Product design system and related equipment

Abstract

The invention discloses a product design system and related equipment, and the system comprises a database module which is used for storing product information, perception evaluation vocabularies and experiment data; the mapping model acquisition module is used for acquiring a mapping model of product appearance and perception evaluation; the scheme generation module is used for generating a design scheme through the mapping model according to design expectation; the scheme evaluation module is used for evaluating the design scheme to obtain an evaluation result; the display module is used for displaying appearance elements, design schemes and evaluation results of the products; the user perception evaluation and the product appearance characteristics can be efficiently integrated, the product design scheme meeting the design expectation is automatically generated, the scheme is comprehensively evaluated, and finally the scheme is displayed to the user for selection and further optimization.

Description

Technical Field

[0001] The present invention relates to the technical field of product design, and particularly to a product design system and related devices. Background Art

[0002] In the field of product design, especially for complex and systematic engineering products such as automobiles, the design process covers multiple aspects, including form design, planning, engineering, and general layout design, etc. Among these elements, the visual perception experience is crucial for the success of the product. Especially in the process of users' initial contact with the product and generating emotional identification, the visual perception stage often plays a decisive role and directly affects users' purchase decisions.

[0003] In recent years, with the rapid development of the market and the intensification of competition, new products have emerged continuously. The production and sales volume of some products (such as automobiles, mobile phones, computers, etc.) has been increasing year by year, and the demand for design creativity has also increased accordingly. Facing the dual pressures of industrial upgrading and user demands, product design work faces higher quality and higher efficiency requirements. However, although relevant research and practices have formed relatively stable design processes and technologies, there are still deficiencies in the research on creative design methods.

[0004] The existing product design research is mainly limited to using computer technology for prediction and the generation of design schemes. However, how to effectively integrate the personal experience and intuitive creativity of designers to enhance the value of design schemes is still an urgent problem to be solved. The experience and intuition of designers play an irreplaceable role in the creative process. However, how to combine these subjective factors with objective design processes and technologies to achieve more efficient and creative designs is a major challenge faced by the current product design field.

[0005] From the perspective of users' visual perception, the depth and comprehensiveness of the research on the laws of product shape design also need to be strengthened urgently. Previous research has mostly focused on the shape characteristics from a certain specific angle, lacking a comprehensive review and systematic research on the product shape. This not only limits the exertion of design creativity but also leads to a lack of scientific guidance in the design process. Especially for certain specific types of products, although there are relevant perception studies, the comprehensive research of qualitative and quantitative aspects is still insufficient, making it difficult to form a comprehensive and in-depth design guidance.

[0006] Therefore, in order to enhance the creativity and quality of product design and meet the dual challenges of industrial upgrading and user demands, it is necessary to strengthen the research on the laws of product shape design, especially starting from the perspective of users' visual perception, to conduct a comprehensive review and systematic research on the product shape. At the same time, it is also necessary to explore how to apply scientific design processes and technologies to integrate the personal experience and intuitive creativity of designers to enhance the value of design schemes. Summary of the Invention

[0007] The object of the present invention is to provide a product design system and related devices, which can efficiently integrate user perception evaluation and product shape features, automatically generate a product design scheme that meets the design expectations, comprehensively evaluate the scheme, and finally display it to the user for selection and further optimization.

[0008] The object of the present invention is achieved by the following technical solutions:

[0009] In a first aspect, the present application provides a product design system, which includes:

[0010] A database module for storing product information, perception evaluation vocabulary, and experimental data; the product information includes product models, shape elements, and shape features.

[0011] A mapping model acquisition module for acquiring a mapping model between product shape and perception evaluation.

[0012] A scheme generation module for generating a design scheme according to the design expectations through the mapping model.

[0013] A scheme evaluation module for evaluating the design scheme to obtain an evaluation result.

[0014] A display module for displaying the shape elements, design scheme, and evaluation result of the product.

[0015] Preferably, the mapping model acquisition module includes:

[0016] A shape set acquisition unit for acquiring a set of product shape elements through the shape features of each shape element of the product.

[0017] A perception evaluation acquisition unit for acquiring the semantic evaluation of each shape element of the product by the user and determining the user perception evaluation.

[0018] A model construction unit for constructing a mapping model between product shape and perception evaluation through the user perception evaluation and the set of product shape elements.

[0019] Preferably, the shape set acquisition unit includes:

[0020] A shape feature acquisition subunit for acquiring the shape features of each shape element of the product from different perspectives.

[0021] An index system establishment subunit for processing the shape features to obtain multiple shape feature indexes of each shape element, encoding each shape element, and establishing a shape feature index system through the shape feature indexes and the encodings of the corresponding shape elements.

[0022] A sorting subunit, configured to analyze the shape features of each shape element to obtain a priority sorting of the shape elements;

[0023] A first selection subunit, configured to obtain a focus shape element according to the priority sorting of the shape elements;

[0024] A clustering subunit, configured to process the shape features of the focus shape element by using a vector space model, and form a product shape feature set based on the shape elements through clustering analysis.

[0025] Preferably, the sorting subunit includes:

[0026] An objective sorting component, configured to obtain a sorting of each shape element of the product based on the results of a visual tracking experiment from different perspectives, and obtain an objective sorting result of the shape elements;

[0027] A subjective sorting component, configured to obtain a subjective sorting result of the shape features of each shape element;

[0028] A priority sorting component, configured to fuse the objective sorting result and the subjective sorting result to obtain a priority sorting of the final shape elements.

