Garment customization 3D simulation and process sheet automatic generation method based on artificial intelligence

Abstract

The invention is suitable for the technical field of garment customization, and particularly relates to a garment customization 3D simulation and process sheet automatic generation method based on artificial intelligence, and the method comprises the steps: providing basic data support through obtaining garment customization parameters; three-dimensional parameter modeling is carried out based on the garment customization parameters, a three-dimensional fitting model corresponding to the garment customization parameters is determined, and the garment upper body effect is visually displayed; performing discrete grid division on the three-dimensional fitting model to obtain a first triangular grid topology corresponding to the three-dimensional fitting model; performing physical constraint iteration on the first triangular mesh topology based on the garment customization parameters to obtain a second triangular mesh topology corresponding to the three-dimensional fitting model; based on the second triangular mesh topology, a customization process sheet corresponding to the garment customization parameters is obtained, simulation and process sheet integration is achieved, the garment making efficiency and quality are effectively improved, and cut-part sewing errors are reduced.

Description

Technical Field

[0001] This application belongs to the technical field of clothing customization, and particularly relates to a method for automatically generating 3D simulation and process sheets for clothing customization based on artificial intelligence. Background Art

[0002] Clothing customization is a personalized service that starts from demand communication, body measurement, design confirmation, fabric selection to production, quality inspection, delivery and after-sales according to specific customer needs. Its advantages lie in meeting personalized needs, ensuring a perfect fit, and providing high-quality craftsmanship, and it is widely applicable to various scenarios such as business formal wear, wedding and special occasion clothing, work uniforms, and fashion items.

[0003] Traditional clothing customization technologies often use static model simulation or sparse grids and particle springs for dynamic simulation in 3D simulation. They only focus on the conversion between 3D simulation and 2D patterns, ignoring the integrated process of 3D simulation and process sheets. The lack of accurate and effective conversion means between the simulation model and the process sheet leads to a long customization cycle and a high error rate in cutting and sewing, restricting the online development space for complex styles. Summary of the Invention

[0004] The embodiments of this application provide a method for automatically generating 3D simulation and process sheets for clothing customization based on artificial intelligence, which can solve the problems in the clothing customization process that due to the lack of effective conversion means between the simulation model and the process sheet, the customization cycle is long, the error rate of cutting and sewing is high, and the online development space for complex styles is restricted.

[0005] In a first aspect, the embodiments of this application provide a method for automatically generating 3D simulation and process sheets for clothing customization based on artificial intelligence, including: Obtaining clothing customization parameters; Performing three-dimensional parametric modeling based on the clothing customization parameters to determine a three-dimensional fitting model corresponding to the clothing customization parameters; Performing discrete grid division on the three-dimensional fitting model to obtain a first triangular grid topology corresponding to the three-dimensional fitting model; Performing physical constraint iteration on the first triangular grid topology based on the clothing customization parameters to obtain a second triangular grid topology corresponding to the three-dimensional fitting model; Based on the second triangular grid topology, obtaining a customized process sheet corresponding to the clothing customization parameters.

[0006] The method for automatically generating 3D simulation and process sheets for clothing customization based on artificial intelligence provided by the embodiments of the present application provides basic data support by obtaining clothing customization parameters. Three-dimensional parametric modeling is performed based on the clothing customization parameters to determine the three-dimensional fitting model corresponding to the clothing customization parameters, intuitively preview the upper body effect of the clothing, adjust the design plan in advance, and avoid the cost of modification after production. The three-dimensional fitting model is discretely meshed to obtain the first triangular mesh topology corresponding to the three-dimensional fitting model, laying a mesh foundation for accurate physical simulation and cutting analysis. Physical constraint iteration is performed on the first triangular mesh topology based on the clothing customization parameters to obtain the second triangular mesh topology corresponding to the three-dimensional fitting model, ensuring that the clothing pattern conforms to the physical characteristics of the fabric and the dynamic requirements of human body wearing. Based on the second triangular mesh topology, the customized process sheet corresponding to the clothing customization parameters is obtained to guide the clothing production process, realizing the integration of simulation and process sheet, effectively improving the clothing production efficiency and quality, and reducing the cutting and sewing error.

[0007] In a second aspect, the embodiments of the present application provide a system for automatically generating 3D simulation and process sheets for clothing customization based on artificial intelligence, including: An acquisition unit for acquiring clothing customization parameters; A modeling unit for performing three-dimensional parametric modeling based on the clothing customization parameters to determine the three-dimensional fitting model corresponding to the clothing customization parameters; A partitioning unit for discretely meshing the three-dimensional fitting model to obtain the first triangular mesh topology corresponding to the three-dimensional fitting model; An iteration unit for performing physical constraint iteration on the first triangular mesh topology based on the clothing customization parameters to obtain the second triangular mesh topology corresponding to the three-dimensional fitting model; A generation unit for obtaining the customized process sheet corresponding to the clothing customization parameters based on the second triangular mesh topology.

