Industrial design generation intelligent auxiliary system and method based on user interaction

Abstract

The invention relates to the technical field of industrial design intelligent assistance, in particular to an industrial design generation intelligent assistance system and method based on user interaction, and realizes efficient and innovative industrial design intelligent assistance meeting actual industrial requirements. The system comprises a user interface module, an intelligent conflict detection module, a user instruction processing module, a multi-level intelligent design generation module and a historical version and data management module. The user interface module provides a design interface supporting multi-user real-time interaction, operation and personalized customization, and establishes a user personalized design file; the intelligent conflict detection module detects conflicts in real time when multiple users edit and design at the same time, and automatically adjusts user permissions and operation priorities according to user priorities; the user instruction processing module receives a user instruction and converts the user instruction into an operation command; the multi-level intelligent design generation module generates design drawings of different levels according to different design stages on the basis of user personalized design archives, operation commands and a domain knowledge base.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial design intelligent assistance, and in particular to an industrial design generation intelligent assistance system and method based on user interaction. Background Art

[0002] With the continuous development of the field of industrial design, design tasks have become more and more complex. Especially in a multi-user collaborative environment, how to efficiently and intelligently generate designs has become the key to improving industrial design efficiency and innovation capabilities. Especially in design tasks involving multi-disciplinary and multi-team collaboration, how to achieve information sharing, real-time interaction and intelligent optimization in the design process has become an important means to improve product design quality, shorten design cycles and reduce design costs. In this context, an industrial design generation intelligent auxiliary system based on user interaction has emerged. By integrating advanced artificial intelligence and other technologies, it provides intelligent support for design teams and promotes the automation and precision of design processes.

[0003] However, although the existing design assistance systems have achieved design automation and collaboration to a certain extent, the existing technologies still have many shortcomings and cannot fully meet the needs of multi-user collaborative design for real-time feedback, personalized customization, conflict resolution and intelligent suggestions. In the collaborative process, traditional design systems often lack intelligent conflict detection mechanisms, cannot effectively handle conflicts when multiple users edit designs at the same time, and cannot dynamically adjust the operation priority. At the same time, the existing systems usually only provide static design generation processes, which makes it difficult to intelligently generate corresponding design drawings according to the needs of different design stages. In addition, the existing technologies have also failed to make full use of speech recognition and natural language processing technologies to improve user operation efficiency, resulting in a less smooth experience for designers during the interaction process. Therefore, it is an urgent need to develop an industrial design intelligent auxiliary generation system that can integrate real-time collaboration, intelligent conflict resolution, voice and image interaction, and multi-level design generation, which is efficient, innovative, and meets actual industrial needs, to improve the efficiency and quality of industrial design.

[0004] Therefore, an intelligent auxiliary system and method for industrial design generation based on user interaction is proposed. Summary of the invention

[0005] The purpose of the present invention is to provide an industrial design generation intelligent auxiliary system and method based on user interaction, so as to realize an industrial design intelligent auxiliary system that is efficient, innovative and meets actual industrial needs. The system includes a user interface module, an intelligent conflict detection module, a user instruction processing module, a multi-level intelligent design generation module and a historical version and data management module; the user interface module provides a design interface that supports multi-user real-time interaction, operation and personalized customization, and establishes a user personalized design archive; the intelligent conflict detection module detects conflicts when multiple users edit the design at the same time in real time, and automatically adjusts user permissions and operation priorities according to user priorities; the user instruction processing module receives user instructions and converts user instructions into operation commands through an instruction processing model; the multi-level intelligent design generation module generates design drawings of different levels according to different design stages based on user personalized design archives, operation commands and domain knowledge bases; the historical version and data management module records the user personalized design archives and manages historical design versions, and stores all design files through the cloud.

[0006] To achieve the above object, the present invention provides the following technical solutions: An industrial design generation intelligent auxiliary system based on user interaction, comprising: The user interface module is used to provide a design interface that supports multi-user real-time interaction, operation and personalized customization, and to establish a user personalized design file by analyzing the historical design data, interaction records and user similarity of different users; the personalized customization includes: interface layout, view mode and theme color; Intelligent conflict detection module, which is used to detect conflicts when multiple users edit designs simultaneously in real time through intelligent conflict detection model, and automatically adjust user permissions and operation priorities according to user priorities; A user instruction processing module, used to receive user instructions and convert the user instructions into operation commands through an instruction processing model; the user instructions include: text instructions, voice instructions and image instructions; A multi-level intelligent design generation module, used to generate design drawings of different levels according to different design stages through a multi-level intelligent design generation model based on the user personalized design file, the operation command and the domain knowledge base; The historical version and data management module is used to record the user's personalized design files and manage historical design versions, and store all design files through the cloud.

