135 results about "Requirement document" patented technology

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 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 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 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 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 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 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 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.

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.

The invention discloses a method and system for software automatic testing, and relates to the technical field of computer software testing, and the method comprises the steps: building a constraint initial test target set covering path input and output; dynamically adjusting a test case generation strategy for the demand document; and updating the reconstructed test case to the constraint initial test target set, and constructing a path priority for the second time to complete the software automatic test. According to the invention, the accuracy of test case generation and the demand coverage integrity are improved; dynamic weight distribution of a test path and self-adaptive adjustment of a test case generation strategy are realized, and the coverage capability on a deep path and a high-risk module is effectively improved; the response capability of the test system to frequent iteration and the reuse efficiency of test resources are enhanced, and the software automatic test with higher automation degree, stronger environmental adaptability and more comprehensive coverage is realized on the whole.

The invention provides a test case generation method and device and a test method and device.In the test case generation method, a target demand document used for conducting function testing on a to-be-tested terminal is obtained; and performing content improvement on the demand content in the target demand document based on the information database related to the target demand document to obtain an improved target demand document. And generating a test case and a corresponding expected test result based on the perfected target demand document. According to the scheme, the demand content in the target demand document is subjected to content improvement through the information database, and the test case with comprehensive coverage is generated based on the improved target demand document; according to the method, the problem of incomplete test cases caused by incomplete demand document content or insufficient business proficiency during manual design by testers can be solved, the test comprehensiveness of subsequent software tests is ensured, the software quality of published software is ensured, and the use experience of users is improved.

The invention provides a multi-agent collaborative system demand document automatic generation method and system.The method is applied to a generation system comprising a data input layer, a demand document processing layer and a document output layer, and specifically comprises the steps that original demand data are input into a large language model, structured decomposition is conducted on the original demand data, a demand entry list is obtained, and the demand entry list is stored in a database; and sequentially generating corresponding initial system demand documents according to a list sequence, performing rationality review on the corresponding initial system demand documents, directionally correcting the corresponding initial system demand documents according to a rationality review result, integrating the corrected initial system demand documents according to the list sequence, and outputting the system demand documents. According to the method, through closed-loop control of a single demand and a link from an auditing process to single demand control in advance, the problem of insufficient document accuracy is solved, and the document generation efficiency is improved.

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 discloses a method and system for automatically generating a bidding document based on a bidding requirement, and relates to the technical field of bidding, and the method comprises the steps: obtaining a bidding requirement file, analyzing and extracting core information, collecting historical materials, building an enterprise bidding database, comparing the core information with database resources, and obtaining matched resources; building a framework filling content according to the matching resources and the bidding specifications to form a draft, and finally verifying and perfecting to make a final bidding file; according to the method, manpower, material resources and time consumption of bidding document making can be reduced, the omission or misunderstanding risk during manual bidding requirement interpretation is reduced, the bidding discarding possibility is reduced, repeated labor caused by enterprise bidding resource dispersion is avoided, the making efficiency is improved, meanwhile, the problem of content inconsistency is reduced, and the making quality of the bidding document is fundamentally improved.

The application discloses an English requirement ambiguity auxiliary checking system, which comprises a storage layer, a model layer, a business logic layer and a display layer, wherein the NLP model of the model layer comprises several submodels, the business logic layer comprises an NLP pipeline management module, the NLP pipeline management module selects corresponding submodels from the NLP model as subtask processing modules according to ambiguity checking requirements, and then connects the subtask processing modules in series to form an NLP pipeline; after a requirement document is imported into the NLP pipeline, each subtask processing module in the NLP pipeline labels the requirement document with a specific label, until the ambiguity checking is performed, and finally, the output is the requirement document with the label.

The invention provides a demand document collaborative generation method and device, and relates to the technical field of document generation. The method comprises the steps of obtaining demand description information of a preset item and a predefined document structure mode; according to the demand description information and the document structure mode, a document frame is generated, and the document frame comprises a chapter tree, at least one structure block under each chapter of the chapter tree and a plurality of to-be-filled fields of each structure block; a planning agent is called, a document task graph is generated according to the reference relation between the structure blocks and the constraint relation between the to-be-filled fields, and the document task graph is composed of multiple types of task nodes; according to the demand description information, a writing agent and a verification agent are called to execute tasks corresponding to task nodes in the document task graph, so that content filling and checking are carried out on the to-be-filled field of the at least one structure block; and generating a demand document of the demand description information after the check is passed.

