicated to the one or more AI models via at least one of: a setting of the one or more AI models, a hyperparameter of the one or more AI models, or a prompt input to the one or more AI models.
The limitations for this claim further recite an additional mental process under Step 2A, Prong 1.
6. The system of claim 1, wherein at least one of the first context information or the second context information indicates a level of impact of the proposed change to the set of executable code, and wherein the one or more processors, to determine the scrutiny level, are configured to: determine the scrutiny level based on the level of impact of the proposed change to the set of executable code.
The limitations for this claim further recite an additional mental process under Step 2A, Prong 1.
7. The system of claim 1, wherein the one or more processors are further configured to: generate, using at least one of the first context information or the second context information, the embedding vector to represent the proposed change in context of the set of executable code; and wherein the one or more processors, to determine the scrutiny level, are configured to: determine the scrutiny level based on a location of the embedding vector in the embedding space.
The limitations generate, using at least one of the first context information or the second context information, the embedding vector to represent the proposed change in context of the set of executable code; and… to determine the scrutiny level, are configured to: determine the scrutiny level based on a location of the embedding vector in the embedding space further recite an additional mental process under Step 2A, Prong 1. The limitation one or more processors amount to no more than mere instructions to apply the exception using generic computer and/or mere computer components to carry out the exception under Step 2A, Prong 2.
8. The system of claim 1, wherein the one or more processors are further configured to: generate, using at least one of the first context information or the second context information, a profile representing the proposed change, wherein the profile indicates one or more parameters of the proposed change; and wherein the one or more processors, to determine the scrutiny level, are configured to: determine the scrutiny level using the profile.
The limitations, generate, using at least one of the first context information or the second context information, a profile representing the proposed change, wherein the profile indicates one or more parameters of the proposed change; and… to determine the scrutiny level, are configured to: determine the scrutiny level using the profile, further recite an additional mental process under Step 2A, Prong 1. The limitation, one or more processors, amount to no more than mere instructions to apply the exception using generic computer and/or mere computer components to carry out the exception under Step 2A, Prong 2.
9. The system of claim 8, wherein the one or more processors, to determine the scrutiny level, are configured to: generate another embedding vector that represents the profile; identify, in the embedding space, a nearest neighbor embedding vector to the other embedding vector; and determine the scrutiny level based on another scrutiny level that was applied for another profile that is represented by the nearest neighbor embedding vector.
The limitations for this claim further recite an additional mental process under Step 2A, Prong 1.
10. The system of claim 1, wherein the one or more processors, to perform the action, are configured to: generate a reviewed pull request indicating a reviewed change to the subset of executable code, wherein the reviewed change incorporates the proposed change and the review information; and cause the reviewed pull request to be merged with the set of executable code.
The limitations, generate a reviewed pull request indicating a reviewed change to the subset of executable code, wherein the reviewed change incorporates the proposed change and the review information, are an additional mental process under Step 2A, Prong 1. The limitation cause the reviewed pull request to be merged with the set of executable code amount to no more than mere instructions to apply the exception using generic computer and/or mere computer components to carry out the exception under Step 2A, Prong 2.
Claim 11, this claim is within at least one of the four categories of patent eligible subject matter as it is directing to a method claim under Step 1.
11. A method for automated code review, comprising:
obtaining, by a device, an indication of a proposed change to a subset of executable code from a set of executable code;
determining, by the device and via one or more models, first context information associated with the proposed change and second context information associated with at least one of the subset of executable code, the set of executable code, or a context of the subset of executable code within the set of executable code;
determining, by the device, a scrutiny level for review of the proposed change based on at least one of the first context information or the second context information;
obtaining, by the device and via the one or more models, review information associated with the proposed change,
wherein the one or more models apply the scrutiny level to obtain the review information; and
performing, by the device, an action based on the review information.