[0007] Preferably, the interface layout includes: adjusting the size of the work area and the position of tools according to the design task requirements; the view mode includes: 2D view and 3D view.

[0008] Preferably, the establishment of the user personalized design file includes: a user behavior analysis unit, a user behavior modeling unit, a user preference inference unit and a user personalized design file establishment unit; wherein, the user behavior analysis unit analyzes the user's interaction records to extract user behaviors; the user behaviors include: common operations, design styles and design modification habits; the user behavior modeling unit analyzes the user behaviors through a clustering algorithm to obtain the user's regular operating behaviors; the user preference inference unit infers user preferences through a recommendation algorithm based on the regular operating behaviors, combined with the user similarities and the user's historical design data; the user preferences include: preferred design options and preferred interface configurations; the user personalized design file establishment unit integrates the historical design data, the interaction records and the user preferences to establish the user personalized design file.

[0009] Preferably, the intelligent conflict detection model includes: a user operation monitoring unit, a conflict detection unit, a user priority judgment unit and a conflict resolution unit; the user operation monitoring unit records the operation of each user in real time through an event-driven mechanism and saves it in the historical version and data management module; the operation includes: operation type, operation object and operation timestamp; when multiple users operate simultaneously, the conflict detection unit determines whether a conflict occurs by comparing the operation type, the state of the operation object and the timestamp; the specific judgment method is: obtaining the first operation of the first user and the second operation of the second user in the historical version; performing a first conflict detection by comparing the operation timestamps; if the timestamps of the first operation and the second operation are the same, performing a second conflict detection by comparing the operation type and the operation object in the first operation and the second operation; if the operation type and the operation object are the same, it is determined that there is a conflict; the user priority judgment unit determines and sorts the user priority according to the user role and the urgency of the task; the conflict resolution unit automatically selects the high-priority operation according to the user priority.

[0010] Preferably, the user instruction processing module includes: an instruction recognition unit, an operation command generation unit and an operation command execution unit; wherein, the instruction recognition unit parses the user instruction and identifies the user intention through NLP technology; the operation command generation unit maps the user intention to the operation command; and the operation command execution unit passes the operation command to the corresponding module for design modification.

[0011] Preferably, the multi-level intelligent design generation module includes: a design stage identification unit, a multi-level design generation unit and a design output unit; wherein, the design stage identification unit identifies the design stage in combination with the operation command and the domain knowledge base; the design stage includes: a conceptual design stage, a preliminary design stage and a detailed design stage; the multi-level design generation unit selects a corresponding multi-level intelligent design generation model according to the design stage to generate designs at different levels; the multi-level intelligent design generation model includes: a conceptual design generation model, a preliminary design generation model and a detailed design generation model; the conceptual design generation model generates designs according to the user personality The invention relates to a method for generating a plurality of concept design drawings based on the digital design archive, the operation command and the domain knowledge base, and screens the concept design drawings according to the design index to obtain the optimal concept design drawing; the preliminary design generation model optimizes the optimal concept design drawing according to the operation command and the design constraint condition to obtain the preliminary design drawing; the detailed design generation model concretizes the preliminary design drawing according to the operation command and the refined design parameters to obtain the final design drawing; the design output unit outputs the optimal concept design drawing, the preliminary design drawing and the final design drawing; the design constraint condition and the design parameter are determined according to the manufacturing process requirements and the product requirements.

[0012] Preferably, an intelligent auxiliary method for industrial design generation based on user interaction comprises: Provide a design interface that supports multi-user real-time interaction, operation and personalized customization, and establish a user personalized design profile by analyzing the historical design data, interaction records and user similarity of different users; the personalized customization includes: interface layout, view mode and theme color; Intelligent conflict detection model detects conflicts when multiple users edit designs simultaneously in real time, and automatically adjusts user permissions and operation priorities based on user priorities; Receiving user instructions and converting the user instructions into operation commands through an instruction processing model; the user instructions include: text instructions, voice instructions and image instructions; Based on the user personalized design file, the operation command and the domain knowledge base, generating design drawings of different levels according to different design stages through a multi-level intelligent design generation model; Record and manage historical design versions and store all design files in the cloud.

