1590 results about "Code generation" patented technology

The invention provides a business module source code generation method and system based on large model business reasoning, and belongs to the technical field of code generation. The business module source code generation method comprises the steps that semantic analysis is conducted on business requirements, and a business association graph with weights is constructed; performing module division, and decomposing a complete task into a plurality of sub-tasks; calling a coordination agent, distributing a corresponding module code generation agent based on a large model for each decomposed subtask, and injecting context information to generate a corresponding module code; wherein the module code generation agent learns a corresponding relationship between tasks and injected context information and codes in advance based on field self-adaptive staged training; and calling the verification agent to perform code quality verification. The method has the beneficial effects that the module division is performed based on the business association graph with the weight, the multi-agent collaborative code generation is constructed by adopting the field-adaptive staged training, and the quality of the generated code is verified, so that the code generation efficiency and quality are improved.

The invention discloses a code generation system based on a natural language and meta-model drive, and the system comprises an AI layer which comprises a plurality of agents which work cooperatively, and is configured to receive a natural language instruction, and carry out the intention recognition, entity extraction, context analysis and constraint verification through the agents, so as to generate structured metadata; the meta-model engine is configured to be used for constructing and instantiating one or more meta-model objects according to the structured metadata generated by the AI layer; and the code template engine is configured to be used for matching one or more corresponding code templates from the code template library according to the content and the type of the meta-model object, and generating executable codes or configuration files of one or more target languages through rendering. By means of the scheme, the natural language is converted into the meta-model decoupled from the technology through the AI, and then the high-quality standardized code is automatically generated through the template engine, so that the development efficiency is improved, and developers can focus on core business innovation.

The invention provides a code generation method and system based on a waterfall model and multi-agent collaboration, and the method comprises the steps: constructing a multi-agent collaboration framework which comprises a problem analysis agent, a solution agent, a pseudo-code agent, a coding agent and a restoration agent based on a software development waterfall model thought; and the interaction process of each agent is coordinated through a dynamic cooperation algorithm. Wherein the problem analysis intelligent body checks similar problems and solutions; the solution intelligent agent generates and evaluates candidate schemes; performing scheme conversion by the pseudo-code intelligent agent; the coding agent generates an executable code; and the repair agent performs fine-grained repair on the code in grammar, runtime and semantic levels through a two-dimensional repair mechanism. According to the method, the limitation of a single agent in a complex programming task is broken through, automatic code generation covering the whole process of demand analysis, scheme design, code implementation and test repair is realized, and the quality of generated codes and the reliability of operation are remarkably improved.

The disclosed technology provides for an improved approach to AI code generation. In various embodiments, the disclosed technology provides for an AI agent architecture platform for generating, revising, testing, and debugging code using a customizable team of agents with specific tasks.

According to the operator code generation method and system based on large model driving and a multi-agent cooperation mechanism, automatic high-performance code generation is achieved through cooperative work of four kinds of agents including strategy recognition, operator generation, compilation testing and function testing. A strategy identification agent accesses a high performance optimization knowledge base (HPOK) by using retrieval enhancement generation (RAG), analyzes operator characteristics by means of a hybrid expert model (MoE), and generates an optimization strategy protocol oriented to a specific optimization target. And the operator generation agent calls a large language model (LLM) to generate an initial code, and iteratively corrects the code according to feedback iteration of compiling and function testing. And the compilation test and function test agents execute code compilation verification and function correctness verification respectively to form a closed-loop error correction mechanism. According to the scheme, through a modularized cooperation framework and dynamic knowledge retrieval, the operator code generation efficiency and quality oriented to diversified hardware platforms such as a CPU and a GPU are remarkably improved.

