95 results about "Code review" patented technology

The invention discloses a full-process automatic unit testing method, device and equipment for an AI chip operator, a medium and a product. The method comprises the following steps: generating an engineering directory and a test framework design document through an architect agent according to operator interface information and a DSL operator design document knowledge base; the method comprises the following steps of: generating a test code for unit test by a software engineer agent according to a test framework design document and a domain knowledge base, and storing the test code in an engineering directory; multiple rounds of interaction are carried out through a software engineer agent and a test engineer agent, a test code is gradually corrected into a target test code which can be successfully compiled, a generated test case can be successfully executed and the generated test case meets the code coverage rate requirement, and a target operator code passing a unit test is obtained; and submitting the target operator code and the target test code which pass the normativity check to a code warehouse through a code auditing engineer agent so as to automatically realize the whole-process unit test of the AI chip operator.

The invention provides an intelligent analysis method, system, equipment and program product for automatic code review, which are applied to the field of computer software engineering and development tools, and the method comprises the following steps: obtaining code difference data, preprocessing to generate a semantic code unit, constructing a structured cue word and inputting the structured cue word into a large language model, according to the scheme, the problems that in existing code review, semantic understanding is insufficient, and efficiency is low can be solved, automatic risk identification and analysis of code changes are achieved, and review efficiency and accuracy are improved.

The invention relates to the technical field of code review, and provides a database code review method based on context enhancement and multi-dimensional confidence filtering, which comprises the following steps of: performing analysis and semantic enhancement processing on submitted code differences, acquiring context information related to current code change semantics by retrieving historical data, and storing the context information in a database; generating an enhanced review prompt; according to the enhanced review prompt, an artificial intelligence model is called for analysis to generate preliminary review suggestions, and a multi-dimensional evaluation system is adopted to evaluate each preliminary review suggestion to generate corresponding confidence evaluation features; and calculating a comprehensive score of each preliminary review suggestion according to the confidence evaluation features, implementing filtering and decision making according to the comprehensive scores, and outputting final review suggestions. According to the method, the accuracy and global correlation of the review opinions can be remarkably improved, the false alarm rate is reduced, the result credibility is enhanced, intelligent filtering is realized, and high-value feedback is output.

The invention provides a code review method and system based on a multi-dimensional knowledge graph and electronic equipment. The method comprises the following steps: constructing a business knowledge graph, a method calling graph and a code review knowledge graph; code data are obtained, a target code in the code data is determined based on the code review request, and the target code comprises code change content; generating a large model cue word in combination with the business knowledge graph, the method calling graph and the code review knowledge graph; and according to the big model cue word, calling an AI big model to perform joint review on the code change content, and generating a review report which at least comprises a repair suggestion. According to the method, multi-dimensional knowledge of business, code calling and code review is integrated, a more comprehensive and closely associated knowledge system is formed, the generated cue word can accurately guide the AI large model to review code change in combination with multi-field knowledge, blindness of the large model during review is avoided, and review efficiency and accuracy are improved.

The embodiment of the invention provides a code review method and a computer program product, and relates to the technical field of artificial intelligence. The method comprises the following steps: analyzing a to-be-reviewed code into an abstract syntax tree, extracting a dependency relationship of each code node from the abstract syntax tree, calculating the code complexity of each code node, generating a topological structure diagram according to each code node and each dependency relationship, marking each network node according to each code complexity and a preset code rule, and generating a topological structure diagram according to each network node. And performing visual review on the to-be-reviewed code. Therefore, the cognitive load and troubleshooting time of a developer for positioning the architecture level problem in a large-scale project are effectively reduced and shortened.

The invention provides an AI-based code review opinion automatic classification and priority ranking method. The method comprises the steps of collecting code review historical data; data preprocessing: preprocessing the collected data, and constructing a training data set; an AI model is selected and trained; inputting a new review opinion; automatic classification: the model automatically classifies the review suggestions, and classification categories include but are not limited to code errors, code style problems, performance optimization suggestions and potential safety hazard prompts; performing priority ranking: performing priority ranking on the review opinions based on a preset priority rule and the classification result; and generating result output. According to the code review method and device, automatic classification and priority ranking of the code review opinions are achieved through the AI model, a traditional manual processing mode is replaced, the problems that manual classification is low in efficiency and priority ranking is high in subjectivity are effectively solved, and the overall efficiency and result accuracy of code review are improved.

