201 results about "Modula" patented technology

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.

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 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.

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 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 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.

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 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 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 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.

The invention provides an operation and maintenance system based on a large language model, and relates to the technical field of operation and maintenance, in the operation and maintenance system, a dialogue module determines an associated entity type name according to an intermediate question text; establishing an association relationship between each preset operation and maintenance tool corresponding to the association entity type name and the large language model; sending the intermediate problem text to a large language model to enable the large language model to work with an entity operation and maintenance agent identity corresponding to the associated entity type name, and obtaining target data according to the intermediate problem text and a preset operation and maintenance tool having an association relationship with the large language model; obtaining an initial feedback text corresponding to the intermediate problem text according to the target data; a corresponding entity operation and maintenance agent identity is given to the large language model, so that the large language model can dynamically associate and call a preset operation and maintenance tool corresponding to the entity, target data are automatically collected, and an initial feedback text is generated; and the response efficiency and the accuracy of the obtained initial feedback text are improved.

The invention discloses a software outsourcing-oriented heterogeneous code warehouse intelligent coupling degree detection system and method, and relates to the technical field of software engineering.The method comprises the steps that an instruction is detected, and code file information, dependency information and development log information are obtained through a distributed crawler module, an abstract syntax tree analysis tool and a natural language processing module; carrying out modular segmentation on the code file by utilizing semantic coupling analysis, inputting the code file into a large language model equipped with a LoRA adapter, identifying a coupling inverse mode, and carrying out preliminary optimization based on a quantum heuristic coupling optimization algorithm; after optimization, a multi-user concurrent scene is simulated through digital twin simulation, and the coupling degree is dynamically detected; meanwhile, a cross-language interface testing tool is used for testing interface compatibility and call chain coupling; the system comprises an information acquisition module, a semantic coupling analysis module, a quantum optimization module and a coupling degree detection module, provides a deep optimization basis for developers, and improves the coupling degree detection and optimization efficiency of the heterogeneous code warehouse.

The invention discloses an application automation operation method and system based on a large language model, and belongs to the technical field of network security, and the method comprises the following steps: 1, receiving the content input by a user; 2, performing control adjustment on task circulation; step 3, collecting and processing an application page state, and outputting multi-modal data; 4, multi-modal input is constructed, and an operation instruction is generated; 5, executing an operation sequence according to the operation instruction generated in the step 4, and recording an operation process; 6, converting the operation instruction generated in the step 4 into an underlying equipment command; 7, after task circulation is finished, a judgment intelligent processing unit module is constructed, global analysis is conducted based on the complete execution history and the user instruction in the process of the step 5, and the completion condition of automatic operation in the step 5 is obtained; the technical problems that in the prior art, the workload is high, and ambiguity is prone to occurring in recognition are solved.

A method, apparatus, a product comprising: obtaining a propagator module of a quantum function of a quantum program, the propagator module is programmed using a classical programming language, the propagator module configured to obtain as input a first domain of values for a first circuit parameter and a second domain of values for a second circuit parameter, and to output first and second sub-domains of the first and second domains of values, respectively; obtaining constraints of the quantum function; obtaining an optimization scheme that is defined over the first and second circuit parameters; generating a constraint problem based on the propagator module, the constraints, and the optimization scheme; resolving the constraint problem based on a constraint solver, a resolution comprising at least first and second values for the first and second circuit parameter; and synthesizing the quantum function according to the resolution.

The invention provides a controller program generation method based on semantic planning and quality optimization, and belongs to the technical field of automation. A multi-stage PLC program generation and optimization method oriented to natural language task description is adopted, and semantic retrieval enhanced task planning, structured code synthesis and a quality closed-loop optimization mechanism based on feedback are fused. A natural language task is automatically converted into a verifiable plan with logic constraints by constructing a semantic index, reasoning scheduling and an intermediate representation structure; through module clustering and multi-round prompt guiding type logic reconstruction, generation of a high-quality PLC program meeting the IEC 61131-3 standard is realized. And static analysis and test feedback are combined, and the code quality is evaluated and enhanced by adopting iterative optimization and a scoring mechanism, so that the problems of intelligence, structuring and verification of the whole process from natural language to PLC program are systematically solved, and the development efficiency, the program robustness and the feasibility of industrial deployment are remarkably improved.