The invention provides a code generation and evaluation method and system based on RAG and a multilevel decision tree, and the method comprises the steps: integrating project related design documents, and constructing a knowledge base capable of semantic retrieval through a vectorization technology; associating business demand description with related documents in the knowledge base based on an RAG technology, and performing demand semantic enhancement to generate a technology demand cue word; receiving the technical requirement cue word by adopting a large language model so as to generate a complete code conforming to business logic; constructing a four-level decision tree evaluation system, and sequentially executing code quality scanning, deployability verification, dynamic test verification and demand satisfaction verification through an evaluation assembly line to generate an evaluation result; and generating an optimization suggestion according to the evaluation result so as to trigger an iteration generation process when the code does not pass the verification, thereby solving the problems of disjunction between code generation and business requirements, low verification efficiency and insufficient iteration optimization.

The invention provides a text code generation method based on multi-modal semantic embedding and a dynamic knowledge graph, and belongs to the technical field of artificial intelligence. According to the automatic code generation method based on multi-modal semantic embedding, the dynamic knowledge graph, constraint-driven code generation and context-aware repair, the semantic understanding precision and the code generation quality are remarkably improved by integrating the technologies of multi-head Transform, the graph neural network, reinforcement learning optimization, genetic algorithm sequence adjustment, the generative adversarial network and the like. According to the method, the knowledge graph can be dynamically constructed to enhance structured semantic modeling, high-quality codes conforming to specific industry standards are generated, functionality, efficiency and conciseness are considered, meanwhile, the iteration cost is reduced through an efficient error positioning and repairing mechanism, and the method is suitable for large-scale popularization and application. And the robustness and the flexibility of the system in diversified scenes are improved by utilizing adaptive weight optimization and multi-target balance.

The invention discloses a multi-data-source intelligent question and answer method and device based on a large model and a storage medium, and relates to the technical field of data processing.The method comprises the steps that metadata corresponding to an initial data set uploaded by a user and questions asked by the user are input into a pre-trained reasoning large model, and query codes are generated; performing screening query on the metadata according to the query code to obtain a target data set; inputting the target data set and the user questions into the large reasoning model to generate data analysis codes; and executing the data analysis code to obtain a code execution result. The unified symbolic structure of the metadata provides reference constraint basis for the model to generate query codes, so that the model can accurately understand the format specification and internal association of data, a natural language question is mapped into query grammar conforming to a data storage format based on a large reasoning model, and the query grammar and the query grammar conforming to the data storage format are obtained through metadata prompt and code generation. And the problem of insufficient adaptation of a large model to heterogeneous data formats and metadata rules is avoided.

The invention relates to the technical field of project intelligent management and control, and discloses a multi-agent power grid project intelligent monitoring, management and control and evaluation system and method, and the system comprises a mixed data resource library, a multi-agent system, an index calculation module and a process control module. The mixed data resource library stores structured business data and unstructured documents; the multi-agent system comprises an information extraction agent, an index design agent, a code generation and treatment agent and the like, works cooperatively, and converts a high-level natural language management and control rule into an executable code; the index calculation module is responsible for executing codes according to a scheduling strategy and calculating quantitative indexes; and the process control module automatically identifies risks and executes management and control operations such as process locking according to the index result and a preset threshold value. According to the invention, the complex business logic can be automated and coded, the accuracy and timeliness of risk identification are improved, and refined and prospective intelligent management and control of the power grid project are realized.

The invention provides a code agent construction system, a construction method thereof and a code generation method, and relates to the technical field of computers, in particular to the technical field of artificial intelligence such as large models. According to the specific implementation scheme, the code agent construction system comprises an intelligent cooperation engine, a layered template library, a semantic understanding and layered retrieval system, a T-RAG generation and optimization system and a closed loop verification system; wherein the layered template library comprises a project-level template, a function-level template and an API-level template; the semantic understanding and hierarchical retrieval system is configured as follows: analyzing user requirements through a natural language understanding module to generate an intention vector, and sequentially executing project-level, function-level and API-level three-level progressive template retrieval; and the T-RAG generation and optimization system is configured to inject the hierarchical retrieval result into the cue word of the large language model to generate deployable codes containing front-end and rear-end logics.