[0008] In a third aspect, the embodiments of the present application provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method described in any item of the first aspect above is implemented.

[0009] In a fourth aspect, the embodiments of the present application provide a computer program product. When the computer program product runs on a terminal device, the terminal device is enabled to execute the method described in any item of the first aspect above.

[0010] It can be understood that the beneficial effects of the second to fourth aspects above can refer to the relevant descriptions in the first aspect above and will not be repeated here. Description of the Drawings

[0011] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0012] Figure 1 It is a schematic flowchart of a method for 3D simulation and automatic generation of process sheets for clothing customization based on artificial intelligence provided by an embodiment of the present application; Figure 2 It is a schematic diagram of a three-dimensional virtual fitting model in a method for 3D simulation and automatic generation of process sheets for clothing customization based on artificial intelligence provided by an embodiment of the present application; Figure 3 It is a schematic diagram of a process sheet in a method for 3D simulation and automatic generation of process sheets for clothing customization based on artificial intelligence provided by an embodiment of the present application; Figure 4 It is a schematic structural diagram of a system for 3D simulation and automatic generation of process sheets for clothing customization based on artificial intelligence provided by an embodiment of the present application; Figure 5 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0013] In the following description, for the purpose of illustration rather than limitation, specific details such as specific system structures and technologies are proposed to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0014] It should be understood that when used in the specification and the appended claims of the present application, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0015] It should also be understood that the term " / and" as used in the specification and the appended claims of the present application refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0016] As used in the specification and claims of this application, the term "if" may be construed contextually as "when" or "once" or "in response to determining" or "in response to detecting". Similarly, the phrases "if determined" or "if the described condition or event is detected" may be construed contextually to mean "once determined" or "in response to determining" or "once the described condition or event is detected" or "in response to detecting the described condition or event".

[0017] In addition, in the description of the specification and claims of this application, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be construed as indicating or implying relative importance.

[0018] The reference to "one embodiment" or "some embodiments" or the like described in the specification of this application means that a particular feature, structure, or characteristic described in connection with that embodiment is included in one or more embodiments of this application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in another way. The terms "comprising", "including", "having", and their variants all mean "including but not limited to", unless otherwise specifically emphasized in another way.

[0019] In the 3D simulation of traditional clothing customization technology, static model simulation dominates, overemphasizing the conversion between 3D simulation and 2D patterns and completely ignoring the integrated process of 3D simulation and production sheets. Moreover, the commonly used particle spring technology in dynamic simulation also has defects. Although the particle spring technology can simulate clothing deformation to a certain extent, since the clothing is simplified as a combination of particles and springs, the simulation of the complex structure of the clothing and the human body surface is too rough. When dealing with complex styles, it is difficult to accurately simulate the deformation of each part of the clothing, resulting in a large deviation between the 3D simulation result and the actual wearing effect. The lack of an accurate and effective conversion means between the simulation model and the production sheet leads to a long customization cycle and a high error rate in cutting and sewing, restricting the online development space for complex styles.

[0020] To solve the above problems, an embodiment of the present application provides an artificial intelligence-based method for automatically generating 3D simulation and process sheets for clothing customization. In this method, by obtaining clothing customization parameters, basic data support is provided. Based on the clothing customization parameters, three-dimensional parametric modeling is performed to determine the three-dimensional fitting model corresponding to the clothing customization parameters, intuitively preview the upper body effect of the clothing, adjust the design plan in advance, and avoid the cost of modification after production. The three-dimensional fitting model is discretely meshed to obtain the first triangular mesh topology corresponding to the three-dimensional fitting model, laying a mesh foundation for accurate physical simulation and cutting analysis. Based on the clothing customization parameters, physical constraint iteration is performed on the first triangular mesh topology to obtain the second triangular mesh topology corresponding to the three-dimensional fitting model, ensuring that the clothing pattern conforms to the physical characteristics of the fabric and the dynamic requirements of human wearing. Based on the second triangular mesh topology, a customized process sheet corresponding to the clothing customization parameters is obtained to guide the clothing production process, realizing the integration of simulation and process sheet, effectively improving the clothing production efficiency and quality, and reducing the cutting and sewing error.

[0021] The artificial intelligence-based method for automatically generating 3D simulation and process sheets for clothing customization provided by the embodiment of the present application can be applied to a terminal device. At this time, the terminal device is the execution subject of the artificial intelligence-based method for automatically generating 3D simulation and process sheets for clothing customization provided by the embodiment of the present application. The embodiment of the present application does not impose any restrictions on the specific type of the terminal device.

[0022] For example, the terminal device can be a mobile phone, a tablet computer, a wearable device, a vehicle-mounted device, an augmented reality (AR) / virtual reality (VR) device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), a desktop computer, a smart large screen, a smart TV, etc., a handheld device with wireless communication function, a computing device, or other processing devices connected to a wireless modem.

