179 results about "Requirement document" patented technology

The invention discloses a code translation method and device based on a large language model, and the method comprises the steps: firstly executing an architecture understanding workflow, and forming an architecture design document O1 of a code library; according to the architecture design document O1 of the code library, in combination with the demand document P1, code translation task decomposition workflow is executed, and a task planning list O2 is formed; elements in the task planning list O2 are sequentially extracted, and the code debugging workflow is executed to complete code translation and debugging work. A warehouse-level code architecture understanding workflow, a code translation task planning workflow and a code debugging workflow are constructed based on a large language model (LLM), and the workflows are organically combined to realize automatic translation of warehouse-level codes. According to the method, the limitation of function level translation in the prior art can be broken through, automatic translation of warehouse level codes is realized, the development cost is greatly reduced, and the translation efficiency is improved.

The invention provides a customer service knowledge base construction method and device and a computer readable storage medium. In the scheme, first information including function requirements, performance indexes and business rules of a target product is extracted from a requirement document of the target product, and second information including interface elements, interface element attributes and interface layout information of the target product is extracted from a prototype graph of the target product; inputting the first information and the second information into a pre-trained GPT large model for analysis to obtain a target knowledge point of the target product; generating customer service knowledge base entries according to the target knowledge points, and obtaining a customer service knowledge base formed by the customer service knowledge base entries; and if it is monitored that the version of the demand document and / or the prototype graph is updated, updating the customer service knowledge base according to the updated demand document and / or the updated prototype graph. According to the scheme, the problem of limitation of construction of the customer service knowledge base in the prior art is solved, wherein the limitation comprises low accuracy, low automation degree and update lag.

The invention discloses a software requirement specification document automatic generation method based on a large language model, and the method comprises the steps: text preprocessing: carrying out the category labeling of sentences in software requirement customer opinion data, and dividing a data set into a training set and a verification set; training a demand classifier: classifying texts in the application data set, designing and training a BERT-GCN model, and summarizing different categories of information into different dimensions of software demands; a text multi-classification task: inputting a to-be-processed customer opinion data text into the trained demand classifier for demand text classification, and outputting a classified tagged text; and generating a standard requirement document: inputting the classified tagged text into a large language model, designing a corresponding output prompt template, and guiding the large language model to generate a standardized software requirement specification document. The problems that an existing method for generating the software requirement specification document is low in efficiency and prone to making mistakes are solved.

The invention relates to the field of vehicle testing, in particular to a test case generation method, a computer program product, electronic equipment and a medium. The test case generation method comprises the following steps: acquiring a demand document of a tested object; extracting document information required by a test case from the demand document; inputting the document information into a large language model to obtain information of a standard test case; and filling the information of the standard test case into a template of the test case to obtain the test case. According to the invention, the pressure of manual test work can be reduced, the test efficiency is improved, and the test cost is reduced.

The invention provides an AI-based automatic test case generation method and system, and relates to the technical field of software testing, and the method comprises the steps: converting an original demand document uploaded by a user into an image format document, and calling a multi-modal large model to recognize text features and non-text features in the image format document, integrating to form an analyzed demand document; dynamically cutting the analyzed demand document to obtain a plurality of logically coherent content blocks; calling a large language model to generate a corresponding test case title for each content block, and forming a test case title set; and inputting each test case title in the test case title set and the corresponding content block into the large language model to generate a complete test case corresponding to the original demand document. The method has the beneficial effects that through multi-modal content analysis and intelligent workflow arrangement, automatic analysis and understanding can be performed on image-text features of a demand document, a high-quality test case is automatically generated, and the test period is greatly shortened.

The invention provides a document generation method and device, and relates to the technical fields of document processing, artificial intelligence, natural language processing, computer vision and the like. According to the specific implementation scheme, a reference document set and document description information are determined based on document demand information of a user; performing visual feature recognition on the reference document set by adopting a multi-modal large model to obtain a visual feature set; performing content semantic and content relationship identification on the document description information by adopting a first large model to obtain data structure information; determining a target reference document from the reference document set based on the visual feature set and the data structure information, and generating document planning information; and based on the document planning information, adjusting the target reference document to obtain a target demand document.

