310 results about "Codebase" patented technology

Targeted dynamic analysis of code is provided by utilizing static analysis and dynamic analysis. A static code analysis system can operate to generate an initial analysis of code. The results of the initial analysis may be used to target a dynamic analysis system to analyze portions of code identified by the static analysis as potentially containing defects. In some cases, a preliminary dynamic analysis may be used to generate code inputs that may be utilized in future analyses to determine the inputs necessary to target particular code paths identified by a static analysis as potentially defective. Future updates to the code base may utilize the generated data to target analysis to code paths affected by the updates.

Systems and methods for resolving code vulnerabilities through collaborative agents which may include accessing a code base of an identified vulnerability; configuring a plurality of autonomous agents, each comprising a predefined agent role associated with application security remediation process; executing a directed workflow of the plurality of agents, wherein the workflow is a conditional sequence of agent-driven processing steps for generating a proposed resolution to the identified vulnerability; and outputting a candidate resolution for the vulnerability based on results produced by the workflow.

The invention discloses an intelligent code change recognition system, method and device based on a large language model and a medium, and relates to the field of software code review and large language models. The system comprises a code monitoring module, a prompt word module, a large language model module and a user-defined rule module. The code monitoring module monitors a code library event and transmits information; the cue word module generates natural language cue words; the large language model module gives a change recognition result based on the cue words and the code review knowledge base; and the custom rule module manages personalized review rules. A code pushing event is monitored through the code monitoring module, the code pushing event is analyzed by the large language model module after being processed by the prompt word module, whether a change request is created or not is intelligently judged, and a knowledge base is updated by utilizing a historical review result. According to the method, unreasonable change requests are reduced, the review workload is reduced, the accuracy and adaptability are improved, and personalized requirements are met.

Systems and processes are disclosed for enhancing cybersecurity and optimizing software repositories through integration of web crawling, web scraping, feature engineering, and advanced machine learning algorithms to detect phishing attempts, prevent account takeover fraud, and identify unused code in repositories. The system collects and refines data from various sources, including transaction logs, customer databases, device details, external data sources, and historical fraud data, to build comprehensive datasets. Feature engineering creates new, meaningful features from the refined data, which are used to train and evaluate machine learning models. The best-performing models are deployed in production to monitor incoming communications and transactions in real-time, flagging suspicious activities and optimizing codebases. This processing ensures timely detection and prevention of security threats while maintaining efficient software development processes. Robust protection is provided against evolving cyber threats and enhances software performance and security through continuous learning and adaptation.

The invention discloses an AI-based low-code automatic development method and system and a medium, mainly relates to the technical field of image processing, and is used for solving the existing problems that the demand conversion efficiency is low, the code quality depends on manpower, and the complex scene support is insufficient. Comprising the steps of extracting a current functional entity corresponding to a code function core feature; based on the current functional entity and the historical functional entity, extracting an associated sub-graph containing the current functional entity and the historical functional entity from a preset knowledge graph corresponding to the demand technical field; dSL grammar corresponding to the demand technical field is obtained, entity nodes related to the associated sub-atlas, inter-node interaction logic rules and code function core features are input into the DSL grammar, and intermediate representation IR is obtained; and according to the intermediate representation IR, the code function core features and the current function entity, a model trained by a large-scale code library is utilized to generate a specific code.

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 relates to the field of wisdom education, and particularly discloses a teaching strategy optimization model and grammar error early warning method based on data mining, and the method comprises the following steps: S1, obtaining original code data in a student code library in real time, and preprocessing the original code data to obtain a structured data matrix; s2, for the structured data matrix, generating a grammar parse tree through a grammar parser, positioning error nodes and extracting context features by using a node traversal algorithm, and constructing a single-error multi-dimensional feature vector; meanwhile, an error association rule base is constructed based on historical error data, a causal relationship across error types is identified, and dynamic knowledge graph data is formed. According to the technical scheme, association analysis and deep mining can be carried out on the multi-source learning data, dynamic solution suggestions for student individual errors or group generality errors are formed, and teachers are assisted to quickly adapt to dynamically changing learning requirements of the students.

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.

An online system performs inference requests in conjunction with the model serving system to perform AI (text-based LLM or multi-modal transformer)-generated integration test variants. Instead of rigid code-specified integration tests, the LLM creates integration test variants that follow a specification. Given one or more files from the codebase of an application and a specification for integration testing, the LLM compiles an integration test including a series of actions (e.g., API calls) as runnable code and assertions about the state of the application after the actions are executed.