[0023] To better understand the artificial intelligence-based method for automatically generating 3D simulation and process sheets for clothing customization provided by the embodiment of the present application, the following provides an exemplary introduction to the specific implementation process of the artificial intelligence-based method for automatically generating 3D simulation and process sheets for clothing customization provided by the embodiment of the present application.

[0024] Figure 1 The schematic flowchart of the artificial intelligence-based method for automatically generating 3D simulation and process sheets for clothing customization provided by the embodiment of the present application is shown. The artificial intelligence-based method for automatically generating 3D simulation and process sheets for clothing customization includes: S100, obtain clothing customization parameters.

[0025] It can be understood that clothing customization parameters are the basic data for realizing personalized clothing customization, which cover key information in many aspects. The user's body size data is an important part of them, such as height, weight, chest circumference, waist circumference, hip circumference, shoulder width, arm length, leg length, etc. These accurately measured data can ensure that the clothing fits the user's body curve. At the same time, clothing style parameters are also indispensable, including the type of clothing (such as shirts, dresses, suits, etc.), collar types (such as lapel, round collar, stand-up collar), sleeve types (such as long sleeves, short sleeves, sleeveless, lantern sleeves), skirt styles (such as straight skirt, A-line skirt, pleated skirt), etc. These parameters determine the overall style and appearance of the clothing. In addition, fabric selection parameters are also among them, such as the material of the fabric (cotton, wool, silk, chemical fiber, etc.), color, pattern (solid color, stripes, floral, etc.), which affect the texture, comfort and visual effect of the clothing. When obtaining clothing customization parameters, it can be through online questionnaires or offline body measurements. Using HTML forms and backend data processing programs, users fill in or select information such as body size and clothing style preferences on the front-end interface, and the backend uses the Flask framework of Python to parse the data and store it in the database. Through clothing customization parameters, a comprehensive and accurate basis can be provided for the subsequent clothing customization process.

[0026] S200, perform 3D parameter modeling based on the clothing customization parameters to determine the 3D virtual fitting model corresponding to the clothing customization parameters.

[0027] It can be understood that 3D parameter modeling is to transform clothing customization parameters into a visual 3D model, please refer to Figure 2 , which can enable users to intuitively feel the upper body effect of the customized clothing in advance. Through computer graphics algorithms and professional modeling software, such as open source libraries like Open3D, etc., the obtained clothing customization parameters are used as input data for processing. Key information can be extracted from the clothing customization parameters, such as human body size information and clothing style parameters. Based on the human body size information and clothing style parameters, a 3D virtual fitting model that can truly reflect the wearing state of the clothing on the human body is gradually constructed. The 3D virtual fitting model can not only display the appearance of the clothing, but also simulate the morphological changes of the clothing during human movement, providing strong support for subsequent design adjustments and user confirmation, effectively reducing the modification cost caused by unreasonable design, and improving the accuracy and efficiency of clothing customization.

[0028] In a possible implementation manner, S200, perform 3D parameter modeling based on the clothing customization parameters to determine the 3D virtual fitting model corresponding to the clothing customization parameters, including: S210, extract human body size information and clothing style parameters based on the clothing customization parameters.

[0029] It can be understood that the user's body size data can be parsed from the clothing customization parameters, such as height accurate to centimeters, chest circumference measurement must be kept horizontal and fit the body. The size data of various body parts is the human body size information, which can accurately reflect the user's body shape characteristics. The clothing style parameters selected by the user can be identified, such as whether the clothing is a casual hooded sweater or a formal business suit, as well as specific details such as collar type and sleeve type. Clothing style parameters determine the design style and version of the clothing. String matching and data classification algorithms can be used to classify and filter the input clothing customization parameters, convert complex parameter information into structured data that is easy to process later, extract human body size information and clothing style parameters, and lay the foundation for building a clothing model that meets user needs.

[0030] S220: extract anatomical features according to the human body size information, and determine a coordinate set of anatomical feature points corresponding to the human body size information.

[0031] It can be understood that the anatomical characteristics of the human body are closely related to the fit of clothing. By extracting the coordinate set of anatomical feature points, clothing can be better adapted to the human body. Based on the acquired human body size information, the feature points of key parts of the human body can be determined according to the principles of human anatomy, such as the acromion point of the shoulder, the nipple point of the chest, and the iliac crest point of the waist. The anatomical feature points represent the key positions of the human skeleton and muscles, and their coordinates can accurately reflect the morphological structure of the human body. The positions of these feature points in three-dimensional space can be quantified using three-dimensional measurement technology and mathematical conversion algorithms to generate a coordinate set of anatomical feature points. The coordinate set of anatomical feature points provides an accurate reference framework for the subsequent construction of human body mechanics models and clothing pattern design, which helps to improve the comfort and wearing effect of clothing and avoid the situation where clothing does not fit well in key parts.

[0032] S230, constructing a human body mechanics model based on the anatomical feature point coordinate set, and generating a dynamic body shape surface model corresponding to the human body size information.

