537results about "Code refactoring" patented technology

The invention discloses an intelligent programming auxiliary method and system based on a multi-modal AI language model, and belongs to the technical field of programming auxiliary tools. The method comprises the following steps: a multi-modal input processing stage; a dynamic context modeling stage; a hierarchical semantic analysis stage; in the code generation stage, codes are generated in two stages by adopting a Codex-Plus large model; the reinforcement learning driven code optimization stage is used for carrying out multi-objective optimization and reward function design on the codes generated in the code generation stage; a multi-dimensional feedback stage; an interaction and visualization stage; code semantic deep analysis, dynamic context sensing, multi-target optimization generation and real-time interactive feedback are realized by fusing code texts, natural language description, developer behavior data and a domain knowledge graph, and programming efficiency and code quality can be remarkably improved.

Disclosed herein are embodiments of systems, methods, and products for modernizing and optimizing legacy software. A computing device may perform an automated runtime performance profiling process. The performance profiler may automatically profile the legacy software at runtime, monitor the memory usage and module activities of the legacy software, and pinpoint / identify a subset of inefficient functions in the legacy software that scale poorly or otherwise inefficient. The computing device may further perform a source code analysis and refactoring process. The computing device may parse the source code of the subset of inefficient functions and identify code violations within the source code. The computing device may provide one or more refactoring options to optimize the source code. Each refactoring option may comprise a change to the source code configured to correct the code violations. The computing device may refactor the source code based on a selected refactoring option.

The invention discloses a code reconstruction method, system and device based on function recognition and a medium, and the method specifically comprises the steps: scanning a project file topological structure, and constructing a knowledge graph based on a code import relation and a technology stack feature; performing context enhancement by analyzing the code function description and combining with the knowledge graph to generate a code modification instruction set; based on the code modification instruction set, in combination with data stream sensitivity marking and performance portrait analysis, evaluating the target code to obtain an evaluation result; based on an evaluation result, matching a historical optimal practice mode through a graph neural network, and generating an optimization scheme which retains an original design style; by comparing abstract syntax tree differences between original codes and verified optimization schemes, only functional logic nodes are replaced, and legal code style features are reserved. According to the method, the efficiency and quality of code reconstruction and optimization are improved, and a more convenient, efficient and intelligent code processing tool is provided for software developers.

The invention discloses an intelligent Bug management method and platform based on an AI large model. The method comprises the steps that structured error codes, unstructured log texts and development communication records are collected; standardized Bug features are obtained after preprocessing; semantic matching is performed based on a CodeBERT large model to generate a historical similar Bug case set, and a problem code segment is analyzed and positioned in combination with an AST abstract syntax tree; according to the project technology stack features, the historical similar Bug case set and the problem code segment, generating a repair scheme including code modification suggestions, automatically generated repair code snippets and implementation risk assessment; constructing and optimizing a triple knowledge graph; and finally, associating the standardized Bug features, the problem code segment, the repair scheme and the knowledge graph to obtain a Bug diagnosis result, and outputting the Bug diagnosis result. According to the method, intelligent positioning and accurate repairing of the Bug are achieved, the average Bug solving time is remarkably shortened, and meanwhile automatic precipitation of development experience is achieved through the continuously optimized knowledge graph.

The invention relates to a code file rewriting method and device based on a large language model, and the method comprises the steps: analyzing a source code file, obtaining the structure of a source code, and enabling the structure of the source code to comprise the definition of each function and the position of each function code in the source code file; respectively inputting each function code into a large language model, and respectively processing according to each cue word to complete rewriting of each function code; and combining each rewritten function code corresponding to each position in the source code file to form a rewritten code file. According to the invention, a scheme for optimizing and rewriting the codes based on the large language model and the file level can be provided.

The invention provides a software package source code optimization method of a cross-instruction-set architecture. The method comprises the following steps: step 1, retrieving and collecting various architecture migration optimization cases; step 2, the verified optimization cases are accumulated through the optimization library; 3, collecting a software package source code with a poor migration effect in a project, and providing the software package source code to a big language model to generate an optimization suggestion of migration between an original architecture and a target architecture; 4, inputting the to-be-optimized software package source code and the optimization suggestion into the large language model to generate a candidate optimization code; 5, further evaluating and screening the candidate optimization codes; step 6, retrieving in the optimization library based on the semantic features of the current code to obtain an excellent instance; step 7, performing optimization again by using a large language model; and step 8, evaluating a construction speed increase rate and function consistency. According to the scheme, a double-stage task decomposition strategy is adopted, the semantic drift risk is effectively reduced, and the accuracy of instruction-level conflict repair is improved.

