Industrial design aided design method and system

Abstract

The invention relates to an intelligent industrial design auxiliary system, and aims to realize intelligence and automation of an industrial design process by integrating advanced technical modules such as user interaction, intelligent generation, component decomposition and display, user modification and feedback, learning updating and the like. According to the intelligent industrial design auxiliary system provided by the invention, by integrating the user interaction module, the intelligent generation module, the component decomposition and display module, the user modification and feedback module, the learning updating module and the like, the intelligence and automation of the industrial design process are realized, and the design efficiency and the creative level are remarkably improved. According to the system, the design cost is reduced, the product marketing period is shortened, the practicability and market competitiveness of a design scheme are improved through continuous optimization, and revolutionary change is brought to the field of industrial design.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial software design, and in particular to an industrial design auxiliary design method and system. Background Art

[0002] With the rapid development of science and technology, the field of industrial design is undergoing unprecedented changes. Traditional manual drawing and simple computer-aided design (CAD) can no longer meet the requirements of modern industrial products for design efficiency, innovation and complexity. Especially in the face of rapidly changing market demands and fierce industry competition, companies are in urgent need of a solution that can significantly improve design efficiency, reduce design costs, enhance design creativity and shorten product launch cycles.

[0003] Currently, the rise of artificial intelligence (AI) technology has brought new opportunities to the field of industrial design. By integrating advanced technologies such as machine learning and deep learning, AI can process and analyze large amounts of design data, extract valuable information and patterns from them, and provide designers with intelligent design suggestions and decision support. At the same time, AI technology can also realize the automatic generation and optimization of design solutions, reduce the interference of human factors, and improve the accuracy and practicality of design solutions.

[0004] However, despite the huge potential of AI technology in the field of industrial design, the relevant systems and tools on the market still have many shortcomings. For example, some systems lack sufficient intelligence and automation and cannot effectively meet the complex needs of designers; some systems are too complex and expensive to be popularized in small and medium-sized enterprises.

[0005] Therefore, developing an intelligent industrial design assistance system with high integration, strong intelligence, easy operation and moderate cost is of great significance to promoting innovation and development in the field of industrial design. This patent is proposed in this context, aiming to realize the intelligence and automation of the industrial design process by integrating modules such as user interaction, intelligent generation, component decomposition and display, user modification and feedback, and learning and updating, so as to provide designers with efficient, convenient and innovative design assistance tools. Summary of the invention

[0006] In order to solve the problems of the prior art, the present invention provides an industrial design auxiliary design method and system.

[0007] In order to solve the above technical problems, the present invention is implemented by the following technical solutions: an industrial design auxiliary design method, the specific method steps are as follows:

[0008] Step 1: Provide a user interaction interface to receive simple instructions input by the user;

[0009] Step 2: According to the instruction input by the user, at least one subsystem is selected from a plurality of preset subsystems, wherein each subsystem has acquired corresponding design capabilities by learning industrial design data in the field;

[0010] Step 3: Using the intelligent algorithm of the selected subsystem, generate a preliminary industrial design plan that matches the user input instructions and the traditional design characteristics in the field;

[0011] Step 4: Intelligently identify and decompose the preliminary solution into multiple basic components, and display them on a user interaction interface, so that the user can modify or replace the components through simple operations;

[0012] Step 5: Update and display the final industrial design plan in real time based on the user's modification or replacement operations.

[0013] Preferably, the subsystem has self-learning capability, can continuously collect new information from user feedback, external design databases or Internet resources, and continuously optimize the design model and algorithm based on the new information;

[0014] The subsystem optimizes design models and algorithms based on new information collected from user feedback, external design databases, or Internet resources.

[0015] Preferably, the intelligent algorithm includes a machine learning and / or artificial intelligence algorithm, which is used to improve the innovation and practicality of the preliminary design scheme;

[0016] This module can optimize the design by analyzing historical design data and user feedback.

[0017] Data collection and integration

[0018] User feedback: The system should be designed to easily collect user feedback on design proposals, including ratings, comments, and modification suggestions. This data is critical to understanding user needs and preferences.

[0019] External Design Databases: Regularly update and synchronize information from external design databases via API or data sharing agreements to obtain the latest design trends and standards in the industry.

[0020] Internet Resources: Use web crawler technology to extract valuable information about industrial design from Internet resources such as websites, forums, and social media platforms.

[0021] Data analysis and processing

[0022] Natural Language Processing: Perform language processing on user text feedback to extract sentiment and keywords to analyze user satisfaction and the importance of design elements.

