122 results about "Design documentation" patented technology

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

The invention relates to the technical field of chip design, in particular to a timing constraint automation generation method. According to the method, the actual demand of the clock needing to be created is determined based on the design document, and then the clock list is generated based on the actual demand; the content of the clock list comprises a PLL source, a clock type, a clock name, a source path, a main clock name, a main clock source path, a frequency, a main clock duty ratio, a derivative clock duty ratio, a frequency division coefficient, whether the clock has a cross-clock requirement or not, and the mutual relation between the created clocks; executing the script in a clock list which needs to be read by the configuration script and the specified script; and traversing all options in the clock list by the script, generating a time sequence constraint, and automatically finishing GCA check. According to the method, timing constraint compiling and checking can be automatically achieved through the script only by completing output of the clock list, and the method for compiling the timing constraint is accurate and easy to maintain.

The invention discloses an engineering design document compliance inspection method, electronic equipment and a storage medium, and the method is based on an OCR and a large language model, and comprises the following steps: standardizing the character recognition and extraction of a document; standardizing character error check and manual correction of the text; performing structured processing on the corrected standard text; vectorization processing of core text content and construction of a standard query system; presetting a specification set range corresponding to each chapter of the design document; carrying out vectorization and similarity query on characters selected by a user in the text editor; corresponding standard content is provided for the user; the method can improve the efficiency and accuracy of specification reference in the document, facilitates the dynamic update management of specification contents, and facilitates the guarantee of the correctness of reference specifications.

The invention provides a method and a system for automatically checking and correcting a PCB (Printed Circuit Board) design rule, belonging to the technical field of PCB design. The method comprises the following steps of: analyzing data such as texts, images and tables in a PCB design document through a multi-modal large model, extracting a structured signal information table, automatically generating a dynamically adaptive checking rule, and automatically checking and correcting the PCB design rule. Comprising bit width check, connectivity verification and functional analysis. And the generated rule is optimized by combining a retrieval enhancement generation (RAG) technology with a verification rule base, so that the coverage is comprehensive and the accuracy is high. The system further evaluates the rule through a form verification tool, automatically corrects potential defects, and improves the quality and adaptability of the rule. According to the method, the efficiency and accuracy of PCB design inspection are remarkably improved, the manual intervention requirement is reduced, the method can be widely applied to complex electronic design scenes, and the rapid changing technology and market requirements are met.

The invention provides a ship management system design assisting method based on a knowledge graph, which comprises the following steps of: processing scattered design documents and design criteria of enterprises by utilizing a natural language processing technology, extracting knowledge triple information in the design documents and design criteria, and on the basis of the constructed knowledge graph, further utilizing a retrieval enhancement generation (RAG) technology to generate a knowledge triple; according to the method, subjective query of design information of a graph database is achieved, analysis and proofreading of design information graph-text and document data corresponding to design drawings and models are achieved, and finally design requirement query and automatic check of the design drawings and models in the design process of aided designers are achieved. Integration and sharing of design knowledge are completed, and the design knowledge utilization rate is increased.

The invention provides an end-to-end software development automation platform and method, and the platform comprises an intelligent design module which automatically generates a structured design document through multi-Agent cooperation and builds a traceable link; the intelligent development module is used for analyzing the UI design draft through computer vision to generate a front-end code and automatically generating a rear-end code based on the design document; the intelligent test module automatically generates a test case and drives a test closed loop; the workflow engine configures a flow through a visual interface and monitors a task through an intelligent Agent; and the RAG knowledge base and the Agent base disk are used for dynamically slicing the document and storing the document in a vectorization manner, and support multi-role Agent collaboration. According to the platform, the time consumed by manual design can be reduced by 50%-70%, and the design period is shortened by 67%; the front-end development efficiency is improved by three times; the automatic coverage rate of back-end codes reaches more than 90%, and the labor cost is reduced by 60%; the test case generation efficiency is improved by three times, and the test period is shortened by 50%.