[0013] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention creates a personalized design profile by analyzing the user's historical design data, interaction records, and user similarity in real time. The profile can fully reflect the user's design preferences, operating habits, and commonly used design elements, so that the user can enjoy a more customized operating interface during the design process, improving the designer's operating efficiency and work comfort. Through personalized customization, designers can optimize the design process according to their needs, reduce unnecessary steps, greatly enhance work flexibility and design creativity, and thus improve design efficiency and innovation level.

[0014] 2. The present invention proposes an intelligent conflict detection model that can monitor conflicts when multiple users are editing designs at the same time in real time, avoiding the common operational conflict problems when multiple users collaborate in traditional design tools. Through the intelligent permission adjustment mechanism based on user priority, the system can not only automatically identify and resolve conflicts, but also intelligently sort and adjust user permissions according to the role and task urgency of each user. This intelligent conflict detection model reduces unnecessary conflicts and duplication of work in the design process. At the same time, it greatly reduces friction in collaboration, ensures a smoother design process, and can significantly improve the efficiency of team collaboration and design, especially in a multi-user, complex task environment.

[0015] 3. The present invention provides a design generation model that meets the characteristics of different design stages (such as conceptual design, preliminary design and detailed design) through a multi-level intelligent design generation module, which can automatically generate and optimize drawings for each design stage based on user instructions, personalized design archives and domain knowledge bases. The system generates comparisons to ensure that multiple design solutions are quickly provided in the conceptual design stage, key parameters are optimized in the preliminary design stage, and specific implementation details are refined in the detailed design stage. This multi-level intelligent design generation method greatly improves the automation level of the design and ensures quality control of the design from concept to detail, effectively reduces manual intervention and human errors, improves the intelligence and efficiency of the design, and ensures the innovation and quality of the final design drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A structural diagram of an industrial design generation intelligent assistance system based on user interaction provided by an embodiment of the present invention; Figure 2 A flowchart of an intelligent auxiliary method for industrial design generation based on user interaction provided by an embodiment of the present invention; Figure 3 A working principle diagram of an intelligent conflict detection module provided by an embodiment of the present invention; Figure 4 A working principle diagram of a multi-level intelligent design generation module provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] With the continuous development of the field of industrial design, design tasks have become more and more complex. Especially in a multi-user collaborative environment, how to efficiently and intelligently generate designs has become the key to improving industrial design efficiency and innovation capabilities. Especially in design tasks involving multi-disciplinary and multi-team collaboration, how to achieve information sharing, real-time interaction and intelligent optimization in the design process has become an important means to improve product design quality, shorten design cycles and reduce design costs. In this context, an industrial design generation intelligent auxiliary system based on user interaction has emerged. By integrating advanced artificial intelligence and other technologies, it provides intelligent support for design teams and promotes the automation and precision of design processes.

[0019] The present invention proposes an industrial design generation intelligent assistance system based on user interaction, which realizes efficient, innovative and industrial design intelligent assistance generation that meets actual industrial needs. This system is implemented by an industrial design generation intelligent assistance method based on user interaction. For the specific method flowchart and system structure diagram, please refer to Figure 1 and Figure 2 In order to illustrate that the system and method of the present invention can play a role in intelligently assisting the generation of industrial designs that are efficient, innovative, and in line with actual industrial needs, the effectiveness of the present invention will be illustrated in two embodiments below.

[0020] See also Figures 1 to 4 ,The present invention provides an intelligent auxiliary system and method for industrial design generation based on user interaction, and the technical scheme is as follows.

[0021] Embodiment 1 The present invention proposes an industrial design generation intelligent auxiliary system based on user interaction, the structure of which is as follows: Figure 1 As shown, including: The user interface module is used to provide a design interface that supports multi-user real-time interaction, operation and personalized customization, and to establish a user personalized design file by analyzing the historical design data, interaction records and user similarities of different users; the personalized customization includes: interface layout, view mode and theme color; the interface layout includes: adjusting the work area size and tool position according to the design task requirements; the view mode includes: 2D view and 3D view.