Regarding claim 11, the limitations “determine,…, first context information associated with the proposed change and second context information associated with at least one of the subset of executable code, the set of executable code, or a context of the subset of executable code within the set of executable code; determining,…, a scrutiny level for review of the proposed change based on at least one of the first context information or the second context information” as drafted, are functions that, under its broadest reasonable interpretation, recite the abstract idea of a mental process. For example, a person is capable of determining the context information with the proposed change to the code using pen and paper and decide how thoroughly to review the code. In the same manner, a person is capable of using context information with aid of pen and paper to be utilized in reviewing the code to determine the scrutiny level of the code review. Therefore, these limitations encompass a human mind carrying out the function through observation, evaluation judgment and/or opinion, or even with the aid of pen and paper. Thus, these limitations recite and falls within the “Mental Processes” grouping of abstract ideas under Step 2A, Prong 1.
Under Step 2A, Prong 2, the additional elements “by a device,” “by the device and via one or more models” and “wherein the one or more models apply the scrutiny level to obtain the review information; performing,…, an action based on the review information” are recited at a high-level of generality such that it amounts no more than mere instructions for executing / applying / running AI model which merely using generic computing equipment to execute / apply the modified proposed changes to perform the abstract idea. See MPEP 2106.05(f). For the additional elements “obtaining,…, an indication of a proposed change to a subset of executable code from a set of executable code,” “obtaining,…, review information associated with the proposed change” do nothing more than to add insignificant extra solution activity to the judicial exception of merely storing / gathering data. See MPEP § 2106.05(g).
Under Step 2B, 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 elements of “by a device,” “by the device and via one or more models” and “wherein the one or more models apply the scrutiny level to obtain the review information; performing,…, an action based on the review information” amount to no more than mere instructions, or generic computer and/or computer components to carry out the exception, thus, cannot amount to an inventive concept. For the additional elements “obtain a pull request indicating a proposed change to a subset of executable code from a set of executable code” “obtain,…, and using the scrutiny level, review information associated with the pull request” the courts have identified functions such as gathering and storing data as well-understood, routine, conventional activity (Berkheimer v. HP, Inc., 881 F.3d 1360, 1368, 125 USPQ2d 1649, 1654 (Fed. Cir. 2018)), thus do not amount to significantly more than the judicial exception. See MPEP 2106.05(d). Accordingly, the claims are not patent eligible under 35 USC 101.
12. The method of claim 11, wherein the one or more models include at least one of: a first one or more models configured to output at least one of the first context information or the second context information, or a second model configured to output the review information.
The limitations, a first/second/or third model, amount to no more than mere instructions to apply the exception using generic computer and/or mere computer components to carry out the exception under Step 2A, Prong 2. For the limitations, configured to output the first context information… configured to output the second context information, or… configured to output the review information, are merely pre and post activities solutions by data gathering and displaying / outputting the review information under step 2A, Prong 2. See MPEP § 2106.05(g).
13. The method of claim 11, wherein obtaining the review information comprises: providing the scrutiny level as an input to the one or more models.
The limitations, obtaining the review information comprises: providing the scrutiny level as an input to the one or more models, for this claim further recite an additional insignificant extra solution activity under step 2A, Prong 2.
14. The method of claim 11, further comprising: generating, using at least one of the first context information or the second context information, an embedding vector that represents the proposed change in context of the set of executable code; and
wherein determining the scrutiny level comprises: determining the scrutiny level based on a location of the embedding vector in an embedding space.
The limitations for this claim further recite an additional mental process under Step 2A, Prong 1.
15. The method of claim 11, further comprising: generating, using at least one of the first context information or the second context information, a profile representing the proposed change, wherein the profile indicates one or more parameters of the proposed change; and wherein determining the scrutiny level comprises: determining the scrutiny level using the profile.
The limitations for this claim further recite an additional mental process under Step 2A, Prong 1.
16. The method of claim 11, wherein the one or more models include a model configured to output the review information, and wherein the model is trained using account information of an account that is associated with the proposed change.
