58 results about "Conceptual design" patented technology

The invention discloses a 3D art model intelligent generation system and method based on multi-source data fusion, and relates to the technical field of computer aided design and graph generation, and the system comprises a multi-source data input module which is used for receiving a conceptual design drawing, text description and a reference 3D model; the feature extraction module comprises an image feature extraction unit used for extracting a style feature vector and a structure contour vector of the conceptual design drawing; and the text semantic analysis unit is used for outputting a key attribute tag vector described by the text. According to the 3D art model intelligent generation system and method provided by the invention, through multi-source data input including the concept design drawing, the text description and the reference 3D model, the design intention is comprehensively fused, the limitation of a single data source generation model is solved, and the dynamic weight distribution strategy and the closed-loop optimization mechanism of the 3D art model intelligent generation system and method are high in practicability. The geometric shape and style characteristics of the generated model are highly consistent with the design intention, and the workload of manual later correction is reduced.

The invention relates to a foldable tilting four-rotor aircraft concept scheme design method based on task requirements. According to the method, task demand indexes such as voyage, cruising speed, task load, cruising height and hovering height are used as input, and the total design weight, power device parameters, rotor wing geometric parameters and fuselage and wing parameters of the aircraft are determined in sequence; and performance indexes such as hovering lift limit, level flight speed, climbing performance, practical lift limit, voyage and endurance in a helicopter mode and a fixed wing mode are calculated and analyzed respectively. And performing matching judgment on a performance calculation result and a task requirement, and performing iterative adjustment on key parameters such as a paddle disc load when the task requirement is not met, so as to form a closed-loop concept design process driven by the task requirement. According to the method, the vertical take-off and landing capacity and the fixed wing cruising performance can be systematically considered in the conceptual design stage, and systematicness, repeatability and engineering feasibility of scheme design of the folding type tilting four-rotor aircraft are improved.

A method for automated spacecraft design includes receiving mission parameters provided by a client for spacecraft design, generating one or more concept designs based on the received mission parameters, a concept design including one or more components selected for each subsystem included in a designed spacecraft, for the concept design, automating a generation of a frame design that accommodates the one or more components selected for each subsystem included in the designed spacecraft, the frame design being a Computer Aided Design (CAD) model that includes individual frame pieces generated, sized and fitted automatically via automated scripts compatible with a CAD system, including one or more structural design software applications; performing a series of analyses or simulations to evaluate a performance of the frame design; and generating a digital twin representing a virtual representation of the designed spacecraft based on the generated frame design and the series of analyses and simulations.

The invention provides a SysML model generation method based on a large language model in conceptual design, which comprises the following steps of: guiding LLM by utilizing a thinking chain cue word template, and converting user input into a conceptual design scheme described in a plain text form; utilizing a cue word template I to guide LLM to split the conceptual design scheme into a sentence list containing complete semantics; using a cue word template 2 to guide LLM to extract entities and relationships thereof from each sentence, and outputting a triple; based on the triple, creating a SysML model hierarchical structure according to a predefined rule; and creating an XMI file by following an XMI format specification to obtain a complete SysML model. According to the method, the automation degree and generalization of SysML model generation are remarkably improved, less text input can be effectively processed, a conceptual design scheme model which can be directly used for actual system design and adapts to products is generated, and the method is particularly suitable for high-complexity large-scale system design.

Embodiments of the present disclosure provide optimal site selection framework. A surrogate process model may be generated based on one or more physics-informed machine learning models and a rigorous dynamic process model. The surrogate process model may comprise a representation of a process including one or more target assets and one or more secondary assets. The process input for the one or more target assets may comprise power output from a renewable energy source. A design optimization algorithm representative of a multi-objective design optimization problem may be generated. The design optimization algorithm may comprise one or more site selection variables and one or more site selection constraints. One or more outputs may be generated by executing an optimization model based on the surrogate process model and the design optimization algorithm. The one or more outputs may comprise predicted optimal sites and an optimal conceptual design for the process.

The invention discloses an industrial master conceptual design method and equipment based on a knowledge graph and MBSE, and belongs to the technical field of industrial design. According to the method, the powerful semantic comprehension and generation capability of a large language model is combined with accurate and reliable knowledge of a knowledge graph and a vector database by utilizing RAG, so that deep analysis of complex requirements, generation of high-quality model elements and more intelligent interaction are realized; the SysML modeling tool is used as a final implementation and visualization platform of the model; comprising the following steps: stage 1, collecting and preprocessing industrial host data, constructing a core knowledge graph, constructing a vector knowledge base, and configuring an RAG system; stage 2, generating an initial model, dynamically modifying the demand and intelligently interacting; and stage 3, performing automatic tracing verification and structure and parameter consistency verification. The concept design of the digital prototype of the industrial master can be quickly generated, and the development efficiency of the industrial master is improved.