The invention belongs to the technical field of software development, and particularly provides a research and development-oriented long and short-term memory framework construction method and system, which adopts a layered memory architecture to construct four core modules including a short-term memory compressor, a medium-term memory aggregator, a long-term memory graph and a cross-layer memory router. The system takes multi-source input such as research and development dialogues, code snippets and project documents as a starting point, extracts research and development elements through semantic analysis and entity recognition technologies, compresses lengthy dialogues into structured short-term memory by utilizing an attention distillation mechanism, upgrades high-frequency short-term memory into medium-term knowledge fragments based on a time sequence attenuation algorithm, and improves the research and development efficiency. And constructing a long-term knowledge graph containing developer portraits, project dependence and normative standards by adopting a graph convolutional network. Context understanding accuracy, multi-round dialogue continuity and personalized service quality of a large model in a research and development scene are remarkably improved, and the method is suitable for mainstream research and development tool scenes such as IDE plug-ins, code review and architecture design.

The invention provides a vulnerability discovery method and system based on symbol-semantic hybrid reasoning, and belongs to the technical field of software security. The method comprises the steps that a target program is analyzed, and an event sequence is extracted; converting the event into a symbol with a time sequence label and confidence, and constructing a symbol dependency graph; reasoning based on the dependency graph, calling a large language model to generate a semantic reasoning action when the certainty is insufficient, and updating the state after symbol verification; new rules are extracted from the inference chain passing verification through reinforcement learning, and self-evolution is achieved; and outputting a vulnerability report containing the reasoning path and the confidence coefficient. The system correspondingly comprises a time sequence probability symbol module, a symbol-semantic bidirectional coupling reasoning module, a reinforcement learning self-evolution module and a report generation module. According to the method, the preciseness of symbol logic and the generalization ability of a semantic model are fused, the accuracy, interpretability and adaptive ability of vulnerability detection are effectively improved, and the method is suitable for security audit and code review of a complex software system.

The invention discloses a code review assisting method and system based on a large model. The system is in butt joint with a code review platform, and after a patch set change event is received, codes are detected out and engineering snapshots are constructed. And the LLM agent interacts with the large language model, calls an LSP client to obtain diagnosis and call chain information when static analysis is needed, and feeds an observation result back to the model to generate an examination conclusion. And when the LSP returns an error, a negative feedback mechanism is triggered, the model is guided to correct parameters and symbols, and illusion is reduced. And the review conclusion is converted into comments and automatically published to the platform, so that high-risk change automatic identification is realized, the manual workload is reduced and the accuracy is improved.

The invention relates to the technical field of computers, in particular to a code review method and device, electronic equipment and a storage medium, which are used for efficiently screening out high-quality and high-diversity training data so as to improve the accuracy of code review. The method comprises the following steps: acquiring a training sample set and a test sample set, and dividing the training sample set into a plurality of training sample subsets; the test sample set comprises test samples reaching expected quality; after a to-be-trained code review model is preliminarily trained based on the training sample set, the test influence degree of each training sample subset on the code review model on the test sample set is determined; for at least one target training sample subset of which the test influence degree meets a preset influence condition in the plurality of training sample subsets, performing clustering according to a sample gradient to obtain a plurality of clusters; and sampling is carried out in each cluster, and the code review model after preliminary training is trained again according to the obtained sampling sample set.

The invention discloses an AI-based code quality and defect analysis method and device, equipment and a medium, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining a code merging request submitted by a user; in response to the code merging request, extracting code change content based on the code change version; inputting the code change content into a pre-trained large model, and performing semantic analysis on the code change content by the large model to detect potential quality problems in the code change content; for each potential quality problem, obtaining related code context information of the potential quality problem, inputting the related code context information into a pre-trained large model, and performing authenticity verification by the large model based on the related code context information to screen out a real quality problem; and according to the real quality problem, generating a code review report. According to the method, efficient, objective and continuous code quality review can be realized on the premise of ensuring the review quality.