A codebase system that maintains and utilizes a dynamic mapping between a collection of tests and files within a codebase to ensure error detection and code validity. The codebase system accesses a collection of tests configured to process files within the codebase to identify errors. It then generates a mapping by executing these tests to determine the specific files each test operates on. Upon detecting updates to the test collection, the codebase system updates this mapping by re-executing the updated tests, identifying the new set of files for each test, and aggregating these updates into the existing mapping. When changes to the files in the codebase are detected, the codebase system accesses the updated mapping to identify which tests relate to the altered files. The codebase system then executes this relevant subset of tests to validate the modifications made to the files.

Intelligent code block selection and codebase updating using generative AI is disclosed herein. A user may request a code block for performing a task based on a given quality parameter (e.g., most energy efficient, fastest, or the like). The system may select an AI model for evaluating code blocks to meet the quality parameter. The system may identify code blocks for evaluation and execute each code block in an isolated testing environment. The selected AI model evaluates each code block execution and selects a code block based on completing the task in a way that most adheres to the quality parameter. The selected code block is returned via a user interface. The selected code block may be stored in a configuration code building block library associated with the quality parameter and the task and used when developing and revising software for the industrial automation environment.

The invention relates to the technical field of software engineering, and discloses a software development code review system and method based on reinforcement learning, and the system comprises a historical code feature collection module, a software development code operation parameter collection module, a code feature matching optimization module, a code feature optimization analysis module, and a code review result output module. The method comprises the following steps: extracting code features in a historical code library according to a time sequence, collecting code operation parameters in a software development process in real time, completing evaluation on software development code operation, performing feature matching optimization on the code operation parameters based on an evaluation result, obtaining an evaluation result of a to-be-evaluated operation code after matching optimization, and performing evaluation on the to-be-evaluated operation code according to the evaluation result. Based on the initial evaluation result and the feature optimization analysis result of the software development code, a code review result is output, early warning information is provided for the client through initial evaluation and matching optimization evaluation, and the code quality and safety in the software development process are improved.

The invention belongs to the technical field of software engineering, and particularly relates to a unit test method for generating a discrimination model based on retrieval. Searching a to-be-tested function, namely a test case pair, and establishing a code library; constructing an efficient code retriever based on code embedding and mixed feature extraction; constructing a multi-input matching discriminator network, preparing an own data set, and training the network; integrating the code library, the retriever and the discriminator into a local knowledge base, and performing fine adjustment on the large model based on the local knowledge base to obtain a retrieval generation discrimination model; and generating a test case based on the retrieval generation discrimination model, and testing. According to the method, the discrimination model is generated by using retrieval, corresponding change is automatically carried out according to the previous test case, and the test with higher coverage rate and quicker speed can be realized.

The invention discloses a large language model reasoning acceleration method and device based on two-stage speculative decoding and a storage medium, and the method comprises the steps: constructing and initializing a Trie tree, and inserting a historical corpus, and phrase sequences in a document library or a code library into the Trie tree one by one; in the reasoning process, longest prefix matching is carried out based on a Trie tree, and a candidate draft sequence is generated by adopting branch backtracking and recursive search; performing confidence evaluation on the candidate draft sequence, calculating a joint confidence score of the sequence through probability multiplication and a Top-K screening mechanism, and judging whether the joint confidence score reaches a confidence threshold; if the accumulated confidence of the candidate sequence reaches a threshold value, skipping a small model generation stage, and directly entering large model verification; otherwise, entering a small model draft completion stage; and the final large model takes the replaced and updated draft sequence as final output. According to the method, adaptive acceleration of the decoding process can be realized, and the long text reasoning delay of the large language model is remarkably reduced while the generation quality is ensured.

The invention discloses a large-scale code library analysis method and device, equipment and a storage medium, and the method comprises the steps: carrying out the first analysis processing of a code file, obtaining a code knowledge graph corresponding to the code file, and storing the code knowledge graph in a graph database; performing second analysis processing on the code file based on the code knowledge graph to obtain semantic logic corresponding to the code file, and storing the semantic logic into a vector database; and performing retrieval based on the graph database and the vector database, and returning a retrieval result corresponding to the query request of the user. The code file is subjected to the first analysis processing to obtain the code knowledge graph, then the code file is subjected to the second analysis processing based on the code knowledge graph to obtain the semantic logic, the code knowledge graph is stored in the graph database, and the semantic logic is stored in the vector database; the interpretability and maintainability of the large-scale code library are improved, and then the accuracy and efficiency of large-scale code library retrieval are improved.

The invention discloses a demand development method, device and equipment. The method comprises the following steps: calling a demand analysis agent to analyze a natural language demand into a structured function demand unit comprising an input specification, an output specification and an execution constraint; the calling code generation agent generates source codes corresponding to the development requirements according to data type definitions and function calling specifications in the structured function requirement unit and the local project code library; calling a code test agent to generate and execute a test case based on the source code and the structured function demand unit; and after determining that a software deployment condition is met based on a test result, calling a code deployment agent to generate a deployment script and configuration information, and submitting the deployment script and the configuration information to a deployment execution engine to complete automatic deployment. According to the application, end-to-end automatic development from natural language requirements to application deployment can be realized.