[0033] It is understandable that during the movement of the human body, the shapes of various body parts will change, and clothing needs to adapt to these changes. The construction of the human body mechanics model is based on the coordinate set of anatomical feature points, taking into account the movement laws and mechanical properties of human muscles and bones, and using mechanical principles and mathematical models to simulate the shape changes of the human body in different movement states. The human body model grid can be divided by using the finite element method based on the coordinate set of anatomical feature points, combined with the mechanical principles of human muscle and bone movement, and the dynamic simulation algorithm is used to solve the deformation of the model in different movement states to generate a dynamic body surface model. For example, when the human arm is lifted, the dynamic body surface model can show the surface deformation around the shoulder and arm. This provides a dynamic reference of the human body shape for the clothing design stage, enabling the customized clothing to not only fit well statically but also remain comfortable and beautiful during dynamic wearing, enhancing the practicality and wearing experience of the clothing.

[0034] S240. Map the clothing style parameters to the dynamic body surface model and perform differential coordinate deformation to determine the 3D virtual fitting model corresponding to the clothing customization parameters.

[0035] It is understandable that clothing style parameters, such as collar type, sleeve type, skirt style, etc., can be mapped to the dynamic body surface model through a specific mapping algorithm, enabling the clothing style to be presented on the human body model. Then differential coordinate deformation is carried out. This is an accurate deformation method based on tiny coordinate changes. By finely adjusting the coordinates on the surface of the dynamic body surface model, details such as the shape and folds of the clothing can be made to better conform to the actual wearing effect. For example, for a body-hugging style of clothing, the fit between the clothing and the human body can be adjusted through differential coordinate deformation, enabling the clothing to better show the human body curves. By integrating the clothing style parameters into the dynamic body surface model, a 3D virtual fitting model that can intuitively display the wearing effect of the clothing is finally generated, providing a more realistic virtual fitting experience for users.

[0036] Optionally, S240. Map the clothing style parameters to the dynamic body surface model and perform differential coordinate deformation to determine the 3D virtual fitting model corresponding to the clothing customization parameters, including: S241. Decompose the clothing style parameters into geometric feature components to obtain the geometric constraint features corresponding to the clothing style parameters.

[0037] It can be understood that the clothing style parameters contain various complex design elements, which can be geometrically decomposed, and the design elements can be transformed into geometric constraint features that are easy to process. Shape analysis and geometric parameter extraction algorithms can be used. Taking the clothing neckline as an example, the edge detection algorithm is used to extract the edge contour of the neckline, and then the geometric parameters such as the curvature and length of the curve are obtained through the curve fitting algorithm. These parameters are used as geometric constraint features to describe the geometric shape and position constraints of the clothing style. For example, for a piece of clothing with a unique neckline design, its neckline shape can be decomposed into geometric features of the curve, such as curvature and length; the pocket design of the clothing can be decomposed into geometric shape features such as rectangles or circles, as well as the constraint information such as their positions and sizes on the clothing. Through geometric feature decomposition, the abstract design of the clothing style is transformed into specific geometric parameters and constraint conditions geometric set constraint features. These geometric constraint features are the basis for accurately mapping the clothing style to the dynamic body surface model later, and can ensure that the presentation of the clothing style on the model meets the design requirements and maintains the original style and characteristics of the clothing.

[0038] S242. Project the geometric constraint features onto the dynamic body surface model through geodesic projection to obtain the characteristic line paths corresponding to the geometric constraint features.

[0039] It can be understood that geodesic projection is an effective method for finding the shortest path in the surface space. The geometric constraint features can be projected onto the dynamic body surface model through geodesic projection to accurately determine the position and orientation of the clothing style on the human body model. The dynamic body surface model is a three-dimensional surface. Through geodesic projection, the high-curvature regions are first identified, and then the shortest path search is carried out. The curvature calculation algorithm can be used to identify the high-curvature region grids of the dynamic body surface model; the shortest path search algorithms such as Dijkstra or A* are used, combined with the geometric constraint features, to search for the shortest path from the starting point to the ending point on the dynamic body surface model to obtain the characteristic line paths. The shortest paths from one point to another on the dynamic body surface model are the characteristic line paths corresponding to the geometric constraint features. For example, for a decorative line on the clothing, geodesic projection can be used to make it distribute along the natural trend of the human body surface on the dynamic body surface model, ensuring the aesthetics and integrity of the clothing, and at the same time providing an accurate reference path for subsequent model deformation.

[0040] Exemplarily, S242. Project the geometric constraint features onto the dynamic body surface model through geodesic projection to obtain the characteristic line paths corresponding to the geometric constraint features, including: S2421. Identify the curvature-sensitive regions of the dynamic body surface model to determine the high-curvature region grids of the dynamic body surface model.