The invention relates to a low-code visualization optimization method and system for power credential development, and the method comprises the following steps: S1, obtaining data in a credential environment, recognizing the interface difference and performance bottleneck points between components through a compatibility test matrix, and building a standardized adaptive interface specification; s2, obtaining a standardized business object model based on the standardized adaptive interface specification; based on the business object model, defining attributes, relationships and constraint rules of each business entity, and forming a data dictionary and an interface specification special for the electric power field; s3, on the basis of the data dictionary and the interface specification special for the power field, constructing a DSL (field specific language) of power visualization; s4, a dragging type interactive design is adopted, and the visual operation is converted into a DSL configuration file; and S5, automatically converting the DSL configuration into a React or Vue component code through a code generation engine, and carrying out compatibility optimization on the kernel of the creative browser. According to the invention, the power credential development efficiency is effectively improved.

The invention discloses a code generation and restoration method and device based on multi-round feedback of a large language model, and the method comprises the following steps: 1, converting problem description into a structured tetrad (target, input, output and constraint) through a two-stage task demand deconstruction mechanism, and generating a pseudo-code frame according to the structured tetrad; 2, generating a plurality of candidate code schemes in parallel based on different implementation strategies; 3, selecting an optimal code implementation scheme through multi-dimensional evaluation; 4, generating an extended test case through boundary condition analysis and public test reasoning, and expanding a verification range; 5, classifying error types in combination with static analysis and dynamic execution information, and applying a special repair strategy; 6, providing detailed repair reasons and ideas by an interpretable repair mechanism; and 7, establishing a multi-round feedback repair verification iteration mechanism composed of testing, analysis, repair and verification. According to the method, the performance of an existing large language model in processing a complex programming task is effectively improved.

The invention relates to a multi-agent large model code generation method and system in the optical field, relates to the technical field of optical design, and aims to solve the technical problems that in the prior art, optical terminologies are insufficiently understood, and optical performance requirements and constraints cannot be correctly extracted. The optical field multi-agent large model code generation system comprises a demand understanding agent, an optical expert agent, an architecture design agent, a script generation module, a test and feedback module, a control scheduling module and an output module. According to the multi-agent large model code generation method and system in the optical field, the accuracy of understanding optical professional requirements is greatly improved; the capability of automatically generating optical software scripts such as Zemax is higher; multiple rounds of test feedback and control scheduling are supported, and the generation accuracy is improved; the overall development period is shortened, and the optical modeling efficiency is higher; the method is more friendly to non-professional users, and the operation threshold is reduced; and the dependence on qualified optical engineers is reduced, and the development cost is reduced.

The invention discloses an aviation airborne software test case intelligent generation and closed-loop optimization method, which comprises the following steps of: knowledge graph construction: analyzing a DO-178C standard document and a related field document, extracting entities and relationships defined in the DO-178C standard document and the related field document, and constructing a field knowledge graph fused with DO-178C standard knowledge; initial test case generation: based on the domain knowledge graph, combining a static analysis result of the source code of the tested airborne software, and utilizing a large language model to drive and generate an initial test case set; and closed-loop iterative optimization: executing the test case, evaluating whether the structural coverage rate reaches the standard or not, automatically identifying uncovered codes when the structural coverage rate does not reach the standard, generating a supplementary test case for iterative optimization, and outputting a final test case set until a coverage rate target corresponding to the software security level is met. According to the method, the test quality and efficiency of the aviation airborne software can be improved.

A method for automated control code generation and verification includes: receiving a natural language command, the natural language command being configured to instruct the large language model to output a code text that meets control requirements corresponding to the natural language command; performing matching retrieval on a vector database according to the natural language command to obtain a sample code snippet; obtaining API structured information corresponding to the sample code snippet from a knowledge graph database; generating an initial control code according to the sample code snippet and the API structured information; and performing a multi-level virtual operation verification on the initial control code in a software motion control system, and generating a target control code according to multi-level verification results confirmed multiple times by the user and the initial control code.

