669results 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.

The invention provides a rapid construction and reuse method and system for an application framework, and relates to the technical field of application framework construction, and the method comprises the following steps: mapping code snippets to a high-dimensional tensor space, extracting multi-level code features, and constructing a code association graph and a deep semantic network; constructing a hierarchical Bayesian network based on the spatial-temporal feature map, executing variational reasoning and adaptive particle filtering, and generating a reconstruction code; driving a multi-level generation network by using a dual-dimension discriminator, optimizing a code structure and a dependency relationship, and generating a final optimization code through program slicing and incremental synthesis; according to the method, rapid construction and reuse of the application framework are realized, and the code quality and the execution efficiency are improved.

Techniques for intelligently prompting an LLM to refactor code are disclosed. A code snippet is accessed. This code is identified as potentially comprising a reference to an out-of-compliance library. Context for the code snippet is generated. An LLM prompt is then built. This prompt will be fed to the LLM, and the prompt instructs the LLM to refactor the code snippet into modified code, which calls a compliant library. Output of the LLM is displayed. This output is based on the LLM operating in response to the LLM prompt. The output includes a proposed rewritten version of the code snippet.

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 discloses a code generation method, which comprises the following steps that: a code development platform receives input information of a user in a first code file in a project, acquires a context in the file and a first cross-file context according to a static structure of the project, and acquires a second cross-file context according to behavior characteristics of the user in a development project, obtaining a third cross-file context according to the evolution coupling degree of at least one second code file in a code warehouse of the project and the first code file, and generating prompt information according to the input information, the context in the file, the first cross-file context, the second cross-file context and the third cross-file context, and inputting the prompt information into the code generation model for reasoning to obtain at least one group of generation codes, and displaying the at least one group of generation codes to the user. According to the method, the multi-dimensional item-level context and the user input serve as the input of the code generation model, the capability of the code generation model for utilizing the cross-file context in the code generation process is improved, and the code generation effect is improved.

An approach is provided that identifies a vulnerability corresponding to an initial source code. Then, the approach generates a prompt comprising the initial source code and the vulnerability. The approach inputs the prompt into an artificial intelligence model (AIM) that is trained to determine whether the initial source code comprises the vulnerability. In turn, the approach removes, using the AIM, the vulnerability from the initial source code to produce a refactored source code in response to determining that the initial source code comprises the vulnerability.

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.

The present application belongs to the technical field of artificial intelligence. Disclosed are a code recommendation method and apparatus, and a device and a computer-readable storage medium. The method comprises: acquiring code generation information, wherein the code generation information is used for describing a programming task of a code; generating at least one candidate code on the basis of the code generation information; determining from among the at least one candidate code a candidate code to be repaired, wherein the candidate code to be repaired comprises a wrong parameter, which does not meet at least one of a syntax constraint and semantic constraint of a programming language corresponding to the programming task; and repairing the wrong parameter comprised in the candidate code to be repaired, so as to obtain a repaired candidate code, and recommending the repaired candidate code and an unrepaired candidate code among the at least one candidate code, wherein the unrepaired candidate code is different from the candidate code to be repaired. After a candidate code is generated, a candidate code having an error is automatically repaired, thereby improving the accuracy of a recommended code.

The invention provides a code defect detection method and system based on a large model. The method comprises the following steps: generating an enhanced semantic understanding vector corresponding to an initial source code by utilizing a pre-trained large-scale language model in combination with an attention mechanism; identifying the logic error pattern to determine the defect type and position of the initial source code; the reinforcement learning algorithm selects an optimal repair path by simulating a plurality of repair paths and evaluating the effectiveness of each repair path, and generates a repair code snippet through the optimal repair path; replacing a corresponding part in the initial source code with the repair code snippet, and generating a target source code; performing quality scoring on the target source code based on the code quality evaluation model to obtain a quality feedback result; and outputting the target source code with the change annotation and the quality feedback result. According to the method and the device, the speed and the accuracy of finding and solving coding errors in the software development process are improved, and meanwhile, the quality of repaired codes is also ensured.