The embodiment of the invention provides a code repairing method, device and equipment based on a large language model.The method comprises the following steps that a code to be repaired is analyzed through a code scanning tool on the basis of a coding specification, error information of the code to be repaired is obtained, the error information comprises an error number, a violation rule, a supplementary description, an error example, a correction example, an error type and an error code segment; generating a cue word template according to a historical repair sample and a coding specification of the large language model, and filling the cue word template with the error information to generate a filled cue word; and inputting the filled cue word into the large language model to generate a repair code segment, judging whether the repair code segment accords with a set conversion specification, and if the repair code segment accords with the conversion specification, replacing the code to be repaired with the repair code segment to generate a repaired code. According to the scheme, the code is repaired through an end-to-end automatic process, and the code repairing efficiency is improved.

The invention discloses a retrieval enhanced warehouse-level code completion method based on semantic topology and disambiguation redundancy pruning. Firstly, a key value code library for accurate mapping of source code fragments and induction sub-graphs is constructed through a specific slicing algorithm; in the retrieval stage, four-level layered optimization is adopted, structural similarity is evaluated by extracting a deep semantic relationship, trimming accurate duplicate items and using a new graph-based measurement (tradeoff is performed on editing according to topological importance), results are reordered to maximize correlation and diversity, candidate items are systematically refined, and the retrieval efficiency is improved. The problems of retrieval redundancy solidification and surface similarity misleading are solved, meanwhile, cross-module dependence is analyzed through an external perception identifier disambiguator, and the problem of cross-file symbol ambiguity is solved; and finally, fusing an optimization result to generate a prompt to drive the LLM to generate higher-quality output. According to the invention, through coordination of semantic and structural signals, strong performance can be obtained even in a large-scale and resource-limited code library. Meanwhile, the design allows it to be orthogonally complementary to other cross-file methods, providing collaborative improvements when used in combination.

The invention provides an intelligent software development auxiliary system and a use method, and belongs to the technical field of computer software development. The system comprises a project demand analysis module which is used for obtaining and analyzing project demand data and generating feature vectors of demands; the code style optimization module is used for analyzing semantics and styles of the original codes, analyzing and normalizing the original code structures, and generating code structures and style specifications meeting project standards; the intelligent code completion module is used for analyzing context semantics of the codes after style optimization, generating code completion suggestions conforming to project standards in combination with project demand data, and outputting structured completion code snippets; the technology stack intelligent recommendation module automatically recommends an optimal technology stack for the project according to the project demand data and the optimized code structure; and the development behavior risk detection module monitors programming behaviors of developers in real time, captures abnormal operations, marks potential risks and generates operation optimization suggestions.

Embodiments of the present invention provide a code reconstruction method and system, a computing device, a storage medium and a program product wherein the code reconstruction method comprises: performing code analysis on a to-be-reconstructed initial code to generate a target reconstruction scheme wherein the target reconstruction scheme comprises a code reconstruction plan and a code test plan; the code reconstruction plan comprises a function dependency relationship of the target code; analyzing a function dependency relationship in the code reconstruction plan, and generating at least two code reconstruction tasks corresponding to the initial code; executing the at least two code reconstruction tasks in sequence to obtain each initial code snippet, and iteratively optimizing each initial code snippet through static analysis and dynamic verification until candidate code snippets conforming to a function dependency relationship are generated; and compiling a test case of each candidate code snippet based on the code test plan, and testing each candidate code snippet based on each test case to obtain a plurality of target code snippets conforming to the function dependency relationship. And the coherence and the consistency of the reconstructed codes are ensured.

Techniques for complex code modification via chain of thought prompting are described. A modification service obtains code to be modified according to a modification goal, and can decompose the modification goal, via use of a database or a machine learning model, to identify a set of modification steps. The set of modification steps may be organized according to a chain of thoughts, tree of thoughts, or graph of thoughts. The modification service can execute the set of modification steps via use of a machine learning model to yield modified code, which can be returned to a user.