The invention provides a communication protocol consistency test method and system. Key function points are extracted by analyzing a target protocol document; based on the key function points, a predefined first prompt template is applied to generate a test case prompt, a large language model is guided to generate a standardized test case corresponding to each key function point, and the first prompt template comprises k few-sample examples; dynamically retrieving a related code context from a pre-constructed long-term memory library through a retrieval enhancement generation mechanism, generating a code generation prompt by applying a predefined second prompt template based on the standardized test case and the related code context, and generating an executable test code based on the code generation prompt; and performing iterative optimization on the executable test code through the large language model, and generating a new code generation prompt based on a code execution result of the previous iteration and the retrieved related code context in each iteration. The test case can be automatically generated and dynamically adapted, and the test coverage rate, efficiency and flexibility are improved.

Disclosed in the present application is a code generation method, which is applied to a code development platform. The code development platform comprises a main plug-in and a plurality of extension plug-ins, wherein the main plug-in is used for providing an actual value of a basic variable of a prompt, and the plurality of extension plug-ins are used for extending the prompt in terms of a programming language, scenario or development framework. The method comprises: a main plug-in receiving a code generation instruction, and then determining, in response to the code generation instruction, at least one extension plug-in corresponding to the code generation instruction from among a plurality of extension plug-ins; the main plug-in receiving a prompt returned by the at least one extension plug-in, wherein the prompt is obtained by means of the at least one extension plug-in extracting an actual value of an extension variable on the basis of extraction logic and replacing an extension variable in a prompt template with the actual value of the extension variable; the main plug-in performing inference by means of a language model and on the basis of the prompt, so as to obtain a second code segment. In the method, a prompt of a specific code generation task and the implementation of prompt engineering is entrusted to corresponding extension plug-ins, thereby realizing flexible extension of prompts.

The invention relates to the technical field of vulnerability repair, in particular to a source code vulnerability repair method, electronic equipment and a storage medium, and the method comprises the following steps: obtaining an abstract syntax tree and a control flow graph according to a source code containing a vulnerability, and generating a vulnerability context feature vector by using a graph neural network model in combination with vulnerability position information, determining a historical vulnerability repair case corresponding to the vulnerability context feature vector from a vulnerability-repair knowledge base, inputting the vulnerability context feature vector and the corresponding historical vulnerability repair case into a code generation model, outputting a candidate repair code set corresponding to the source code, evaluating each candidate repair code, and determining the vulnerability-repair knowledge base according to the candidate repair code set. Screening out an optimal repair code to automatically repair the source code vulnerability; according to the method, deep semantic analysis is performed on the vulnerability context, and intelligent reasoning is performed, so that the repair code with correct grammar and adaptive context can be generated, and the automation level and accuracy of vulnerability repair are remarkably improved.

The invention provides a printing color consistency automatic calibration and management system and method, and the method comprises the steps: collecting a current environment temperature and humidity ink matching parameter density curve data dot increase compensation parameter in real time through a state detection device, and forming a current state data set; performing similarity analysis on the reference data set and the current state data set by adopting a matching degree evaluation algorithm, and judging a relationship between a matching degree numerical value and a preset threshold value; adjusting and correcting the calibration reference value and the color control parameter in the reference data set according to the offset compensation set to obtain a compensated and adjusted parameter set; on the basis of the compensated and adjusted parameter set, generating update code data by combining a current time identifier and an operator identifier, and forming new two-dimensional code information; and outputting the new two-dimensional code information to a subsequent work order carrier by adopting a code generation module, and establishing a parameter transmission tracing chain.