[0029] Preferably, the objective sorting component includes:

[0030] An experimental data acquisition sub-component, configured to obtain the mean values of the visual tracking experimental data of each shape element of the product from different perspectives when the subjects observe multiple products of the same type;

[0031] A first single-item sorting sub-component, configured to sort the mean values of the visual tracking experimental data of each shape element respectively from the same perspective, and obtain a first single-item sorting of the shape elements based on this item of data from this perspective;

[0032] An objective sorting sub-component, configured to obtain an objective sorting result of each shape element from this perspective according to the multiple first single-item sortings of multiple experimental data from the same perspective.

[0033] Preferably, the clustering subunit includes:

[0034] An input feature selection component, configured to obtain multiple features of a certain shape element of multiple products of the same type for a certain focus shape element; if the ratio of the number of times a certain feature appears in the product set is within a preset range, then use this feature as an input feature option for the space model;

[0035] A feature contribution degree acquisition component, configured to obtain the contribution degree of this feature by the number of products in which each input feature appears and the total number of products in the set of similar products;

[0036] Construct a spatial model of the shape features of the shape element based on the contribution degree of the features;

[0037] Based on the spatial model, perform clustering analysis on the shapes of multiple similar products from each perspective, and obtain the clustering results of the product shapes from each perspective.

[0038] Preferably, the solution generation module includes:

[0039] A design expectation acquisition unit for acquiring the design expectation of the user terminal;

[0040] A solution generation unit for automatically generating multiple design solutions of the product according to the design expectation through the mapping model.

[0041] Preferably, the display module includes:

[0042] A solution selection unit for selecting a design solution of an automatically generated product;

[0043] A solution display unit for displaying the selected design solution from each perspective;

[0044] A shape element selection unit for the shape elements of the product;

[0045] A shape element display unit for displaying the shape features corresponding to the shape elements;

[0046] An evaluation display unit for displaying the evaluations of each shape element and / or design solution.

[0047] In a second aspect, the present application provides a product device, and the product device includes:

[0048] A memory that stores a computer program;

[0049] A processor that implements the functions of the system described in the present application when executing the computer program;

[0050] A display for displaying the target product output by the processor.

[0051] In a third aspect, the present application provides a computer-readable storage medium that stores computer instructions, and when a computer reads the computer instructions, the computer implements the functions of any system described in the present application.

[0052] Compared with the prior art, the beneficial effects of the present invention at least include: storing a large amount of product information, perception evaluation vocabulary, and experimental data through the database module, providing a solid foundation for subsequent analysis and design. The mapping model acquisition module can accurately establish the association between the product appearance and perception evaluation, enabling the design scheme to closely fit the user's visual perception and needs. The scheme generation module can automatically generate multiple design schemes according to the user's design expectations through the mapping model, greatly improving the design efficiency and creativity. At the same time, the system can also automatically evaluate the design scheme, providing valuable feedback and suggestions for designers to further optimize the design scheme. The system can generate personalized design schemes according to the visual perception evaluation and needs of different users. By collecting and analyzing the semantic evaluations of users on various appearance elements of the product, the system can accurately grasp the user's preferences and expectations, thereby providing more customized products that meet the user's needs. The system sorts and clusters the importance of appearance elements through objective data such as visual tracking experiments and the subjective evaluations of users, providing scientific data support for design. This data-driven design method helps to discover the appearance elements and features that users truly care about, thereby optimizing product design. The display module shows the appearance factors, design schemes, and evaluation results of the product through intuitive graphics and interfaces. Users can easily select, view, and evaluate the design schemes through this module, improving the transparency and interactivity of the design. The design of each module and unit of the system is flexible and can be extended and optimized according to actual needs. For example, more perception evaluation vocabulary can be introduced, new experimental data can be added, or the construction method of the mapping model can be improved to adapt to the changing market demands and user preferences.

[0053] In summary, this product design system greatly improves the efficiency, accuracy, and personalization of product design through intelligent, data-driven, and visual methods, providing strong support and assistance for designers. Brief Description of the Drawings

[0054] Figure 1 is a schematic diagram of a product design system according to an embodiment of the present invention;

[0055] Figure 2 is a schematic diagram of a product design process according to an embodiment of the present invention;

[0056] Figure 3 is a schematic diagram of a display page of a product design system according to an embodiment of the present invention;

[0057] Figure 4 is another schematic diagram of a display page of a product design system according to an embodiment of the present invention. Detailed Embodiments

[0058] Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. Like reference numerals in the figures denote like or similar structures, and thus their repetitive description will be omitted.

[0059] In the present invention, the words describing the expression positions and directions are all illustrated by taking the accompanying drawings as examples, but can be changed according to needs, and all the changes made are included in the protection scope of the present invention.

[0060] This application provides a product design system, which includes:

[0061] A database module for storing product information, perception evaluation vocabulary, and experimental data; the product information includes product models, appearance elements, and appearance features.

[0062] A mapping model acquisition module for acquiring a mapping model between the product appearance and perception evaluation.

[0063] A solution generation module for generating a design solution according to the design expectation through the mapping model.

[0064] A solution evaluation module for evaluating the design solution to obtain an evaluation result.

[0065] A display module for displaying the appearance elements, design solutions, and evaluation results of the product.

[0066] The working principle and effects of the above technical solution are as follows: The system first stores a large amount of product information through the database module, and this information includes but is not limited to product models, appearance elements, and appearance features (such as shape, lines, proportion, etc.). At the same time, the database also stores perception evaluation vocabulary related to product design, and these vocabularies are used to describe the visual perception and emotional reactions of users to the product. In addition, experimental data (such as user research data, visual tracking data, etc.) is also stored in the database to support subsequent analysis and modeling;

[0067] Examples of the appearance elements of the product are as follows:

[0068] Smartphone: including screen, frame, camera, speaker, charging port, etc.

[0069] Notebook computer: including keyboard, touchpad, display screen, shell, heat dissipation port, power plug, etc.