The invention discloses a software development management method based on big data, and relates to the technical field of software development management, and the method comprises the steps: collecting multi-source development data, transmitting the multi-source development data to a data lake in real time through a distributed message queue, and generating a structured data stream with a timestamp and a time sequence relation graph; performing Monte Carlo sampling on the three-dimensional radiation field model of the neural radiation field and the causal influence graph, simulating the cascade influence submitted by the current code, and outputting a risk value and a dependency chain; loading a neural radiation field three-dimensional code space model, a node risk value and a dependency chain, dynamically rendering a causal influence path, and generating a visual risk report; and generating a code optimization task according to the visual risk report, submitting an optimized code version to a code library, and calibrating parameters of the neural radiation field three-dimensional code space model. According to the method, the spatio-temporal characteristics of code change are analyzed, Monte Carlo simulation is combined, hidden dependence and a risk conduction chain are identified, and the comprehensiveness and predictive ability of framework corruption analysis are improved.

Systems are provided for generating, modifying and using SBOMs for facilitating risk assessment and threat mitigation for corresponding programs, and particularly for large programming builds. The creation and modification of the SBOMs includes processes for omitting declarations referenced in chunk SBOMs of program chunks incorporated into a final programming build associated with a build SBOM, but which are not actually utilized by the final programming build, as well as processes for adding new declarations for code segments that are not declared in the related chunk SBOMs, even though the code segments are utilized by the final programming build. Systems are also configured to use SBOMs in combination with configuration restriction records to assess and resolve threat events in a manner that can prevent unnecessary remedial actions for threat events that appear to be relevant to one or more files or dependencies incorporated into a program.

The invention discloses a front-end multi-module development method and system based on module federation. The method comprises the following steps: extracting necessary examples, public components and public methods in a front-end project to a public basic module, and constructing a module federated product; decoupling other functional modules, and configuring a module code and a module federation construction entry in the construction configuration file; remote module lists and configuration information are managed in a centralized mode through the project configuration module; executing a construction command to call the project construction module to independently package each module and update the project configuration module; and when the application is started, the project loading module loads the public basic module and the remote function module according to the project configuration module. Compared with an existing Module Federation scheme with application as granularity, independent construction, configuration management and flexible loading during operation are achieved on the module level, dependence on repeated and redundant logic is avoided, module plug and play and version switching are supported, and therefore development efficiency, construction performance and expansibility are improved.

The invention provides a permission configuration method and device. The method comprises the following steps: acquiring a source code and relative path information of a target document edited in a current editing environment; wherein the relative path information is used for representing position information of the target document relative to a root directory of a working area of the current editing environment; analyzing the source code to obtain a document structure object of the target document; performing node traversal on the document structure object to identify a target node corresponding to the interaction component from each node of the document structure object; according to the permission attribute corresponding to the target node and the relative path information, generating an attribute value of the permission attribute in the source code; wherein the attribute value is used for performing permission configuration of the interaction component, so that the accuracy and consistency of permission configuration are improved, the workload of manual permission configuration of developers is reduced, and the development efficiency is improved.

Provided are embodiments for code and deviation management. A method implementing a large language model (LLM) may be provided. The method may include: receiving, from a user, a source code; determining whether or not the source code violates at least one coding rule; based on determining that the source code violates the at least one coding rule, presenting information associated with the violation to the user; receiving, from the user, a user feedback associated with the presented information; determining, based on the user feedback, whether or not at least one rule deviation is to be implemented; based on determining that the at least one rule deviation is to be implemented, performing at least one operation to manage at least one deviation report; and based on determining that the at least one rule deviation is not to be implemented, performing at least one operation to manage the source code.

The invention provides a user-defined script dynamic editing and executing method and system of a Unity engine. The method comprises the following steps that codes are input and preprocessed; executing text cleaning, word segmentation and annotation preprocessing according to the line feed as a code line set; grammatical analysis and semantic understanding; constructing an abstract syntax tree, identifying a syntax structure, and combining context analysis semantics to generate a symbol table; processing errors in real time; positioning an error line through a multi-stage matching strategy, highlighting an error position through a visual interface, and generating a repair suggestion in combination with a line number mapping table, error propagation analysis and a multi-evidence fusion mechanism; executing dynamic codes; explaining and executing the corrected script, and feeding back an execution result; through interaction with a Unity engine, operation control of a script on a game object and a scene is realized; through three core technologies of semantic weight dynamic matching, an anti-interference navigation state machine and a hybrid sorting algorithm, the long-standing problems of low matching precision, poor interaction experience and the like in the field of code completion are solved.

