108 results about "Design knowledge" patented technology

The invention provides a ship design knowledge retrieval method and system based on a multi-modal knowledge graph. The method comprises the steps of collecting and constructing a ship design set from the ship design field; forming a hierarchical multi-modal knowledge graph for describing a ship design field concept, physical characteristics and design specifications; enhancing association among different modal data through vector similarity calculation; the hierarchical multi-modal knowledge graph is integrated into a ChatGLM model; positioning knowledge nodes related to user demands in the hierarchical multi-modal knowledge graph; matching and positioning the ship design knowledge related to the query content of the user, and feeding back the ship design knowledge obtained by the intelligent semantic retrieval to the user in a hierarchical form. According to the method, ship design knowledge retrieval based on the multi-modal knowledge graph enhanced ChatGLM is realized, and the information acquisition efficiency of engineering designers and the practical application value of the system are improved.

The invention relates to a multi-modal data and RAG technology fused power design knowledge base construction method, and belongs to the technical field of power software development. The method comprises the following steps: carrying out collection and information extraction on multi-source heterogeneous original data; the method comprises the following steps of: constructing a multi-dimensional knowledge element structure containing parameters, specifications and case relationships by carrying out classification, specialized and precise processing and cross-modal association on data; based on a vector, graph and relational database mixed storage architecture, semantic vector efficient retrieval, knowledge graph relation management and business data synchronization are achieved respectively; and a dynamic optimization result is subjected to hybrid retrieval, a dual-drive reasoning mechanism outputs compliance conclusions and bases, and a retrieval enhancement generation service ensures that output contents conform to specifications. And systematic management and intelligent application of the electric power design knowledge are realized.

A system and method for interactive visualization of knowledge provided by large language models (LLMs) is disclosed. The system advantageously organizes LLM responses into an interactive knowledge graph visualization. Additionally, the system enables the user to interactively expand a knowledge graph by further prompting the LLM to provide additional responses that include additional knowledge. When applied to the task of design ideation, the interactive knowledge graph visualization helps to mitigate design fixation and enhances the overall efficiency, quality, quantity, and depth of concepts in the ideation process.

The invention provides a transformer substation AI aided design method based on LLM and RAG, and the method comprises the steps: carrying out the demand analysis through a large language model LLM, and extracting key information; performing knowledge retrieval by using an RAG technology, wherein the knowledge retrieval comprises transformer substation aided design knowledge base construction, transformer substation aided design knowledge retrieval and knowledge reordering; according to the demand analysis and the knowledge retrieval result, the LLM is utilized to generate a preliminary design scheme of the transformer substation, and the design scheme comprises an electrical main wiring diagram, equipment type selection and layout. By adopting the combination of the LLM, RAG and AI aided design, the comprehensive improvement of the design efficiency, standardization and innovation of the transformer substation can be realized, and the problems of low efficiency, insufficient standardization and lack of innovation in the prior art are solved.

The invention discloses a product collaborative design management method and system based on data driving, and relates to the technical field of product design management, and the method comprises the steps: constructing a double-flow heterogeneous quantitative collection network; establishing an incidence matrix and calculating dynamic coupling strength among the parameters; designing a recursive deep belief network based on the incidence matrix and the dynamic coupling strength, encoding product structure parameters and design process data into a probability graph model, and constructing a design knowledge base; dynamically distributing the design rules in the design knowledge base by adopting a swarm intelligent optimization algorithm, generating a collaborative decision-making unit, and establishing a constraint propagation link; and generating a multi-target collaborative optimization scheme group, and screening an optimal scheme group based on Pareto frontier. According to the invention, omnibearing acquisition of product structure parameters and design flow data is realized through the double-flow heterogeneous quantitative acquisition network, and the data integrity is improved.