Given prompts including code changes, association intent, and extended context made to a source code program, a code review is automatically generated by a large language model. From the perspective of the code reviewer, the intent represents the problem of code changes and is predicted from a neural classifier given code changes in a code difference format. The neural classifier is a neural encoder transformer model that is pre-trained on various code review datasets and fine-tuned on code disparity blocks of code changes tagged with intent.

The embodiment of the invention provides a code specification review method and device based on the combination of a large language model and a static code check tool and electronic equipment, and relates to the field of code specification review. Each code specification rule is read and understood; the type of each code specification rule is analyzed, a proper checking tool is distributed to each code specification rule, and the checking tools comprise a large language model and a static code checking tool; generating a configuration file of the static code checking tool according to the code specification rule type, and dynamically adjusting parameters of the configuration file according to the specific condition of the project; scheduling a large language model or a static code checking tool for checking by utilizing an MCP architecture; and summarizing all inspection results to generate a structured code review report. The method solves the problems that a traditional code review tool is low in execution efficiency and lacks intelligent judgment.

The application discloses a code review method and related equipment, and relates to the technical field of software development. The method comprises the following steps: if a review triggering event for target code is detected, obtaining context information of the target code; based on the context information, calling a preset large language model to perform primary code review on the target code, and generating a primary review result; if the primary review result meets a preset condition, obtaining user feedback information for the primary review result; based on the context information, the primary review result and the user feedback information, calling the preset large language model to perform secondary code review on the target code, and generating a target review result. The application introduces a large language model primary review based on context and a secondary review mechanism combined with user feedback in the code review process, realizes the automation and iterative optimization of code review, reduces the dependence on manual work, improves the review efficiency, and improves the accuracy and reliability of the review result.

A code review comment is automatically generated using multiple agents that perform a dedicated task using a particular language model. A code quality estimator agent uses a code quality encoder model to determine whether a code change to a file of a repository presents a risk to the repository if merged. For those code changes classified as presenting a risk, a comment generator agent uses a generative language model to generate an initial code review comment for the code change and determines a severity of the issue with the code change. A comment critic agent uses a reasoning language model to critique the initial code review comment generated by the generative language model. A final code review comment is output by the comment critic agent when the comment critic agent determines that the initial code review comment is satisfactory.

The invention discloses a kernel code review method and device fusing reinforcement learning and prompt word tuning, and relates to the technical field of code review, and the method comprises the steps: extracting patch meta-information, building a code review task, extracting a code difference item and a necessary context thereof to form a to-be-reviewed target code segment, and carrying out the review of the to-be-reviewed target code segment; and forming a primary review prompt template, calling the code review large language model to perform primary code review, summarizing primary review results, forming a filled expert-level review prompt template in combination with the patch meta-information and the kernel knowledge base, and performing expert-level code review to generate a comprehensive review result. A code review process is constructed by applying a Boosting thought in machine learning, the code review efficiency is improved, it is ensured that single input content is located in a context window of a large language model, the integrity of code semantic understanding of the model is guaranteed, a preorder model is corrected by using a postorder model, and the code review efficiency is improved. And the discovery capability of complex logic defects and cross-file problems is effectively improved.

A method and a system for automating a peer code review are provided. The method includes: receiving a pull request associated with an evaluation of a source code; generating, based on the pull request, a workflow associated with the evaluation of the source code; transmitting the workflow and the source code to a plurality of AI agents; performing, via the plurality of AI agents, a review of the source code, and each respective AI agent of the plurality of AI agents is responsible for a separate code review process from among a plurality of code review processes; aggregating each respective result from among the plurality of code review processes; and determining, based on the aggregating of each respective result, whether the pull request passes the evaluation of the source code.

The invention discloses a code review method and device based on artificial intelligence. The method comprises the following steps: in response to a code merging request of a navigation service, pulling a to-be-reviewed code data source; and based on the declaration or definition of the review elements in the review prompt words in the code review protocol of the navigation service and the review check items in the review prompt words, reviewing the to-be-reviewed code data source to obtain an artificial intelligence review result of the to-be-reviewed code data source. The code review specification comprises review prompt words for a map function, a retrieval function, a guide function or a path calculation function of the navigation service. The review elements and the review check items in the review prompt words are determined based on the reviewed corresponding functions, and the code review work of the navigation service can be automatically realized by applying the review prompt words aiming at the corresponding functions of the navigation service through an artificial intelligence technology. The interaction cost of navigation service code review is saved, the review efficiency is improved, and the burden of manual code review is relieved.