Various embodiments include methods and systems for automatically evaluating infrastructure configuration and / or architectural design documentation for compliance with relevant standards, requirements, and policies. Embodiments provide a framework for automating compliance reviews of infrastructure configuration and / or architectural designs against standards, requirements, and policies. Methods may include transforming input requests for analysis and infrastructure configuration and / or architectural design documents into formats suitable for processing by a large language model (LLM), prompting the LLM to identify concepts and / or elements that are likely subject to a standard, requirement, or policy, querying a compliance criteria vector database to identify standards, requirements, or policies relevant to the requested analysis and documents, prompting the LLM to determine whether infrastructure configuration and / or architectural design documents comply with each relevant standard, requirement, or policy, and producing reports from LLM outputs regarding compliance of the infrastructure configuration and / or architectural design documents with each of the relevant standards, requirements, or policies.

The invention relates to the technical field of software engineering and information processing, in particular to a semantic verification method and device based on a large model.The method comprises the steps that a source code file and a corresponding software requirement and design document are obtained, code semantic representation is generated based on grammar analysis and static program analysis, and a semantic verification result is obtained; based on text analysis and business flow chart structure identification, generating a design demand semantic representation; respectively inputting the code semantic representation and the design demand semantic representation into a pre-training language large model to generate a code implementation logic description and a design demand logic description; and performing semantic consistency verification on the two types of logic descriptions to obtain a semantic inconsistency result, determining a code position in the source code file based on the semantic inconsistency result, and outputting a scanning report. According to the invention, the automation degree and the rechecking performance of consistency checking of requirements can be improved, and the leak detection and reworking cost can be reduced.

The invention relates to the technical field of artificial intelligence, and provides a construction plan generation method and device, electronic equipment and a storage medium. According to the method, firstly, a construction design document of a target project is preprocessed to obtain a coding vector, then an intention analysis model responds to a received construction plan construction instruction to perform intention analysis on the coding vector, and an initial construction subtask set is obtained; the intention analysis module also retrieves each sub-task in the initial construction sub-task set, and adjusts a sub-task division mode based on a retrieval result until a target sub-task set meeting a preset condition is obtained; and finally, inputting the target sub-task set into an inference model, integrating the construction period and the construction path of each construction sub-task by the inference model based on the constraint conditions in the target sub-task set, and obtaining a construction plan of the target project, thereby improving the automatic generation efficiency of the construction plan, and enabling the generated construction plan to better meet the requirements of users.

The invention provides a system function test method and device, electronic equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: disassembling a demand document and a design document of a to-be-tested system function to obtain key index parameters; on the basis of the key index parameters, testing logic for the to-be-tested system functions is configured, and the testing logic is converted into script codes; marking the service data of the system function to be tested on the basis of the script code; and generating a test result for the to-be-tested system function based on the labeled service data. According to the invention, the possibility of faults when system functions are online can be reduced.

The invention provides an automatic generation method supporting an MBSE system model and a design document. MBSE system model project information is read, and design document basic information is automatically generated; system design flow information of a methodological model constructed in an MBSE system model project is read, corresponding document chapters are generated according to flow design content C, the sequence of the document chapters is determined according to the design flow sequence A, and the outline level of each chapter in the design document is determined according to the hierarchical relation in the design flow hierarchy B; on the basis of the generated design document structure and the read design process corresponding model D, automatically filling each chapter with model content; and dynamically updating the content of the design document. The problems that in the prior art, a design document generation method based on templates and rules is poor in flexibility, and the document and the model are difficult to dynamically synchronize can be solved, and the consistency of the system model and the design document is guaranteed.

The present disclosure relates to systems, methods, and non-transitory computer-readable media that provides customized editing access rights for sub-portions of a digital design document. In particular, the disclosed systems generate a mapping between a selected sub-portion of a plurality of sub-portions of a digital design document and a user account indicating editing access rights to the selected sub-portion for the user account. Furthermore, the disclosed systems receives digital content from a client device associated with the user account for the selected sub-portion. Moreover, the disclosed systems modify the selected sub-portion to include the digital content from the client device based on the mapping between the selected sub-portion and the user account.

The invention relates to the technical field of data processing, and discloses a building structure automatic design method and system based on artificial intelligence. The method comprises the steps that a collaborative building information model is constructed by collecting building design task data, load analysis and rigidity parameter calculation are carried out, a Timoshenko beam model is constructed, a structural arrangement prediction result is generated in combination with graph network optimization, a parameterized modeling program is input to generate a building structure model, and multi-working-condition analysis is completed to obtain a structural design scheme. Design documents and construction information are automatically generated, and a parameter and analysis result corresponding relation database is established. By integrating modeling, structural analysis and design document generation, the problems of intelligent collaboration and efficient output in the whole process of structural design are effectively solved.