The embodiment of the invention provides a modeling method and device for an airborne system function architecture model, computer equipment and a medium, and relates to the technical field of aviation architecture design, the method comprises the following steps: inputting a design requirement document into an airborne large language model, and in the large language model, under the structural constraint of an airborne system knowledge graph, establishing a design requirement document; the method comprises the following steps: extracting a logical relationship between entities required by airborne system modeling from a design demand document, screening a corresponding airborne meta-model according to the extracted logical relationship between the entities, and constructing a demand graph; constructing and outputting a text model of a concept scene, a text model of a task scene, a text model of a system function, a text model of a logic architecture and a text model of a physical architecture of the airborne system based on the demand graph; and inputting each text model into a system modeling language modeling terminal for visualization to obtain a multi-level functional architecture model of the airborne system. According to the scheme, the modeling efficiency, consistency and normalization are improved.

The invention relates to the technical field of software development management, in particular to a cloud platform collaboration method and system oriented to elastic resource scheduling, and the method comprises the following steps: dynamically collecting a development data source and a demand document, determining a developer capability portrait based on the development data source, and determining a task demand portrait based on the demand document; inputting the updated developer capability portrait and the task demand portrait into a preset matching model, and dividing the received to-be-processed project task into a plurality of groups of subtask sets based on the updated preset matching model; and determining a developer matching scheme of each subtask in the subtask set by using the updated optimization algorithm. According to the method, a static skill label is upgraded into a quantifiable and updatable dynamic portrait, an optimization function is constructed by multiple targets such as skill matching degree, load balance, project priority and cooperation cost, and a specific implementation method of an optimal developer matching scheme is solved for an atomic task.

The present invention provides a test case generation method, device, system, and medium based on an AI model. The method includes: obtaining a requirement document, at least one title keyword, and business keywords input by a user, and being able to automatically traverse the requirement document to automatically distinguish different requirement modules by the target title and create corresponding first and second documents; when traversing to a target image, extracting first content from the target image based on an OCR module and writing it into the first document, and being able to record the first content recognized by the OCR module from the flowchart through the first document; when traversing to a new target title, triggering the input of the first document into the AI model to obtain target test cases and first inference information, improving the generation efficiency of test cases, and at the same time recording the inference information of the test cases in the first document, providing a basis for the inference process for testers to judge the reliability of the test cases.

The invention discloses a multi-agent system for knowledge-driven automatic software architecture design, and belongs to the technical field of computer aided design, and the multi-agent system comprises an analysis agent, a modeling agent, a design agent and an evaluation agent which are constructed based on a large language model, the analysis agent is used for extracting, screening and classifying requirements which influence the software architecture design from a software requirement specification and generating a requirement document; the modeling agent is used for generating a software architecture view according to a demand document and an external knowledge base; the design agent is used for generating a software architecture document according to the demand document and the software architecture view; and the evaluation agent is used for evaluating and analyzing the software architecture according to the demand document, the software architecture view and the software architecture document to generate an evaluation and analysis report. According to the method, through cooperation and interaction between the intelligent agents and prompt of external knowledge, the reliability, practicability and creativity of software architecture design can be effectively enhanced.

A system and method for an AI-based Automated Software Application Development Platform which intelligently gathers requirements from a business analyst and generates a runnable software application from those requirements. The AI-based platform enables the business analyst with no technical knowledge to visually model their requirements rapidly without requiring any programming Using the abstract requirements architecture and the platform, the analyst creates requirements models for the application's business processes and business tasks for each of the processes, including defining the supporting information needs. The system intelligently assists the user in defining the information needs for each of the business processes and their tasks. Once the requirements models are created by the analyst with the help of the platform, the platform automatically designs and creates an appropriate persistent canonical data model for the application from the defined information needs. The platform then creates a runnable software application. The system also provides a template for the user to input their requirements in descriptive text, and accepts requirements document for applications as written free form text or text documents written in English as input, and in a non-English language that the system automatically translates them into English. The system provides a method for reverse engineering an existing application, including generating a requirements document for the existing application such as a legacy modernization or digital transformation an old applications for redesigning, updating or revising them to accommodate a new requirements set for such applications.

The invention discloses a test case generation method, device and equipment and a readable storage medium, and relates to the technical field of software testing, and the method comprises the steps: partitioning a preset demand document based on a natural language processing technology NLP and data sensitivity, so as to generate a plurality of target demand documents with different sensitivities; for each first target demand document, calling an online large model or a local large model to generate at least one first test case for the first target demand document; for each second target demand document, calling the local large model to generate at least one second test case for the second target demand document, the sensitivity of the second target demand document being greater than that of the first target demand document; and integrating all the first test cases and the second test cases to generate a target test case set corresponding to the preset demand document. According to the method and the device, the generation cost of the test case can be effectively reduced on the basis of ensuring the data security and compliance.