The present invention discloses a design method for a vehicle-mounted platform architecture based on dual cores, comprising the following steps: Step 1, requirement analysis; Step 2, domain modeling; Step 3, key determination; Step 4, conceptual design; Step 5, detailed design; Step 6, architecture verification; wherein in the above-mentioned Step 1, according to the dual-core structure of the vehicle-mounted platform, the complexity of the architecture is analyzed to find out the requirements of the vehicle-mounted platform in terms of function, quality and constraints, and then the priorities of the functional requirements, quality requirements and constraint requirements are determined, and the design requirements of the vehicle-mounted platform architecture are clarified; the invention adopts a combined architecture verification method, with more comprehensive review, improved rationality of the design scheme, small development risks, easy to implement, sufficient analysis of the design requirements, distinction of the importance of different requirements, avoidance of the problem that different requirements in the design affect or even restrict each other, and achieving the effect of taking into account multiple requirements.

The invention provides a bionic robot part design method and system, a medium and a computer. The method comprises the steps that finite element analysis is conducted on a concept design model of a bionic robot part to obtain a finite element analysis result; performing iterative optimization on the finite element analysis result based on the optimization parameter of the finite element analysis result to obtain an iterative optimization result; performing statics analysis on the concept optimization model obtained by repairing based on the iterative optimization result to obtain a statics analysis result; performance parameters of the conceptual design model and the conceptual optimization model are calculated and analyzed to obtain performance optimization parameters; and carrying out topological optimization on the concept optimization model by utilizing the optimization parameters so as to establish a design model of the bionic robot part. According to the method, optimization parameters and a designed structure are subjected to three-dimensional modeling, key parts or an overall structure are imported into finite element software for finite element analysis, topological optimization is performed on a result, and model reconstruction is performed on the key parts according to a topological result.

This invention discloses a method and system for application design transformation based on technological experience, relating to the field of digital technology. The method includes: collecting open-source technology product data via the internet to construct a digital technology experience center; providing online technology experiences for students to obtain experience monitoring data; designing online courses based on a technology application creation platform to obtain online teaching courses; teaching students to obtain technology application concept design proposals; conducting simulation verification and evaluation through a mechanism simulation system to obtain simulation evaluation results for the design proposals; presenting the technology application concept design proposals in a roadshow to obtain a design demonstration dataset; conducting online expert evaluation; and transforming the technology application concept design proposals into innovative achievements based on the evaluation results. This addresses the technical problems of limited teaching resources, limited practical scenarios, and restricted technological innovation capabilities in existing science and technology education, achieving the technical effect of enriching technological experiences and enhancing technological innovation capabilities.

The invention discloses a ship type conceptual design method and device based on ship typical performance driving and a medium, and relates to the technical field of ship design, and the method comprises the steps: obtaining to-be-designed geometric parameters and demand performance indexes; inputting the geometric parameters to be designed and the demand performance indexes into a ship type generation model, and performing semantic analysis on the demand performance indexes through the ship type generation model to obtain a semantic analysis result; determining a target performance index corresponding to the semantic analysis result; and taking the target performance index as a constraint condition to obtain a target ship form design corresponding to the geometric parameter to be designed. The method is used for solving the problem that in the prior art, the design efficiency is low during ship type concept design, and ship type design meeting user requirements is efficiently and accurately completed.

The application provides a concept design SysML model generation method based on a large language model, and the method comprises the following steps: guiding an LLM by using a thinking chain prompt word template, converting user input into a concept design scheme described in pure text form; guiding the LLM by using a prompt word template 1 to split the concept design scheme into a sentence list containing complete semantics; guiding the LLM by using a prompt word template 2 to extract entities and their relationships from each sentence and output triples; creating a SysML model hierarchical structure according to a predefined rule based on the triples; and creating an XMI file in accordance with an XMI format specification to obtain a complete SysML model. The method significantly improves the automation and generalization of SysML model generation, can effectively process less text input, and generates a concept design scheme model that can be directly used for actual system design and adapts to products, and is particularly suitable for highly complex large system design.