The limitations configured to output the review information are merely pre and post activities solutions by data gathering and displaying / outputting the review information under step 2A, Prong 2. See MPEP § 2106.05(g). For the limitations wherein the model is trained using account information of an account that is associated with the proposed change is an additional insignificant extra solution activity under step 2A, Prong 2.
17. The method of claim 11, wherein the one or more models include a large language model configured to generate and output the review information.
The limitation the one or more models include a large language model amount to no more than mere instructions to apply the exception using generic computer and/or mere computer components to carry out the exception under Step 2A, Prong 2. For the limitations, configured to generate and output the review information are merely pre and post activities solutions by data gathering and displaying / outputting the review information under step 2A, Prong 2. See MPEP § 2106.05(g).
Claim 18, this claim is within at least one of the four categories of patent eligible subject matter as it is directing to a computer-readable medium claim under Step 1.
18. A non-transitory computer-readable medium storing a set of instructions, the set of instructions comprising:
one or more instructions that, when executed by one or more processors of a device, cause the device to:
obtain a pull request indicating a proposed change to a subset of executable code from a set of executable code;
determine, using one or more artificial intelligence (AI) models, first context information associated with the proposed change and second context information associated with at least one of the subset of executable code, the set of executable code, or a context of the subset of executable code within the set of executable code;
determine a scrutiny level for review of the pull request based on at least one of the first context information or the second context information;
obtain, via the one or more AI models and using the scrutiny level, review information associated with the pull request; and
provide, for display or output, the review information.
Regarding claim 18, the limitations “determine,…, first context information associated with the proposed change and second context information associated with at least one of the subset of executable code, the set of executable code, or a context of the subset of executable code within the set of executable code; determine a scrutiny level for review of the pull request based on at least one of the first context information or the second context information” as drafted, are functions that, under its broadest reasonable interpretation, recite the abstract idea of a mental process. For example, a person is capable of determining the context information with the proposed change to the code using pen and paper and decide how thoroughly to review the code. In the same manner, a person is capable of using context information with aid of pen and paper to be utilized in reviewing the code to determine the scrutiny level of the code review. Therefore, these limitations encompass a human mind carrying out the function through observation, evaluation judgment and/or opinion, or even with the aid of pen and paper. Thus, these limitations recite and falls within the “Mental Processes” grouping of abstract ideas under Step 2A, Prong 1.
Under Step 2A, Prong 2, the additional elements “non-transitory computer-readable medium storing a set of instructions,” “one or more instructions that, when executed by one or more processors of a device, cause the device to” and “using one or more artificial intelligence (AI) models,” and “via the one or more AI models” are recited at a high-level of generality such that it amounts no more than mere instructions for executing / applying / running AI model which merely using generic computing equipment to execute / apply the modified proposed changes to perform the abstract idea. See MPEP 2106.05(f). For the additional elements “obtain a pull request indicating a proposed change to a subset of executable code from a set of executable code,” “obtain,…, and using the scrutiny level, review information associated with the pull request” do nothing more than to add insignificant extra solution activity to the judicial exception of merely storing / gathering data. For the additional elements “provide, for display or output, the review information” are merely pre and post activities solutions by data gathering and displaying / outputting the review information See MPEP § 2106.05(g).
Under Step 2B, 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 elements of “non-transitory computer-readable medium storing a set of instructions,” “one or more instructions that, when executed by one or more processors of a device, cause the device to” and “using one or more artificial intelligence (AI) models,” and “via the one or more AI models” amount to no more than mere instructions or generic computer and/or computer components to carry out the exception, thus, cannot amount to an inventive concept. For the additional elements, “obtain a pull request indicating a proposed change to a subset of executable code from a set of executable code,” “obtain,…, and using the scrutiny level, review information associated with the pull request” and “provide, for display or output, the review information” the courts have identified functions such as gathering, storing and displaying data as well-understood, routine, conventional activity (Berkheimer v. HP, Inc., 881 F.3d 1360, 1368, 125 USPQ2d 1649, 1654 (Fed. Cir. 2018)), thus do not amount to significantly more than the judicial exception. See MPEP 2106.05(d). Accordingly, the claims are not patent eligible under 35 USC 101.