The invention relates to a digital twinning model construction method and device, computer equipment and a storage medium, and relates to the technical field of digital twinning. The method comprises the following steps: acquiring a demand document of a to-be-constructed scene of a to-be-constructed digital twin model; inputting the demand document into a pre-trained large language model; the pre-trained large language model is used for analyzing the demand document, calling a duplicated model for constructing an entity in the to-be-constructed scene based on an analysis result, and generating a logic code of a to-be-constructed digital twin model; constructing a digital twinborn model based on a duplicated model called by a pre-trained large language model and the generated logic code; according to the method, the required digital twinborn model can be intelligently constructed according to the description of the actual demand document by utilizing the pre-trained large language model, and the establishment of the digital twinborn model for each demand document is not needed, so that the establishment efficiency and accuracy of the twinborn model corresponding to the scene to be constructed are improved.

The embodiment of the invention provides a requirement document auditing method and device, computing equipment, a storage medium and a product. The method comprises the following steps: acquiring an auditing request for a target demand document sent by a user side, and analyzing the target demand document in a reasoning stage by using a multi-modal artificial intelligence module to determine key information corresponding to various modal data contained in the target demand document and at least one action plan involved in the target demand document; performing knowledge retrieval based on the at least one action plan in the action stage to determine reference data associated with the at least one action plan, and auditing the target demand document according to the key information and the reference data; generating an auditing report according to the auditing result; and feeding back the auditing report to the user side. According to the technical scheme provided by the embodiment of the invention, the auditing efficiency and accuracy of the demand document can be improved.

The invention provides a software development cost evaluation method and device, a medium, equipment and a product. The method comprises the steps of obtaining a demand document corresponding to a target software project; performing paragraph splitting on the demand document to obtain at least one functional process; splitting each functional process into a plurality of sub-processes; identifying keywords in each sub-process, and calculating a CFP score of each sub-process according to a corresponding relationship between the keywords and a preset CFP basic score; and outputting a cost evaluation report about the target software project according to all the sub-processes and the CFP score of each sub-process. According to the method, manual item writing and workload calculation are not needed, the function process and the sub-process thereof can be automatically split and written according to the content in the demand document, the automation degree of the COSMIC method is improved, the complexity of original work is reduced, the time cost is reduced, and meanwhile the accuracy and the normalization of the CFP score of the calculation project are improved.

The invention discloses a business demand book recommendation method and device, relates to the technical field of artificial intelligence, can be used in the financial science and technology field, and comprises the steps: employing a fine-grained semantic information extractor to respectively carry out fine-grained semantic extraction on a to-be-matched title and a corresponding label of a business demand book, and contents of stock and the corresponding label of the business demand book, obtaining fine-grained business semantics of the title and fine-grained business semantics of the content; a coarse-grained semantic information extractor is adopted to perform coarse-grained semantic extraction on a to-be-matched title and a corresponding label of the business demand book, and the content of the stock and the corresponding label of the business demand book, and coarse-grained business semantics of the title and coarse-grained business semantics of the content are obtained; according to all extracted business semantics, calculating a matching degree score of the title and the content of each stock; and recommending the content of the stock with the highest matching degree score to a business demand book writer. According to the method and the device, high-adaptability content can be recommended to the title of the target demand book.

The invention discloses a software development requirement document generation method and device, equipment and a storage medium, and relates to the technical field of document generation, and the method comprises the following steps: obtaining first requirement information collected when target software is developed, and carrying out data preprocessing on the first requirement information to obtain corresponding second requirement information; determining each target entity corresponding to the second demand information, and constructing a target knowledge graph based on each target entity; complementing missing information in the second demand information based on the target knowledge graph by using the target large model to obtain third demand information, and performing logic verification on the third demand information to determine target demand information based on a logic verification result; and determining a corresponding target demand document template based on the software development demand type corresponding to the target software, and generating a target software development demand document corresponding to the target software based on the target demand document template and the target demand information. According to the invention, the generation efficiency and accuracy of the software development requirement document can be improved.

The invention discloses a test method and system and a medium. The method comprises the following steps: receiving a mind map file as input; converting nodes in the mind map into items of a test case; selecting a corresponding use case template according to the test scene; exporting the test case as a spreadsheet file; analyzing the demand document and the test case file to count a demand coverage rate; collecting a test execution result and defect information; and generating a test report containing statistical data, charts and analysis. According to the invention, the efficiency of test case generation and report writing can be improved, and automatic statistics of the demand coverage rate is realized.