[0023] Image recognition: Use computer vision technology to automatically analyze design images uploaded by users or image materials obtained from the Internet to extract design elements and style features.

[0024] Model and algorithm optimization

[0025] Online Learning: Implementing online learning mechanisms allows the model to receive new data in real time and quickly adjust parameters without having to retrain from scratch.

[0026] Transfer learning: Use pre-trained models to transfer knowledge from new data to existing models, thereby shortening the learning cycle and improving model adaptability.

[0027] Reinforcement learning: Through continuous trial and error learning methods, the design parameters are optimized to make the design more efficient and in line with actual needs.

[0028] Continuous evaluation and verification

[0029] A / B testing: Run side-by-side tests on old and new models to compare their performance and ensure that the newly introduced changes or optimizations are indeed effective.

[0030] User satisfaction survey: Conduct user satisfaction surveys regularly to understand whether model optimization has truly improved user experience.

[0031] Feedback loop

[0032] Closed-loop ecosystem: Establish a closed-loop ecosystem from data collection to model optimization to user feedback, ensuring that the output of each step can serve as the input for the next step, forming a self-driven continuous improvement cycle.

[0033] A system for industrial design auxiliary design method, comprising:

[0034] The user interaction module is used to receive simple instructions input by users and display the design results. As a bridge between the system and users, it provides a friendly interface for users to input design requirements, display design results, and provide necessary interactive support during the design process. It ensures that users can easily express their needs and intuitively understand the design solutions generated by the system.

[0035] Subsystem library, including multiple subsystems for different design fields, each with built-in learning models and algorithms; including multiple subsystems specifically for different design fields (such as machinery, architecture, electronic products, etc.), each with built-in specialized learning models and algorithms to handle specific types of design problems; providing specialized and customized design solutions to ensure the professionalism and diversity of design;

[0036] Intelligent generation module, which can intelligently generate preliminary design solutions according to user instructions and selected subsystems; It can intelligently generate preliminary design solutions according to user's simple instructions and selected subsystems; It can automate the design process, quickly respond to user needs, and provide innovative and practical design solutions;

[0037] The component decomposition and display module is used to decompose the preliminary plan into basic components and display them; decompose the intelligently generated preliminary design plan into basic components and clearly display them to the user so that the user can understand the details of the design; enhance the user's understanding of the design plan and facilitate the user to make specific modifications or optimizations;

[0038] User modification and feedback module, which receives user modification instructions and updates the design results in real time; receives user specific modification instructions for the preliminary plan, updates the design results in real time, and collects user feedback for future design optimization; ensures that the design can meet the user's specific requirements, improves user satisfaction, and promotes continuous improvement of the system through feedback;

[0039] The learning update module is used for self-learning and optimization of subsystems. It is responsible for the self-learning and optimization of all subsystems, and continuously improves the built-in learning models and algorithms by analyzing user feedback and historical design data. It enables the system to have the ability of continuous learning and self-optimization, and continuously improves the design quality and the overall performance of the system.

[0040] Data is transferred between the user interaction module and the intelligent generation module, and user needs are converted into specific design tasks.

[0041] The intelligent generation module calls the subsystem in the corresponding subsystem library for processing according to the task type.

[0042] The component decomposition and presentation module obtains the intelligently generated solution and presents it in detail for users to review and modify.

[0043] The user fine-tunes the design through the User Modification and Feedback Module, which passes feedback information to the Learning Update Module.

[0044] The learning update module uses the received feedback and new data to continuously optimize the models and algorithms in the subsystem.

[0045] Preferably, it further includes a design verification module, which is used to verify and optimize the design scheme after it is generated to ensure the stability and practicality of the design scheme.

[0046] Preferably, the user interaction module is further configured to provide a simulated display of the design solution, so that the user can preview the design effect in different usage scenarios.

[0047] Preferably, it further includes a design solution library for storing the user's design history records for the user to view and reuse.

[0048] Preferably, it further includes a communication interface for exchanging data with other design software or databases, so as to enrich design materials and update design algorithms.

[0049] Preferably, the intelligent generation module adopts a generative adversarial network model;

[0050] Specific training uses:

[0051] Data preprocessing: including standardization, normalization, and encoding variables to improve model performance and avoid bias. Standardize (such as subtracting the mean and dividing by the standard deviation) and normalize (scaling the data to between 0 and 1) the numerical features of the design data, which helps speed up the convergence of gradient descent and reduce numerical problems in training.