19. The non-transitory computer-readable medium of claim 18, wherein at least one of the first context information or the second context information indicates a level of impact of the proposed change to the set of executable code, and wherein the one or more processors, to determine the scrutiny level, are configured to: determine the scrutiny level based on the level of impact of the proposed change to the set of executable code.
The limitations for this claim further recite an additional mental process under Step 2A, Prong 1.
20. The non-transitory computer-readable medium of claim 18, wherein the one or more instructions further cause the device to: generate, using at least one of the first context information or the second context information, an embedding vector that represents the proposed change in context of the set of executable code; and wherein the one or more instructions, that cause the device to determine the scrutiny level, cause the device to: determine the scrutiny level based on a location of the embedding vector in an embedding space.
The limitations generate, using at least one of the first context information or the second context information, an embedding vector that represents the proposed change in context of the set of executable code; and… to determine the scrutiny level… determine the scrutiny level based on a location of the embedding vector in an embedding space further recite an additional mental process under Step 2A, Prong 1. The limitation the one or more instructions, that cause the device amount to no more than mere instructions to apply the exception using generic computer and/or mere computer components to carry out the exception under Step 2A, Prong 2.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-8 and 10-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over USPN 20240184570 to Fu et al. in view of USPN 20200026511 to SWIERC et al.
Per claim 1:
Fu discloses:
1. A system for automated code review using artificial intelligence (AI), the system comprising:
one or more memories (Fig. 8, elements 808, 810 and related discussion); and
one or more processors, communicatively coupled to the one or more memories (Fig. 8, elements 804, 810 and related discussion), configured to:
obtain a pull request indicating a proposed change to a subset of executable code from a set of executable code (Paragraph [0022,0023] “data mining engine 104 mines source code repositories 102 for pull requests, commits, comments, and source code files having code changes 103” also see Fig. 7 the pull request 708 and related discussion);
determine, using one or more AI models (Paragraph [0022] “a pre-training engine 110 and a neural encoder 112”), first context information associated with the proposed change (the code diff hunk 114 is a sequence of changed source code lines… surrounded by a few unchanged lines or context see, Paragraph [0023] “code diff hunk 114 is a sequence of changed source code lines, including deleted lines, surrounded by a few unchanged lines or context. The code diff format is an efficient representation of the code changes since the unchanged lines occur only once”) and second context information associated with at least one of the subset of executable code, the set of executable code, or a context of the subset of executable code within the set of executable code (Since this appears to be MARKUSH type language requiring at a minimum just one from the list, Fu teaches Paragraph [0026] “model receives the masked sequences of code diff hunks and code review comments (i.e., second context information) and the model learns to reconstruct the original text by predicting the replacement of the masked tokens”);
generate an embedding vector representing at least one of the first context information or the second context information (Since this appears to be MARKUSH type language requiring at a minimum just one from the list, Fu teaches Paragraph [0021] “generating the neural encoder that produces encodings or embeddings for each chunk of a code diff hunk… include edits of changed code with and without code review comments… changed code is represented with its surrounding context in a code diff format to show the edits made to the original code or previous version of the code that produced the changed code”);
determine, using the embedding vector and an embedding space (Paragraph [0039] “encoded by the neural encoder 310 and each encoded chunk or embedding 312 is used as a search key by the database engine 316 to retrieve the top-k semantically-similar code review comments”), of the pull request (Paragraph [0024] “code diff hunk generator 106 receives the pull requests”) based on at least one of the first context information or the second context information (Since this appears to be MARKUSH type language requiring at a minimum just one from the list, Fu teaches Paragraph [0019] “each chunk, its approximate k-nearest code review comments are obtained using the L2 distance between an encoding of the chunk associated with a code review… value of k is pre-configured and limits the number of retrieved code review comments to at most k code review comments based on their respective L2 distance”);
obtain, via the one or more AI models, review information associated with the pull request (Paragraph [0026] “pre-training dataset generator 108… code review comment or review comments 116… model receives the masked sequences of code diff hunks and code review comments and the model learns to reconstruct the original text”); and
perform, based on the review information, an action to modify the proposed change or to commit the proposed change to the set of executable code (Since this appears to be MARKUSH type language requiring at a minimum just one from the list, Fu teaches Paragraph [0017] “developer may make additional changes to the code based on the comments submitted by the peers… the changes are merged into the main branch of the source code repository”).
