449 results about "Modula" patented technology

The invention relates to the technical field of software development, in particular to a zero-code software development and test system based on artificial intelligence, and provides the following scheme that the system comprises a natural language analysis module, a code generation module, a code optimization module, an intelligent test module and a cross-platform deployment module. The natural language analysis module analyzes the natural language description input by the user into a software development requirement document; the code generation module generates source codes based on the demand document and can select a programming language and a framework; the code optimization module is used for performing static analysis and reconstruction optimization on the generated codes; the intelligent test module automatically generates a test script through interface model extraction, case generation and case analysis logic, executes a test and feeds back a test result; and the cross-platform deployment module realizes automatic packaging, compatibility check, deployment configuration and release management of software. The invention aims to simplify the software development process and improve the development efficiency and quality.

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 large language model parameter fine tuning method, system and device, a storage medium and a product, and relates to the field of natural language processing. The fine tuning method comprises the steps that a pre-training model and a parameter matrix of the pre-training model are acquired, a parameter fine tuning module is arranged on a self-attention layer of the pre-training model, the parameter fine tuning module comprises LoRA modules of different task types and a router, each LoRA module comprises a general feature matrix and a specific feature matrix, and the general feature matrixes of the multiple LoRA modules are shared; obtaining a fine tuning data set; loading and freezing a parameter matrix of the pre-training model, and initializing parameters of a parameter fine tuning module; and performing fine tuning on the parameters of the parameter fine tuning module based on the fine tuning data set to obtain a fine-tuned large language model. Parameters of the MoE architecture are remarkably reduced, it is ensured that the model captures differences of various tasks to the maximum extent, and the cross-task generalization of the model 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.

Various embodiments concern a method of training a large language model (LLM) for an unseen task T′ comprising: obtaining a plurality of pre-trained Low-Rank Adaptation (LoRA) modules, using a set of examples Q to obtain a set of weights for the plurality of pre-trained LoRA modules, using the set of weights on the plurality of pre-trained LoRA modules to obtain a fused LoRA module, and applying the fused LoRA module to the LLM to get an adapted LLM for the unseen task T′. Systems and machine-readable media are also provided.

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 discloses a big language model evaluation system and method, and belongs to the technical field of big language model evaluation. The system comprises a data preparation module, a basic performance evaluation module, an efficiency evaluation module, a robustness and multi-mode evaluation module, a distributed task scheduling module and a feedback optimization module. Through the system, the technical effect of multi-dimensionally, efficiently and automatically evaluating the large language model is achieved.

The invention discloses a dynamic module operation management system based on a programming language, and the system comprises a module analyzer which manages the dependency relationship between modules in the system, applies a compiling optimization technology before the modules are loaded, and optimizes the code execution through code expansion and constant folding; operation environment establishment: optimizing execution speed and resource scheduling by integrating a just-in-time compiling JIT technology and an optimization measure during operation; the module warehouse is used for controlling the retrieval and loading process of the module by adopting an optimized organization and index strategy; data structure optimization: using a skip list to adjust data structure design, and controlling data processing efficiency; dynamic optimization: the system dynamically adjusts an optimization strategy according to performance feedback and an operation environment, and controls improvement of self-adaptive performance; garbage collection: dynamically adjusting a garbage collection strategy by adopting a self-adaptive garbage collection algorithm, and reducing the module retrieval time, accelerating the module loading process and improving the data access efficiency.

The invention discloses a programming assistant framework, a programming assisting method, equipment, a medium and a product, and relates to the technical field of artificial intelligence, and the programming assistant framework comprises a DevOps platform integration module, a DevOps platform integration module, a DevOps platform integration module, a DevOps platform integration module, a DevOps platform integration module and a DevOps platform integration module, wherein the DevOps platform integration module is used for receiving input information sent by any link in links for code development and maintenance; the input information is sent to a code completion and dialogue function module; the code completion and dialogue function module is used for acquiring code related problems in input information, reading source codes in a project code library, and performing abstract syntax tree analysis on the source codes to obtain an abstract syntax tree; and the RAG retrieval enhancement generation module is used for performing semantic recognition on code related problems to obtain a user intention, traversing the abstract syntax tree according to the user intention, determining code context information, obtaining retrieval information according to the user intention and the code context information, and outputting code suggestions generated according to the retrieval information. The overall development efficiency in the development process is improved.

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.