In some aspects, a management system is provided that interfaces with software code to execute a refactoring process. The process executes iteratively, where a generative AI component (e.g., an LLM) is given the task to make a repository pass a given validation iteratively. In each step, the LLM in provided as an input a list of failed validations to resolve and the ability to interact with the repository. In some examples, the LLM is configured to read source files, write source files, and retrieves information from other data sources such as the Internet or semantically-indexed source repositories, including the repository that the process is currently operating on, among other operations. Further, external APIs and databases can also be included in the process. The LLM will then execute one or multiple of these operations and process one or multiple files to generate modified and / or new code.

The invention provides a defect repairing method and device based on a large model, electronic equipment and a medium, and relates to the field of defect repairing, and the method comprises the following steps: obtaining original log data generated in real time; analyzing the original log data through a preset model, and determining defect logs and user operation parameters; determining a target code file corresponding to the defect log; repairing the target code file through a preset model, and generating a repairing scheme to determine a repaired code file; and submitting the repair code file to a code warehouse to cover the target code file, determining an updated code warehouse, and determining a production system instance according to the updated code warehouse. According to the method, the original log of the deployed system is obtained in real time, the defect log and the associated user operation parameters are automatically analyzed and determined, the target code file is positioned, the repair scheme adjustment code is generated, then the repair code is submitted to the warehouse for updating, the production system instance is determined, and automation of the whole process of defect repair is achieved.

The invention discloses a VerilogA code automatic error correction method based on a classification error library and a large language model, and the method comprises the steps: constructing a classification system of the error types of VerilogA codes, starting from an MTJ device, carrying out the statistics of 84 common errors in the VerilogA codes of MTJ based on the system, and developing an automatic training sample generation system according to the 84 common errors; the method comprises the following steps: selecting a DeepSeek-R1-7B model as a basic model through a benchmark test, and carrying out fine tuning training by utilizing a classified error data set generated by scripting to form a special error correction model for the field. The processing process comprises the steps that VerilogA codes to be corrected are received, error types and reasons are positioned through a trained model, correction codes are generated, and verification of eight types of typical circuits is passed. An error classification-model training-simulation verification system is established, verification and error correction of VerilogA codes are achieved, and time and resources in the development process are saved.

Methods and systems for improving modernization of legacy software using an intelligent discovery platform are described herein. A client-based agent may generate metadata regarding the received legacy software. The code metadata may be analyzed by a code classifier module, which computes a plurality of score factors from the metrics from the legacy software metadata using a knowledge base from a modernization platform. The classified code metadata may be used by a project-specific model to derive a plurality of sub-scores based on the plurality of score factors associated with the legacy software. An analytics engine may then identify a code module from the legacy software having a greatest derived vulnerability score factor. A graphical interface including reconstructed code, corresponding modern code, and an explanation of vulnerabilities may then be generated by the analytics and reporting component for the identified code module.

The invention discloses a method for generating a text system, and aims to solve the problems of long development cycle, disjunction of requirements and technology implementation and the like of traditional software and realize automatic generation from a natural language requirement to a deployable service system based on a large language model. The method is divided into two stages: in the first stage, a system is disassembled into a logic subsystem through man-machine cooperation, core business logic is extracted, a large language model is called by adopting a divide-and-conquer strategy, and a detailed specification containing a functional process and an interface form is generated; in the second stage, a large language model is called to generate a database table structure and a DDL script, an engineering framework of a basic technology stack is initialized and integrated through a predefined scaffold, CRUD codes are generated, the codes are analyzed to generate a transformation plan for structured data, and target logic codes are incrementally integrated. According to the method, control is achieved through Python, the problem of large model input limitation is solved, and generated codes are standard and extensible. The development cycle is shortened, the requirement-design-code consistency is guaranteed, the threshold is lowered, platform locking is avoided, and enterprise digital transformation is assisted.

A computer-implemented method and system standardize code patterns within enterprise software environments. A code modernization system utilizes a Large Language Model (LLM) and a specialized prompt library. The library includes pattern recognition prompts to guide the LLM in identifying specific code patterns within selected software code, potentially using enterprise-specific context. It also includes standardized solution prompts to guide the LLM in generating replacement code conforming to predefined enterprise standards for the identified patterns. The system orchestrates communication, transmitting code and relevant prompts to the LLM and receiving identified patterns and subsequently the generated standardized replacement code. This automated approach facilitates improved code quality, consistency, maintainability, and can support code translation efforts within the enterprise.