[0070] The automobile appearance elements refer to various components and features that make up the appearance of the automobile, such as engine cover, front bumper, headlight, tire, etc.

[0071] This module utilizes the product information and perceptual evaluation vocabulary in the database, and constructs a mapping model between the product appearance and perceptual evaluation through advanced algorithms and technical means (such as machine learning, data mining, etc.). This model can accurately reflect the users' visual perception and emotional experience of different product appearances, providing an important basis for the subsequent generation of design schemes. After the user inputs the design expectations, the scheme generation module uses the mapping model to parse and transform the design expectations. Through intelligent algorithms and model predictions, the system can automatically generate multiple product design schemes that meet the design requirements. These schemes match the users' design expectations and perceptual evaluation vocabulary in terms of form, color, material, etc.

[0072] To ensure the quality and feasibility of the generated design schemes, the scheme evaluation module is used to obtain the users' evaluations of the design schemes. These evaluation criteria may include multiple aspects such as aesthetics, functionality, practicality, and market acceptance. Through evaluation, the system can generate evaluation results, indicating the advantages and disadvantages of each design scheme, providing a direction for subsequent optimization.

[0073] The display module visually displays the product's shape factors, design schemes, and evaluation results to the users. Users can view the design schemes from various perspectives through this module, understand the evaluation of each shape element and design scheme. Users can also select and modify the design schemes according to the displayed information, or provide feedback for the system to further optimize.

[0074] In summary, the product design system provided by this application integrates product information, perceptual evaluation vocabulary, and experimental data, constructs a mapping model between the product appearance and perceptual evaluation, and realizes the efficient and intelligent generation and evaluation of product design schemes. This system not only improves the efficiency and accuracy of product design, but also provides a more convenient and intuitive design tool and service for designers and users.

[0075] Refer to the attached Figure 2 , taking an automobile (SUV) as an example, the design process of the SUV is realized through the various modules of this system.

[0076] In some embodiments, the mapping model acquisition module includes:

[0077] A shape set acquisition unit, which is used to obtain the set of product shape elements through the shape characteristics of each shape element of the product;

[0078] A perceptual evaluation acquisition unit, which is used to obtain the semantic evaluations of each shape element of the product by users and determine the users' perceptual evaluations;

[0079] A model construction unit, which is used to construct a mapping model between the product appearance and perceptual evaluation through the users' perceptual evaluations and the set of product shape elements.

[0080] The working principle of the above technical solution is as follows: The shape set acquisition unit first identifies and extracts each shape element of the product, which are the basis for constituting the appearance and functional characteristics of the product. Then, for each shape element, the unit further analyzes its shape characteristics, and these factors may include size, shape, color, material, texture, etc. By integrating the shape characteristics of each shape element, a product shape set can be constructed.

[0081] The perception evaluation acquisition unit mainly focuses on the semantic evaluation of each shape element of the product by users; it usually involves the subjective feelings and cognitions of users regarding aspects such as the appearance, function, and quality of the product. To obtain these evaluations, the unit may adopt methods such as questionnaires, user interviews, visual tracking, etc. to collect the feedback and opinions of users on each shape element. By sorting out and analyzing these feedbacks, the unit can determine the visual perception evaluations of users on each shape element of the product, and these images usually manifest as a series of descriptive words or phrases.

[0082] After obtaining the product shape set and user perception evaluations, this unit begins to construct a mapping model between the product shape and perception evaluations. The goal of this model is to establish a mapping relationship between the product shape elements and user perception evaluations. In other words, it should be able to predict or explain how a given combination of product shape elements triggers specific user perception evaluations. To achieve this goal, the unit may adopt advanced algorithms and technical means (such as machine learning, data mining, neural networks, etc.) to perform matching and correlation analysis on the product shape set and user perception evaluations. Eventually, the unit can generate a highly accurate and reliable mapping model, which can provide strong support for subsequent design scheme generation and evaluation.

[0083] In summary, through the collaborative work of the shape set acquisition unit, perception evaluation acquisition unit, and model construction unit, the mapping model acquisition module can construct a mapping model that accurately reflects the relationship between the product shape and user perception evaluations. This model not only helps designers better understand user needs and market trends but also provides a scientific basis and decision-making support for product design and optimization.

[0084] Taking a car as an example, car shape elements refer to various components and characteristics that constitute the appearance of a car, such as the engine cover, front bumper, headlights, tires, etc. These elements jointly determine the appearance and style of the car. For each shape element, extract its unique shape characteristics; these factors can be the size, shape, lines, proportion, etc. of the form, which are used to describe and distinguish different car forms; according to the extracted shape characteristics, car forms are classified into different types or sets.

[0085] Taking a smartphone as an example, the external form elements of a smartphone refer to various components and features that make up the appearance of the phone, such as the screen, the material of the back cover, the camera module, the button layout, etc. These elements together determine the appearance and style of the smartphone.

[0086] For each external form element, we can extract its unique external form features. For example:

[0087] Screen: size (diagonal length), resolution, screen-to-body ratio (i.e., the ratio of the screen area to the overall area of the phone), degree of curvature, etc.

[0088] Back cover material: metal, glass, plastic, ceramic, etc., as well as characteristics such as the luster and touch presented by these materials.

[0089] Camera module: the number of cameras, the arrangement, the pixel count, the aperture size, etc., as well as the coordination of the camera module with the overall design of the phone.

[0090] Button layout: the distinction between physical buttons and virtual buttons, the size, shape, position, and touch of the buttons, etc.

[0091] Based on these extracted external form features, we can divide the smartphone forms into different types or sets. For example:

[0092] Full-screen phones, foldable phones, phones with prominent cameras, phones with a metallic texture.

[0093] By obtaining the views and feelings of users on different product forms (such as words like "trendy", "energetic", "business", etc.); and organizing and analyzing them. Through statistics and induction, determine the visual perception evaluation of users on different automotive external form elements.