The invention discloses a boiler design file intelligent identification system and method based on a multi-modal knowledge graph. The method comprises the steps that S1, a data collection module is used for collecting a large number of existing boiler design files as a data set; s2, extracting information on the boiler design drawing in the data set by using a multi-modal feature extraction module to form a text-image multi-modal joint feature vector; s3, constructing a multi-modal boiler design knowledge graph with engineering semantics, graph structure association and reasoning capability; and S4, inputting the extracted key point information on the boiler design drawing to be examined into the knowledge graph model, and judging whether each design point meets the design specification requirements of the boiler drawing or not. According to the method, the identification period is greatly shortened, the working efficiency is improved, and the missed examination rate is remarkably reduced.

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 relates to the field of knowledge graph data processing, and discloses an indoor space automatic layout and rendering method and system based on a design knowledge graph, and the method comprises the steps: maintaining an entity knowledge graph containing a variation path, and discretizing a continuous geometric space into an environment topological graph; executing node mapping and resource topology handshake verification based on subgraph isomorphism; and responding to the mapping deadlock, triggering recursive topology rewriting along the variation path to reconstruct the query sub-graph, and generating a configuration instruction. According to the method, continuous geometric search is converted into discrete atlas isomorphism and attribute propagation, the high-dimensional space layout calculation complexity is reduced, the deadlock problem under the over-constraint condition is solved by utilizing a recursive variation mechanism, and the configuration efficiency is improved. And the logic leakproofness and engineering compliance of the layout scheme are ensured.

The invention discloses a generative artificial intelligence-based banquet creative design system, which comprises: a demand determination module, which is used for interacting with a user terminal, obtaining a user demand and generating a demand theme; the banquet creativity generation engine is used for determining and operating a proxy artificial intelligence assembly line and generating a banquet creativity design project; comprising a main control unit, a domain knowledge acquisition unit, a creativity generation unit and a integrating degree evaluation unit, each unit is embedded with a multi-level intelligent agent as an execution main body, and prompt information is defined as input of the execution main body; the brand domain knowledge vector library is used for providing domain knowledge; the banquet design domain knowledge vector library is used for providing banquet design knowledge; and the design output module is used for obtaining the banquet creative design project and forming a banquet creative design scheme. According to the technical scheme, multi-modal brand domain knowledge and banquet creative design can be deeply fused, and automatic generation of multi-modal information of a high-end banquet catering art scheme is achieved.

The invention discloses an AI-AD intelligent machine design method and system based on a learning-generation mode. The method comprises the following steps: S1, enabling an AI-AD intelligent mechanical design system to understand design knowledge at first; s2, compiling a workflow with low codes; s3, compiling a Prompt strategy of the design Agent and a called knowledge base; s4, repeating the steps S1 to S3, and compiling various agents needing to complete various specific design functions; s5, according to the designed various agents, a multi-agent self-organizing framework is utilized, and product creation type design is completed; and S6, according to the generated design result, generating a VBA file and storing the VBA file in the cloud. And S7, the SW establishes a conversation with the agent through a back-end API of the agent, timely reads a VBA code of the cloud for modeling, and outputs a model. According to the invention, a system structure of knowledge processing, cloud data storage, SolidWorks-based secondary development modeling and a human-computer interface module is constructed, Agents are enabled to learn at first, then design is created, and a 3D model meeting user requirements is generated, so that the current situation that knowledge engineering has extremely high requirements for practitioners' admission threshold can be reduced.

The invention discloses an AI processing method and system for long-term memory of mechanical design knowledge, and the method comprises the steps: carrying out the semantic analysis and feature extraction of heterogeneous knowledge, such as parameterization formulas, engineering charts, technological processes and design principles, in the field of mechanical design through a multi-agent collaborative learning system; and establishing a multi-dimensional modular knowledge base and context-based Prompt strategy coupling mechanism. The method solves the problems of low efficiency, insufficient analysis accuracy, limited innovation support capability and the like in the existing mechanical design knowledge processing technology, and particularly solves the technical problems of high calculation complexity, inaccuracy in reasoning, poor adaptability and the like when multiple types of design knowledge are processed. Through the implementation of the method, the processing efficiency of the design knowledge and the design automation level are remarkably improved, the technical threshold of a designer is reduced, the design period is shortened, efficient analysis, accurate matching and innovative application of the mechanical design knowledge are achieved, and powerful support is provided for intelligent development of mechanical design.