The application relates to an artificial intelligence-based large model design construction method, system, device and storage medium, wherein the large model design construction method comprises the following steps: first, based on the text or voice input of a user, input information is taken as a guide word to generate a corresponding concept design; then, the NLP2SQL technology is used to carry out multi-round and multi-conversation with the user to automatically extract design parameters; then, a vector retrieval technology is used to retrieve the user demand in a design specification to obtain design specification parameters with the highest similarity to the user demand; finally, parameterized modeling design is carried out in combination with a design software to obtain a final design effect. The application can automatically generate a large model design meeting the requirements according to the design specification and user requirements, and improve the design efficiency and quality.

The invention relates to the technical field of industrial design, and discloses a lightweight assembly type mobile equipment industrial design generation method based on artificial intelligence, and the method comprises the following steps: S1, constructing and training a dual-stage AI model which comprises a concept generation module and an industrial conversion module; s2, receiving multi-modal design demand information input by a user; s3, generating at least one visual concept design scheme through the concept generation module; and S4, in response to a selection instruction of a user for the visual concept design scheme, the selected concept scheme is converted into an industrial-grade design scheme through the industrial conversion module, and the industrial-grade design scheme comprises at least one of a bill of material, a technical drawing and a manufacturing instruction. Through the two-stage AI model, full-automatic generation from fuzzy text originality to an accurate industrial-grade manufacturing scheme is realized for the first time, the design period is shortened from several weeks to several hours, and the design cost is reduced.

The present invention discloses a method for evaluating the spatial posture of a conceptual configuration of a branched-chain driven parallel robot. First, a kinematic analysis method based on singular values ​​is used to judge the reachability of all the terminal postures of the branched-chain driven parallel mechanism, and the terminal posture of the branched-chain driven parallel mechanism in the reachable workspace is obtained; then, based on the screw theory and the principle of virtual work, the complete Jacobian matrix and the full stiffness matrix of the mechanism are obtained, and the stiffness performance parameters of all the terminal postures of the branched-chain driven parallel mechanism are calculated, and the stiffness performance parameters corresponding to the terminal postures of all the mechanisms are obtained; finally, according to the terminal posture in the reachable workspace, combined with the stiffness performance parameters corresponding to the terminal postures of all the mechanisms, the optimal posture set is screened and obtained. The present invention can not only quantitatively evaluate the optimal posture set, but also realize the innovative mechanism concept design that meets the needs by comparing the optimal posture sets of mechanisms with different configurations.

The present invention relates to the field of BIM design technology, and more specifically, to a three-dimensional forward design method and system for municipal highway bridges. The method comprises three phases: bridge concept design, in which the bridge concept object is created based on the three-dimensional road route, pavement, geophysical three-dimensional model, and initial bridge data to complete the bridge concept design; bridge overall design, in which the overall three-dimensional bridge design is completed based on the resource library template and the design resources at the profile, feature, component, and assembly levels are designed and reused based on the bridge concept design results; and bridge detailed design, in which the design information carried by the bridge overall design is inherited and the component granularity mapping and splitting are achieved. The split components can then be refined according to design requirements, thereby completing the detailed three-dimensional bridge design. The present invention can effectively improve bridge design efficiency.

The invention discloses a hot stamping part conceptual design feasibility evaluation method based on deep learning. The hot stamping part conceptual design feasibility evaluation method comprises the steps that a forming-service material model inheriting the forming history is constructed; constructing a deep learning agent model based on image representation; and evaluating the design feasibility based on the forming-service simulation model. The problem that in the prior art, in the hot stamping part development process, complex part design is difficult to deal with only relying on the experience of a designer, and the influence of the hot forming history on the part service performance is neglected, so that the structural design is unreasonable is solved, and by representing the degradation transfer and accumulation rule of the material performance from the forming stage to the service stage, the material performance is improved. The complex corresponding relation between part design parameters and forming response is defined, seamless connection and real-time linkage of the part forming process and the service process are achieved, the feasibility of all schemes can be rapidly and accurately evaluated in the conceptual design stage, guidance is provided for designers to select reasonable part design schemes, and design according to performance is achieved in the early development stage.