The invention particularly relates to a code writing, checking and modifying method based on a large model. According to the code writing, checking and modifying method based on the large model, a fine-tuning large language model is adopted to analyze user requirements, and multi-language initial codes are generated; executing deep code review through a static analysis engine, wherein the deep code review comprises syntax tree verification, security vulnerability mode matching and API dependency chain detection; executing the automatically generated test case set in an isolation environment, monitoring operation indexes in real time, and generating a defect thermodynamic diagram; and driving the large model to perform iterative code reconstruction based on a defect analysis result until it is confirmed that a preset quality standard is met. The code writing, checking and modifying method based on the large model is suitable for multiple languages, the defect rate of codes is reduced, the software development period is prolonged, the labor cost is reduced, and the vulnerability detection rate is greatly increased.

The invention provides a cloud native micro-service splitting and reconstructing method based on runtime behaviors. A three-layer architecture design is adopted, and the system comprises a dependency network graph construction module, a micro-service division module and a code reconstruction module. The dependency network diagram construction module models specific project source codes and user access operation into abstract representation capable of being processed by an algorithm, the micro-service division module divides a network diagram, obtains a splitting scheme for the dependency network diagram through visual page interaction with a user and manual modification, and inputs the splitting scheme into the code reconstruction module; and a code reconstruction module performs code reconstruction based on the splitting scheme and the dependency network diagram to obtain a complete and operable micro-service architecture code, so that the effect of automatically analyzing Spring Boot project source codes and monitoring the running project to generate the dependency network diagram is realized.

Module information about software modules constituting first software and produced by one or more first companies included in a supply chain of the first software is received from a terminal corresponding to the first companies. Different parts of the module information are stored in a storage device and a distributed ledger that uses a block chain platform. Software information including information about one or more software modules constituting the first software is generated based on one or more pieces of the module information stored in the storage device and the distributed ledger. The software information is transmitted to a terminal corresponding to a second company.

The invention discloses an automatic code complementing and optimizing method and device and a medium. The method comprises the following steps: performing data preprocessing on an obtained code sample data set to generate high-quality training data; training the training data by adopting a pre-constructed algorithm model to generate a code completion model; performing problem diagnosis on the to-be-completed code by adopting a multi-dimensional code diagnosis strategy, and outputting a completion keyword of the to-be-completed code; inputting the completion keyword of the to-be-completed code into the code completion model, and outputting a code completion rule of the to-be-completed code; and complementing and optimizing the to-be-complemented code according to the code complementing rule to obtain a complemented code.

A graph representing the source code is computed, the graph comprising a plurality of nodes connected by edges, each node representing a software component of the source code and each edge representing a relationship between software components. A domain model of a domain related to the legacy code base is computed, the domain model comprising a plurality of concepts and relationships between the concepts. A node of the graph matching one of the concepts is identified. A functional role of model is assigned to the identified node. The knowledge of the assigned functional role is used to trigger any of: migration, deployment as a microservice, deployment as a containerised service, deployment as a cloud-native application, maintenance, refactoring.

The present application relates to the technical field of artificial intelligence, and discloses a code processing method and apparatus, a computing device cluster, and a storage medium. According to the code processing method provided by the present application, in a code processing process, a first code and modification opinion information are obtained, and due to the semantic meaning of the modification opinion information, an association between the first code and the modification opinion information, and the like, a certain rule exists between a modification intent and a code modification position. Therefore, on the basis of the first code and the modification opinion information, the modification intent and the code modification position can be obtained, so as to realize automatic understanding of the modification opinion information. The first code is processed on the basis of the modification intent and the code modification position. Since the amount of codes to be processed may be enormous, compared with manually understanding the modification opinion information and then processing the codes, the code processing method provided by the present application can reduce the error rate in the code processing process, and improve the code processing efficiency.

The invention discloses a cross-language migration-based low-resource programming language corpus enhancement method, which comprises the following steps of: receiving a source language code, and driving a large language model to generate an initial target language code through a two-way retrieval mechanism fusing example guidance and knowledge constraint; secondly, constructing an automatic iterative repair closed loop by utilizing the feedback of a compiler, and carrying out self-correction on codes which fail to be compiled; thirdly, high-quality codes are screened out through automatic quality gating and fed back to a corpus and a knowledge base, and self-enhancement circulation of data and knowledge is formed; finally, the method further comprises an offline model evolution step based on grammar and semantic alignment driven by a compiler, a big language model is trained by collecting preference data generated by an online process, and the ability of the big language model to understand a target language is improved fundamentally. According to the method, the core problems of low quality, poor efficiency and lack of self-evolution ability of a low-resource programming language in code migration are solved.