[0094] The effects of the above technical solution are: by deeply analyzing the external form features of each external form element of the product, the external form set acquisition unit can accurately capture the appearance and functional features of the product, providing basic data for subsequent design and evaluation. This unit can quickly integrate the features of all external form elements, construct a complete product external form set, thereby shortening the design cycle and improving the design efficiency. Through in-depth analysis and excavation of the product external form set, designers can discover new design inspirations and creative points, promoting the innovation and development of product design.

[0095] In some embodiments, the external form set acquisition unit includes:

[0096] An external form feature acquisition subunit, which acquires the external form features of each external form element of the product from different perspectives;

[0097] The index system establishment subunit processes the shape features to obtain multiple shape feature indexes of each shape element, encodes each shape element, and establishes a shape feature index system through the shape feature indexes and the encodings of the corresponding shape elements;

[0098] The sorting subunit is used to analyze the shape features of each shape element to obtain the priority sorting of the shape elements;

[0099] The first selection subunit is used to obtain the focus shape elements according to the priority sorting of the shape elements;

[0100] The clustering subunit is used to process the shape features of the focus shape elements by using the vector space model and form a product shape feature set based on the shape elements through clustering analysis.

[0101] The working principle of the above technical solution is as follows: The shape feature acquisition subunit is mainly responsible for capturing the shape elements of the product from multiple perspectives (such as the front, side, top, etc.) and extracting the shape features of these shape elements. These features may include dimensions, shapes, colors, textures, etc. By using advanced image processing and computer vision technologies, this subunit can automatically identify and extract the shape features of the product from different perspectives, providing the basic data for subsequent processing and analysis.

[0102] After obtaining the shape features of the product, the index system establishment subunit processes these features to extract representative and discriminative shape feature indexes; this subunit also encodes each shape element so that they can be uniquely identified in subsequent analysis and processing. By combining the shape feature indexes and the encodings of the corresponding shape elements, this subunit can establish a complete shape feature index system. This system not only reflects the shape features of the product but also provides convenience for subsequent analysis and processing.

[0103] The main task of the sorting subunit is to analyze the shape features of each shape element to determine their importance.

[0104] This subunit may use various methods (such as principal component analysis, independent component analysis, etc.) to evaluate the importance of the shape elements and sort them according to the evaluation results. Through sorting, this subunit can identify which shape elements have a greater impact on the overall form of the product, thus providing the focus objects for subsequent processing.

[0105] According to the priority sorting results provided by the sorting subunit, the first selection subunit will screen out the focus shape elements. These focus shape elements are usually the elements that have an important impact or significant features on the overall form of the product, so they deserve more attention in subsequent analysis and processing.

[0106] The clustering subunit mainly processes the shape features of the focus shape elements using the vector space model. In the vector space model, each shape element can be represented as a vector, and the components of the vector correspond to different shape feature indicators. By calculating the distance or similarity between vectors, the clustering subunit can divide the shape elements into different categories or clusters. These categories or clusters reflect different types or styles of the product shape, thus forming a set of product shape features based on the shape elements.

[0107] In summary, through the collaborative work of the shape set acquisition unit, the shape feature acquisition subunit, the index system establishment subunit, the sorting subunit, the first selection subunit, and the clustering subunit, the shape elements and their features of the product can be accurately obtained, and a complete shape feature index system can be established. At the same time, through sorting and clustering analysis, this unit can also identify the focus shape elements and the product shape feature set, providing strong support for subsequent design and analysis.

[0108] In some specific applications, to better display the morphological characteristics of the product, the product can be analyzed from a three-dimensional space perspective; the elements can be analyzed from three perspectives: the front, the side, and the back (rear) respectively to obtain the characteristics of each morphological element; and the morphological elements can be encoded to establish a shape feature index system.

[0109] Taking a mobile phone as an example: Each index corresponds to a code, which is convenient for directly finding the corresponding morphology according to the code, as shown in Table 1:

[0110] Table 1

[0111]

[0112] In some embodiments, the sorting subunit includes:

[0113] An objective sorting component for obtaining the objective sorting result of the shape elements of the product based on the results of visual tracking experiments from different perspectives.

[0114] A subjective sorting component for obtaining the subjective sorting result of the shape features of each shape element.

[0115] A priority sorting component for fusing the objective sorting result and the subjective sorting result to obtain the priority sorting of the final shape elements.

[0116] The working principle and effect of the above technical solution are as follows:

[0117] The objective sorting component works based on the results of visual tracking experiments. Visual tracking technology can record the movement trajectories and fixation point distributions of the user's eyes when observing the product, thereby reflecting the user's visual attention and points of interest on the product. From different perspectives, the objective sorting component analyzes the visual tracking data to determine which shape elements attract more attention and focus from the user. By statistically analyzing this data, the component can sort the various shape elements of the product and obtain an objective sorting result based on the user's visual attention.

[0118] The subjective sorting component focuses on obtaining subjective evaluations from users or experts regarding the shape characteristics of the various shape elements of the product. This may involve various forms such as questionnaires, user interviews, and expert scoring, aiming to collect the subjective perceptions and comprehensive evaluations of users regarding the shape element characteristics (such as aesthetics, functionality, innovation, etc.). Based on these subjective evaluation data, the component calculates the subjective comprehensive weight of each shape element and conducts a sorting to obtain a subjective sorting result.

[0119] The priority sorting component's task is to fuse the objective sorting result and the subjective sorting result to obtain the final priority sorting of the shape elements. This involves various fusion strategies such as weighted average, maximum-minimum value selection, fuzzy comprehensive evaluation, etc. The choice of the specific strategy depends on the actual application scenario and requirements analysis. Through fusion, the component can comprehensively consider both aspects of the user's visual attention (objective) and the user / expert subjective evaluation (subjective) to obtain a more comprehensive and accurate priority sorting of the shape elements.