[0052] Training and validation split: The data set is divided into a training set and a validation set for model training and effect monitoring. The prepared data is divided into two parts: one for training and the other for validation. This can help the team monitor the performance of the model on unseen data and avoid overfitting;

[0053] Loss function and optimizer selection: Select the cross entropy loss function and Adam optimizer. The cross entropy loss function is selected because it is suitable for measuring the difference between the probability distribution of the model output and the true distribution, and is often used in classification and generation models. The Adam optimizer is used, which combines the advantages of the momentum gradient descent method and RMSProp, and can effectively adjust the learning rate to meet the learning needs of different stages.

[0054] Batch training and iteration: The model is trained by batch processing data through multiple iterations until the model performance reaches the predetermined standard or converges; the model continuously adjusts parameters through multiple rounds of training iterations. After each round of iteration, the model performance is evaluated through the validation set, and the hyperparameters or training strategies are adjusted based on the results.

[0055] The beneficial effects of the present invention are:

[0056] 1. The intelligent industrial design assistance system proposed in this invention realizes the intelligence and automation of the industrial design process by integrating modules such as user interaction, intelligent generation, component decomposition and display, user modification and feedback, and learning and updating, and significantly improves the design efficiency and creativity level. The system not only reduces the design cost and shortens the product launch cycle, but also improves the practicality and market competitiveness of the design solution through continuous optimization, bringing revolutionary changes to the field of industrial design;

[0057] 2. The intelligent generation module uses machine learning algorithms to quickly generate preliminary design plans, reducing the time designers spend on manual drawing and modeling, greatly improving design efficiency. At the same time, the component decomposition and display module enables designers to intuitively understand the design structure, facilitating subsequent modification and optimization;

[0058] 3. The system's built-in multiple subsystems and algorithm models can combine user needs and design field characteristics to generate diverse design solutions, provide designers with rich creative inspiration, and enhance the innovation and uniqueness of the design;

[0059] 4. Through the automated and intelligent design process, the manpower input and material consumption in the design process are reduced, effectively reducing the design cost. In addition, the system can optimize the design plan, reduce unnecessary design iterations, and further save design resources; the rapid transformation from the preliminary design plan to the final product benefits from the efficient operation and real-time feedback mechanism of the system. Designers can quickly respond to market changes and adjust the design plan, thereby shortening the time cycle from product design to market launch. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is a schematic diagram of the overall structure of the present invention.

[0061] Figure 2 It is a logical flow diagram of the present invention. DETAILED DESCRIPTION

[0062] 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.

[0063] Example: Figure 1-2 An industrial design auxiliary design method and system shown integrates multiple modules such as user interaction, intelligent generation, component decomposition, user modification, learning and updating to form a closed-loop design auxiliary system.

[0064] User interaction module

[0065] Develop a graphical user interface (GUI) that supports multiple operating systems (e.g., Windows, macOS, Linux) and browsers (e.g., Chrome, Firefox, Safari).

[0066] The user interface consists of a menu bar, a toolbar, a canvas area, and a property panel. The menu bar provides the main function entry of the system, the toolbar contains commonly used design tools, the canvas area is used to display the preliminary design plan and the component decomposition view, and the property panel is used to adjust component properties and view design parameters.

[0067] Users input simple commands through keyboard, mouse or touch screen, such as selecting design areas, entering design requirements, etc.

[0068] Subsystem Library

[0069] Build a database containing multiple subsystems, each targeting a specific design field (such as automotive design, electronic product design, furniture design, etc.).

[0070] Each subsystem integrates machine learning models and algorithms to quickly generate preliminary design plans through pre-trained models.

[0071] The subsystem supports dynamic loading and unloading, and users can choose to load a specific subsystem as needed.

[0072] Intelligent generation module

[0073] Receive user instructions and selected subsystem information transmitted by the user interaction module.

[0074] The intelligent algorithm of the selected subsystem is called to generate a preliminary design plan based on user instructions and design field characteristics.

[0075] The algorithm uses deep learning technology (such as convolutional neural network CNN and generative adversarial network GAN) for image generation or shape optimization.

[0076] The generated preliminary plan is displayed in the canvas area in the form of an image or a 3D model.

[0077] Component breakdown and display module

[0078] The preliminary design scheme generated by the intelligent generation module is intelligently identified and decomposed into multiple basic components (such as body, wheels, seats, etc.).

[0079] Each component is displayed as a separate layer or object in the canvas area, and users can select it individually and view its properties.