The invention discloses a code review opinion generation method based on retrieval enhancement. The code review opinion generation method comprises the steps of 1, constructing a comparative learning training data set fusing code change structure features and review intention semantic features; 2, driving a universal pre-training code encoder to carry out transfer learning to a code review field by utilizing the comparative learning data set to obtain a review intention perception retriever; step 3, recalling a historical reference case as a reference context based on the retriever after fine tuning, and constructing a structured prompt template containing an anti-noise mechanism; and step 4, combining the prompt template, and performing instruction fine tuning on the large language model by using a low-rank adaptive technology (LoRA). Through cooperation of retrieval vector space remodeling and efficient parameter fine tuning, the problem that in the prior art, review opinions are seriously generalized is effectively solved, the pertinence and reference value of automatically generated opinions are remarkably improved, and the expert-level automatic code review opinion generation technology in the low-computing-resource environment is achieved.

The invention relates to the technical field of software engineering, in particular to an automatic code review method based on retrieval enhancement generation (RAG), and relates to the technical field of software engineering, in particular to an automatic code review method based on RAG. The method comprises the steps that a vector database containing historical code repair examples is constructed, after code change fragments are encoded, similar examples are retrieved, and a retrieval result is fused to guide a generation model to complete a review task; by introducing a contrast learning mechanism, the representation capability of an encoder is optimized, so that code snippets with similar semantics are more closely distributed in a vector space, and the retrieval accuracy is improved; furthermore, retrieval data is organized by adopting a graph structure, a graph is constructed according to meta-information such as defect types, project affiliation and semantic similarity, graph-guided retrieval is performed based on the graph, and a GraphRAG method is realized. According to the method, four tasks of code problem detection, problem positioning, problem type identification and optimized code generation are automatically completed, the accuracy, consistency and interpretability of a review result are remarkably improved, and the method is suitable for intelligent auxiliary development and quality guarantee scenes in a large-scale software project.

This invention discloses a collaborative code review method, device, and medium based on role-based division of labor among multiple review agents, relating to the field of artificial intelligence. The method includes: responding to a code review trigger event, acquiring the code to be reviewed and related context information, and preprocessing it to generate a standardized context data packet; synchronously distributing the context data packet to at least two review agents, each configured to specialize in a different code quality dimension; each review agent independently and in parallel reviewing the data packet based on a review strategy customized for its corresponding dimension, and generating structured results; aggregating all structured results and performing automated processing, including deduplication, conflict resolution, and priority ranking; and generating and outputting a code review report based on the processing results. This invention achieves deeply specialized, highly efficient, parallel, and structured automated code review.

The application provides a code review method, device, storage medium and program product. The method comprises: performing semantic labeling on variables in target code according to a requirement document to generate a variable description document; generating a prompt word of a large language model according to the requirement document, the target code and the variable description document; inputting the prompt word of the large language model into the large language model to generate a review result of the target code. Compared with the prior art, the embodiment of the application establishes a mapping relationship between the code and the requirement document by performing semantic labeling on the variables in the target code according to the requirement document to generate the variable description document; and the large language model can accurately understand the meaning of the variables in the target code by further generating the prompt word in combination with the requirement document and the target code, thereby improving the reliability of the code review and the accuracy of the code review result.

This invention relates to a two-tiered evaluation method for targeted code review capabilities of candidates, belonging to the field of intelligent recruitment and technical capability assessment. The method includes: acquiring candidate background data, task objective data, and code review task configuration data; extracting experience highlights from the background data; constructing generation constraints based on experience highlights and task objective data; generating targeted code review tasks based on these constraints; matching corresponding problem patterns from a preset problem pattern library and embedding them into basic code to construct the code to be reviewed; acquiring the candidate's output problem identification results and improvement plan results; performing structured analysis on the two results to establish a correspondence between problems and solutions; generating code review evaluation results based on this correspondence and outputting capability detection results. This invention solves the problems of the review task being disconnected from the candidate's background and the single evaluation dimension, improving the targeting, objectivity, and discriminativeness of code review capability assessment.