[0120] The comprehensive workflow is as follows:

[0121] First, the objective sorting component and the subjective sorting component respectively collect visual tracking data and subjective evaluation data.

[0122] Based on the collected data, the two components respectively conduct a preliminary sorting to obtain the objective sorting result and the subjective sorting result.

[0123] The priority sorting component fuses the two preliminary sorting results to obtain the final priority sorting of the shape elements.

[0124] The final sorting result can be used to guide product design, optimization, and improvement, as well as provide important references for product evaluation and market analysis. Through this process, the sorting subunit can comprehensively consider both aspects of the user's visual attention and subjective evaluation to obtain a more accurate and comprehensive priority sorting result of the shape elements, providing strong support for product design and optimization.

[0125] In some embodiments, the objective sorting component includes:

[0126] An experimental data acquisition sub-component, which is used to obtain the mean values of various items of visual tracking experimental data of each external form element of the product from different perspectives when the subject observes multiple products of the same type;

[0127] A first single-item sorting sub-component, which is used to sort the mean values of various items of visual tracking experimental data of each external form element respectively under the same perspective, so as to obtain the first single-item sorting of the external form elements based on this item of data under this perspective;

[0128] An objective sorting sub-component, which is used to obtain the objective sorting result of each external form element under this perspective according to multiple first single-item sortings of multiple experimental data under the same perspective.

[0129] The principles and effects of the above technical solutions are as follows:

[0130] The experimental data acquisition sub-component obtains the mean values of various items of visual tracking experimental data of each external form element of the product from different perspectives when the subject observes multiple products of the same type. This sub-component uses professional visual tracking experimental equipment to record the eye movement trajectories of the subject when observing the product. The recorded data is processed to extract the key visual tracking indicators of the subject when observing each external form element, such as fixation time, fixation count, pupil diameter, etc. Calculate the mean values of these key visual tracking indicators as the basis for subsequent sorting.

[0131] The first single-item sorting sub-component sorts the mean values of various items of visual tracking experimental data of each external form element respectively under the same perspective, so as to obtain the first single-item sorting of the external form elements based on this item of data under this perspective. This sub-component receives the mean values of visual tracking experimental data provided by the experimental data acquisition sub-component. For the data under each perspective, sort them respectively according to different visual tracking indicators (such as fixation time, fixation count, etc.). The sorting result is the first single-item sorting of the external form elements based on this item of data under this perspective, which reflects the degree of attention of the subject to each external form element under this perspective. According to multiple first single-item sortings of multiple experimental data under the same perspective, obtain the objective sorting result of each external form element under this perspective.

[0132] This sub-component receives multiple first single-item sorting results provided by the first single-item sorting sub-component. Conduct a comprehensive analysis of these first single-item sorting results, considering the weights and mutual influences between different visual tracking indicators. Use appropriate algorithms (such as weighted average, principal component analysis, etc.) to fuse multiple first single-item sorting results into a comprehensive sorting result. This comprehensive sorting result reflects the comprehensive degree of attention of the subject to each external form element under this perspective, providing an objective basis for product design and optimization.

[0133] The objective sorting component processes and analyzes the data by obtaining the visual tracking experiment data of the subjects, using the first single-item sorting sub-component and the objective sorting sub-component, and finally obtains the objective sorting results of each shape element. This process provides a scientific basis for product design and optimization, and helps to improve the user experience and market competitiveness of the product.

[0134] Taking a mobile phone as an example:

[0135] Table 2

[0136]

[0137] The subjective evaluation mainly uses the analytic hierarchy process. According to the criteria of the analytic hierarchy process, the indicators of each level of the product form are formed, the weights of the relevant indicators are determined, and the priority ranking of the indicators is completed. As shown in Table 3:

[0138] Table 3

[0139]

[0140] Integrate the sorting results of the objective experimental data and the subjective evaluation to obtain the final priority ranking of the shape elements

[0141] The effects of the above technical solutions are as follows: Sorting the means of the visual tracking experiment data from the same perspective can reflect the degree of attention of users to each shape element from this perspective, avoiding the contingency of a single data point. By comprehensively considering the sorting results of multiple experimental data, a more comprehensive and accurate objective sorting of the shape elements can be obtained, improving the accuracy and objectivity of the sorting. By obtaining the subjective evaluation of users on the shape elements, it can reflect the personal preferences and comprehensive evaluations of users on the characteristics of the shape elements, providing a subjective basis for sorting. Integrating the objective sorting results and the subjective sorting results can comprehensively consider both the visual attention of users and the subjective evaluation, and obtain a more comprehensive and scientific priority ranking of the shape elements. This integration not only improves the accuracy of the sorting, but also better meets the needs and expectations of users, providing strong support for product design and optimization.

[0142] Through the priority ranking of the form elements obtained by the sorting subunit, designers can more clearly understand the degree of attention and preferences of users for product form elements, thereby more accurately grasping user needs during the design process, enhancing the attractiveness and competitiveness of products. By optimizing the design of product form elements to make them more in line with users' visual attention and subjective evaluations, it can improve users' usage experience and satisfaction, and enhance users' loyalty and stickiness to the product. Through the priority ranking of form elements provided by the sorting subunit, the R & D team can more quickly determine the priorities and key points of product design, thereby shortening the R & D cycle and improving R & D efficiency. By optimizing product design and reducing unnecessary form elements and redundant functions, it can reduce the production cost and R & D cost of products, and improve the economic benefits and market competitiveness of enterprises.