The invention discloses a multi-language dynamic switching system and method of embedded equipment, and relates to the technical field of human-machine interfaces and embedded systems.The method comprises the steps that source codes in an HMI program are traversed through a character extraction module to extract all character strings; eliminating repeated items, numbering the character strings, and outputting a database file and a replacement array; substituting the serial number into the source code file again by using the substitution array to replace the character string at the corresponding position; outputting the translated database file as a C language source code, compiling the C language source code into a dictionary generation module project, generating an executable file, and outputting the dictionary file to an HMI running directory after the device is started; after the HMI program is started, the dictionary is read into different dictionary arrays according to blocks, and character strings at corresponding positions in the dictionary arrays are extracted after a page sends a request. The method has the advantages of being lower in maintenance difficulty, more efficient in resource utilization, shorter in indexing time, better in system robustness and the like.

The invention belongs to the technical field of artificial intelligence, and particularly relates to a dynamic reasoning method and system based on a language model and a knowledge graph. The method comprises the following steps: step 1, encoding an input QA context text by using a language model encoder; reasoning the knowledge graph by using a graph encoder; 2, iteration is carried out in a hierarchical aggregation module, a joint reasoning module and a dynamic pruning module, so that multi-modal fusion is carried out on the features of the QA context text and the knowledge graph; and step 3, calculating a final output answer. The dynamic reasoning method and the dynamic reasoning system have better answer accuracy, have the advantages of convenience and wide application range, can provide new thoughts and choices for the multi-modal fusion technology in the field of natural languages, and have good application prospects.

The invention relates to a comprehensive management process design system and method based on AI code interpretation, and belongs to the technical field of computer networks. The system comprises a process design console, an AI code interpreter and a business logic execution framework, the flow design console is used for providing a Web interface, so that a user can design and manage a flow in an interactive form, including interactive natural language programming, real-time feedback and preview, flow deployment and management, and historical record and version control; the AI code interpreter is used for converting business requirements and processes expressed by a user in a natural language form into executable codes, and comprises a natural language understanding sub-module, a code generation sub-module and a security verification sub-module; the business logic execution framework comprises a code execution sub-module, a data access sub-module and an exception handling sub-module. According to the method, the technical threshold of process design is lowered, personnel can easily master, and organic combination of intelligence and humanization is achieved.

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 provides a training method, a reasoning method, a device and equipment for a large language model. Relates to the technical field of computers. The method comprises the steps of obtaining a training text, wherein the training text comprises a first text fragment which is not labeled and a second text fragment which is labeled as a block text; inputting the training text into a large language model, and processing the second text fragment through a block attention mechanism module in the large language model; processing the first text fragment through a standard attention mechanism module in the large language model; calculating a first loss based on a prediction result of the first text fragment output by the large language model; calculating a second loss based on a prediction result of a second text fragment output by the large language model; determining total loss according to the first loss and the second loss; and optimizing parameters of the large language model based on the total loss to obtain a trained large language model. According to the method, the memory reading frequency is reduced, and the efficiency of large language model reasoning is improved.

The invention discloses a development method and system based on a zero-code platform, electronic equipment and a medium, and belongs to the field of software development. The development method comprises the following steps: providing a zero code platform, wherein the zero code platform comprises a designer and an object module library; selecting an object module from an object module library and importing the object module into a graphical interface of the designer; in a graphical interface of the designer, configuring a selected object module, and presenting a reference relationship, a logic connection line and a data flow path of the object module through a visual interface; verifying whether the selected object module is compliant or not; and after the verification is passed, persistently packaging to the local, and generating a corresponding project program. According to the method, a graphical design interface and visual configuration are provided, so that a user can complete complex system design through simple configuration operation without programming skills, the development threshold is greatly reduced, the project development period can be greatly shortened, and users in more fields can participate in system development.

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 method and equipment for assisting in compiling codes, a medium and a product, and relates to the technical field of software development. The method comprises the following steps: analyzing a code snippet of a development object; technical information related to the code snippets is obtained according to the analysis result of the code snippets, the technical information is obtained based on a knowledge graph or a pre-trained deep learning module, and the technical information comprises at least one of a technical scheme and technical level information; and displaying the technical information to the development object to assist the development object to write codes. According to the embodiment of the invention, the development object can be helped to quickly obtain the technical information required by code writing, and the code writing efficiency is improved, so that the software development cost and time are effectively reduced, the software development difficulty is reduced, and the development efficiency is improved.