The invention relates to the technical field of flow battery pile end plates, in particular to a flow battery pile end plate design method based on simulation driving, and finally obtains a lightweight pile end plate structure scheme with the highest material utilization rate through a response surface model and construction of a topological space. According to the invention, the trial-manufacture cost is reduced, the stack is delivered in mass production, and the BOM cost of the stack is greatly reduced; on the basis that the pile end plate meets the structural reliability, the overall weight of the pile is effectively reduced, and the light weight of the pile is realized; simulation verification is advanced from a traditional post link to a conceptual design stage, the whole process of scheme argumentation, preliminary design, detailed design and the like is penetrated, the research and development design cycle of the galvanic pile is effectively shortened, and the design cycle can be shortened by 50%; the industrial design effect of the electric pile end plate is achieved, appearance design and packaging of the electric pile are not needed, and the external cost of market-end industrial design is reduced.

The present invention discloses a method for designing a conceptual diagram of the appearance and interior decoration of a ship based on the relationship between text and graph, comprising the following steps: S1, performing entity recognition and relationship extraction on the images of the appearance and interior decoration of the ship; S2, based on the neural network architecture of text-graph modeling, splicing and fusing the image feature representation and the text feature representation corresponding to the labels to generate a fused feature representation; S3, fusing the latent space representation self-learned by the variational autoencoder and the image generation ability of the generative adversarial network, optimizing the parameters of the two through joint training, and generating a conceptual design diagram of the appearance and interior decoration of the ship based on the transformation or differentiability of the rules of the recursive model.

The application discloses a kind of based on FBS concept design model's field knowledge graph construction method, it is related to knowledge graph construction technical field.The present application includes: from document backtracking analysis and product concept design relevant design structure, design behavior, design function, and design structure relevant feature attribute, by predefining the relationship type between these design elements, construct design knowledge graph, to solve the problem of multiple entities corresponding to single entity in document, the structure of traditional Casre l model is improved, and attention module is added.According to the mapping relationship between function and structure, the design structure set that can realize the function is retrieved;For two functions that exist interaction, retrieve the structure that exists connection path in the two design structure sets corresponding to two functions, take the union of design structure.The method of the present application can construct the knowledge graph that provides stable and systematic design knowledge, and the improved Casre l model can effectively handle the problem of single entity relationship overlap.

The invention discloses a three-dimensional dynamic sign design and networked cooperation device and method, and relates to the technical field of three-dimensional dynamic sign design. A three-dimensional model dynamic concept design module completes three-dimensional reconstruction on a two-dimensional basic sign image through the steps of format unification, feature extraction and the like through multi-source data acquisition; combining industry classification codes, brand tonality vectors and design style labels to generate a three-dimensional dynamic sign conceptual model; after the model is generated, the equipment division module obtains real-time performance data and historical task data of the equipment, and precise matching of tasks and the equipment is achieved through comprehensive performance evaluation; and the cooperation permission analysis module sets differentiated permission levels based on project personnel position types after equipment division is completed, and realizes safe sharing of model networked cooperation. The full-process automation and intelligentization of three-dimensional sign design from modeling, equipment scheduling to cooperative management are realized.

The invention relates to the field of AIGC, and particularly discloses a prefabricated building design scheme generation system and method based on AIGC, and the method comprises the steps: coding a project red line, a design task book, a structure network and other macroscopic constraints into a global tensor, guiding a submerged space diffusion model to carry out the sampling of a predefined component discrete code book, a discrete layout index matrix conforming to strict modulus limitation is generated; and graph optimization and BIM instantiation are carried out on the layout by using a connection rule base, and the model is forced to follow microcosmic physical connection logic in the generation process. In this way, it is ensured that the generation result can accurately correspond to the factory inventory unit and meet the physical assembly requirement, and therefore the purpose of automatic generation of BIM data from conceptual design to industrial production level is achieved.

A method for constructing a design graph based on the RFPC conceptual design framework belongs to the technical field of design graph construction. It obtains design knowledge data from text data, then maps the design knowledge to the RFPC model of requirements-function-principle-feature markers for the design knowledge-assisted product conceptual design. It uses natural language processing technology and dependency syntax analysis to characterize the design knowledge elements and the relationships between them, and uses a graph database to provide a knowledge storage and management solution for the design knowledge. This method can more intuitively realize the retrieval and reuse of knowledge in the conceptual design process and support the generation of conceptual design solutions. The present invention solves the limitations of traditional data analysis technology and overcomes the drawbacks of difficulty in effective storage and analysis. The construction of a product design knowledge graph makes it possible to intelligently generate innovative product design solutions, which will facilitate the application of design knowledge and technological innovation in the early stages of product development.