[0041] It can be understood that the curvature of the dynamic body surface model varies in different parts. High-curvature regions often correspond to human joints, bone protrusions, etc. High-curvature regions have a greater impact on the deformation and fit of clothing. By calculating the curvature values of each point on the dynamic body surface model and using the curvature calculation algorithm and threshold judgment method, the regions with curvature values greater than the threshold can be identified. The regions with curvature values greater than the threshold are high-curvature regions. These high-curvature regions can be divided into a grid form to form a high-curvature region grid. For example, in the joint parts such as the elbows and knees of the human body, due to the large bending degree and high surface curvature during movement, they belong to high-curvature regions, which helps the clothing to better adapt to human movement in these key parts during the subsequent shortest path search and model deformation processes, improving the comfort and flexibility of the clothing.

[0042] S2422, perform the shortest path search based on the geometric constraint features and the high-curvature region grid to obtain the characteristic path corresponding to the geometric constraint features.

[0043] It can be understood that on the complex surface of the dynamic body surface model, it is necessary to find an optimal path that conforms to the geometric constraint features, which is the purpose of the shortest path search. Using the geometric constraint features, such as the starting point, ending point, and shape requirements of the clothing decoration line, and the high-curvature region grid information, taking the starting point and ending point of the geometric constraint features as the search start and end conditions, and using the shortest path search algorithm (such as Dijkstra algorithm, A* algorithm, etc.), search for the shortest path from the starting point to the ending point on the dynamic body surface model. The existence of the high-curvature region grid will affect the path selection because the deformation of the clothing is more complex in these regions. The shortest path obtained through the search is the characteristic path corresponding to the geometric constraint features, ensuring that the layout of the clothing style on the human body model is reasonable, and when the human body moves, the lines and structures of the clothing can naturally change with the human body, avoiding unnatural wrinkles or stretching.

[0044] S243, construct a local deformation coordinate system based on the characteristic path and adjust the dynamic body surface model through differential coordinate deformation to determine the three-dimensional virtual fitting model corresponding to the clothing customization parameters.

[0045] It can be understood that in order to better present the clothing style effect of the dynamic body surface model, a local deformation coordinate system can be constructed and differential coordinate deformation can be performed. Based on the feature path, the axis directions of the local coordinate system are defined, that is, precise deformation operations can be performed on the local areas related to the clothing style. By generating differential coordinate constraints and calculating the average offset of the model vertices relative to the neighboring vertices, a reference quantity is obtained, and this reference quantity reflects the deformation degree of the local area. According to this reference quantity, a vertex displacement constraint equation is constructed and iteratively solved in the local deformation coordinate system to gradually adjust the vertex positions of the dynamic body surface model, making the model more in line with the design requirements of the clothing style. The finally determined 3D fitting model can accurately display the wearing effect of the clothing on the human body, including details such as the fit of the clothing and the distribution of wrinkles, providing an intuitive reference for clothing customization. Exemplarily, S243, constructing a local deformation coordinate system based on the feature path and adjusting the dynamic body surface model through differential coordinate deformation to determine the 3D fitting model corresponding to the clothing customization parameters, including: S2431, defining the u-axis of the local coordinate system based on the tangent direction of the feature path and defining the v-axis based on the normal direction of the dynamic body surface model to construct the local deformation coordinate system.

[0046] It can be understood that the local deformation coordinate system is a reference framework for adjusting the dynamic body surface model, and the local deformation coordinate system can be constructed by using vector calculation and coordinate system construction algorithms. The tangent direction of the feature path reflects the extension direction of the clothing style on the surface, and it can be defined as the u-axis, along which stretching, shrinking and other deformation operations can be performed on the model. The normal direction of the dynamic body surface model is perpendicular to the surface of the model, and it can be defined as the v-axis, and the v-axis can control the displacement and deformation of the model in the direction perpendicular to the surface. By defining the u-axis and the v-axis, a two-dimensional local deformation coordinate system can be constructed. In the local deformation coordinate system, it is more convenient to perform local adjustments on the model, such as precise deformation operations on a specific part of the clothing, such as the collar and cuffs, to ensure that the details of the clothing style can be accurately presented on the model, improving the authenticity and accuracy of the model.

[0047] S2432, generating differential coordinate constraints according to the local deformation coordinate system, calculating the average offset of the vertices of the dynamic body surface model relative to the neighboring vertices, and obtaining the reference quantity for differential coordinate deformation.

[0048] It can be understood that in the local deformation coordinate system, there is a certain positional relationship between each vertex and its neighboring vertices. The vertex displacement calculation and averaging algorithm can be used. In the local deformation coordinate system, calculate the displacement vector between each vertex and its neighboring vertices, obtain the displacement difference through vector operations, and then perform an average calculation on the displacement difference to obtain the average offset, which serves as the reference quantity for differential coordinate deformation and is used to measure the deformation degree of the local area. By calculating the average offset of the vertices of the dynamic body surface model relative to their neighboring vertices, a reference quantity reflecting the deformation trend of the local area can be obtained. For example, in the wrinkled parts of clothing, the relative offset between vertices is large. By calculating the average offset, this deformation degree can be quantified. The reference quantity provides a standard for subsequent differential coordinate deformation, making the deformation of the model more orderly and controllable, avoiding excessive deformation or uneven deformation, and ensuring the quality and accuracy of the model.