[0022] Through personalized interface layout adjustment and view mode switching, the present invention can optimize the user interface according to the requirements of different design tasks, help designers quickly adjust the working environment according to different task requirements, and improve the convenience and operability of design work. The switching between 2D and 3D views further improves the intuitiveness of the design, ensuring that designers can perform accurate visual verification and modification at different design stages, allowing designers to operate and manage design tasks more efficiently.

[0023] Preferably, the establishment of the user personalized design file includes: a user behavior analysis unit, a user behavior modeling unit, a user preference inference unit and a user personalized design file establishment unit; Wherein, the user behavior analysis unit analyzes the user's interaction record to extract user behavior; the user behavior includes: common operations, design style and design modification habits; The user behavior modeling unit analyzes the user behavior by a clustering algorithm to obtain the user's regular operation behavior; The user preference inference unit infers user preferences through a recommendation algorithm based on the conventional operation behavior, combined with the user similarity and the user's historical design data; the user preferences include: preferred design options and preferred interface configurations; The user personalized design file establishing unit integrates the historical design data, the interaction record and the user preference to establish the user personalized design file.

[0024] Specifically, the user similarity includes: operation frequency similarity, design style similarity and design modification habit similarity; the specific calculation formula is: ; ; ; ; in, is the user similarity between user a and user b; is the operation frequency similarity weight; is the similarity of operation frequency between user a and user b; is the design style similarity weight; is the design style similarity between user a and user b; Modify the custom similarity weights for design; The similarity of design modification habits between user a and user b; is a set of common operations of user a; is a set of common operations of user b; is the weight factor; Design style for user a The set of choices on ; Design style for user b The set of choices on ; Design modification operation for user a Frequency of modification on Design modification operation for user B The frequency of modification on .

[0025] Through behavior analysis, modeling, and preference inference, this application can accurately capture the user's operating habits and preferences and help build a personalized design solution. Combined with the user's historical data and interaction records, the system can automatically recommend design options and interface configurations that meet the preferences of different users, greatly improving the personalization and efficiency of the design.

[0026] Preferably, the intelligent conflict detection module is used to detect conflicts when multiple users edit the design simultaneously in real time through the intelligent conflict detection model, and automatically adjust the user permissions and operation priorities according to the user priorities; see Figure 3 ; The intelligent conflict detection model includes: a user operation monitoring unit, a conflict detection unit, a user priority determination unit and a conflict resolution unit; The user operation monitoring unit records the operation of each user in real time through an event-driven mechanism and saves it in the historical version and data management module; the operation includes: operation type, operation object and operation timestamp; When multiple users operate simultaneously, the conflict detection unit determines whether a conflict occurs by comparing the operation type, the state of the operation object and the timestamp; Specifically, the conflicts include: data write conflict, structure deletion conflict, permission overwrite conflict, version split conflict and dependency chain conflict; the data write conflict is when two users perform modification operations on the same parameter within ±500ms; the structure deletion conflict is when the first user modifies a layer and the second user deletes the layer within ±1s; the permission overwrite conflict is when an ordinary user initiates a sensitive operation during the administrator's permission adjustment; the version split conflict is when two users submit modifications with a difference of more than 30% based on the same version; the dependency chain conflict is when a user modifies a design parameter that is dependent on the operation results of other users; The specific process of real-time recording through the event-driven mechanism is as follows: monitor user terminal operation events through WebSocket long connection, and event triggering conditions include: design parameter modification, layer addition and deletion, object displacement, permission change, and version submission; use the NTP protocol to synchronize the clocks of each terminal, and record events with millisecond timestamp accuracy; convert operation events into structured data packets, including: user ID, operation type code, object UUID, timestamp, and operation value; implement event sorting through message queues, and use RabbitMQ's x-recent-seq feature to ensure that events are written to the historical version and data management module in a global order; the x-recent-seq feature is an extension mechanism used to ensure the global sequential writing of multi-user operation times.