[0143] In summary, the beneficial effects of the sorting subunit and its components are mainly reflected in improving the accuracy and objectivity of sorting, integrating subjective and objective evaluations to enhance the comprehensiveness of sorting, optimizing product design and user experience, and improving R & D efficiency and reducing costs. These beneficial effects jointly promote the scientific and precise process of product design and optimization.

[0144] In some embodiments, the clustering subunit includes:

[0145] An input feature selection component, which is used to obtain multiple features of a certain form element of multiple products of the same type for a certain focus form element; if the ratio of the number of times a certain feature appears in the product set is within a preset range, then this feature is used as an input feature option for the spatial model;

[0146] A feature contribution degree acquisition component, which is used to obtain the contribution degree of a feature through the number of products in which each input feature appears and the total number of products in the set of products of the same type;

[0147] Wgi = Fgi * log(M / (Pgi + 1))

[0148] Wgi is the contribution degree of feature i in product category g; Fi is the number of times feature i appears in the set of product category g; M is the total number of products in the set of product category g; Pgi is the number of files containing feature i in the set of product category g;

[0149] Based on the contribution degree of the feature, a spatial model of the form features of this form element is constructed;

[0150] Based on the spatial model, cluster analysis is performed on the forms of multiple products of the same type from each perspective respectively, and the clustering results of the product forms from each perspective are obtained.

[0151] The working principle of the above technical solution is: for a certain focus form element, multiple features of this form element are extracted from multiple products of the same type.

[0152] Select a certain shape element as the analysis object, such as the screen of a smartphone; the keyboard of a laptop; the headlight of a car, etc.

[0153] Collect data of multiple products of the same type, including product pictures, description information, user evaluations, etc. Use technical means such as image processing and text mining to extract multiple features related to the selected shape element from the data.

[0154] The determination of feature items is the key to determining the vector space. The shape features of the products summarized in the previous step can be used to define the feature vector space according to these features. The number of these features is relatively large. If all are used as different feature items, it is the simplest approach, but this approach is likely to obtain a vector space with a relatively high complexity in the research. Such a vector space not only has a large amount of calculation but may also result in insignificant clustering results due to too many relatively meaningless features. Therefore, it is necessary to minimize the number of features to be processed as much as possible to reduce the dimension of the vector space, and try to select representative shape features as vector dimensions to improve the speed of subsequent product feature comparison. For the selection of feature elements, generally retain the shapes that have an important influence on the vehicle form as the coordinate basis of the vector space.

[0155] Count the number of times each feature appears in all products. If the number of occurrences of a certain feature is within a preset range (such as higher than a certain threshold or lower than a certain threshold, specifically set according to actual needs), then use this feature as an input feature option for the space model.

[0156] Calculate the contribution degree of each feature through the number of products in which the input feature appears and the total number of products in the set of similar products.

[0157] Calculate the number of times each feature appears in all products, that is, how many products have this feature.

[0158] Calculate the total number of products in the set of similar products, that is, the reciprocal of the proportion of products containing this feature in all products, which reflects the rarity of this feature.

[0159] Combine the number of occurrences of the feature and the total number of products in the set of similar products, and use a certain algorithm (such as TF-IDF, entropy weight method, etc.) to calculate the contribution degree of each feature. The higher the contribution degree, the greater the importance of this feature in the shape element.

[0160] Build a space model of the shape features of this shape element based on the contribution degree of the features.

[0161] Use the selected input features as the dimensions of the space model, and each feature corresponds to one dimension.

[0162] Determine the importance of this dimension in the spatial model according to the contribution degree of each feature.

[0163] Construct a multi-dimensional space, where the position of each product in this space is jointly determined by the characteristic values (after standardization) and contribution degrees of its shape elements.

[0164] Based on the spatial model, perform clustering analysis on the shapes of multiple similar products from different perspectives.

[0165] Select a suitable clustering algorithm (such as K-means, DBSCAN, hierarchical clustering, etc.), and set clustering parameters (such as the number of clusters, distance metric method, etc.) according to actual needs. From each perspective, input the characteristic values of the shapes of multiple similar products into the spatial model to obtain their positions in the multi-dimensional space.

[0166] Use the clustering algorithm to perform clustering analysis on the positions of products in the multi-dimensional space to obtain the clustering results of the product shapes from different perspectives. The clustering results reflect the similarities and differences between product shapes from different perspectives.

[0167] The clustering subunit realizes the clustering analysis of a certain focal shape element of multiple products of the same type through four links: input feature selection, feature contribution degree acquisition, spatial model construction, and clustering analysis. This process provides a scientific basis for product design and optimization, helps enterprises better grasp market demands and user preferences, and enhances the competitiveness and market share of products.

[0168] Cluster each vehicle model using the proximity of features to find groups with similar features.

[0169] For example: Set the spatial model of the corresponding dimension for the important shape features of SUVs. Through the analysis results of the contribution degree of each feature to this vehicle type; for example, features such as the shape of the front lights (grille), the overall shape of the front view, the front face shape, and the front light shape have higher importance in the front view, and a main spatial model can be established based on relevant indicators. Cluster the SUV vehicle models using the proximity of features to find groups with similar features. For the analysis of the side shape of SUVs, the importance order of the side view shape features of SUV vehicles is: the overall shape of the side view, the waistline shape, the front side projection shape, the rear side projection shape, the side window shape, the bottom skirt shape, and the wheel hub shape; preferentially select the shape indicators with higher importance as the dimensions for establishing the SUV side view shape space.

[0170] For example, a spatial model is set for the important external features of a mobile phone in corresponding dimensions. Based on the analysis results of the contribution of each feature to this model; for example, the number and shape of the cameras have a high contribution in the rear view, and a spatial model of the main body can be established according to relevant indicators. The mobile phones are clustered using the proximity of features to find groups with similar features.