The invention discloses a task book demand standardization method based on retrieval enhancement generation, and the method comprises the following steps: S1, gathering historical demand documents and standardized records, completing cleaning, term unification and structured storage, and forming a maintainable and searchable domain knowledge base; s2, segmenting the document into entries, carrying out keyword labeling and vectorization representation and indexing, and establishing a complete knowledge base system; s3, generating a high-quality reference set through pre-retrieval enhancement, semantic matching retrieval and post-retrieval enhancement; s4, based on the multi-layer template, driving the large model to output a structured demand confirmation document draft; and S5, providing interactive auxiliary revision containing user feedback and a double termination mechanism, and providing powerful intelligent support for finally forming a demand document. According to the method, the defects of element recognition, knowledge reuse and consistency guarantee in the prior art can be overcome, and a feasible engineering path is provided for large-scale and cross-scene demand standardization.

The invention discloses a test case generation method and related equipment. The method comprises the following steps: receiving multiple input source data; performing semantic integration and context association analysis on the demand document and the use case document through a content processor to generate structured processing data; calling a file processor to carry out format standardization processing on the input source data, and generating an intermediate file adaptive to AI model input; generating a semantic guidance instruction based on the preset cue word set and a preset multi-type cue word template through a word processor; inputting the structured processing data, the intermediate file and the semantic guidance instruction into an AI engine, and triggering a test case generation model; and receiving an original test case set output by the AI engine, and executing duplicate removal and priority ranking to generate a test case scheme. According to the method, the test case can be efficiently, comprehensively and accurately generated, and various defects existing in the software test case generation process in the prior art are effectively overcome.

The embodiment of the invention discloses a demand document generation method and device, equipment, a medium and a product, and the method comprises the steps: inputting demand text information into a first agent for demand analysis, and obtaining a demand analysis result; inputting the demand analysis result into a second agent to construct a business demand model to obtain a demand framework model; inputting the demand framework model into a third agent for document generation to obtain a first demand document; inputting the first demand document into a fourth agent with a document content conflict detection function to perform document content verification to obtain a document verification result, and outputting the first demand document after the verification is passed; wherein the fourth agent is a deep learning model pre-trained based on a natural language processing model. According to the technical scheme, the problem that current demand document generation depends on manual coordination and is low in efficiency is solved, manual intervention of demand document generation can be reduced, content conflict-free logic is guaranteed, and generation efficiency and reliability are improved.

The invention discloses an intelligent demand analysis and man-hour evaluation method and system, and belongs to the technical field of computer vision and artificial intelligence. Analyzing the multi-modal demand document containing the text, the picture and the table to generate structured demand data; based on the structured demand data and the system module description, performing module-level splitting on the demand to generate a module task set; retrieving an associated system implementation context for each task in the module task set based on a multi-dimensional knowledge base; fusing the structured demand data, the module task set and the system implementation context to generate a fine-grained technical task; based on a historical case index, calculating reference working hours for the fine-grained technical task; and cross-module cooperative correction and personalized correction based on the ability of the task executor are sequentially performed on the reference working hours to obtain final evaluation working hours, so that automatic deep analysis and accurate and personalized working hour evaluation of software requirements can be realized.

The invention belongs to the crossing field of artificial intelligence and software engineering, and particularly relates to an automatic engineering-level code iteration generation method and system. The method comprises the following steps: acquiring an iteration demand document, an engineering original code and engineering demand document multi-source input, analyzing the engineering original code, constructing a knowledge graph, associating engineering business elements, analyzing the engineering demand document, outputting a structured demand combing result in combination with the knowledge graph, and defining a function boundary and an implementation path. Then integrating an iteration demand document to generate and correct a source code technical document to form an engineering document, performing training optimization, finally generating an initial code by a large model, forming a final code through auditing and debugging, and feeding back data to the model for training, so as to realize full-process automation from demand input to code output. Therefore, manual intervention is greatly reduced, the development efficiency is improved, and the iteration period is shortened.

The invention discloses a code generation method based on a model, which is used for improving the generation efficiency of codes and relates to the technical field of artificial intelligence (AI). According to the application, for the given demand document, the service process in the demand document is analyzed through the AI model, and the service process in the demand document is presented by adopting a state machine representation mode, so that an interactive interface for representing the service process based on the state is realized, and an interactive action for representing the service process based on an event for triggering state conversion is realized. State machine representation is further analyzed through the AI model, codes are automatically generated, the manual code writing process is omitted, and the code generation efficiency is improved. Moreover, according to the scheme, the language understanding capability of the AI model is utilized, the complex business process is firstly converted into the simple state machine representation with a simple structure, and then the state machine representation is converted into the code, so that multi-step disassembly of the complex task is realized, and the AI model can more accurately understand the actual business process in the code generation process to generate the accurate code.

