323 results about "Modula" patented technology

The invention discloses a software test case generation method and system based on a large language model, and relates to the technical field of software testing, and the system comprises a to-be-tested module detection subsystem which is used for constructing a to-be-tested module set; the test case generation subsystem is used for constructing a prompt template according to the to-be-tested module and generating a test case by utilizing a program generation model based on an adaptive focus context generation mechanism and the prompt template; the correction verification subsystem is used for performing multi-stage correction processing on the test case, eliminating errors and generating an initial test suite; and the test case supplement subsystem is used for carrying out coverage rate analysis and variation test on the initial test suite, constructing a model input text according to a result, and generating a supplement test case by utilizing a program generation model so as to update the initial test suite and obtain a final test suite. By combining the functional annotation of the to-be-tested module with the logical reasoning ability of the LLM, misjudgment caused by assertion errors can be reduced, and the accuracy of test feedback is ensured.

The invention discloses a mechanical arm natural language instruction control system and method based on a large language model, and belongs to the field of intelligent manufacturing. Aiming at the limitation that traditional mechanical arm control depends on pre-programming and a static rule library, a dynamic mapping mode from a natural language instruction to an atomic action sequence is designed, an atomic skill library including detection, grabbing, moving, placement and other operations is constructed, and semantic analysis and a multi-mode cooperation technology are combined, so that the atomic action sequence is obtained. And support is provided for man-machine cooperation of a flexible assembly task. The method specifically comprises the steps that a DeepSeek-Distil-Llam-8B large model and a LoRA fine tuning technology are adopted, and a natural language instruction is converted into an executable atomic action sequence; based on a transfer learning optimized YOLOv8 target detection technology and a binocular vision positioning technology, a sensing module adaptive to an assembly scene is constructed and is fused with a mechanical arm motion planning module, and positioning grabbing of parts and tools is achieved. And an interactive interface is built by combining a voice-to-text large model and a Gradio front-end framework, so that the convenience of man-machine interaction is improved. By optimizing large model reasoning and motion planning cooperation efficiency, response delay from instructions to execution is reduced, and an efficient and extensible solution is provided for man-machine cooperation in intelligent manufacturing.

The invention discloses a structured text code generation and review method, which comprises the following steps of: receiving a control task demand input by a user, supporting natural language, structured form or graphical process input, performing deep semantic analysis by utilizing a demand analysis module, identifying control conditions, control actions and constraint factors, and generating and reviewing a structured text code. The task is converted into a plurality of control units through the SCoT chain; the SCoT chain reader generates a semantic vector according to a task demand, the AST reader generates AST representation through a grammar rule structure and a hierarchical relationship, and the decoder predicts a next grammar rule and generates an ST code in combination with the SCoT chain and AST features; and verifying grammar and logic of the ST code through an interactive automatic review and repair mechanism, if compiling errors occur, analyzing errors by the teacher model and providing repair suggestions, and performing code repair by the student model according to guidance until the code conforms to an expected function and passes compiling.

Some implementations of the disclosure provide a computer-implemented method including operations of receiving, by an orchestration agent, user input corresponding to a user question, wherein generating a response to the user question includes one of generating, editing, or refining programming code, and generating, by the orchestration agent, a prompt instructing a first sub-large language model (LLM) to perform a first task. In response to the prompt, generating, by the first sub-LLM, instructions for a second sub-LLM to perform a second task, wherein results of performing the second task by the second sub-LLM are provided to the first sub-LLM and performing, by the first sub-LLM, the first task utilizing the results of the second task generated by the second sub-LLM. An additional operation includes generating, by the orchestration agent, a GUI that displays the response to the user question, wherein the response includes or is based on the programming code.