The invention discloses a software code defect automatic detection and repair system based on deep learning, and relates to the technical field of deep learning technology.A data acquisition module acquires multiple source codes and metadata and adapts to a mainstream programming language; the preprocessing module cleans codes, extracts features and divides data sets; the detection model is used for identifying 12 types of defects by using a Bi-LSTM (Bidirectional Long Short Term Memory) and Transform mixed architecture; the repair model generates a repair scheme based on CodeBERT; defect verification is integrated with static / dynamic verification; the system management realizes configuration, user, task and log management, and supports RBAC authority control. According to the method, the code defect detection accuracy and repair efficiency are improved, and multiple defect types and programming languages are covered; the repairing scheme adapts to the scene and is explained, so that the labor cost is reduced; model dynamic updating and cross-language adaptation are supported, a development process can be integrated, and the comprehensive effects of code quality improvement, efficiency improvement and maintenance cost reduction are achieved.

The invention discloses an intelligent code writing and quality assurance system for multi-language code analysis, which relates to the technical field of intelligent code development and quality control and comprises a multi-language code analysis engine, an intelligent engineering management module, a self-adaptive compiler, an interactive console, a multi-dimensional instance library and a personalized configuration center, each module realizes real-time data interaction through a distributed data bus; the system supports more than 15 mainstream programming languages, new language support can be expanded through plug-ins, and the multi-language code analysis engine integrates static analysis, dynamic tracking and cross-language call detection functions. Static analysis identifies grammar errors and undefined variables through abstract syntax tree analysis. According to the intelligent code writing and quality assurance system for multi-language code analysis, the single-language limitation of a traditional system is broken through, conjoint analysis of programming languages is achieved, cross-language defect recognition accuracy is improved, and potential risks of multi-language projects are remarkably reduced.

The invention relates to the technical field of computers, in particular to a cross-architecture application program migration method and device, equipment and a medium. According to the embodiment of the invention, firstly, the source code is automatically analyzed, the function dependency relationship is obtained, and the specific code segment of the original architecture is accurately identified, so that high cost and low efficiency caused by manual intervention are avoided, and the problem of insufficient automatic migration capability is solved; secondly, a cross-architecture migration mapping library is utilized, an original architecture code segment is automatically converted into a target architecture compatible code according to a rule, third-party library dependence is processed in batches through a preset rule, and the risk of migration failure caused by the library compatibility problem is reduced; finally, the converted codes are reconstructed based on the function dependency relationship, it is ensured that calling logic among the modules is correct, and normal operation of the third-party library under the target architecture is further ensured. Through the series of automatic operations, efficient and stable application migration is achieved, and the success rate and reliability of cross-architecture migration are improved.

The invention relates to the technical field of software engineering and artificial intelligence, and discloses a high-credibility programming agent system and method based on a large model and a formalization method. A high-credibility programming agent system based on a large model and a formalization method comprises an agent core module used for providing common perception, memory, decision and execution capabilities for various professional agents; the multi-agent cooperation module is constructed on the agent core module and comprises a coding agent, a form analysis agent and a form verification agent; the coding agent is responsible for generating, complementing, reconstructing and optimizing program codes based on natural language requirements or contexts. The system realizes full-process automation from demand understanding to code generation, analysis, verification and restoration through autonomous planning and multi-task execution capability of the intelligent agent, reduces manual intervention links, and remarkably shortens the development period.

The invention discloses a large language model reasoning acceleration method based on GQA feature optimization, and the method comprises the steps: 1, determining the segmentation granularity of a query tensor Q, and segmenting the query tensor Q into one or more subtasks; step 2, adaptively determining segmentation numbers of a key tensor K and a value tensor V; and step 3, calculating a query tensor Q, and after calculation is completed, scheduling the key tensor K and the value tensor V to different calculation unit groups to perform calculation in parallel. The invention further discloses a reasoning acceleration system for implementing the reasoning acceleration method. The reasoning acceleration system comprises a calculation task dynamic division module, a parallel scheduling module, a dynamic addressing multiplexing module and a zero-copy access module. The reasoning acceleration method and system have wide application value.

The invention relates to the technical field of artificial intelligence, in particular to an ST-language-oriented assistant system and method, electronic equipment and a storage medium, and the method comprises the steps: constructing an ST-language-oriented intelligent programming system through the cooperative work of a data processing module, a model training module, a deployment integration module and a data production module; firstly, multi-source industrial ST data is processed to construct a training sample, then a special large language model is obtained through continuous pre-training and supervised fine tuning, finally, the model is integrated into a development environment to provide the functions of code completion, question and answer interaction and the like, and a closed-loop optimization mechanism is formed by collecting user interaction and model generation data. According to the method, a closed-loop system integrating four modules is constructed, deep compatibility and local security deployment of ST grammar specifications of multiple manufacturers are achieved, the code generation accuracy and development efficiency of industrial ST programming are improved, and meanwhile the system has the continuous self-adaptive optimization capacity by means of a data driving mechanism.