The invention relates to a method and a device for integrating multi-version demand documents and computer equipment, and relates to the technical field of computers, and the method in one embodiment comprises the following steps: obtaining multi-version demand documents of a target system, and sorting the multi-version demand documents based on the latest update time of the demand documents to obtain a demand document sequence; structural analysis is conducted on the demand documents of all the versions, the content of the demand documents is disassembled into structural knowledge units, and each knowledge unit comprises an independent function point and corresponding attribute information; determining knowledge units describing the same function point in the demand document of each version, and associating the knowledge units describing the same function point in the demand document of each version based on the demand document sequence to form a knowledge unit change chain; and generating an integrated demand document based on the knowledge unit change chain of each function point. By adopting the scheme of the embodiment, the management efficiency of multi-version demand documents is improved.

The invention provides an enterprise application component building method and system based on a large language model, and the method comprises the steps: S1, obtaining a user component demand, carrying out the analysis, generating a structured demand document, and determining whether to enter a step S2 or not according to a user demand confirmation result; s2, generating a core function module of a component through a component generation engine based on the structured demand document confirmed by the user; s3, matching a corresponding interface template from a preset universal interface library according to an adaptive system list in the structured demand document, and generating an interface adaptive code; and S4, deploying the core function module and the interface adaptation code to a preview environment for a user to preview, and selecting to automatically package and generate a component installation package or re-executing the steps S1, S2 or S3 according to a user preview confirmation result. According to the method, a full-link automation mechanism of'natural language demand-component generation-interface adaptation 'is constructed, so that the component building threshold is reduced, and rapid adaptation of the component and the existing system is realized.

The invention relates to the technical field, and discloses an intelligent software development auxiliary platform fusing multi-modal information, which comprises a multi-modal information acquisition module, a multi-modal fusion module, an interaction and auxiliary generation module, an atlas construction module, a collaborative management module and a feedback closed loop module. According to the method, information of different forms such as requirement documents, design drafts, codes and operation and maintenance data is automatically understood and associated, a unified project knowledge graph is constructed, 'information isolated island 'in a traditional development tool chain is broken, complete and traceable contexts are provided for developers, manual switching and information splicing among multiple tools are not needed, and the development efficiency is improved. And the cognitive load and the context switching cost are obviously reduced. The high-quality code can be directly generated according to the natural language description or the design manuscript, and repeated work is liberated.

The invention provides a high-priority test case screening method and device, a storage medium and computer equipment, and relates to the technical field of computers.The method comprises the steps that a demand document and a test case set are received; preprocessing the demand document, and constructing a cue word based on a preprocessing result; inputting the cue word and the test case set into a large language model to obtain an initial high-priority test case; after text normalization processing is conducted on the initial high-priority test case, a target high-priority test case is obtained through text matching processing, and the target high-priority test case is marked. According to the method, high-priority test cases can be automatically and accurately screened out in a rapid iteration software development environment, the coverage rate and efficiency of regression testing and smoking testing are improved, meanwhile, the correctness of core functions is guaranteed, and the reliability and applicability of case screening results are remarkably enhanced.

This invention discloses a method, apparatus, device, and medium for implementing an intelligent quality valve in the requirement submission process, relating to the field of requirement process quality review in fintech. The method includes: acquiring a requirement description and uploading it to a created large-scale intelligent platform; expanding the document based on comparison with existing similar requirements and performing standardization processing to fill in missing elements, generating a requirement document; acquiring voice data from requirement review meetings and uploading it to the large-scale intelligent platform; analyzing the voice data to generate a requirement review meeting summary and submitting the summary to a DevOps platform; creating a requirement review model, which uses retrieval enhancement technology to acquire private domain data in real time to review the requirement document currently awaiting review. This application enables automated review operations, significantly reducing the burden of manual review and improving the accuracy and efficiency of the review process.