The invention provides a multi-agent collaborative supply chain bill system automatic development method and device, and the method comprises the steps: receiving a user demand document related to a to-be-developed supply chain bill system, and obtaining an enterprise specification document used for constraining development technical specifications; initializing a workflow arrangement module and a state data structure for automatically developing the supply chain bill system; wherein the workflow arrangement module comprises a directed graph, an intelligent agent is used as a node, and a circulation rule is used as an edge; and the intelligent agent processing module is used for enabling the intelligent agents to work serially and / or concurrently according to an execution path determined by the workflow arrangement module by taking the enterprise specification document as a constraint, analyzing the user demand document to obtain a design document, planning a development task according to the design document, generating review opinions by reviewing the planned development task, and sending the review opinions to the intelligent agents according to the review opinions. And generating a code file based on the design document, the development task and the review opinion, and compiling the code file to obtain an executable file related to the supply chain bill system.

The embodiment of the invention provides a code generation method and device, equipment and a storage medium. The method comprises the following steps: receiving a code generation request through an interactive interface associated with a model; response content generated by the model based on the code generation request is presented in the interactive interface, the response content comprises a design document, and the design document describes development demand information determined based on the code generation request; presenting an editing window of the design document, wherein the editing window is configured to receive at least one editing operation for the design document; and providing code content generated by the model based on the design document. Based on the mode, according to the embodiment of the invention, the design document determined based on the code generation request can be edited, so that the code content can be generated based on the edited design document, and the generation quality of the code content is effectively ensured.

This invention belongs to the field of natural language processing and information extraction technology, and provides a method and system for extracting parameters from boiler design documents based on multi-round self-feedback RAG. The method includes: preprocessing the boiler design document and the original query, converting them into several text segments and expected inputs respectively; encoding the text segments and expected inputs into high-dimensional vectors and query vectors respectively, storing the high-dimensional vectors and constructing a vector index; generating a response based on retrieved external knowledge to assist a large language model, and iteratively optimizing the generated results through multiple rounds. This invention effectively solves the problems of incorrect and missing parameter extraction in complex or fuzzy query scenarios, significantly improving the reliability of the final results; it overcomes the limitations of traditional methods and standard large language models in handling multimodal data, enhancing the processing capability for complex multimodal documents; and it improves the accuracy of information retrieval, laying a solid foundation for subsequent accurate parameter extraction.

The invention discloses a vehicle data processing method, and relates to the technical field of automobile engineering. The method comprises the steps of obtaining a design failure mode and influence analysis file, a design document and a test case file of a vehicle; determining a design failure mode and a supplementary item of the influence analysis file based on a first problem set in the target knowledge base; determining an avoidance measure of the design document based on a second question set in the target knowledge base; determining uncovered items of the test case file based on a third question set in the target knowledge base; and updating the design failure mode and influence analysis file based on the supplementary item, updating the design document based on the avoidance measure, and updating the test case file based on the uncovered item, so as to carry out vehicle research and development according to the updated file. According to the invention, the technical problem that the research and development cost and time are increased because the historical problem of the automobile research and development process is easy to relapse in the related technology is solved.

Provided is a technology for visualizing an environmental load corresponding to product configurations on the basis of design documents.　This environmental load evaluation device is provided with one or more processors and outputs an environmental load of a product to be produced. The environmental load evaluation device is characterized: by including a storage unit that stores a bill of materials of the product, a diagram of the product, and basic unit information indicating basic units of an environmental load; and in that the processor is provided with a basic unit proposal unit that uses the bill of materials and outputs, as a proposal, candidates for basic units corresponding to components constituting the product, and an environmental load calculation unit that combines the proposed basic units with the bill of materials and calculates the environmental load of the product.