The invention provides a flight-thrust integrated performance conceptual design method based on multidisciplinary coupling, and relates to the field of overall design of aircraft propulsion systems, and the flight-thrust integrated performance conceptual design method comprises the following steps: S1, constructing a joint analysis model of geometric-pneumatic lift-drag characteristics of an aircraft; s2, constructing a component-level aviation propulsion system performance simulation model; and S3, establishing and solving a ternary matching relationship of the flight-thrust integrated design, wherein the ternary matching relationship is composed of a designed take-off total weight matching equation, a designed take-off thrust matching equation and a wing plane area matching equation. According to the method, an aircraft model based on geometric body approximate substitution and a component-level aero-engine steady-state performance simulation model are effectively integrated into an aircraft concept design process, so that conjoint analysis and design of aircraft concept design and conjoint analysis and design of aircraft geometric preliminary design and aerodynamic characteristic conjoint analysis and aero-engine thermodynamic cycle design are realized; and a foundation is laid for realizing global efficiency design optimization of the flight-push system.

This invention discloses a collaborative optimization design method for bearing systems based on TRIZ theory, belonging to the field of mechanical design and innovation methods. First, based on the optimization requirements of the bearing system performance, this invention establishes a three-level functional model of supersystem-system-subsystem and identifies key problem clusters. The functional model includes at least one of the following: useful functions, harmful functions, insufficient functions, and excessive functions. Then, based on the three-level functional model, contradiction solutions and resource analysis are performed at the component level, system level, and supersystem level to obtain contradiction solutions. Subsequently, a matter-field model is constructed and solved, and the TRIZ evolutionary law is applied to guide system reconstruction to obtain a system evolution scheme. Finally, the contradiction solutions and the system evolution scheme are cross-integrated and their feasibility is evaluated to generate an innovative conceptual design scheme for the bearing system. This invention effectively solves the problems of existing technologies being limited to single problems and isolated components.

The invention relates to the technical field of production line design, in particular to an assembly production line concept design method and system based on Bayesian framework learning. Comprising the following steps: S1, constructing a knowledge graph of product design, performing fine adjustment on a large model by using the knowledge graph, and generating a product design scheme by using the adjusted large model; s2, in response to the product design scheme, adopting a Bayesian framework to produce a plurality of production line schemes meeting production; and S3, performing data verification on the plurality of production line schemes, judging whether a production line scheme meeting a preset condition exists or not, if so, outputting the production line scheme meeting the preset condition as a final scheme, and if not, executing the step S2 again. The technical problems, such as complex multi-objective optimization, uncertainty management and quick response to demand change, in the conceptual design of the assembly production line are effectively solved, so that the design period is shortened, the production line performance is improved, and the development cost is reduced.

1. Name of the Design Product: Graphical User Interface of the Business Process Decision Modeling Designer for Electronic Devices. 2. Use of the Design Product: Used to build a structured management model for the user's business process. 3. Design Key Points of the Design Product: Lies in the interface displayed by this product. 4. Picture or Photo that Best Illustrates the Design Key Points of this Design: The front view of Design 1. 5. Views to be Omitted: The hardware product is a conventional design, and the other views are parts that are not commonly seen during use, so they are omitted. 6. Basic Design: Design 8. 7. Interface Use: Used for the creation, modification, and grouping adjustment of different models of the user's business process. 8. Description of the changing states of the graphical user interface: The changing state diagram 1 of Design 1 is the interface displayed after clicking on the model data of "D0254 Model" in the main view of Design 1; The changing state diagram 2 of Design 1 is the interface displayed after clicking on the "Publish" menu in the changing state diagram 1 of Design 1; The changing state diagram 1 of Design 2 is the interface displayed after clicking on the model data of "D0254 Model" in the main view of Design 2; The changing state diagram 2 of Design 2 is the interface displayed after clicking on the "Historical Versions" menu in the changing state diagram 1 of Design 2; The changing state diagram 1 of Design 3 is the interface displayed after clicking on the model data of "D0254 Model" in the main view of Design 3; The changing state diagram 2 of Design 3 is the interface displayed after clicking on the "Delete Draft" menu in the changing state diagram 1 of Design 3; The changing state diagram 1 of Design 4 is the interface displayed after clicking on the model data of "D0254 Model" in the main view of Design 4; The changing state diagram 2 of Design 4 is the interface displayed after clicking on the "Insert Phase" menu in the changing state diagram 1 of Design 4; The changing state diagram 1 of Design 5 is the interface displayed after clicking on the model data of "D0254 Model" in the main view of Design 5; The changing state diagram 2 of Design 5 is the interface displayed after clicking on the "Import Model" menu in the changing state diagram 1 of Design 5; The changing state diagram 1 of Design 6 is the interface displayed after clicking on the model data of "D0254 Model" in the main view of Design 6; The changing state diagram 2 of Design 6 is the interface displayed after clicking on the module menu of the "Conceptual Design" phase in the changing state diagram 1 of Design 6; The changing state diagram 1 of Design 7 is the interface displayed after clicking on the model data of "D0254 Model" in the main view of Design 7; The changing state diagram 2 of Design 7 is the interface displayed after clicking on the decision module menu of "Whether the conceptual design is completed" in the changing state diagram 1 of Design 7; The changing state diagram 1 of Design 8 is the interface displayed after clicking on the model data of "D0254 Model" in the main view of Design 8; The changing state diagram 2 of Design 8 is the interface displayed after entering through the menu of "A total of 3 processes, 2 processes are ready to exit" in the "1. Conceptual Design" module in the changing state diagram 1 of Design 8; The changing state diagram 3 of Design 8 is the interface displayed after clicking on the "Insert Process" menu in the changing state diagram 2 of Design 8; The changing state diagram 4 of Design 8 is the interface displayed after clicking on the "Requirement Review" menu in the changing state diagram 3 of Design 8; The changing state diagram 5 of Design 8 is the interface displayed after clicking on the "Input / Output" menu in the changing state diagram 4 of Design 8; The changing state diagram 6 of Design 8 is the interface displayed after clicking on the "Knowledge Package" menu in the changing state diagram 5 of Design 8.