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.

A computer-implemented method includes receiving an original code snapshot corresponding to original code from a first file of a plurality of files. The method also includes receiving a modified code snapshot corresponding to modified code that includes a code modification modifying the original code. The method also includes generating, using a large language model (LLM), refactoring code based on the original code snapshot and the modified code snapshot. The refactoring code is configured to apply the code modification to code from other files of the plurality of files associated with the original code. The method also includes identifying target code from a second file of the plurality of files where the target code is associated with the original code. The method also includes applying the code modification to the identified target code using the refactoring code.

Disclosed in the present application is a code generation method. The method comprises: a code development platform receiving input information from a user for a first code file in a project; acquiring in-file context and first cross-file context on the basis of a static structure of the project; acquiring second cross-file context on the basis of behavior characteristics of the user when developing the project; acquiring third cross-file context on the basis of the degree of evolution coupling between at least one second code file in a code warehouse of the project and the first code file; generating prompt information on the basis of the input information, the in-file context, the first cross-file context, the second cross-file context and the third cross-file context; inputting the prompt information into a code generation model for reasoning, so as to obtain at least one group of generated codes; and presenting to the user the at least one group of generated codes in parallel. The method takes multi-dimensional project-level context and a user input as inputs of a code generation model, thereby improving the capability of the code generation model using cross-file context during code generation, and improving the code generation performance.

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 code review method based on a large language model and related equipment, and the code review method based on the large language model comprises the steps that a plurality of code change files are obtained, and each code change file in the code change files comprises a code change log; if the total mark number of the code change files is larger than the maximum mark receiving number of a preset large language model, the integral of each code change file is determined based on the meta-information of the updated project and the code change log of each code change file; compressing the plurality of code change files based on the integral and the meta-information to obtain a plurality of compressed code change files; and reviewing the plurality of compressed code change files based on a preset large language model to obtain a code review result. According to the method and the device, comprehensive, efficient and accurate review of code changes is realized, and the code review accuracy and efficiency are improved.

The invention discloses a code recommendation method, device and equipment and a computer readable storage medium, and belongs to the technical field of artificial intelligence. The method comprises the steps of obtaining code generation information, wherein the code generation information is used for describing a programming task of a code; generating at least one candidate code according to the code generation information; a to-be-repaired candidate code is determined from the at least one candidate code, the to-be-repaired candidate code comprises wrong parameters, and the wrong parameters do not meet at least one of grammatical constraints or semantic constraints of a programming language corresponding to the programming task; the candidate code to be repaired comprises wrong parameters, the repaired candidate code is obtained, the repaired candidate code and an unrepaired candidate code in the at least one candidate code are recommended, and the unrepaired candidate code is different from the candidate code to be repaired. After the candidate codes are generated, the candidate codes with errors can be automatically repaired, and the accuracy of the recommended codes is 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.

The invention discloses a JavaScript language security reinforcement method based on a virtual machine technology, and belongs to the field of JavaScript languages. The method comprises the following steps: firstly, building a test system comprising a compiler, an assembler, a virtual machine and a packer; then, a developer submits the JavaScript program or the function requirement to be tested to the test system; a test system constructs a to-be-tested program by using a Yarn environment, and a compiler compiles a JavaScript source code and analyzes and converts the JavaScript source code into an intermediate representation IR; the assembler converts the IR into byte codes, and converts the relative reference address into an absolute address by generating a character string table and a lookup table; and the generated byte code is optimized. The test system submits the optimized byte code to the virtual machine, the virtual machine runs a byte code program, and after execution is completed, the test system collects an execution result of the virtual machine and compares the execution result with an expected result; and finally generating a test report and delivering the test report to developers for confirmation. According to the method, the security of the JavaScript code is enhanced through a virtualization technology, and malicious access and analysis are prevented.

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.