The invention discloses a behavior tree code automatic generation method based on a large language model. The method comprises the following steps: 1, acquiring a behavior tree model of an XML file format defined by a user and prompt information input by the user; 2, analyzing the obtained XML file, and providing a generation rule of a behavior tree code; step 3; the analyzed XML file and prompt information input by a user are combined with a behavior tree code generation rule, and a task specific prompt is generated; 4, combining the task specific prompt with the general code generation prompt to generate a complete prompt; 5, a proper LLM is selected, complete prompt information is input, and the LLM generates codes according to prompts; 6, running the generated code in a safe environment to ensure the safety of the code and the correctness of an output format; and 7, displaying an execution result on a visual interface, auditing the result by a user, and modifying a generated code. The method has the characteristics of high universality, high flexibility and high interpretability.

The invention provides a large-model-oriented heterogeneous computing power adaptive compiling method, which comprises the following steps that: a user inputs a trained large model through a system interface, and a system front-end conversion module analyzes a computational graph of the model and converts the computational graph into an intermediate representation based on a unified operator description language (UDL); the system hardware sensing module automatically detects and extracts hardware feature fingerprints of at least one piece of target hardware; based on the unified operator description language UDL intermediate representation and the hardware feature fingerprint, automatically generating an optimization adaptation rule oriented to at least one piece of target hardware; wherein the basis of parameterized filling comprises specific parameters of hardware feature fingerprints and optimized attribute tags carried in an intermediate representation of a unified operator description language (UDL); and generating and deploying multiple back-end codes. The method has the beneficial effects that intelligent compiling based on hardware features can be realized, and the deployment efficiency and the operation performance of a large model in a complex heterogeneous computing power cluster are remarkably improved.

Systems and methods include input of a code generation prompt to a text generation model, reception of code from the text generation model in response to the input code generation prompt, execution of the received code, determination of execution information associated with the execution of the received code, input of a repair prompt, the code generation prompt and the execution information to the text generation model, and reception of an updated code generation prompt from the text generation model in response to the input repair prompt, code generation prompt and execution information.

The invention discloses a method for evaluating the code generation capability of a fine-tuned credential large model, and relates to the technical field of artificial intelligence, and the method comprises the steps: S1, constructing an evaluation data set which is constructed according to a half-and-half rule, S2, executing a model generation test, and based on the evaluation data set, carrying out a model generation test; the method comprises the following steps of S1, adjusting a code output result, S2, calling the adjusted credential large model to generate a corresponding code output result, S3, carrying out multi-dimensional evaluation analysis, S4, forming a comprehensive evaluation result, and calculating the credibility 7 degree of the large model code generation capability for guiding model performance optimization and subsequent iteration improvement; according to the fine-tuned evaluation method for the code generation capability of the credential large model, evaluation deviation caused by a single index is effectively reduced, and the obtained quality credibility is more practical and explanatory and can be used as a decision basis for supporting large model optimization strategy formulation and parameter fine tuning.

The invention relates to the field of computer software, and provides an AI-based low-code visual component dynamic generation method and system. The method comprises the following steps: receiving a component demand description input by a user, and converting the component demand description into structured cue word data to obtain an initial cue word sequence; retrieving matched template data and grammatical rule data from a component knowledge base according to the initial cue word sequence, and fusing the template data, the grammatical rule data and the initial cue word sequence to obtain an enhanced cue word sequence; performing semantic analysis and code generation processing on the enhanced cue word sequence through a large language model to obtain a component source code; and performing real-time rendering processing on the component source code through a component rendering engine, and generating an interactive component instance in a preview interface to obtain reusable component resources. According to the method, the code quality consistency is ensured, and the development efficiency is improved.

The invention relates to the technical field of software collaborative research and development assistance, and discloses a software collaborative research and development assistance method and device, electronic equipment and a storage medium. The method comprises the steps that instruction information input by a user is analyzed to obtain intention information, and then a corresponding demand sub-agent, a corresponding development sub-agent and a corresponding test sub-agent are determined; performing retrieval analysis on the intention information to compare the intention information with conflict detection of a preset historical demand library to obtain a demand document, executing code generation based on the demand document to obtain an intermediate software code, inputting the intermediate software code into the test sub-agent for testing to obtain a test result, and adjusting the intermediate software code to obtain the test result. And obtaining the target software code. The method has the beneficial effects that the software research and development process is converted from manual cooperation to intelligent execution, and the research and development efficiency is greatly improved while the quality is guaranteed.