Fu does not explicitly disclose a scrutiny level for review.
However, SWIERC discloses in an analogous computer system a scrutiny level for review (Paragraph [0039,0041] “determine a confidence (i.e., scrutiny level) 134 for each training source code file 106 included in an association rule 118… one or more of the predefined support threshold 132, the predefined confidence (i.e., scrutiny level) threshold 136”).
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention was made to incorporate the method of a scrutiny level for review as taught by SWIERC into the method of a code review for given a proposed source code change as taught by Fu. The modification would be obvious because of one of ordinary skill in the art would be motivated to add/incorporate the features of a scrutiny level for review to provide an efficient technique for maintaining and synchronize the code change with the distributed version control system where plurality of user access the files so as to avoid any errors during compilation or runtime as suggested by SWIERC (paragraph [0001]).
Per claim 2:
Fu discloses:
2. The system of claim 1, wherein the review information includes at least one of:
natural language text indicating a review of the proposed change, or proposed executable code to be included in the proposed change (Since this appears to be MARKUSH type language requiring at a minimum just one from the list, Fu teaches Paragraph [0075] “natural language text of the code reviews used in the pre-training datasets”).
Per claim 3:
Fu discloses:
3. The system of claim 1, wherein the one or more AI models include at least one of:
a first model configured to output the first context information, a second model configured to output the second context information, or a third model configured to output the review information (Since this appears to be MARKUSH type language requiring at a minimum just one from the list, Fu teaches Paragraph [0024] “surrounding context includes unchanged lines of code before and after the source code lines of code change”).
Per claim 4:
The rejection of claim 1 is incorporated and further, Fu does not explicitly disclose wherein the scrutiny level indicates a level of review to be applied by the one or more AI models when reviewing the pull request.
However, SWIERC discloses in an analogous computer system wherein the scrutiny level indicates a level of review to be applied by the one or more AI models when reviewing the pull request (Paragraph [0039,0041] “determine a confidence (i.e., scrutiny level) 134 for each training source code file 106 included in an association rule 118… one or more of the predefined support threshold 132, the predefined confidence (i.e., scrutiny level) threshold 136”).
The feature of providing wherein the scrutiny level indicates a level of review to be applied by the one or more AI models when reviewing the pull request would be obvious for the reasons set forth in the rejection of claim 1.
Per claim 5:
The rejection of claim 1 is incorporated and further, Fu does not explicitly disclose a setting of the one or more AI models, a hyperparameter of the one or more AI models, or a prompt input to the one or more AI models.
However, SWIERC discloses in an analogous computer system a setting of the one or more AI models, a hyperparameter of the one or more AI models, or a prompt input to the one or more AI models (Since this appears to be MARKUSH type language requiring at a minimum just one from the list, SWIERC teaches Paragraph [0041] “the predefined confidence threshold 136, and the predefined lift threshold 140 may be set”).
The feature of providing a setting of the one or more AI models, a hyperparameter of the one or more AI models, or a prompt input to the one or more AI models would be obvious for the reasons set forth in the rejection of claim 1.
Per claim 6:
The rejection of claim 1 is incorporated and further, Fu does not explicitly discloses determine the scrutiny level based on the level of impact of the proposed change to the set of executable code.