[0049] S2433. Construct a vertex displacement constraint equation through the reference quantity, and iteratively solve the vertex displacement constraint equation in the local deformation coordinate system to determine the 3D fitting model corresponding to the clothing customization parameters.

[0050] It can be understood that equation construction and iterative solution algorithms can be applied. Construct a vertex displacement constraint equation based on the reference quantity and the vertex displacement relationship. Iterative algorithms such as the Gauss-Seidel iteration method or the conjugate gradient method can be used to continuously adjust the vertex positions in the local deformation coordinate system. Stop the iteration when the vertex displacement change is less than the preset threshold to obtain the 3D fitting model that conforms to the clothing customization parameters. The vertex displacement constraint equation reflects the relationship between the displacement of the vertex in the local deformation coordinate system and the reference quantity. In the local deformation coordinate system, this equation is continuously solved iteratively. Each iteration adjusts the vertex positions according to the previous calculation results, gradually making the model meet the requirements of the clothing customization parameters. After multiple iterations, when the displacement change of the model vertices is very small and meets the preset convergence condition, the final 3D fitting model is determined. The 3D fitting model can accurately display the wearing effect of the clothing on the human body and provide a reliable visual basis for clothing customization.

[0051] S300. Perform discrete grid division on the 3D fitting model to obtain the first triangular grid topology corresponding to the 3D fitting model.

[0052] It can be understood that discrete grid division is to convert a continuous 3D fitting model into a discrete triangular grid representation. The first triangular grid topology describes the connection relationships and layout structures among these triangular grids. Through discrete grid division, the surface of the 3D fitting model can be segmented into many small triangular patches, which are the basic units that make up the grid. The first triangular grid topology records the vertex information of each triangular patch and their adjacency relationships. Through this topological structure, each part of the model can be quickly accessed and operated on, facilitating further optimization of the model and generation of a clothing customization process sheet. At the same time, it can also improve the computational efficiency and ensure the smooth progress of the entire clothing customization process.

[0053] In a possible implementation, in S300, perform discrete grid division on the 3D fitting model to obtain the first triangular grid topology corresponding to the 3D fitting model, including: S310, perform triangulation based on the 3D fitting model to generate an initial triangular grid, and perform bisection subdivision on the triangular patches in the initial triangular grid whose side lengths exceed a preset threshold until the side lengths of all triangular patches are less than or equal to the threshold; where the triangular patches are the basic components in the initial triangular grid.

[0054] It can be understood that triangulation is to convert the 3D fitting model into a triangular grid. Through a specific triangulation algorithm, the model surface is divided into multiple triangles to generate an initial triangular grid. The Delaunay triangulation algorithm can be used to generate the initial grid. By calculating the Delaunay triangulation of the surface point set of the 3D fitting model, the initial triangular grid is constructed; a side length comparison algorithm can be adopted to compare the side lengths with the preset threshold. For the triangular patches with side lengths exceeding the threshold, use bisection to divide along the midpoint of the longest side and repeat continuously until the side lengths of all triangular patches meet the requirements, ensuring that the density and accuracy of the triangular grid meet the requirements, making subsequent processing of the model more accurate. For example, when performing physical simulation and cutting analysis, more accurate results can be obtained, improving the quality of clothing customization.

[0055] S320, optimize the grid vertex distribution of the subdivided triangular grid to obtain the first triangular grid topology corresponding to the 3D fitting model.

[0056] It can be understood that the vertex distribution of the subdivided triangular mesh may not be uniform enough, which will affect the quality of the model and the subsequent processing effect. Therefore, optimization is required. The position of the triangular mesh vertices can be adjusted through mesh vertex distribution optimization algorithms, such as Laplacian smoothing algorithm, Taubin algorithm, etc., to make the vertex distribution more uniform. During the optimization process, the new position of each vertex can be calculated according to the relationship between the vertex and its neighboring vertices, making the mesh surface smoother and reducing local unevenness. The optimized vertex distribution can improve the stability and computational efficiency of the model. When performing physical simulations, it can more accurately reflect the mechanical properties of the clothing; when generating the cutting process sheet, it can more precisely calculate the shape and size of the cut pieces, ensuring the accuracy and consistency of clothing customization and obtaining a first triangular mesh topology with higher quality.

[0057] S400. Perform physical constraint iteration on the first triangular mesh topology based on the clothing customization parameters to obtain the second triangular mesh topology corresponding to the 3D virtual fitting model.

[0058] It can be understood that clothing is subject to various physical forces during wearing. To more realistically simulate the wearing effect of clothing, physical constraint iteration can be performed on the first triangular mesh topology. Based on clothing customization parameters, such as the elasticity and weight of the fabric, anisotropic mechanical constraints are imposed on the first triangular mesh topology, considering the differences in mechanical properties of the clothing in different directions. The motion and deformation laws of the mesh vertices under the action of physical forces can be described by constructing a projection dynamics equation, and the vertex displacement field can be solved through local-global alternating iteration. During the iteration process, the positions of the mesh vertices are continuously adjusted to make the mesh topology gradually conform to the physical state of the clothing during actual wearing, and finally the second triangular mesh topology is obtained. The second triangular mesh topology can more accurately reflect the true shape of the clothing on the human body, providing a more reliable basis for generating a customized process sheet that meets the actual wearing requirements subsequently.