The embodiment of the invention discloses a design code generation method based on cloud service. The method is applied to a cloud management platform. According to the method, the dominant design intention input by the user can be obtained from the configuration interface, and the target design knowledge associated with the current dominant design intention of the user can be inquired from the knowledge graph so as to capture the implicit design intention implicit to the target design object. Thus, the dominant design intention and the target design knowledge from the knowledge graph can be combined to guide the large language model to efficiently and accurately generate the target design code meeting the design requirement of the user, intelligent generation of the target design code is achieved, the design task is accurately and efficiently achieved according to the target design code, and the user experience is improved. And obtaining a target design object.

The invention discloses a knowledge graph and RAG-based multi-modal engineering design intelligent generation method and system. The method comprises the following steps of S100, multi-modal data analysis and structured processing; s200, constructing a domain knowledge graph; s210, constructing a standardized module library; s300, performing intelligent retrieval and scheme generation; and S400, compliance verification and feedback learning are carried out. Through deep collaboration of the domain knowledge graph and the standardized module library, spanning of engineering design knowledge from'retrieval 'to'understanding and driving' is achieved, the problems of knowledge fragmentation and low reuse rate are solved, and the design efficiency, quality and automation level are remarkably improved.

Disclosed in the embodiments of the present application is a cloud service-based design code generation method, the method being applied to a cloud management platform. The method can not only acquire from a configuration interface an explicit design intention input by a user, but also query a knowledge graph for target design knowledge associated with the current explicit design intention of the user so as to capture an implicit design intention of a target design object. Thus, the explicit design intention and the target design knowledge from the knowledge graph can be combined to guide a large language model in efficiently and accurately generating target design code that meets a design requirement of the user, thereby intelligently generating the target design code so as to accurately and efficiently implement a design task on the basis of the target design code to obtain the target design object.

The invention discloses a home decoration design description specialization optimization method fusing a semi-structure RAG technology, and belongs to the technical field of artificial intelligence and home decoration design crossing. The method comprises the following steps: constructing a semi-structured home decoration design knowledge base, cooperatively processing an original corpus through a script and AI, generating a structured JSON knowledge unit, and performing vectorization storage; receiving natural language query of a user, performing intention recognition and vectorization, and recalling related knowledge units by adopting a mixed retrieval strategy in combination with semantic retrieval and metadata filtering; and dynamically constructing an enhanced cue word through an RAG technology, and inputting the enhanced cue word into the large language model to generate a professional and detailed home decoration design description text. According to the method, the problems that the content generated by the existing AI design tool is lack of specialty and the user demand conversion is inaccurate are effectively solved, the quality and the practicability of the design text are improved, and the use threshold of professional design is reduced.

The invention discloses a personalized design knowledge recommendation method based on knowledge graph and dynamic demand modeling, which comprises the following steps: firstly, constructing a design knowledge presentation layer which comprises a knowledge ontology and a knowledge graph, and then constructing a knowledge recommendation layer which comprises a knowledge ontology and a knowledge graph; the knowledge recommendation layer comprises a task stage knowledge demand model and a packet receiving party knowledge demand model, a dynamic knowledge demand vector and a task stage knowledge demand vector of a packet receiving party are matched with design knowledge nodes in the knowledge graph, and knowledge nodes most relevant to the demand of the packet receiving party are screened out; and according to a knowledge graph matching result, screening out a knowledge node most related to the demand of the packet receiving party, and generating a final recommendation result through an optimization algorithm. The method has the advantages that dynamic changes of knowledge requirements of a crowdsourcing party can be effectively solved, more personalized and accurate design knowledge recommendation can be provided, and the execution efficiency and design quality of crowdsourcing design tasks can be improved.