The invention discloses a research, development and operation method and device for security left shift, and relates to the field of software development processes and security management.The method comprises the steps that a security demand baseline is established in the demand analysis stage, security demands and business demands are fused, and risk protection measures are determined; security architecture design review is carried out in the architecture design stage, and a security team carries out threat modeling on the system architecture and carries out one-ticket negative right; in the code development stage, code specifications, open source component vulnerabilities and logic risks are scanned in real time through a static code analysis tool, and a code security closed-loop management mechanism is established; in the compiling and constructing stage, code review and component list filing are implemented, a security review report is formed by combining a dynamic penetration test and a running flow test, and a security strategy is updated through a continuous monitoring mechanism to deal with new threats. Security practice can be systematically integrated in the early stage of the software development life cycle, and the later vulnerability repair cost is remarkably reduced.

The application relates to a code review method and device, computer equipment and a storage medium. The foregoing method comprises the following steps: in response to a review request of a current code line, extracting context feature data of the current code line, obtaining a code submission record corresponding to the current code line, obtaining code branch information to which the current code line belongs according to the code submission record, obtaining function requirement information corresponding to the current code line according to the code branch information, inputting the context feature data, the historical code submission record and the function requirement information into a pre-trained code review model, and obtaining a review result corresponding to the current code line. The method can improve the efficiency of code review and refine the review granularity.

This application discloses a method, apparatus, device, and storage medium for finding empty statement blocks. By obtaining the project source code, extracting the abstract syntax tree from the Java files in the project source code, and using the abstract syntax tree with a preset list and preset key nodes, it quickly finds the empty statement blocks that may exist in the project source code. This solves the technical problems of high difficulty, low success rate, high time consumption, high labor cost, and low efficiency of manual code review.

The invention relates to the technical field of data governance and artificial intelligence large model application, in particular to a method and system for improving data governance ability based on a large model, and the method and system extract data standard information from a standard file and update the data standard information to a data governance platform to assist a user in decision making. The extraction process comprises the steps of reading a data standard specification file, performing data element extraction and solidifying a data standard extraction result; the method has the beneficial effects that the multi-mode capability and the code generation capability provided by a large model are utilized, a large model reasoning service interface is connected in a data standard definition and data development link of data management, an intelligent analysis function of a data standard file is provided, and data standard information can be automatically extracted from a standard file; in addition, natural language demand analysis is provided, corresponding SQL codes are rapidly generated, and the functions of code review and code testing are provided. According to the method, the technical threshold of data development can be greatly reduced, and the efficiency and accuracy of data development are improved.

The invention relates to the technical field of artificial intelligence, in particular to an AutoGen-based code generation and review system and method, and the method comprises the steps: receiving a code demand input by a user; through an AutoGen core arrangement module, a demand understanding Agent is scheduled to convert the demand into a structured task; the scheduling code generation Agent generates an initial code; scheduling the test case generation Agent to write a test case; scheduling a code execution Agent to run the code and the test case, and capturing an execution result; scheduling a code review Agent to review the code, and generating a review opinion; the method has the beneficial effects that revolutionary improvement is brought to code generation and review by introducing an AutoGen multi-agent collaboration framework, so that the method is superior to the prior art in the aspects of automation degree, code quality guarantee, problem solving capability, flexibility and economic benefits, and has remarkable social benefits and economic benefits.

In some implementations, a code review system may identify a set of open code review requests that are each associated with a respective proposed change to source code stored in a code repository. The code review system may assign a respective priority to each open code review request, in the set of open code review requests, according to a respective set of attributes associated with each open code review request. The code review system may receive, from a reviewer device, a request to perform a code review workflow for an open code review request. The code review system may select an open code review request, in the set of open code review requests, associated with a highest priority. The code review system may manage the code review workflow for the open code associated with the highest priority.

Apparatus and methods for creating a real-time functional code reviewer with an architecture placemat are provided. The apparatus and methods may include a server with an artificial intelligence / machine learning (“AI / ML”) real-time functional code reviewer program. The real-time functional code reviewer program may receive source code in a markup language for review. The program may analyze the source code. The program may generate functional context feedback, review feedback, and an architecture placemat. A code reviewer, through a user device, may review the functional context feedback, review feedback, and the architecture placemat. The code reviewer may provide feedback to the source code developer.