[0027] The specific judgment method is: obtaining a first operation of a first user and a second operation of a second user in a historical version; performing a first conflict detection by comparing the operation timestamps; if the operation timestamps of the first operation and the second operation are the same, performing a second conflict detection by comparing the operation type and the operation object in the first operation and the second operation; if the operation type and the operation object are the same, determining that a conflict exists; The user priority determination unit determines and sorts user priorities according to user roles and task urgency; The conflict resolution unit automatically selects a high priority operation according to the user priority.

[0028] Table 1 shows the effect of the intelligent conflict detection module on improving team design efficiency.

[0029] Table 1 Real-time conflict detection effect

[0030] The intelligent conflict detection model proposed in this application can effectively prevent operational conflicts when multiple users are editing at the same time, ensuring smooth team collaboration. By real-time monitoring of user operations, intelligently determining priorities and automatically adjusting permissions, this module can automatically resolve editing conflicts, avoid unnecessary delays and misoperations caused by conflicts, and thus improve the design efficiency of the team.

[0031] Preferably, the user instruction processing module is used to receive user instructions and convert the user instructions into operation commands through the instruction processing model; the user instructions include: text instructions, voice instructions and image instructions; The user instruction processing module includes: an instruction recognition unit, an operation command generation unit and an operation command execution unit; The instruction recognition unit analyzes the user instruction and recognizes the user intention through NLP technology; Specifically, the specific process of parsing the user instructions and identifying the user intentions through NLP technology is as follows: The input interface monitors text, voice and image commands in real time, wherein voice commands are converted into text through ASR, and image commands extract text information through optical character recognition or computer vision technology to form a unified text format; loads user historical interaction records, generates a semantic tree based on syntactic analysis for grammatical parsing; outputs user intent based on a hybrid model of BERT+BiLSTM; the hybrid model based on BERT+BiLSTM is an existing hybrid model based on BERT and BiLSTM, which is used for sentiment analysis in the NLP field.

[0032] The operation command generating unit maps the user intention into the operation command; Specifically, the user intention is mapped into the operation command through the instruction-operation mapping knowledge graph; The operation command execution unit transmits the operation command to the corresponding module for design modification.

[0033] The instruction processing model proposed in the embodiment of the present application supports the rapid conversion of voice instructions, image instructions and text instructions, and recognizes user intentions through natural language processing technology, effectively reducing the complexity of designer operations. By automatically converting operation commands to the corresponding modules for design modification, designers can make design modifications more efficiently, further improving the intelligence of the design process and user experience.

[0034] Preferably, the intelligent conflict detection module is used to generate design drawings of different levels according to different design stages through a multi-level intelligent design generation model based on the user personalized design file, the operation command and the domain knowledge base; Figure 4 ; The multi-level intelligent design generation module includes: a design stage identification unit, a multi-level design generation unit and a design output unit; The design stage identification unit identifies the design stage by combining the operation and the domain knowledge base; the design stage includes: conceptual design stage, preliminary design stage and detailed design stage; The multi-level design generation unit selects a corresponding multi-level intelligent design generation model according to the design stage to generate design drawings at different levels; the multi-level intelligent design generation model includes: a conceptual design generation model, a preliminary design generation model and a detailed design generation model; The concept design generation model generates a plurality of concept design drawings according to the user personalized design file, the operation command and the domain knowledge base, and screens the concept design drawings according to the design index to obtain the optimal concept design drawing; Specifically, the conceptual design generation model uses a GAN generative adversarial network to generate multiple conceptual design drawings, and generates high-quality conceptual design drawings by training a generator and a discriminator through adversarial training; the GAN generative adversarial network includes: a generator and a discriminator; the generator is based on a U-Net structure and combined with a transposed convolutional layer to improve the authenticity of the conceptual design drawings; the discriminator uses CNN stacking to gradually downsample and extract the features of the conceptual design drawings, and outputs the authenticity discrimination probability of the generated conceptual design drawings through a Sigmoid function; The specific process of training the GAN generative adversarial network is as follows: input the real concept design drawing and the generated concept design drawing obtained by the generator, and calculate the discrimination loss; fix the discriminator, optimize the generated concept design drawing by back propagation, and calculate the generator loss; continuously iteratively train the generator and the discriminator by generating adversarial loss to obtain multiple concept design drawings with authenticity; The multiple concept design drawings are screened by calculating the design quality score, and the concept design drawing with the highest design quality score is screened out as the optimal concept design drawing; the design quality score is obtained by comprehensively analyzing the functionality score, manufacturability score, structural stability score, innovation score, aesthetic effect score and production cost score, and the specific formula is: ; in, Rate the quality of the design; For the The weight of each evaluation dimension; For the Ratings of evaluation dimensions; is the number of evaluation dimensions. ; The preliminary design generation model optimizes the optimal conceptual design drawing according to the design constraint conditions to obtain a preliminary design drawing; The detailed design generation model concretizes the preliminary design drawing according to the refined design parameters to obtain a final design drawing; The design output unit outputs the optimal concept design drawing, the preliminary design drawing and the final design drawing.