The invention relates to an electronic product PCB design system and method. In the system, a data preparation and knowledge base construction module is used for collecting, cleaning and de-duplicating multi-source PCB design data and constructing a comprehensive PCB design knowledge base; the polymorphic large model construction and training module adopts a hybrid neural network based on a transformer architecture, and constructs a polymorphic large model with a cross-modal reasoning capability by jointly training a schematic diagram semantic understanding model, a layout topology optimization model and a signal integrity prediction model; the intelligent auxiliary Agent module is used for integrating a reinforcement learning agent and a rule verification agent, and providing a wiring path optimization suggestion, element type selection recommendation and design specification compliance detection in real time; and the system integration module is used for automatically designing the generation module and converting the optimization scheme output by the polymorphic large model into a final PCB design file. The system can improve the design automation level.

The invention discloses a numerical control machining method for a wood substitute transition mold based on equal-residue dynamic machining. The numerical control machining method comprises the following steps that S1, a machining path is optimized; s11, designing a knowledge enhanced path planning model; s12, generating an equal-residual-height cutter contact track; s2, cutting parameter collaborative optimization; s21, designing a multi-target parameter optimization model; s22, designing a dynamic parameter adjustment strategy; s3, numerical control machine tool parameter joint optimization design; s31, servo shaft parameter matching is carried out; and S32, cooling system cooperative control is carried out. According to the method, multi-dimensional collaborative optimization is adopted, and path planning, parameter optimization, machine tool debugging and cooling control are fused to form a closed-loop optimization system; according to the method, intelligent decision making is adopted, a knowledge graph and reinforcement learning are combined, and self-adaptive adjustment of a processing strategy is achieved; and high-precision guarantee is achieved, and the machining precision is improved to + / -0.02 mm through servo parameter matching and cooling control.

We provide an invention creation system and program that can systematically analyze technical and market information, accurately identify unexplored areas, and efficiently create and evaluate novel solutions for those areas. The invention creation system creates new inventions by analyzing a database containing technical literature, patent information, and market information. This invention creation system is characterized by comprising: a technology space modeling unit that analyzes the database, classifies technical elements into functional features and structural features, and maps the relationships between them onto a multidimensional technology space; a white space identification unit that identifies, as technological blank areas, areas in the multidimensional technology space where the combination density of existing technologies is low or areas where no structural features corresponding to specific functional features exist; a general-purpose design knowledge base that systematizes the mapping relationship between the functional space and the structural space and technological principles; and an automatic invention creation unit that sets required functions in the technological blank areas, searches for structural combinations that realize the required functions based on the general-purpose design knowledge base, and generates design solutions.

The invention provides a multi-modal knowledge graph generation method and system for hardware design analysis, which break through design, verification and physics, realize information barriers among the three traditional EDA (Electronic Design Automation) fields, perform semantic fusion and association on information from different data fields, create a unified and queriable hardware design knowledge representation, and improve the reliability of hardware design analysis. And a coherent and operable unified knowledge model is formed. A multi-modal design knowledge graph is created by integrating a simulation result (dynamic data) and a physical implementation feature (performance data) into a static structure model, and a comprehensive design model with structure, behavior and performance features is analyzed in a unified framework. An engineer does not need to manually switch between different tools and data formats, but can access all-dimensional information about a static structure, a dynamic behavior and a physical property of a design through a single query interface.

The present invention provides a ship design knowledge retrieval method and system based on a multimodal knowledge graph, the method comprising: collecting and constructing a ship design set from the field of ship design; forming a hierarchical multimodal knowledge graph that describes concepts, physical properties, and design specifications in the field of ship design; enhancing the association between different modal data by vector similarity calculation; integrating the hierarchical multimodal knowledge graph into a ChatGLM model; locating knowledge nodes related to user needs in the hierarchical multimodal knowledge graph; matching and locating ship design knowledge related to user query content, and feeding back the ship design knowledge obtained by intelligent semantic retrieval to the user in a hierarchical form. The present invention realizes ship design knowledge retrieval based on multimodal knowledge graph-enhanced ChatGLM, which improves the information acquisition efficiency of engineering designers and the practical application value of the system.