[0059] In a possible implementation, S400, performing physical constraint iteration on the first triangular mesh topology based on the clothing customization parameters to obtain the second triangular mesh topology corresponding to the 3D virtual fitting model, includes: S410. Impose anisotropic mechanical constraints on the first triangular mesh topology based on the clothing customization parameters and construct a projection dynamics equation, and solve the vertex displacement field through local-global alternating iteration; wherein, local iteration is used to calculate the ideal displacement of the vertex under the action of elastic force and gravity, and global iteration is used to correct the vertex position through implicit surface constraints and update the mesh topology.

[0060] It can be understood that the mechanical differences of the anisotropic mechanical constraint clothing fabric in different directions can make the simulation more realistic. According to the information such as the elastic modulus and Poisson's ratio of the fabric in the clothing customization parameters, the elastic force constraints in different directions are determined. A mechanical model and an iterative algorithm can be used to establish an anisotropic elastic mechanics model based on the fabric parameters, apply mechanical constraints in combination with the gravity formula, and construct a projection dynamics equation to describe the vertex motion. Explicit Euler's method can be used for local iteration to calculate the ideal displacement of the vertex, and the implicit surface constraint equation can be used for global iteration to correct the vertex position, update the mesh topology, and solve the vertex displacement field through alternating iteration. The projection dynamics equation is used to transform the mechanical constraints into a mathematical form to describe the motion and deformation of the mesh vertices. Local iteration mainly focuses on the mechanical response of a single vertex and its neighborhood, calculates the ideal displacement of the vertex under the action of elastic force and gravity, and determines the local deformation situation. Global iteration starts from the overall model, corrects the vertex position through implicit surface constraints, ensures that the overall shape of the mesh conforms to the human body surface characteristics, and updates the mesh topology. Through the local-global alternating iteration method, the vertex displacement field is gradually solved, making the mesh model more realistically simulate the state of the clothing in the physical environment and improving the solution efficiency and accuracy.

[0061] S420. When the vertex displacement fields of consecutive preset number of iterations are all less than the preset convergence threshold, stop the iteration to obtain the second triangular mesh topology corresponding to the 3D virtual fitting model.

[0062] It can be understood that during the physical constraint iteration process, it is necessary to judge whether the iteration converges to determine when to stop the iteration to obtain the final second triangular mesh topology. A convergence judgment algorithm can be used to preset a convergence threshold to measure the change degree of the vertex displacement field. After each iteration, calculate the change amount of the vertex displacement field. If the vertex displacement fields of consecutive preset number of times (such as 5 times or 10 times) are all less than this convergence threshold, it means that the position change of the mesh vertices is very small and the model is basically in a stable state. At this time, stop the iteration, and the obtained triangular mesh topology is the second triangular mesh topology. The second triangular mesh topology can accurately reflect the final shape of the clothing under physical constraints, provide an accurate model basis for generating the subsequent customization process sheet, ensure the accuracy and reliability of clothing customization, and avoid clothing production problems caused by inaccurate models.

[0063] S500. Based on the second triangular mesh topology, obtain the customization process sheet corresponding to the clothing customization parameters.

[0064] It can be understood that the second triangular mesh topology is the key data basis for generating a customized process sheet, which contains the detailed structure and shape information of the garment in three-dimensional space. By further processing it, it can be transformed into the technical parameters required for garment production, thereby guiding the actual production of garments. The customized process sheet is an important guiding basis for garment production, covering the specific requirements of each link from fabric cutting, sewing process to pressing and packaging, ensuring that the garment is accurately produced according to the customized parameters and achieving the goal of personalized garment customization.

[0065] In a possible implementation manner, S500, based on the second triangular mesh topology, obtain a customized process sheet corresponding to the garment customization parameters, including: S510, generate cut piece alignment marks on the second triangular mesh topology according to the anatomical feature point coordinate set, and flatten the second triangular mesh topology into a two-dimensional geometric contour through conformal mapping.

[0066] It can be understood that the second triangular mesh topology is the key data basis for generating a customized process sheet, which contains the detailed structure and shape information of the garment in three-dimensional space. In the prior art, the garment is usually simplified into a combination of mass points and springs through the mass point spring technology. When simulating the garment deformation to determine the cut pieces, the conversion accuracy of complex human body surfaces and asymmetric cutting is insufficient. Therefore, the marker generation algorithm can be used first, and then the conformal mapping algorithm can be adopted to improve the conversion accuracy between the three-dimensional model and the two-dimensional cut pieces. Using the coordinate matching algorithm, the anatomical feature point coordinates are corresponded to the points on the second triangular mesh topology to generate cut piece alignment marks. The second triangular mesh topology can be flattened into a two-dimensional geometric contour by applying an algorithm based on discrete conformal mapping, such as the Laplace-Beltrami operator method, to maintain the graphic shape and angular relationship.