The invention provides a robot control method and system based on a big language model, a double big language model evaluation mechanism is adopted, a big language model of a code generation and modification module uses Claide 3.5 sonnet, control codes are generated by the Claide 3.5 sonnet, evaluation is provided by adopting a gpt-4o evaluation model of OpenAI to optimize suggestions, and the big language model of the code generation and modification module is used for evaluating the control codes. The risk that problems are difficult to find due to homogenization of the same module is reduced, and the generation quality, safety and supportability are improved; in addition to a double large language model evaluation mechanism, due to the fact that safety prompt words are added into prompt words of a generation model and a generation template example is provided, operation of the generation model in a specific framework can be limited, the possibility of error occurrence is reduced, and specification and safety of a generation effect are further provided; in addition, the control class verification module constructs a simple simulation environment after the control class codes are generated, so that grammar errors and logic vulnerabilities of the generated codes can be screened in advance, and potential safety hazards are further reduced.

The invention provides a large model reasoning and calculation enhancement system, method, device and medium, and belongs to the technical field of artificial intelligence, the system comprises a user interaction module for obtaining and processing a natural language question input by a user, and returning a calculation result to the user; the reasoning and calculating module is used for converting the processed problem into a standard Prolog code by using the adjusted large language model; the Prolog code integrity verification module is used for carrying out integrity verification on the converted Prolog code; and the Prolog interpreter module is used for analyzing and executing the Prolog code which passes the verification, and then providing a calculation result to the user interaction module. According to the method, the natural language understanding ability of the large language model is combined with the precise calculation ability of Prolog, so that the limitation of the large language model in the aspects of mathematical calculation and logical reasoning is effectively solved, and the accuracy and reliability of a reasoning result are improved.

The invention provides a business code generation method and a business code generation device fusing code specification detection, which adopt a'generation-review-optimization 'closed-loop process to convert traditional post auditing into beforehand quality construction. Based on a pre-training code large model, an initial code is generated under a three-level cue word composed of a user demand, a context abstract and a system instruction, the system instruction is dynamically injected into an enterprise specification, and it is ensured that the generated code is initially compliant. And the auditing module performs semantic and architecture verification through abstract syntax tree analysis and a pre-training auditing model, automatically checks problems, sorts and repairs priorities, and generates an auditing report. And if defects are found, the system drives the model to be iteratively generated according to the priority until codes meeting the standard are output. The whole-process defect data is used for incremental fine adjustment to promote continuous evolution of the model.

Some implementations of the disclosure provide a computer-implemented method including operations of receiving a user question by an orchestration agent, where generating a response to a user question includes generation of programming code, executing, by a sub-large language model (LLM), an instruction to generate the programming code and performing, by the sub-LLM, a validation process including determining whether the programming code generated by the sub-LLM includes a syntax error. When the validation process indicates the programming code does not include the syntax error, the method includes operations of invoking a logic module configured to execute the programming code, wherein the logic module is provided the programming code generated by the sub-LLM and executes the programming code and generating, by the orchestration agent, a graphical user interface that displays the response to the user question that includes or is based on results of execution of the programming code.

Disclosed herein are computer-implemented systems and methods for code value assessment. For example, in one aspect, the system comprises, an input module configured to receive program code submissions from developers, a processing unit equipped with Text-Based Models with Contextual Understanding (TBM-CUs) configured to evaluate the functional meaning, purpose, and value of submitted code segments and distinguish between code contributions from human programmers and machine learning systems, a visualization module configured to present the assessed value of the analyzed code over various time periods and dimensions, offering insights into trends, patterns, and comparative performance, a communication module configured to translate programming code meaning or function into plain language summaries for non-technical stakeholders, and an AI peer review module configured to automatically review, accept or reject code contributions.

A system and method for optimizing instructions for Large Language Models (LLMs). The system and method comprise a text embedding model configured to convert the text prompt into an embedding space. An optimization module is configured to optimize the prompt in the embedding space, and an invertible embedding model is configured to decode the optimized embedding space back into a text prompt that may be input to a blackbox LLM.