The invention provides a cross-modal multi-scale information fusion method and system supporting design knowledge push, and the method comprises the steps: constructing a patent data set containing patent abstracts and abstract drawings, extracting long text features and short text features through a text encoder, and extracting fine-grained and coarse-grained image features through an image encoder; the text and image features are input into a cross-modal attention fusion module, cross-modal information interaction of the text and the image is realized through a multi-head attention mechanism, and fused text and image features are generated; a loss function based on comparative learning is adopted, and the alignment effect of the image and text features in the semantic space is optimized; and inputting an innovative design concept, extracting feature representation of the innovative design concept, calculating the matching degree of the feature representation and patent data based on cosine similarity, and pushing related patent abstracts and attached drawings to designers according to similarity sorting. According to the method, the limitation in existing image-text matching and cross-modal information fusion can be solved.

The present invention provides a solid rocket engine knowledge management method, which is aimed at the management of various forms of design knowledge of solid rocket engines. A professional knowledge base platform is used to uniformly classify, store and manage engine design knowledge to form a design knowledge base suitable for solid rocket engines. A knowledge engineering application paradigm covering engine knowledge acquisition, knowledge sharing, knowledge application, and standardized management of software tools is constructed to achieve rapid query, automatic push and other applications of engine design knowledge. The solid rocket engine knowledge management method includes research on engine design knowledge system, research on design knowledge acquisition methods, research on design knowledge base construction, and research on knowledge application based on knowledge engineering. The present invention solidifies the content related to model development and forms a unified engine design knowledge system, and promotes engine knowledge management and control clearly, orderly and continuously through knowledge acquisition, knowledge automation application technology and knowledge management methods.

This invention relates to a process architecture for optimizing ship hydrodynamic configurations based on artificial intelligence technology. The architecture includes modules such as expert experience, historical sample data of ship hydrodynamic configurations, design input for ship hydrodynamic configurations, a knowledge base for ship hydrodynamic configuration design and evaluation, a parametric model of ship hydrodynamic configurations, knowledge-driven reconstruction of the ship hydrodynamic model, AI-based optimization design of ship hydrodynamic configurations, rapid evaluation of ship hydrodynamic performance, and a comprehensive evaluation index model for ship hydrodynamic performance. This invention fully leverages the design experience contained in historical sample data, extracting the experience of numerous experts into design knowledge and integrating it into the ship hydrodynamic configuration optimization design process. The process architecture drives intelligent reconstruction of the ship hydrodynamic model through design knowledge, and improves upon the shortcomings of traditional ship hydrodynamic performance prediction methods, such as time consumption and low efficiency, by establishing a rapid prediction proxy model for hydrodynamic performance based on machine learning algorithms.

The application discloses a kind of based on key value memory network's complex electromechanical system design knowledge active recommendation method.First, the scene feature semantic information extraction of software platform log file in the design process of complex electromechanical system is carried out, and scene ontology is established based on scene feature semantic information, and system scene knowledge base is formed by scene ontology and original knowledge base;Then, the scene maximum frequent sequence is used to describe the scene sequence feature similarity between designers;Again, the knowledge item interaction sequence of all designers is learned, and the knowledge item sequence preference vector corresponding to all designers is obtained;Further, input to key value memory network, and the initial design knowledge active recommendation sequence is obtained;Finally, after knowledge item selection, the final design knowledge active recommendation sequence of each designer is obtained.The application obtains design knowledge active recommendation sequence more in line with the needs of designers, and then improves the efficiency of complex electromechanical system design.

The invention discloses a distribution network multi-source design data integration system based on AI association fusion, and the system comprises a data collection module which is used for collecting and standardizing CAD, GIS, equipment ledger and operation monitoring data; the feature extraction module is used for extracting text semantics, numerical values and spatial features to generate feature vectors; the semantic embedding modeling module is used for constructing a semantic embedding space for the TransE model; the self-adversarial optimization module is used for introducing a self-adversarial negative sampling mechanism to dynamically optimize model parameters; the strategy training module is used for outputting strategy parameters according to the A3C algorithm; the joint optimization module is used for updating the embedding model according to the strategy and the state value; and the knowledge graph construction module is used for fusing the multi-source data to generate a power distribution network design knowledge graph. According to the method, efficient fusion and intelligent optimization of the distribution network multi-source data are realized, and the design precision and the processing efficiency are improved.