[0035] The preliminary design generation model optimizes the conceptual design drawing by a gradient descent algorithm according to the design constraints to obtain the preliminary design drawing; The detailed design generation model uses CAD or other design tools to finely model the preliminary design drawing according to the refined design parameters to ensure that the size, shape, performance, etc. of each part meet the standards to obtain the final design drawing.

[0036] Table 2 shows the generation efficiency of the multi-level intelligent design generation model and the quality score table of the final design drawing.

[0037] Table 2 Generation efficiency and quality score table of multi-level intelligent design generation model

[0038] By introducing a multi-level intelligent design generation module, the embodiment of the present application enables the system to generate design drawings at different levels according to different design stages. Specifically, the system can automatically identify the conceptual design, preliminary design, and detailed design stages of the design task, and select the corresponding design generation model according to the needs of each stage. At the same time, by combining the user's personalized design files and operation commands, the GAN model is used in the conceptual design generation process to generate multiple conceptual design drawings based on user preferences and domain knowledge bases. The generated design drawings are then screened using preset design indicators to ensure that the final selected design meets the user's personalized needs and design standards. This phased and hierarchical design approach can ensure that the output of each design stage is more in line with actual needs and reduces design errors. It not only meets the user's customization needs, but also greatly improves the efficiency and innovation of the design.

[0039] Preferably, the historical version and data management module is used to record the user's personalized design files and manage historical design versions, and store all design files through the cloud.

[0040] The industrial design generation intelligent auxiliary system provided by the embodiment of the present application effectively improves the design efficiency and user experience through personalized design interface, intelligent conflict detection and multi-user real-time collaboration. The system establishes a personalized design archive by analyzing the user's historical design data, interaction records and similarity, and can provide a working environment that meets the needs of each user according to the preferences of each user, thereby enhancing the personalization of the design. At the same time, when multiple users collaborate at the same time, the intelligent conflict detection module monitors and resolves the operation conflict in real time, automatically adjusts the user authority and operation priority, and ensures the smooth progress of the design process. Users can interact with the system through text, voice and image instructions, and convert user instructions into operation commands through the instruction processing module, providing a variety of design operations. The multi-level intelligent design generation module generates corresponding design drawings according to different design stages, ensuring that each link from conceptual design to detailed design can be effectively supported. The historical version and data management module are stored in the cloud to ensure the integrity and traceability of the design data. Overall, the present invention provides an efficient, intelligent and innovative design auxiliary system, which significantly improves the efficiency and innovation of design collaboration and meets the actual needs of modern industrial design.

[0041] Embodiment 2 The present invention proposes an intelligent auxiliary method for industrial design generation based on user interaction, the process of which is as follows: Figure 2 As shown, including: Provide a design interface that supports multi-user real-time interaction, operation and personalized customization, and establish a user personalized design profile by analyzing the historical design data, interaction records and user similarity of different users; the personalized customization includes: interface layout, view mode and theme color; The interface layout includes: adjusting the work area size and tool position according to the design task requirements; the view mode includes: 2D view and 3D view.

[0042] Preferably, the establishment of the user personalized design file includes: a user behavior analysis unit, a user behavior modeling unit, a user preference inference unit and a user personalized design file establishment unit; wherein the user behavior analysis unit analyzes the user's interaction records to extract user behaviors; the user behavior modeling unit analyzes the user behaviors through a clustering algorithm to obtain the user's regular operating behaviors; the user preference inference unit infers user preferences through a recommendation algorithm based on the regular operating behaviors, combined with the user similarities and the user's historical design data; the user preferences include: preferred design options and preferred interface configurations; the user personalized design file establishment unit integrates the historical design data, the interaction records and the user preferences to establish the user personalized design file.