The invention provides a design document detection method and device, equipment, a storage medium and a program product, and relates to the field of artificial intelligence, and the method comprises the steps: obtaining first item information of a target item to which a to-be-detected design document belongs, the to-be-detected design document being used for indicating the current business logic of the target item; based on the first project information, a historical design document of the target project is retrieved, and the historical design document is used for indicating historical business logic of the target project; inputting the to-be-detected design document and the historical design document into a pre-trained first deep learning model, judging whether the current business logic and the historical business logic have conflicts or not by the first deep learning model based on the to-be-detected design document and the historical design document, and outputting first detection information when the conflicts exist, the first detection information is used for indicating that the current service logic conflicts with the historical service logic. According to the method, the easily ignored and deep business logic conflicts in the design document can be efficiently and accurately identified.

The invention relates to the technical field of data processing, in particular to an asset import method and device, computer equipment and a storage medium. The method comprises the steps that text content of a design document is obtained to serve as a target text, cue words of all asset types are obtained, and the cue words are used for explaining and limiting data corresponding to the asset types; constructing an extraction template based on each cue word and the target text; the extraction template is used for indicating to extract data from the target text based on each prompt word; calling an extraction model to process the extraction template to obtain asset data corresponding to each asset type; the extraction model is constructed based on a large language model; and importing the asset data corresponding to each asset type into the development platform. By adopting the scheme of the invention, the efficiency of designing the asset import development platform can be improved.

The invention discloses a communication engineering design optimization method, system and device and a medium, and the method comprises the steps: matching corresponding description documents and investigation materials according to a to-be-optimized design type and a to-be-optimized design stage; analyzing the description document to generate a stage description document corresponding to the to-be-optimized design stage; constructing a data material library based on the investigation material; establishing an initial design document based on the stage description document and the data material library; responding to an updating instruction of the initial design document, and obtaining the updated initial design document; initial design data are extracted from the updated initial design document, a design optimization suggestion of the updated initial design document is generated according to the initial design data, and the optimization suggestion can be generated by matching a description document and a reconnaissance material required by design, combining initial design document building and updating response and data extraction analysis. The policy compliance is accurately controlled, the cross-professional data consistency is guaranteed, and the communication engineering design quality and the overall working efficiency are effectively improved.

The invention relates to the technical field of software testing, and particularly discloses a test case generation method and system based on a large language model, and the method comprises the steps: carrying out the analysis based on a function demand and a design document of a test system, and obtaining a main function coverage scene; acquiring a secondary function coverage scene based on an external environment condition of the test system; performing user behavior analysis and emotion analysis based on the user group data of the test system to obtain an auxiliary function coverage scene; determining a function test requirement of the test system based on the main function coverage scene, the secondary function coverage scene and the auxiliary function coverage scene; and based on the function test demand R, generating a test case by using a large language model. According to the method, the accuracy and comprehensiveness of test case generation can be improved, so that the software quality and stability can be guaranteed through a more perfect test.

The invention discloses a graphical code verification method, and relates to the technical field of rail transit signal systems, and the method comprises the following steps: S1, reading a new version demand document FS, a design document AD and a graphical code EMIL of a subsystem; s2, comparing the demand document FS and the design document AD of the new version and the old version, and associating to obtain an NEWTrace table file and an OLDTrace table file; s3, the NEWTrace table file and the OLDTrace table file are traversed, and a ChangeLog table is obtained; s4, reading a new and old version graphical code EMIL and a ChangeLog table, and generating a code comparison text file and an AD check text file; s5, traversing and updating the Themes verification table; s6, verifying the consistency of the requirement for modifying the entry and the code; and S7, summarizing all verification results of the Themes verification table. According to the method, demand design and codes are integrated, corresponding modification demands and modification codes are identified and triggered through an automatic method, walking verification is facilitated, and the code walking verification efficiency is improved.

The invention provides a knowledge question-answering method and system for a vertical domain design document, and the method comprises the steps: reading a design document, carrying out the preprocessing of the design document, and obtaining an input text; converting the input text into word embedding representation; establishing a double-scoring layer, learning word embedding representation through the double-scoring layer, obtaining a fusion scoring matrix of the vertical domain knowledge and the corresponding label, and converting the fusion scoring matrix into a prediction sequence of the corresponding label of the vertical domain knowledge; according to the scoring sequence, a vertical domain knowledge dictionary is extracted from the input text through a candidate mechanism, and a vertical domain knowledge base is constructed according to the vertical domain knowledge dictionary; and performing knowledge query by the vertical domain knowledge base and returning a query result. According to the method and the device, the question and answer type query results can be constrained to be from the vertical domain knowledge existing in the document, so that the credibility of answers is ensured, the security of data is improved, meanwhile, convenient query of the vertical domain design document knowledge is realized, and the working efficiency is improved.