The invention discloses a code conversion system and method, electronic equipment and a storage medium, and belongs to the technical field of artificial intelligence, and the code conversion system comprises a project input module which is used for obtaining a code engineering project containing a project file, and the code engineering project is written by a first programming language; the data preprocessing module is used for creating a knowledge base corresponding to a code engineering project and splitting a project file into a plurality of split texts; the function analysis module is used for determining a function list of the code engineering project according to the knowledge base, the split text and the first programming language, and the function list comprises a plurality of functions achieved by the code engineering project and calling relations among the functions; and the code conversion output module is used for generating a target conversion code corresponding to the code engineering project according to the function list and the second programming language, so that reliable conversion of any project-level code of any programming language can be realized, and the code conversion effect is relatively good.

The invention discloses a multi-agent-based automatic code generation method for a complex desktop application program, which is used for remarkably improving the efficiency of developers in a development stage and reducing the time cost. According to the method, the demand software is split into different modules for implementation, so that the code of the complex desktop application program is automatically generated, and the ever-increasing application development demand is met. According to the method, a multi-agent technology is used, each agent plays roles of demand analysis, code generation, code verification and optimization and the like, and full-process automatic development from original demands to high-quality executable codes is realized through collaborative optimization of demand analysis and code generation processes. Finally, the application potential of a multi-agent system based on a large language model (LLM) in complex code generation is further explored, and a more efficient and intelligent multi-agent code generation system is achieved by improving an agent cooperation mode and cue word engineering.

The invention provides a manufacturing execution system natural language interaction method and system based on a large language model, and relates to the technical field of intelligent manufacturing and industrial informatization. The method comprises the steps of obtaining a natural language request input by a user through a text interface, performing entity standardization processing on the natural language request through a request rewriting module based on a large language model, and eliminating semantic ambiguity to obtain a standardized request; performing task decomposition on the standardized request by adopting a multi-step dynamic operation planning and execution module to obtain an atomic operation chain; and dynamically executing each step of operation in the atomic operation chain, and generating a user readable response by using a large language model according to an execution result. Natural language interaction replaces a traditional graphical user interface, the system development and maintenance cost and the user learning complexity are remarkably reduced, and the operation efficiency and reliability of a manufacturing execution system are improved.

The invention discloses an intelligent graphic programming language application system and method based on a large model technology, and the system comprises an input module which is used for obtaining a programming logic document; the large model analysis and generation module is used for performing semantic analysis on the programming logic document and generating corresponding graphical programming language initial code representation; the graphical language generation module is used for converting the initial code representation into a program structure of a graphical programming language; the small model proofreading and optimizing module is used for verifying a program structure according to a preset graphic language grammar rule and automatically modifying and optimizing when a part which does not conform to the grammar rule is detected; and the output module is used for outputting the verified and optimized graphical programming language program. According to the intelligent graphic programming language application system and method based on the large model technology, the advantages of an artificial intelligence large model and an artificial intelligence small model are comprehensively utilized, and automatic conversion and optimization verification from a text requirement to a graphic program are achieved.

The invention discloses a stereo garage fault analysis system and method based on a large language model (LLM), and the method comprises the steps: generating a private large language model through the fine adjustment of a low-rank adaptation (LoRA) method of the large language model, and constructing an equipment maintenance knowledge base through knowledge graph generation software; when the system runs, equipment internet-of-things signals are subjected to semantic processing, classified according to attributes and features and correspondingly input into the local questioning sub-module and the global questioning sub-module to be processed, and the whole process from description of equipment running states to automatic giving of fault root cause analysis results and fault solutions is achieved. According to the invention, the efficiency and accuracy of fault diagnosis are improved, the maintenance cost is reduced, and comprehensive fault root cause analysis results and fault solutions are provided.