The invention provides a script generation method and device, electronic equipment, a storage medium and a program product. The method comprises the steps of performing feature extraction on a demand document of an application to obtain a first feature of the demand document; determining a plurality of first prompt texts including script logic; for each first prompt text, based on the first feature, determining a first parameter of the demand document in the first prompt text, and based on the first parameter, determining a first similarity between the first prompt text and the demand document, the first parameter being used for representing an occurrence frequency of a segment in the demand document in the first prompt text; on the basis of the first similarity, a second prompt text is selected from the multiple first prompt texts, a detection script is generated on the basis of the second feature and the first feature of the second prompt text, and the detection script is used for detecting the application. Through the method, the detection performance of the detection script can be effectively improved.

The invention provides a code testing method and device, electronic equipment and a storage medium, and the method comprises the steps: responding to a to-be-tested code submission operation, and generating a target test case according to a to-be-tested abstract syntax tree and a to-be-tested demand document of a to-be-tested code; generating a target UI test script corresponding to the target test case according to interactive elements in the to-be-tested code user interface; and executing a test task constructed based on the target test case and the target UI test script to obtain a test result. The labor cost and the time overhead of a test link are remarkably reduced, a rapid feedback closed loop from code submission to test execution is constructed, and the software development efficiency and the quality guarantee capability are integrally improved.

The invention discloses a test case generation method and device and electronic equipment, and belongs to the technical field of artificial intelligence. The test case generation method comprises the steps that a first control and a second control are displayed on a target interface; acquiring target demand data under the condition that the first control is triggered; under the condition that the second control is triggered, sequentially carrying out demand element extraction and demand element-based code text processing on the target demand data to obtain a standard demand document; analyzing the standard demand document to obtain tested function elements and test type elements; determining first prompt information matched with the test type element, wherein the first prompt information is used for indicating the large-scale generative language model to output a test case for testing the tested functional element in a test mode indicated by the test type element; inputting the first prompt information and the standard requirement document into a large-scale generative language model to obtain a test case; and rendering the test case in a rendering mode corresponding to the test type element in the target interface. According to the method and the device, one-button test case generation and display can be realized.

The invention provides a front-end page creating method which can be applied to the technical field of software development and artificial intelligence. The front-end page creating method comprises the steps that target component configuration information matched with different types of fields in a page description file is determined, and the target component configuration information comprises target table component configuration information, target display configuration information, target desensitization configuration information and target risk prompt configuration information; generating a page description file based on the configuration information of each target component and functional requirements defined in the project development requirement document; and converting the page description file into a corresponding visual component through a low-code parsing rendering engine, and generating a target display page. The invention further provides a front-end page creating device and equipment, a storage medium and a program product.

The invention discloses a demand document analysis method and device, computer equipment and a readable storage medium, in a financial scene, demand documents relate to different types of financial businesses, in a medical scene, the demand documents relate to function design of a medical system, and the demand documents relate to different types of financial businesses. According to the method, the problems of low efficiency and incomplete coverage caused by manual evaluation of the demand document can be solved, so that the quality and efficiency of demand document analysis are remarkably improved. The method comprises the following steps: constructing a security demand corpus; generating a training sample based on the security demand corpus, and performing model training on a pre-constructed security demand review model by adopting the training sample to obtain a target review model; inputting the to-be-recognized demand document and the analysis cue word into a target review model; on the basis of the target review model, the analysis cue words are utilized to screen the to-be-analyzed demand points, and a review result of each to-be-analyzed demand point is determined; and aggregating the review result corresponding to each to-be-analyzed demand point to obtain an analysis result corresponding to the to-be-identified demand document.

Methods, systems, and computer-readable storage media for determining a set of queries corresponding to a set of configuration settings of an application, for each query in the set of queries, querying a database to return a set of chunks, each chunk in each set of chunks including a portion of a requirements document, providing a set of prompts, each prompt corresponding to a query in the set of queries and including a respective set of chunks as context, receiving, from a large language model (LLM), a set of responses, each response corresponding to a prompt in the set of prompts, querying a knowledge graph based on the set of responses to provide a set of knowledge graph results, providing a configuration file using the set of responses and the set of knowledge graph results, and configuring the application using the configuration file.