The invention relates to the technical field of knowledge skeleton construction, and provides a cross-domain knowledge skeleton construction method for multi-process equipment, and the method comprises the steps: dividing knowledge domains for design knowledge, the knowledge domains comprising a demand domain, a structural domain, a behavior domain, a control domain and a performance domain; extracting knowledge elements corresponding to the knowledge domains from the equipment and the components thereof; knowledge elements are divided into interface knowledge elements, external knowledge elements and internal knowledge elements, the interface knowledge elements are used for transmitting information between equipment and components, the external knowledge elements comprise performance domain knowledge elements and behavior domain knowledge elements which are used for establishing association between every two of the equipment and the components, and the internal knowledge elements are included in the equipment or the components. Knowledge elements not associated with knowledge elements in another equipment or component; and according to a division result of the knowledge elements, establishing association among the internal knowledge elements of the equipment or the components by using an adjacent matrix, and associating external knowledge elements among different equipment or components to obtain a cross-domain knowledge skeleton.

The invention belongs to the technical field of software engineering, and particularly relates to a code digital twinning construction method based on a large model. According to the method, domain concept extraction, software functional characteristic knowledge extraction, high-level design decision analysis, code units and structural relations thereof are comprehensively utilized to construct a code digital twinborn model which is co-constructed, shared and synchronously evolved with codes and is used for conceptualized representation of software domain knowledge; the method comprises the following specific steps: knowledge representation design: designing different representation modes for various knowledge; product-oriented skeleton knowledge is extracted; explanatory knowledge extraction with the design principle as the center; product-knowledge mapping construction is carried out; and joint evolution and incremental updating are carried out, a construction process and software product evolution are in butt joint, and synchronous evolution of the knowledge base and the software product is ensured. According to the method, developers can be helped to understand field background knowledge, functional characteristics and design knowledge contained in complex software codes, so that software development and maintenance tasks are better completed, and intelligent development and maintenance support is provided.

The invention provides a nuclear power process flow intelligent configuration mapping method and system. The method comprises the following steps: calling a nuclear power process design knowledge base; wherein the knowledge base at least comprises a design scheme, a design standard and a design report of the selected heap type; establishing a nuclear power process model based on the knowledge base; establishing a first selection logic in the nuclear power process model, and determining a target reactor and a main function module associated with the target reactor based on the first selection logic; establishing a second selection logic in the nuclear power process model and determining a technical route of each main function module; wherein the technical route is composed of at least two functional units; and a third selection logic is established in the nuclear power process model, a functional unit is configured, and a design drawing comprising equipment and / or pipelines is formed. By calling the nuclear power process design knowledge base, automatic configuration of the process of nuclear power design is supported, the configuration scheme of specific equipment or pipelines can be formed, mapping design is obtained, manual drawing work of designers can be reduced, and design efficiency is improved.

The invention discloses a multimedia recommendation method based on cross-modal feature decoupling and knowledge distillation. The method comprises the following steps: 1, constructing a user-article interaction graph; 2, graph learning; 3, carrying out multi-modal feature processing; 4, a cross-modal difference feature learning module; 5, a cross-modal common feature learning module; 6, score calculation and loss function construction; and 7, model training and recommendation result generation. According to the method, an explicit decoupling strategy is provided for a recommendation task of multi-modal data, the multi-modal preference of a user is divided into independent learning processes of cross-modal difference features and common features, meanwhile, efficient learning of the cross-modal features is promoted by innovatively designing a knowledge distillation mechanism, and the user experience is improved. Therefore, the problems of confusion and entanglement of user preferences in the multi-modal content can be effectively relieved, and the understanding depth and prediction precision of a recommendation system for complex multi-modal data are remarkably enhanced.