[0043] Preferably, the conflicts when multiple users edit the design at the same time are detected in real time by an intelligent conflict detection model, and the user authority and operation priority are automatically adjusted according to the user priority; the intelligent conflict detection model includes: a user operation monitoring unit, a conflict detection unit, a user priority judgment unit and a conflict resolution unit; The user operation monitoring unit records the operation of each user in real time through an event-driven mechanism and saves it in the historical version and data management module; the operation includes: operation type, operation object and operation timestamp; When multiple users operate simultaneously, the conflict detection unit determines whether a conflict occurs by comparing the operation type, the state of the operation object and the timestamp; the specific determination method is: obtaining a first operation of a first user and a second operation of a second user in a historical version; performing a first conflict detection by comparing the operation timestamps; if the operation timestamps of the first operation and the second operation are the same, performing a second conflict detection by comparing the operation type and the operation object in the first operation and the second operation; if the operation type and the operation object are the same, determining that a conflict exists; The user priority determination unit determines and sorts user priorities according to user roles and task urgency; The conflict resolution unit automatically selects a high priority operation according to the user priority.

[0044] Preferably, accepting user instructions and converting the user instructions into operation commands through an instruction processing model; the user instructions include: text instructions, voice instructions and image instructions; The user instruction processing module includes: an instruction recognition unit, an operation command generation unit and an operation command execution unit; The instruction recognition unit analyzes the user instruction and recognizes the user intention through NLP technology; The operation command generating unit maps the user intention into the operation command; The operation command execution unit transmits the operation command to the corresponding module for design modification.

[0045] Preferably, based on the user personalized design archive, the operation command and the domain knowledge base, a multi-level intelligent design generation model is used to generate design drawings of different levels according to different design stages; the multi-level intelligent design generation module includes: a design stage identification unit, a multi-level design generation unit and a design output unit; The design stage identification unit identifies the design stage by combining the operation command and the domain knowledge base; the design stage includes: conceptual design stage, preliminary design stage and detailed design stage; The multi-level design generation unit selects a corresponding multi-level intelligent design generation model according to the design stage to generate design drawings at different levels; the multi-level intelligent design generation model includes: a conceptual design generation model, a preliminary design generation model and a detailed design generation model; The concept design generation model generates a plurality of concept design drawings according to the user personalized design file, the operation command and the domain knowledge base, and screens the concept design drawings according to the design index to obtain the optimal concept design drawing; The preliminary design generation model optimizes the optimal conceptual design drawing according to the design constraint conditions to obtain a preliminary design drawing; The detailed design generation model concretizes the preliminary design drawing according to the refined design parameters to obtain a final design drawing; The design output unit outputs the optimal concept design drawing, the preliminary design drawing and the final design drawing.

[0046] Table 3 Overall system efficiency improvement and design quality

[0047] Preferably, historical design versions are recorded and managed, and all design files are stored in the cloud.

[0048] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An industrial design generation intelligent auxiliary system based on user interaction, characterized in that: include: User interface module, used to provide a design interface that supports multi-user real-time interaction, operation and personalized customization, and to establish a user personalized design profile by analyzing the historical design data, interaction records and user similarities of different users; The personalized customization includes: interface layout, view mode and theme color; Intelligent conflict detection module, which detects conflicts when multiple users edit designs simultaneously in real time through intelligent conflict detection model, and automatically adjusts user permissions and operation priorities according to user priorities; A user instruction processing module, used to receive user instructions and convert the user instructions into operation commands through an instruction processing model; the user instructions include: text instructions, voice instructions and image instructions; A multi-level intelligent design generation module, used to generate design drawings of different levels according to different design stages through a multi-level intelligent design generation model based on the user personalized design file, the operation command and the domain knowledge base; The historical version and data management module is used to record the user's personalized design files and manage historical design versions, and store all design files through the cloud.

2. The intelligent auxiliary system for industrial design generation based on user interaction according to claim 1, characterized in that: The interface layout includes: adjusting the work area size and tool position according to the design task requirements; the view mode includes: 2D view and 3D view.