The embodiment of the invention provides a Gradle-based compiling method and device, equipment, a medium and a program, and the method comprises the steps: detecting a module of a project to obtain compiling reference information of a first source code module without source code change in the project, and the compiling reference information comprises an identifier without source code change and information of a binary file; obtaining a dependency relationship tree of each module of the project, and determining a target module which has no source code change and has a dependency type of source code dependency in the dependency relationship tree of each module according to the compiling reference information of the first source code module, according to the binary file of the target module, modifying the source code dependency of the target module in the dependency relationship tree of each module into binary dependency; and compiling each module according to the modified dependency relationship tree of each module. The dependency type of the module is changed from source code dependency to binary dependency, and source code compiling does not need to be performed on the modified module, so that the time required for source code compiling is saved, and the engineering compiling efficiency is improved.

The invention discloses a lightweight cross-platform PLC (Programmable Logic Controller) multi-language code generation method, which relates to the field of industrial process control, and firstly provides a unified intermediate data model, and on the basis, a module for converting each PLC language into the unified intermediate data model is realized; on the basis of a standardized JSON data structure, a modularized unified intermediate language conversion chain is further supported, an analyzer and a generator communicate through a JSON interface, a cross-platform conversion path is supported, and unified intermediate language conversion from PLC to JSON to XML to ST to C is completed; the method comprises the following steps of: integrating an open source compiler and runtime, constructing an open and pluggable automatic execution framework, compiling a generated C code into a platform executable file by using an adaptive GCC tool chain aiming at different target platforms, and deploying a program generated by compiling to a soft PLC runtime system supporting multiple platforms. According to the method, a JSON intermediate data structure which is light in weight, unrelated to languages and uniform in structure and a matched conversion framework of the JSON intermediate data structure are constructed.

The invention provides a large language model training acceleration method and a large language model training acceleration device based on a Fast Parallelism framework. The method comprises the following steps: training a large language model on a plurality of GPUs (Graphics Processing Unit) by adopting a Fast Parallelism framework, wherein the Fast Parallelism framework comprises a tensor parallel module, a data parallel module and a hyper-parameter adjustment module; the method comprises the following steps of: when the large language model is trained, setting a sample number batch-size and a gradient accumulation which are trained in each iteration in a hyper-parameter adjustment module; a Deepspeed ZeRO data parallel processing strategy is adopted in the data parallel module; in the tensor parallel module, tensor segmentation is carried out in two dimensions and four dimensions, and large language model accelerated training is carried out in combination with the data parallel module and the hyper-parameter adjustment module. According to the method, a FastParallelism framework is innovatively designed, the framework adopts modular design, data parallelism, tensor parallelism, hyper-parameter adjustment and other strategies are applied, the internal performance of a computer system can be improved, and under the condition of limited resources, the large model training speed is increased.

The invention provides a code analysis method, system and equipment based on a multi-programming language sandbox and a medium, and belongs to the technical field of code analysis and detection.The method specifically comprises the steps that an input code and a corresponding unit test sample are obtained, and a programming language type specified by the code is determined; sending the code and the unit test sample to a sub sandbox environment of a corresponding language for execution; a compiler in the sub sandbox reports a missing library according to a code compiling result and prompts a user to install the missing library; calling an analysis tool of a code analysis module to analyze the code; compiler feedback of the sub sandboxes and various analysis results generated by the code analysis module are integrated into a large language model; inputting the integration result into a large language model through a preset template; and analyzing and evaluating the code case based on the user instruction. Through multi-language sandbox isolation, automatic analysis tool integration and large language model enhancement, the security, efficiency and quality of a code processing flow are improved.

Post-training quantization of weight values and activation values substantially reduces the memory and processing requirements of floating-point (FP) large language models (LLMs). A quantization parameter training process is performed on the FP LLM to determine quantization parameters. Weight-activation scaling may be applied to linear modules of the LLM, including down projection layers, enabling subsequent per-tensor quantization for activation values. The weight and activations values of the FP LLM are quantized from FP to integer values. Different layers may have different integer sizes. For example, weight values may be reduced to 4 bit integers and activation values to 8 bit integers. Layers within the model are modified to operate on the integer values. For example, an integer SiLU module may provide an integer approximation of a sigmoid-weighted linear unit activation function.