However, SWIERC discloses in an analogous computer system determine the scrutiny level based on the level of impact of the proposed change to the set of executable code (SWIERC note here that the estimated probability determine the scrutiny level of impact that is recommended by the rule, see, Paragraph [0041] “predefined support threshold 132, the predefined confidence threshold 136, and the predefined lift threshold 140 may be set based at least in part on an estimated probability that a training source code file 106 recommended by an association rule 118”).
The feature of providing determine the scrutiny level based on the level of impact of the proposed change to the set of executable code would be obvious for the reasons set forth in the rejection of claim 1.
Per claim 7:
The rejection of claim 1 is incorporated and to determine the scrutiny level taught by as applied above to claim 1 and further, Fu discloses:
7. The system of claim 1, wherein the one or more processors are further configured to:
generate, using at least one of the first context information or the second context information, the embedding vector to represent the proposed change in context of the set of executable code (Paragraph [0021] “generating the neural encoder that produces encodings or embeddings for each chunk of a code diff hunk… include edits of changed code with and without code review comments”); and
wherein the one or more processors, are configured to: determine the scrutiny level based on a location of the embedding vector in the embedding space (Paragraph [0055] “initial inputs to an encoder block 402 are the input embeddings 418 of an input sequence, such a code diff hunk 420. In order to retain the order of the tokens in the input embedding 418, positional embeddings 422 are added to the input embedding 418 forming a context tensor 42”).
Per claim 8:
The rejection of claim 1 is incorporated and to determine the scrutiny level taught by as applied above to claim 1 and further, Fu discloses:
8. The system of claim 1, wherein the one or more processors are further configured to:
generate, using at least one of the first context information or the second context information, a profile representing the proposed change, wherein the profile indicates one or more parameters of the proposed change (note here each developer has its own profile, see, Paragraph [0016] “Each developer obtains a full copy of the files in the repository in their own branch… developer makes changes to their version of a file of the repository”); and
wherein the one or more processors, are configured to: determine the scrutiny level using the profile (note here each developer has its own profile Paragraph [0016] “Each developer obtains a full copy of the files in the repository in their own branch… developer makes changes to their version of a file of the repository”).
Per claim 10:
Fu discloses:
10. The system of claim 1, wherein the one or more processors, to perform the action, are configured to:
generate a reviewed pull request indicating a reviewed change to the subset of executable code (Paragraph [0099] “a request to the code review generation engine 300 for a code review comment for the changed code of the pull request”),
wherein the reviewed change incorporates the proposed change and the review information (Paragraph [0068] “changed code may include a code review comment which includes comments describing the reasons for the change, suggestions for remedies, and so forth”); and
cause the reviewed pull request to be merged with the set of executable code (Paragraph [0099] “developer 706 may submit additional pull requests including additional changes and eventually the changes are merged into the source code file of the hosting service”).
Per claim 13:
The rejection of claim 1 is incorporated and further, Fu does not explicitly discloses providing the scrutiny level as an input to the one or more models
However, SWIERC discloses in an analogous computer system providing the scrutiny level as an input to the one or more models (Paragraph [0046] “providing input that indicates whether one or more training source code files 106 recommended by the one or more association rules 118 are relevant… the machine learning algorithm 100 may increase or decrease a probability of applying an association rule 118”).
The feature of providing the scrutiny level as an input to the one or more models would be obvious for the reasons set forth in the rejection of claim 1.
Per claim 16:
Fu discloses:
16. The method of claim 11, wherein the model is trained using account information of an account that is associated with the proposed change (note here that he developer 706 have a sourced filed stored so, it is inherent that source file is associated with an account of a developer, see, Paragraph [0099] “hosting service 700 interacts with a developer 706 having a copy of a source code file stored” also see computing device 802 and related discussion).
Fu does not explicitly disclose wherein the one or more models include a model configured to output the review information.
However, SWIERC discloses in an analogous computer system wherein the one or more models include a model configured to output the review information (Paragraph [0025] “output a source code file recommendation notification 40 including an indication 46 of each source code file 36 of the second set 44 of one or more source code files 36”).
The feature of providing wherein the one or more models include a model configured to output the review information would be obvious for the reasons set forth in the rejection of claim 1.