The invention relates to a code generation method based on a large model dynamic routing mechanism, which comprises the following steps of: constructing a difficulty-perceived task routing module, and performing complexity judgment on an input programming problem; for simple problems, code generation is carried out by directly adopting few-sample prompt, and complex reasoning of excessive thinking is avoided; for complex problems, an intention thinking chain is introduced, reasoning is divided into two stages of specification description and thought generation, and the method is used for explicit modeling of task intention and logic structures. Then, according to a difficulty judgment result of the task, executing a generation process along the determined scheduling path: for a simple task, outputting a code by adopting a direct generation path; for a complex task, an intention thinking chain is generated firstly, and then a structured code consistent with a task intention is generated based on the thinking chain. By using the method provided by the invention, efficient generation of the programming task in the industrial intelligent system can be realized.

Disclosed herein are systems, apparatuses, and methods for configuring and using one or more modular software libraries for use with large language models (LLMs) for automatically generating code from one or more user task queries. The systems, apparatuses, and methods compare a user's task query to generate code for a task with only headers of docstring. After identifying potentially relevant code from the most closely matching headers, the systems, apparatuses, and methods combine the user's task query with the identified docstring bodies as a prompt to one or more LLMs to converge upon software modules, functions, classes, and / or submodules (e.g., software code components) that contain relevant code. The systems, apparatuses, and methods then generate code responsive to the user's task query from the selected modules, functions, classes, and submodules.

A compiling method and related device can avoid full compilation as much as possible and reduce the time cost of compilation in the scenario of the first compilation of a code project. For example, a code project and a first dependency relationship are included in a server, the code project includes N modules, and the N modules have not been compiled. A terminal device sends a first compiling instruction to the server, which is used to instruct to compile a first module in the code project. The server determines a second module in the code project that has a dependency relationship with the first module according to the first module and the first dependency relationship, and the first dependency relationship is used to describe the dependency relationship between the N modules. The server compiles the first module and the second module.

In some embodiments, a secure chatbot includes a generative language module (GLM) and a prompt manager configured to dynamically update GLM input prompts according to outputs of the GLM. The input prompts instruct the GLM to perform a task (e.g., determine whether a target message received by a user indicates online fraud) and, in response, output a particular token. In response to detecting the token within the output of the GLM, the prompt manager can selectively execute a code snippet identified according to the respective token. Executing the code snippet effectively updates the prompt, which is then fed back to the GLM for a next inference step. In contrast to conventional LLM prompts, the updates to the prompts herein include modifications (e.g., insertion of other tokens, etc.) rather than merely appending inferred tokens to previous prompts. Moreover, the prompt modifications are executed inline, i.e., without submitting a wholly new prompt to the GLM.

The invention relates to the technical field of data enhancement and system engineering, in particular to a user behavior data enhancement method of a large language model based on RFLP driving. Comprising the steps of determining a core driving problem and an expected application scene of to-be-generated user behavior data, determining a task target, a data structure requirement, a data characteristic requirement, a constraint condition and a non-functional requirement of a large language model data generation system based on RFLP driving according to the core driving problem and the expected application scene, and encoding the requirement specifications into a plurality of functional modules; and forming a data generation function set according to the modules, constructing a logic scheme based on'strategy-component-combination 'for the system based on the function set, converting the logic scheme into an executable scheme, finally controlling the large language model to execute the executable scheme, and generating to-be-generated user behavior data. Therefore, the problem that the cue word is difficult to ensure the quality and consistency of the generated data is solved, and a scientific methodological support is provided for constructing a high-quality, controllable and extensible synthetic user data generation system.

Techniques for transforming code modules to different programming languages are disclosed. A system accesses a first non-code representation of a first code module expressed in a first programming language and parses the first non-code representation to identify a nested data element of the first non-code representation that represents a nested expression of the first code module. The system executes a transformation technique to transform the nested data element, in the first non-code representation, to a first non-nested data element in the first non-code representation. The system modifies the first non-code representation based on one or more attributes of a second programming language to generate a second non-code representation suitable for representing code modules in the second programming language. The system generates a second code module based at least on the second non-code representation.