[0171] The effects of the above technical solution are as follows: Through the input feature selection component, multiple features related to specific external elements can be accurately extracted from multiple products of the same type. This not only reduces the complexity of the data but also improves the accuracy of the analysis. The feature contribution degree acquisition component scientifically calculates the contribution degree of each feature by using the number of products in which each input feature appears and the total number of products in the set of similar products. This step ensures that the importance of each dimension in the spatial model is reasonably reflected, thereby improving the accuracy of the clustering analysis. Based on the contribution degree of the features, a multi-dimensional spatial model is constructed, where the position of each product in this space is jointly determined by the feature values and contribution degrees of its external elements. This model provides a solid foundation for the subsequent clustering analysis. Advanced clustering algorithms such as K-means and DBSCAN are used to perform clustering analysis on the positions of products in the multi-dimensional space. This not only improves the intelligence level of the clustering analysis but also makes the analysis results more objective and accurate. Through the clustering analysis, the similarities and differences between the external shapes of products can be clearly seen from different perspectives. This helps enterprises or designers better grasp the market demand and user preferences, so as to design products that better meet the user needs.

[0172] In some embodiments, the solution generation module includes:

[0173] A design expectation acquisition unit for acquiring the design expectation of the user terminal;

[0174] A solution generation unit for automatically generating multiple design solutions for the product according to the design expectation through the mapping model.

[0175] The design expectation is obtained by acquiring the selection result of the input or menu option selected by the user terminal; the design expectation can be the design style. The user can input the design expectation through the user terminal (such as a computer, mobile phone, etc.), or provide design information by uploading design sketches, description files, etc. The design expectation acquisition unit will receive and parse this information to provide a basis for the subsequent generation of design solutions.

[0176] The solution generation unit first analyzes the design expectations, extracts the key design parameters and requirements. According to these design expectations, the mapping model searches for matching design elements and rules in its internal knowledge base or database, and conducts reasoning and combination. After a series of reasoning and combination, the mapping model generates multiple possible design solutions. These solutions may include different appearance styles, functional layouts, etc.

[0177] In some embodiments, the display module includes:

[0178] A solution selection unit for selecting a design solution of a certain automatically generated product;

[0179] A solution display unit for displaying the selected design solution from various perspectives;

[0180] An outer shape element selection unit for the outer shape elements of the product;

[0181] An outer shape element display unit for displaying the outer shape features corresponding to the outer shape elements;

[0182] An evaluation display unit for displaying the evaluations of each outer shape element and / or design solution;

[0183] A perceptual vocabulary database display unit for displaying visual evaluation vocabulary.

[0184] By means of an algorithm or manual user input, one or more design solutions are selected from a pre-generated or real-time generated product design solution library as the object to be currently displayed. This unit may involve techniques such as database query, algorithm recommendation, or user interface interaction. Using three-dimensional rendering technology, virtual reality (VR) or augmented reality (AR) and other technologies, the selected design solution is displayed from multiple perspectives (such as the front, side, top, bottom, and rotating perspectives). This helps users comprehensively understand the appearance and structural design of the product.

[0185] A user interface is provided to allow users to select each component or design element of the product from a preset outer shape element library. These outer shape elements may include color, material, shape, texture, etc. Users can select by dragging, clicking, or inputting, etc. When the user selects a certain outer shape element, this unit will display the outer shape features corresponding to the element, such as the shape outline, etc. This can be displayed in the form of images, videos, or three-dimensional models, etc., to help users more intuitively understand the effects of each element.

[0186] Based on user feedback, expert evaluation, or algorithm evaluation, etc., the evaluation information of each outer shape element and / or design solution is collected and displayed. The evaluation may include aesthetic evaluation, functional evaluation, cost-benefit analysis, etc. This unit conveys the advantages and disadvantages of the design solution to users in the form of charts, scores, or text descriptions.

[0187] The implementation effects of this display module are mainly reflected in the following aspects:

[0188] Through intuitive 3D displays and interactive interfaces, users can more easily understand product design solutions and form elements, thereby improving user satisfaction and engagement. By providing comprehensive design information and evaluation data, users can make design decisions more quickly, reducing hesitation and repetition during the design process. The form element selection unit provides users with a wealth of design options, stimulating users' creativity and imagination, and contributing to the generation of more innovative design solutions. This module integrates the processes of generating, displaying, and evaluating design solutions, forming an efficient design process that helps reduce design costs and improve design efficiency. By sharing design information and evaluation data in the display module, team members can communicate and collaborate better, jointly promoting the progress of design projects.

[0189] Refer to the appendix Figures 3 - 4 , taking the design of an automobile (SUV) as an example;

[0190] The interface includes functional areas such as a form factor display area, a solution (goal) display area, a perceptual image evaluation area, an upload and download area, etc.

[0191] (1) The form factor display area shows the form features of the SUV product from three main perspectives: front view, side view, and rear view, and each form factor has established a corresponding association relationship with the corresponding perceptual image vocabulary. In this area, the form factors can be adjusted and optimized according to the design object to ensure the accuracy of the relevant form factors.

[0192] In this area, the form factors can be adjusted and optimized according to the design object to ensure the accuracy of the relevant form factors.

[0193] (2) The solution (goal) display area mainly shows corresponding design combination solutions, image evaluation vehicles, and designer-derived design solutions, etc.

[0194] (3) The perceptual image evaluation area includes two drop-down menus: perceptual image vocabulary and perceptual evaluation. Relevant perceptual vocabulary can be deleted and added in combination with the perceptual research of design expectations. The perceptual evaluation operation is carried out for the evaluation targets in the display area. The 7-point Likert scale is used to score the relevant solutions. The corresponding score can be obtained by dragging the slider left and right. The system platform will statistically analyze the scores of each participant, improving the evaluation efficiency.