[0080] Provide interactive functions such as rotation, scaling, and movement of components so that users can observe design details from different angles.

[0081] User modification and feedback module

[0082] Users can adjust component properties (such as color, material, size, etc.) through the property panel, or directly drag and replace components in the canvas area.

[0083] The system responds to user operations in real time, updates the display content of the canvas area, and generates new design solutions.

[0084] Users can save, export or share design plans.

[0085] Learning Update Module

[0086] Gather new information from user feedback, external design databases, and Internet resources.

[0087] The collected information is preprocessed and feature extracted for training or optimizing the machine learning model within the subsystem.

[0088] Regularly update the subsystems in the subsystem library, introduce new design styles and algorithm optimizations, and improve the quality and efficiency of design generation.

[0089] Optional modules

[0090] Design Verification Module:

[0091] Develop a set of verification tools based on physical simulation and engineering calculations to verify the stability, safety, and practicality of the design solution.

[0092] The verification results are presented to the user in the form of a report, and suggestions for improvement are provided.

[0093] Design Library:

[0094] Establish a cloud or local design solution library to store the user's design history.

[0095] Provides search, filtering and comparison functions to facilitate users to view and reuse previous design solutions.

[0096] Communication interface:

[0097] Develop API interface or plug-in mechanism to allow this system to exchange data with other design software (such as AutoCAD, SolidWorks, etc.) or databases.

[0098] Introduce external design materials and algorithm updates to enrich design resources and improve system performance.

[0099] 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 aided design method, characterized in that: The specific steps are as follows: Step 1: Provide a user interaction interface to receive simple instructions input by the user; Step 2: According to the instruction input by the user, at least one subsystem is selected from a plurality of preset subsystems, wherein each subsystem has acquired corresponding design capabilities by learning industrial design data in the field; Step 3: Using the intelligent algorithm of the selected subsystem, generate a preliminary industrial design plan that matches the user input instructions and the traditional design characteristics in the field; Step 4: Intelligently identify and decompose the preliminary solution into multiple basic components, and display them on a user interaction interface, so that the user can modify or replace the components through simple operations; Step 5: Update and display the final industrial design plan in real time based on the user's modification or replacement operations.

2. The industrial design aided design method and system according to claim 1, characterized in that: The subsystem has self-learning capabilities, can continuously collect new information from user feedback, external design databases or Internet resources, and continuously optimize design models and algorithms based on the new information; The subsystem optimizes design models and algorithms based on new information collected from user feedback, external design databases, or Internet resources.

3. The industrial design aided design method and system according to claim 1, characterized in that: The intelligent algorithm includes a machine learning and / or artificial intelligence algorithm, which is used to improve the innovation and practicality of the preliminary design plan; This module can optimize the design by analyzing historical design data and user feedback.

4. The system of an industrial design aided design method according to claims 1-3, characterized in that: include: User interaction module, used to receive simple instructions input by users and display design results; Subsystem library, which contains multiple subsystems for different design fields, each with built-in learning models and algorithms; Intelligent generation module, which intelligently generates preliminary design plans based on user instructions and selected subsystems; Component decomposition and display module, used to decompose the preliminary plan into basic components and display them; User modification and feedback module, which receives user modification instructions and updates the design results in real time; Learning and updating module, used for self-learning and optimization of subsystems.

5. The industrial design aided design method according to claim 1, characterized in that: It further includes a design verification module for verifying and optimizing the design scheme after it is generated to ensure the stability and practicality of the design scheme.

6. The industrial design aided design system according to claim 4, characterized in that: The user interaction module is further configured to provide a simulated display of the design solution, so that the user can preview the design effect in different usage scenarios.

7. The industrial design aided design system according to claim 4, characterized in that: The system further includes a design solution library for storing the user's design history for the user to view and reuse.

8. The industrial design aided design system according to claim 4, characterized in that: It further includes a communication interface for exchanging data with other design software or databases, thereby enriching design materials and updating design algorithms.

9. The industrial design aided design system according to claim 4, characterized in that: The intelligent generation module adopts a generative adversarial network model; Specific training uses: Data preprocessing: including standardization, normalization, and encoding variables to improve model performance and avoid bias; Training and validation split: The data set is divided into a training set and a validation set for model training and effect monitoring; Loss function and optimizer selection: Select the cross entropy loss function and Adam optimizer; Batch training and iteration: The model is trained by processing data in batches through multiple iterations until the model performance reaches a predetermined standard or converges.

Images