The invention discloses a low-code automatic generation method based on AI agent collaboration, and relates to the technical field of computer processing, and the method comprises the following steps: S1, receiving a function demand description text input by a user through a natural language; s2, an input analysis agent reads and analyzes the function requirement description text, key information is extracted, and the key information comprises a key intention, an entity object and an operation constraint condition; s3, performing semantic similarity matching in a predefined model library by a model retrieval agent according to the key information, and retrieving and defining a basic generation model with closest semantics; and S4, receiving the basic generation model and the key information by an adaptive modification agent, and performing context semantic understanding enhancement on the basic generation model. According to the method, end-to-end automatic conversion from business demand description to executable codes is realized through natural language understanding and an automatic code generation technology.

The invention relates to an intelligent map making system and method based on a large language model, and the method comprises the steps: enabling a client to input data analysis information and a map making demand to a task planning Agent of a server, and carrying out the reasoning and disassembly of the input information into preliminary planning information through a double-LLM mechanism, the method comprises the following steps that Agent is used as a tool library, a tool library document, a knowledge library and a memory library are further inquired, a tool is selected through RAG and sent to a client side, if an existing tool cannot meet requirements, the Agent will generate a special code to complete a task, the client side calls the tool to carry out specific drawing according to received information, and a user can re-plan and adjust the drawing process through dialogue. The memory bank records session information and charting interaction operation information of this time and history. The problem of system fragmentation is solved through a unified architecture, stability and flexibility are balanced by combining large language model driving, tool agent and code generation, domain knowledge is introduced to enhance decision and improve specialty, and a user preference memory mechanism is constructed to realize personalized services.

The invention discloses a code generation method and system based on multi-objective reinforcement learning, and belongs to the technical field of digital integrated circuit design, and the method comprises the following steps: S1, generating an SFT training data set; s2, generating an MORL data set; s3, performing supervision and fine tuning on the model by taking the SFT training data set as input, so that the model masters the basic RTL code generation capability; s4, taking the MORL data set as input to train the model after supervision and fine tuning in the S3, and realizing multi-objective optimization; and S5, according to a user demand, describing a multi-target constraint through vector rewards, screening non-dominated candidate codes by using Pareto optimization to obtain an optimal RTL code, and outputting the optimal RTL code, vector reward details and a PPA equilibrium curve. According to the method and the system, basic constraints are met, and meanwhile generation of RTL codes with PPA indexes capable of being customized according to requirements is achieved.

Efficient generation of multi-platform compatible source code and test code with consistency and quality in software development SOLUTION: The schema-driven development system includes a user input unit, a schema generation unit, and a code generation unit, wherein the user input unit acquires data in various formats such as a natural language and a CSV file, the schema generation unit converts the acquired data into a schema, and the code generation unit generates a source code and a test code based on the generated schema.SELECTED DRAWING: Figure 1

The invention discloses a kernel probe generation method and device, computer equipment and a storage medium, and relates to the technical field of operating system kernel monitoring, and the kernel probe generation method comprises the steps of obtaining a target metadata file corresponding to a current operating system kernel in response to a kernel probe generation request; determining a target declarative strategy file; and determining a target program logic file corresponding to the target declarative strategy file, and generating a probe code according to the target program logic file and the target metadata file to obtain a kernel probe program. The probe program source code adaptive to the current kernel version can be dynamically generated in combination with the target metadata file and the target declarative strategy file, kernel probe development logic and underlying kernel knowledge can be decoupled through the source code generation function, and developers do not need to deeply understand kernel internal data structures and version differences; the development threshold is lower, a specific operating system or probe type is supported, and a universal Linux kernel and multiple probe types are also supported.