The invention discloses a vehicle-mounted system modular framework and a collaboration method thereof, the vehicle-mounted system modular framework comprises an agent module cluster, and the agent module cluster comprises an interaction agent and at least one function execution agent; a large language model is deployed in each agent, and all the large language models are coordinated through a standardized interface; the interaction agent is used for receiving a natural language instruction of a user and analyzing the natural language instruction by using a large language model deployed in the interaction agent to generate a task instruction; and the function execution agent is used for receiving the task instruction, analyzing and extracting key parameters by using a large language model deployed in the function execution agent, executing security rule check, and executing a corresponding specific task if the task instruction passes the security rule check. According to the method, the rule code quantity can be reduced, the interactive agent realizes cross-agent dynamic task distribution based on the big language model reasoning ability, new function access does not need to modify a bottom layer architecture, only peripheral agents need to be increased or decreased, the development period can be effectively shortened, and the development progress can be accelerated.

The invention discloses a spray combustion sub-model integrated development method and equipment based on a large language model, and belongs to the technical field of engines. The method is realized by relying on a retrieval enhancement generation system and a multi-agent collaborative framework, and comprises the following steps: S1, user instruction and thesis extraction: extracting core information from related technical literatures to form a structured file according to a sub-module extension requirement proposed by a user; s2, source code analysis and comparison data generation; s3, function and interface planning: performing adaptive planning of an original model-OpenFOAM platform; s4, code generation and packaging: code conversion, dependency processing, test example generation and compilation packaging; s5, layered testing and verification graph generation; and S6, debugging and repairing: executing a positioning-repairing-regression closed-loop process through a debugging agent. According to the method, the problems that the spray combustion sub-model is difficult to migrate to the OpenFOAM simulation platform under different frameworks and the development period is long can be solved.

The invention discloses a unified programming model compiling and runtime system oriented to a Shenwei supercomputing platform, which comprises a compiling module used for compiling SYCL programming model codes and detecting kernel functions to generate equipment end intermediate representation; processing the equipment end intermediate representation to obtain a kernel function dynamic link library and an executable code of a host end; and the public runtime module is used for calling the kernel function dynamic link library when the executable code at the host side runs. Based on a compiling module and a public runtime module, a vertical optimization system from a compiler to runtime is constructed, efficient operation of SYCL in a domestic supercomputing system is realized, a semantic gap between a domestic many-core architecture and a universal programming model is overcome, and the development of the system is facilitated. The SYCL programming model is processed by a host end and an equipment end respectively after being extracted by a kernel during compiling, and is dynamically called by a common runtime module, so that the cooperative computing capability of the host end and the equipment end is fully exerted.

The invention discloses a system for realizing bidirectional conversion between a model and a code, and the system comprises a meta-model architecture module which is used for constructing a unified model specification; the meta-model engine module is used for generating, analyzing and processing the meta-model architecture module; and the bidirectional conversion module is used for realizing forward and reverse synchronous conversion between a zero code model and a Java model serving as a program code by adopting the meta-model engine module. By means of the scheme, a unified specification with the meta-model architecture as the core is established, a powerful meta-model engine is used for automatic processing, and the barrier between a zero-code visualization model used by business personnel and bottom-layer Java codes written by developers is seamlessly broken through. The synchronization capability of the model and codes ensures the continuous alignment of business design and technical implementation, and effectively supports the quick iteration of agile development and business.

The invention discloses a reasoning-based multi-language security protection framework, a medium and equipment, and belongs to the technical field of artificial intelligence. According to the framework, cross-language knowledge migration and interpretability enhancement are realized in a mode of combining thinking chain reasoning and constraint alignment optimization; comprises: an SFT-based cold start module configured to perform knowledge distillation on a basic large language model through supervised fine tuning so as to endow the model with a preliminary reasoning ability for a safety protection task; the reasoning training module based on the GRPO is configured to be capable of improving normalization, accuracy and diversity of a model reasoning chain and enhancing interpretability; and the CAO-based cross-language alignment module is configured to realize knowledge migration from a high-resource language to a low-resource language and avoid performance reduction of the high-resource language. The method can solve the problems that an existing method mainly depends on a classifier lacking interpretability, the performance of a low-resource language safety fence is insufficient, and the performance of the low-resource language safety fence is poor.