The invention discloses an engineering design document standard specification checking method and system, and the method comprises the following steps: 1, constructing an engineering standard library, carrying out the classified storage of national standards, industrial standards and local standards, and dynamically updating the state information of each standard; 2, receiving an engineering design document uploaded by a user, performing text preprocessing on the engineering design document, and intelligently extracting standard specification reference information in the document; 3, performing multi-dimensional comparative analysis on the extracted standard specification reference information and data in an engineering standard library, and identifying information difference and a standard validity state; 4, generating a modification suggestion according to a comparison and analysis result, and performing a modification operation on the error reference based on the current effective standard in the engineering standard library; and 5, outputting a checking result, wherein the checking result comprises outputting the engineering design document with the error mark and / or the modified engineering design document.

The application discloses a software design and development method and a terminal, a detailed design document corresponding to an architecture design document is generated according to software requirements, a corresponding core class code is generated according to a core class diagram of the detailed design document, and an engineering code is obtained by directly developing based on the core class code by a developer; if the engineering code does not match the core class in the detailed design document, the core class diagram and the corresponding design document are re-generated, thereby greatly improving the consistency of software design and software development; if the engineering code matches the core class of the detailed design document, the engineering code is submitted to a code warehouse, the submitted document is ensured to be correct and reliable, and the design document is ensured to be well landed in the development stage.

The system according to this embodiment aims to clarify application requirements based on user responses and to quickly create prototypes. [Solution] The system according to the embodiment comprises a reception unit, an analysis unit, a generation unit, and an output unit. The reception unit receives responses from the user. The analysis unit analyzes the responses received by the reception unit and clarifies the application requirements. The generation unit creates a prototype application based on the requirements clarified by the analysis unit. The output unit outputs a requirements definition document and a design document based on the prototype application created by the generation unit.

Implementations herein leverage knowledge about historical process automation facilities to automate designing a new process automation facility. A first level design input may be processed to generate a first embedding that encodes design aspect(s) of the requested process automation facility with a degree of detail commensurate with a first level of a hierarchy reflected by design documents typically used to design a process automation facility. The first embedding may be used to find first level reference embeddings that encode design aspects of reference process automation facilities. Second level reference embedding(s) may be identified based on mapping(s) from the selected first level reference embedding(s). Each second level reference embedding may encode design aspect(s) of a respective reference process automation facility with a degree of detail that is commensurate with a second level of the design document hierarchy. Based on the second level reference embedding(s), template design document(s) may be provided.

The application relates to an artificial intelligence-based software design scheme automatic evaluation method and system, which automatically extracts function entities and architecture topologies in a design document through a multi-modal analysis technology to generate a structured design scheme atlas; performs standardized compliance checking based on an enterprise architecture benchmark library to identify technical specification deviation and component reuse defects; fuses a defect prediction model and a risk quantification mechanism to analyze component coupling degree and historical defect data to generate a risk atlas; combines constraint rules and a similar case library to deduce an executable architecture optimization path; finally, constructs a closed-loop decision chain of technical compliance, risk control and asset reuse to generate a quantitative evaluation report. The application solves the problems of traditional evaluation methods, such as dependence on manual work, low efficiency, non-uniform standards and decision disconnection, realizes full-process automatic evaluation from design analysis to improvement guidance, significantly improves evaluation efficiency and decision accuracy, and guides software architecture optimization decision.

This invention discloses a method, apparatus, device, medium, and product for compliance testing of design documents, relating to the field of artificial intelligence technology and applicable to the fintech field. The method includes: acquiring a target design document to be tested, and determining at least one clause item to be tested contained in the target design document and the target clause item type corresponding to the clause item; if the target clause item type is a first clause item type, determining target compliance rules based on the target clause item type, and performing compliance testing on the clause item to be tested according to the target compliance rules; if the target clause item type is a second clause item type, using a target large language model to perform compliance testing on the clause item to be tested. This invention combines the deep semantic understanding capability of a large language model with the accuracy of structured compliance rules, comprehensively improving the accuracy and comprehensiveness of design document compliance testing, and reducing the false positive and false negative rates of design document compliance testing.