Methods, systems, apparatuses, devices, and computer program products are described. A processing device may support a large language model (LLM) for automatically improving pull requests to a codebase. To use the LLM, the processing device may create and maintain a vector space tracking information relating to historical pull requests to the codebase. The processing device may receive a new pull request indicating a change to code in the codebase and may determine, from the vector space, a vector corresponding to a code chunk affected by the pull request. The processing device may send, as an input to the LLM, a prompt including the code chunk affected by the pull request and one or more comments from a set of historical comments relating to the code chunk and indicated by the determined vector. The processing device may modify the pull request based on the one or more comments.

Examples described herein provide a computer-implemented method that includes, in response to receiving a request against the workload in an environment comprising predetermined cloud-based containers, searching predetermined container runtime interface metadata across a plurality of compute nodes in the environment to locate runtime processes. The method further includes selecting, for each runtime process located, a respective applicable profiler from a set of predetermined profilers sharing a transactional database. The method further includes injecting, for each runtime process located, predetermined code libraries for each respective applicable profiler. The method further includes re-linking the predetermined code libraries for each respective applicable profiler. The method further includes executing, for each runtime process located, each respective applicable profiler to produce a set of results.

The invention relates to the technical field of computers, in particular to a code sample optimization method and system based on a language large model, and the method comprises the steps: firstly, obtaining a source code sample, determining a code sample boundary, and generating a mark sequence; then, based on a compiling result, a static analysis result and a unit test result, a quality label is generated, and a training sample set is formed; then, taking a Transform neural network model of bidirectional context coding as an encoder, and carrying out training under the supervision of quality annotation to obtain a quality evaluation model; and finally, screening according to a preset quality score threshold to obtain a high-quality code sample set. According to the technical scheme, by combining the deep grammar analysis and context understanding of the code samples, the accuracy and efficiency of automatic screening are improved, manual intervention is reduced, and the method can adapt to automatic evaluation of a large-scale code library.

The present invention sets forth a technique for performing automated software security scanning. The method includes copying a plurality of codebase branches included in a code repository into a clone database, based on one or more scripts included in a script database. The method also includes simultaneously executing one or more scanning operations on each of the plurality of codebase branches via a plurality of processing threads and generating one or more scan results based on the one or more scanning operations executed on the plurality of codebase branches.

Techniques for implementing an AI threat modeling tool are disclosed. A static analysis tool is used to extract a candidate code snippet from a code repository. The candidate code snippet is identified as potentially being a security relevant code element. The static analysis tool generates additional context associated with the candidate code snippet. An LLM prompt is generated. This prompt is structured to include the candidate code snippet, the context, and a directive to assign a classification to the candidate code snippet. The classification includes a source classification, a sink classification, a sanitizer classification, or a flow step classification. The LLM operates on the prompt to generate output comprising a specific classification for the candidate code snippet. The output is formatted into a data extension file that is consumable by the static analysis tool.

The invention discloses a program defect repairing method and device, equipment and a storage medium. The method comprises the steps that a defect code segment is obtained from a first program code which is reported to be wrong, and a similar defect code segment and a similar repair patch corresponding to the defect code segment are inquired in a historical code library; constructing a first prompt word based on the defect code segment, the similar defect code segment and the similar repair patch, generating a repair patch based on the first prompt word, and repairing the first program code through the repair patch to obtain a second program code; and under the condition that the verification of the second program code is not passed, regenerating a repair patch based on a defect code segment appearing in the verification process of the second program code, and repairing the second program code through the newly generated repair patch. According to the method, the big language model is guided to generate the high-credibility repair patch through the historical similar defects and the repair patch thereof, and the problem that in the prior art, the repair patch is unreliable due to the fact that the big language model is separated from an actual repair case is solved.

A method in one embodiment comprises implementing a first process for carrying out an application deployment configuration change using a deployment repository, and implementing a second process for carrying out an application logic change using a source repository, the second process being different than the first process. The method further comprises identifying a particular type of change to be made to at least one application, and controlling execution of a particular sequence of one or more instances of at least one of the first process and the second process responsive to identification of the particular type of change to be made to the at least one application. The deployment repository and the source repository are illustratively part of a continuous integration / continuous deployment (CI / CD) system. The CI / CD system controls software code for applications executed by host devices of a host platform coupled to the CI / CD system over at least one network.