Embodiments of the present disclosure provide an optimal conceptual design framework. A surrogate process model may be generated based on one or more physics-informed machine learning models and a rigorous dynamic process model. The surrogate process model may comprise a representation of a plant process including one or more target assets and one or more secondary assets. The process input for the one or more target assets may comprise power output from a renewable energy source. A design optimization algorithm representative of a multi-objective design optimization problem may be generated. An optimal conceptual design for the process may be generated by executing an optimization model based on the surrogate process model and the design optimization algorithm.

This invention discloses a CAE simulation analysis method for misuse of die-casting trolleys, comprising: deriving a geometric model based on a preliminary design; dividing the element mesh; generating a finite element model; defining materials, boundary conditions, initial volumetric parameters, and control parameters; solving; viewing the analysis results; determining the usability of the model based on the analysis results; if not, improving the model and returning to the step of deriving the geometric model; if yes, determining whether the analysis results meet the design requirements; if yes, obtaining the final design; if not, obtaining the improved structure, obtaining the improved design based on the improved structure, and returning to the step of deriving the geometric model. This invention's CAE simulation analysis method for misuse of die-casting trolleys considers the strength performance of the trolley during the conceptual design stage. If the requirements are not met, it is immediately returned to the designer for modification or redesign, greatly shortening the physical experiment cycle and reducing costs.

The present invention discloses a product form generation design method based on deep learning and parametric modeling, which relates to the technical field of styling design and solves the technical problem of rapid three-dimensional model generation for complex products facing user intentions. The key points of its technical solution are to integrate the professional domain knowledge in design science into the generative design algorithm. This method mines the user's perceptual awareness of the style image of product styling elements, uses the degree of conformity between the styling and the image as the design guidance to help designers accurately grasp the design feature elements and user needs, reduce design risks. At the same time, a generative product design system is established through deep learning and parametric modeling technologies to assist designers in quickly generating design schemes in the conceptual design stage, efficiently and extensively exploring the design space, enabling rapid exploration of product families, accelerating the product iteration speed, and shortening the R & D cycle.

The invention discloses a man-machine mutual cognition concept design method and device based on deep learning and knowledge management, and the method comprises the steps: collecting operation data in a concept design process of a designer, and obtaining a design image and a design description; marking a design image and a design description, and mapping the design image and the design description to a design intention to obtain a private design multi-modal data set of a designer; dividing the private design multi-modal data set into a training data set and a test data set; training the deep learning network by using the training data set to obtain a model pre-training weight of the recognition model; calling a model pre-training weight, and performing design intention recognition on the test set through the recognition model to obtain a to-be-fed-back design intention; using a design knowledge matching framework to match design knowledge concerned by a designer from a design knowledge base based on the to-be-fed-back design intention; and according to a design knowledge matching result, recommending to a designer in sequence by utilizing a knowledge recommendation algorithm. According to the method, the man-machine cooperation efficiency of the conceptual design is effectively improved.