[0195] (4) The function of the upload and download area is to meet the need for local data exchange between the UVPIDES system and the client. Users can upload relevant target models and designer-derived design solutions, and can also download relevant system-generated solutions, etc.

[0196] An embodiment of the present application further provides a product device, which includes a memory, a processor, and a display. The memory stores a computer program, and when the processor executes the computer program, it implements the steps of any of the methods in the embodiments of the present application or the functions of the device as described in the embodiments of the present application; the display is used to display the target product output by the processor.

[0197] An embodiment of the present application further provides a computer-readable storage medium, which is used to store a computer program. When the computer program is executed, it implements the steps of any of the methods in the embodiments of the present application. Its specific implementation manner is consistent with the implementation manner and the achieved technical effects described in the above method embodiments, and some contents will not be elaborated here.

[0198] In the present application, the readable storage medium may be any tangible medium that contains or stores a program, and this program can be used by or in conjunction with an instruction execution system, apparatus, or device. The program product may adopt any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the readable storage medium include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0199] A computer-readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries the readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. The readable storage medium may also be any readable medium that can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical fiber cable, RF, etc., or any suitable combination of the foregoing. The program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and also including conventional procedural programming languages such as the C language or similar programming languages. The program code may be executed entirely on the user computing device, partially on an associated device, executed as a stand-alone software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or, alternatively, may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0200] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention without departing from the principles and spirit of the present invention, and all such changes should fall within the scope of protection of the claims of the present invention.

Claims

1. A product design system, characterized in that, The system includes: A database module for storing product information, perception evaluation vocabulary, and experimental data; the product information includes product model, shape elements, and shape features. A mapping model acquisition module for acquiring the mapping model between product shape and perception evaluation. A design scheme generation module for generating a design scheme according to the design expectation through the mapping model. A design scheme evaluation module for evaluating the design scheme to obtain an evaluation result. A display module for displaying the shape elements of the product, the design scheme, and the evaluation result.

2. The product design system according to claim 1, characterized in that, The mapping model acquisition module includes: A shape set acquisition unit for acquiring a set of product shape elements through the shape features of each shape element of the product. A perception evaluation acquisition unit for acquiring the semantic evaluation of each shape element of the product by users to determine the user perception evaluation. A model construction unit for constructing the mapping model between product shape and perception evaluation through the user perception evaluation and the set of product shape elements.

3. The product design system according to claim 2, wherein, The shape set acquisition unit includes: A shape feature acquisition subunit for acquiring the shape features of each shape element of the product from different perspectives. An index system establishment subunit for processing the shape features to obtain multiple shape feature indexes of each shape element, encoding each shape element, and establishing a shape feature index system through the shape feature indexes and the encodings of the corresponding shape elements. A sorting subunit for analyzing the shape features of each shape element to obtain the priority sorting of the shape elements. A first selection subunit for obtaining the focus shape element according to the priority sorting of the shape elements. A clustering subunit for processing the shape features of the focus shape element using the vector space model and forming a product shape feature set based on the shape elements through clustering analysis.

4. The product design system according to claim 3, characterized in that, The sorting subunit includes: An objective sorting component for obtaining the objective sorting result of the shape elements of the product based on the results of the visual tracking experiment from different perspectives. A subjective sorting component for obtaining the subjective sorting result of the shape features of each shape element. A priority sorting component for fusing the objective sorting result and the subjective sorting result to obtain the priority sorting of the final shape elements.

5. The product design system according to claim 4, wherein The objective sorting component includes: An experimental data acquisition sub-component for acquiring the mean values of the visual tracking experiment data of each shape element of the product by the subjects from different perspectives when observing multiple products of the same type. A first single-item sorting sub-component for sorting the mean values of the visual tracking experiment data of each shape element respectively from the same perspective to obtain the first single-item sorting of the shape elements based on this item of data from this perspective. An objective sorting sub-component for obtaining the objective sorting result of each shape element from this perspective according to the multiple first single-item sortings of multiple experimental data from the same perspective.

6. The product design system according to claim 3, wherein The clustering subunit includes: An input feature selection component, which is used to obtain multiple features of a certain shape element of multiple products of the same type for a certain focus shape element; if the ratio of the number of times a certain feature appears in the product set is within a preset range, then this feature is used as an input feature option for the spatial model; A feature contribution degree acquisition component, which is used to obtain the contribution degree of a feature by the number of products in which each input feature appears and the total number of products in the product set of the same type; A spatial model construction component, which is used to construct a spatial model of the shape features of this shape element based on the contribution degree of the features; A clustering component, which is used to perform clustering analysis on the shapes of multiple products of the same type from each perspective based on the spatial model, and obtain the clustering results of the product shapes from each perspective.

7. The product design system according to claim 1, wherein The solution generation module includes: A design expectation acquisition unit, which is used to acquire the design expectation of the user terminal; A solution generation unit, which is used to automatically generate multiple design solutions of the product according to the design expectation through the mapping model.

8. The product design system according to claim 1, wherein, The display module includes: A solution selection unit, which is used to select a design solution of a certain automatically generated product; A solution display unit, which is used to display the selected design solution from each perspective; A shape element selection unit, which is used for the shape elements of the product; A shape element display unit, which is used to display the shape features corresponding to the shape elements; An evaluation display unit, which is used to display the evaluations of each shape element and / or design solution.

9. A product device, characterized in that, The product device includes: A memory, which stores a computer program, A processor, which realizes the functions of the system according to any one of claims 1-8 when executing the computer program; A display, which is used to display the target product output by the processor.

10. A computer-readable storage medium, characterized in that, The storage medium stores computer instructions, and when the computer reads the computer instructions, it realizes the functions of the system according to any one of claims 1-8.

Images