To assist users in artificial intelligence driven software development, techniques for agentic software development assistance leveraging application behavioral models are disclosed. A software agent receives a codebase issue and orchestrates an iteration of a refining process. To orchestrate the process, the software agent feeds the codebase issue and instructions to generate a plan into a development assistant, which automatically returns a plan to the agent. The agent feeds the plan and instructions to generate a solution to the codebase issue back to the development assistant, which automatically returns a solution to the agent. The agent feeds the solution back to the development assistant, which tests the solution in order to verify the solution's quality in responding to the codebase issue. The solution is awarded a quality score, and the quality score is returned to the agent. Based on the quality score, another iteration of the refining process can be performed.

The invention discloses a game function development system and method based on a natural language instruction, and relates to the technical field of game development, the system comprises a project code library analysis module, a development instruction receiving and analysis module, a function deconstruction and code generation module, an automatic integration and debugging module and a development report generation module; the project code library analysis module constructs a code dependency graph and recognizes an API interface to provide a precise basis for subsequent development, the development instruction receiving and analysis module converts natural language requirements into structured information, efficient understanding of the requirements is achieved, and the development efficiency is improved. The function deconstruction and code generation module disassembles requirements and calls a specific engine programming large model to generate standard codes, manual coding and automatic integration are reduced, the problems of automatic code insertion and test development of the debugging module according to a graph and rapid recognition and repair are solved, dependence on professional programmers is reduced, the function development period is shortened, and efficiency is improved. And compatibility errors caused by manual operation are reduced.

Some embodiments find locations of targets which are related to a symbol in a source code snippet, when the snippet is external to a project codebase. Finding a target's location allows user-directed or proactive automatic navigation from the symbol into the codebase, display of data type, signature, and other semantic information of the symbol, proactive automatic creation of an import statement for a definition of the symbol, and other utilizations of the target location in an enhanced editor or enhanced debugger or another tool. In some scenarios, the external snippet is generated by an artificial intelligence agent, using part of the codebase as context. Some embodiments find a target of an external snippet's symbol in another external snippet, allowing a tool utilization that is informed by the project codebase even when both snippets are outside the project codebase.

An automated AI-driven software development system utilizes generative neural models to determine the commands needed to execute a software engineering task. The system uses a conversation manager that manages conversations between an AI-autonomous environment and a codebase environment to determine the operations needed to complete a software engineering task until all operations complete. The AI-autonomous environment utilizes the AI-agents coupled to the generative neural models to determine the commands needed to achieve a user task and any follow-on tasks needed to ensure that the user task works as intended. The codebase environment performs the operations needed for the user task in a secure execution environment with access to the user's codebase.

The invention relates to a code generation method based on reasoning time extension. The method comprises the following steps: 1, in a scene without external information: step 1, generating an initial code draft with API (Application Program Interface) calling; 2, the large model considers the influence of PythonAPI version evolution on code migration according to a given rough code, library requirements and version constraints, and generates a refined code with correct API calling; and 2, introducing a rough code retrieval scene by using external information: step 1, capturing a Python library from PyPI and GitHub, and constructing an external knowledge base; the method comprises the following steps of: 1, generating a rough code snippet, 2, generating a rough code snippet, and 3, generating a refined code snippet subjected to knowledge enhancement by a large model according to a given rough code, library requirements, version constraints and retrieved knowledge snippets. The method can improve the correctness of the API, is compatible with a deployment standard, and improves the code generation capability of a large model when the large model deals with API demand evolution.

Systems and methods for reconciling software release scope requirements are disclosed. A method may include: identifying code release version for a release candidate codebase; retrieving a log of changes made to the release candidate codebase and an implemented requirements identifier for each change; retrieving planned requirements identifiers for the code release version from a code requirements database; comparing the implemented requirements identifiers and the planned requirements identifiers; determining, based on the comparison, that an out-of-scope code change is included in the code release version; reverting the code release version to a prior version of the release candidate codebase that does not include the out-of-scope code change; retaining or reapplying in-scope code changes for the planned requirement identifiers to the prior version of the release candidate codebase; and deploying the prior version of the release candidate codebase with the in-scope changes to a production environment.

The invention relates to the technical field of software testing, can be applied to the field of science and technology finance / digital medical treatment, and discloses a software product function testing method and device, electronic equipment and a storage medium. The method comprises the steps of generating an artificial intelligence script for function testing of a target software product, wherein the artificial intelligence script runs based on a pre-trained product function automatic checking model; inputting the demand document, the test case, the code library and the test case of the target software product to the product function automatic checking model as test support data; driving the product function automatic checking model to generate interface test data according to the test support data and the artificial intelligence script; and in the test environment of the target software product, calling the tested function interface of the target software product by using the interface test data through the artificial intelligence script to obtain a function test result. According to the method, full-process automation of software product function testing is achieved, and testing efficiency and accuracy are improved.