Per claim 17:
Fu discloses:
17. The method of claim 11, wherein the one or more models include a large language model configured to generate and output the review information (Paragraph [0040] “neural transformer model with chunk cross-attention 330. A beam search engine 328 uses the neural transformer model with chunk cross-attention 330 to predict one or more code review candidates 332”).
Claims 11-12 and 14-15 is/are the method claim corresponding to apparatus/system claims 1+4, 3, and 7-8 respectively, and rejected under the same rational set forth in connection with the rejection of claims 1+4, 3, and 7-8 respectively, as noted above.
Claims 18-20 is/are the medium/product claim corresponding to method claims 1 and 6-7 respectively, and rejected under the same rational set forth in connection with the rejection of claims 1 and 6-7 respectively, as noted above.
Allowable Subject Matter
Claim 9 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. Please note that if any of the objected claims are rejected under statues 101 and/or 112 above, applicants must overcome those rejections in order for these claims to be allowed.
The cited prior art taken alone or in combination fail to teach, in the context of the claim limitations and in combination with the other claimed limitations “generate another embedding vector that represents the profile; identify, in the embedding space, a nearest neighbor embedding vector to the other embedding vector; and determine the scrutiny level based on another scrutiny level that was applied for another profile that is represented by the nearest neighbor embedding vector” as recited in the claim 9.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Related cited arts:
Brindescu, Caius, et al. "How do centralized and distributed version control systems impact software changes?." Proceedings of the 36th international conference on Software Engineering. 2014. pp. 322-333.
Rao, N. Rama, and K. Chandra Sekharaiah. "A methodological review based version control system with evolutionary research for software processes." Proceedings of the Second International Conference on Information and Communication Technology for Competitive Strategies. 2016. pp. 1-7.
Muşlu, Kıvanç, et al. "Transition from centralized to decentralized version control systems: A case study on reasons, barriers, and outcomes." Proceedings of the 36th international conference on software engineering. 2014. pp. 334-344.
US 20160070568 A1 - Systems and methods for managing review of source code are described. The method may comprise receiving a version of source code that includes a specific change at a specific location in the version of source code that has been affected by one or more programming actions compared to a prior version of source code; and identifying a plurality of prior review requests associated with the specific change. The method may comprise assigning corresponding review points to the plurality of prior review requests; and based on the corresponding review points, selecting a code reviewer from a plurality of code reviewers who each have created or processed a subset of the plurality of prior review requests. The method may further comprise generating a review request for the specific change in the version of source code for processing by the selected code reviewer.
US 20200341752 A1 - An electronic apparatus for automatically performing a source code review and a method thereof are provided. The electronic apparatus includes a communication interface, a memory storing at least one instruction, and at least one processor to control the communication interface. The at least one processor, by executing the at least one instruction, is configured to, based on a source code being submitted to a source code repository with a pull request, receive a webhook event message from the source code repository through the communication interface, download the submitted source code from the source code repository, extract a changed source code among the downloaded source codes, and perform a code review of the extracted source code through at least one inspection module.
US 20210311729 A1 - Systems and methods provide acquisition of a plurality of code artifacts and one or more code review comments associated with each code artifact, generation of a set of code features based on each of the plurality of code artifacts, input of each set of code features to a neural network to generate code review comments respectively associated with each of the plurality of code artifacts, determination of a loss by comparing each generated code review comment respectively associated with one of plurality of code artifacts with the one or more review comments associated with the one of plurality of code artifacts, and modification of the neural network based on the loss.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Satish Rampuria whose telephone number is 571-272-3732. The examiner can normally be reached on Monday-Friday from 8:30 AM to 5:00 PM.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Chat Do, can be reached at telephone number 571-272-3721. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
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) Form at https://www.uspto.gov/patents/uspto-automated- interview-request-air-form.
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.
/Satish Rampuria/Primary Examiner, Art Unit 2193
*****
Prosecution Insights