The invention discloses an automatic code debugging and optimizing system and method based on an AI agent, and relates to the technical field of artificial intelligence and automatic programming, the system comprises a coordinator module, a plan generation module, a code generation module, a test verification module, a deployment operation module, a project summary module, a language model module and a context management module; the coordinator module supports to select and call an Agent for specific task execution according to the current task process, and the plan generation module is configured to automatically generate a development task plan according to the requirements of a user and transmit a task list to the code generation module. Through the exception retry mechanism and the task backtracking mechanism, the system can automatically detect errors in the code generation process and repair the errors, and the tedious process of traditional manual debugging is avoided. The system optimizes the code generation process by backtracking the historical task and adjusting the generation strategy, and the quality of the final code is ensured.

A computer-implemented technique for generating program code includes receiving a natural language description of a hardware module, generating a first plan based on the natural language description, extracting first circuit information from the natural language description, generating a second plan based on the first plan and the first circuit information, and generating first program code in a hardware description language based on the second plan.

The invention relates to a teaching experiment automatic generation and intelligent deployment device and method. An input module is arranged to collect experiment steps of experiment configuration and natural language description; the method comprises the following steps of: converting an experimental step described by a natural language into an operation script of the experimental step and a judgment script for judging whether the experimental step is correctly executed by arranging a judgment engine module, and integrating experimental configuration, the experimental step described by the natural language and the operation script and the judgment script of the experimental step into an experimental configuration document; and mapping the experiment configuration document into an experiment environment which is arranged and constructed by using Kubernetes through setting an environment deployment management module. The lesson preparation efficiency is improved, hardware investment is saved, and the teaching effect is improved.

The invention provides an interactive real-time loop feedback programming teaching system based on a large language model, and the system comprises a task driving module which is used for generating a multi-language exercise library based on the large language model and dynamically recommending tasks in combination with the programming capability of a user and an interest label; the code writing and debugging module is used for writing multi-language codes by a user, receiving the multi-language codes submitted by the user, executing multi-language compilation and generating compilation data, and the compilation data comprises execution logs, performance data and error information; the programming capability portrait module is used for analyzing the compiling data by utilizing a large language model to obtain programming behavior data, and processing the programming behavior data to obtain a user programming capability portrait; the intelligent interaction module is used for analyzing the programming ability portrait by adopting a large language model to generate targeted teaching feedback, and calling AI assistant teaching to execute five-step guide teaching based on the targeted teaching feedback; the reflection internalization module is used for generating a reflection log based on the user ability portrait generated by the programming ability portrait module, the reflection log comprises an error mode, a learning habit and a cognitive blind spot, and an internalization strategy is recommended according to the content of the reflection log. The internalization strategy refers to providing personalized learning methods, learning plans, learning guide, learning guidance and recommendation tasks of updating the task driving module for the user according to the current error type.

The invention discloses an FPGA test case automatic generation system and method based on a large language model. The system comprises a demand input module, a demand structuring module, a large language model case generation module, a case confirmation module, a verification execution module and a closed-loop optimization module. The large language model can automatically analyze the unstructured demand document and extract key information such as function points, input and output, boundary conditions and the like, and manual one-by-one interpretation is not needed. A big language model is guided through Prompt Engineering to dismantle complex requirements into test key points which cannot be subdivided, and it is ensured that all logic branches are covered by tests. The large language model can dynamically generate diversified test cases based on test key points, including a normal process, an abnormal process and an edge scene. And in combination with FPGA design specifications, historical error cases and other plug-in knowledge bases, the large language model can generate test cases closer to actual hardware behaviors.