3. The intelligent auxiliary system for industrial design generation based on user interaction according to claim 1, characterized in that: The establishment of the user personalized design file includes: a user behavior analysis unit, a user behavior modeling unit, a user preference inference unit and a user personalized design file establishment unit; wherein the user behavior analysis unit analyzes the user's interaction records and extracts user behaviors; the user behavior modeling unit analyzes the user behaviors through a clustering algorithm to obtain the user's regular operation behaviors; the user preference inference unit infers user preferences through a recommendation algorithm based on the regular operation behaviors, combined with the user similarities and the user's historical design data; the user preferences include: preferred design options and preferred interface configurations; the user personalized design file establishment unit integrates the historical design data, the interaction records and the user preferences to establish the user personalized design file.

4. The intelligent auxiliary system for industrial design generation based on user interaction according to claim 1, characterized in that: The intelligent conflict detection model includes: a user operation monitoring unit, a conflict detection unit, a user priority judgment unit and a conflict resolution unit; the user operation monitoring unit records the operation of each user in real time through an event-driven mechanism and saves it in the historical version and data management module; the operation includes: operation type, operation object and operation timestamp; when multiple users operate simultaneously, the conflict detection unit determines whether a conflict occurs by comparing the operation type, the state of the operation object and the timestamp; the specific judgment method is: obtaining the first operation of the first user and the second operation of the second user in the historical version; performing a first conflict detection by comparing the operation timestamps; if the operation timestamps of the first operation and the second operation are the same, performing a second conflict detection by comparing the operation type and the operation object in the first operation and the second operation; if the operation type and the operation object are the same, it is determined that there is a conflict; the user priority judgment unit determines and sorts the user priority according to the user role and the urgency of the task; the conflict resolution unit automatically selects the high-priority operation according to the user priority.

5. The intelligent auxiliary system for industrial design generation based on user interaction according to claim 1, characterized in that: The user instruction processing module includes: an instruction recognition unit, an operation command generation unit and an operation command execution unit; wherein the instruction recognition unit parses the user instruction and recognizes the user intention through NLP technology; the operation command generation unit maps the user intention into the operation command; and the operation command execution unit passes the operation command to the corresponding module for design modification.

6. The intelligent auxiliary system for industrial design generation based on user interaction according to claim 1, characterized in that: The multi-level intelligent design generation module includes: a design stage identification unit, a multi-level design generation unit and a design output unit; wherein, the design stage identification unit identifies the design stage in combination with the operation command and the domain knowledge base; the design stage includes: a conceptual design stage, a preliminary design stage and a detailed design stage; the multi-level design generation unit selects a corresponding multi-level intelligent design generation model according to the design stage to generate design drawings of different levels; the multi-level intelligent design generation model includes: a conceptual design generation model, a preliminary design generation model and a detailed design generation model; the conceptual design generation model generates design drawings according to the user's personalized design The invention relates to a method for generating a plurality of concept design drawings based on the design file, the operation command and the domain knowledge base, and screening the concept design drawings according to the design index to obtain the optimal concept design drawing; the preliminary design generation model optimizes the optimal concept design drawing according to the operation command and the design constraint conditions to obtain the preliminary design drawing; the detailed design generation model concretizes the preliminary design drawing according to the operation command and the refined design parameters to obtain the final design drawing; the design output unit outputs the optimal concept design drawing, the preliminary design drawing and the final design drawing; the design constraint conditions and the design parameters are determined according to the manufacturing process requirements and the product requirements.

7. An intelligent auxiliary method for industrial design generation based on user interaction, characterized in that: include: Provide a design interface that supports multi-user real-time interaction, operation and personalized customization, and establish a user personalized design profile by analyzing the historical design data, interaction records and user similarities of different users; The personalized customization includes: interface layout, view mode and theme color; Intelligent conflict detection model detects conflicts when multiple users edit designs simultaneously in real time, and automatically adjusts user permissions and operation priorities based on user priorities; Receiving user instructions and converting the user instructions into operation commands through an instruction processing model; the user instructions include: text instructions, voice instructions and image instructions; Based on the user personalized design file, the operation command and the domain knowledge base, generating design drawings of different levels according to different design stages through a multi-level intelligent design generation model; Record and manage historical design versions and store all design files in the cloud.

Images