[0067] Optionally, S510, generate cut piece alignment marks on the second triangular mesh topology according to the anatomical feature point coordinate set, and flatten the second triangular mesh topology into a two-dimensional geometric contour, including: S511, generate cut piece alignment marks on the second triangular mesh topology according to the anatomical feature point coordinate set, and determine the cut piece coordinate positions corresponding to the cut piece alignment marks.

[0068] It can be understood that the set of anatomical feature point coordinates corresponds closely to the key parts of the human body and is crucial for the splicing accuracy of fabric pieces in clothing production. Through coordinate matching and position determination algorithms, specifically coordinate transformation and nearest neighbor search algorithms, the anatomical feature point coordinates can be mapped onto the second triangular mesh topology. The nearest grid points are found as the alignment marks for the fabric pieces. Based on the indices and topological relationships of the grid points, the fabric piece coordinate positions corresponding to the alignment marks for the fabric pieces are determined, providing positioning for the splicing of the fabric pieces. Each alignment mark for the fabric piece corresponds to a specific fabric piece coordinate position, which precisely defines the relative position relationship of the fabric piece within the three-dimensional grid. By determining the alignment marks for the fabric pieces and their corresponding fabric piece coordinate positions, a clear positioning standard is provided for the subsequent sewing of the fabric pieces, ensuring the accuracy of the splicing of each part of the clothing and improving the production quality and fit of the clothing. S512, flatten the second triangular mesh topology into a two-dimensional geometric contour according to the fabric piece coordinate position corresponding to the alignment mark for the fabric piece.

[0069] It can be understood that the fabric piece coordinate position corresponding to the alignment mark for the fabric piece provides a basis for the flattening of the second triangular mesh topology. The conformal mapping algorithm can be applied. Based on the principle of discrete conformal mapping, by adjusting the positions of the grid vertices, the three-dimensional grid can be flattened into two dimensions while keeping the interior angles unchanged. The vertex displacements are calculated using the Laplace-Beltrami operator, and the flattening process is constrained according to the fabric piece coordinate position to obtain a two-dimensional geometric contour. The two-dimensional geometric contour can visually display the shape of the clothing fabric piece, facilitating cutting layout and process planning, effectively reducing sewing problems caused by inaccurate fabric piece shapes, and improving the efficiency and quality of clothing production.

[0070] S520, input the two-dimensional geometric contour into the process sheet generation model to obtain a customized process sheet corresponding to the clothing customization parameters. Among them, the process sheet generation model is a machine learning model pre-trained.

[0071] It can be understood that the two-dimensional geometric contour contains key information such as the shape and size of the clothing fabric piece. However, to be transformed into a complete customized process sheet, further processing is required with the help of the process sheet generation model. The process sheet generation model is a machine learning model trained with a large amount of clothing production data, which has learned the correlation rules between different clothing styles, fabrics, and production processes. The two-dimensional geometric contour can be used as input, and the model can automatically generate a customized process sheet containing rich information according to the learned knowledge. The customized process sheet details specific process parameters such as the way of fabric cutting, the stitching methods and sequences, the width of the seam allowance, the temperature and time of ironing, etc., providing comprehensive and accurate guidance for the actual production of clothing, realizing the transformation from clothing customization parameters to executable processes, and facilitating the intelligent integration of the entire process from clothing style design to delivery for clothing customization.

[0072] Exemplarily, obtain the process sheet of actual production. Please refer to Figure 4 , which contains detailed process information such as cutting, sewing, pressing, etc.; at the same time, collect the two-dimensional geometric contour data corresponding to the process sheet, which can be obtained by digitizing the clothing pattern design drawings. For example, collect data of various types of clothing such as shirts, dresses, suits, etc., each type of clothing includes multiple sizes and different fabric selections to ensure data diversity. Label the collected two-dimensional geometric contour data and process sheet, and associate the two-dimensional geometric contour with the key information in the corresponding customized process sheet. The labeled content includes the shape, size, sewing order, stitch type, seam width, pressing temperature and time, etc. of the cut pieces. For example, mark the boundaries of each part such as the neckline cut piece and the cuff cut piece on the two-dimensional geometric contour, and information such as whether the stitch type used for neckline sewing in the corresponding process sheet is overlock stitch or bound edge stitch, and the seam width is 0.5 cm. According to the characteristics of the tasks generated by the process sheet, select a suitable machine learning model, such as a convolutional neural network (CNN) or a recurrent neural network (RNN). CNN is good at processing image features and can effectively extract features such as shape and structure from two-dimensional geometric contour data; RNN has stronger processing ability for data with sequential features and is suitable for processing the sequential information of the process steps in the process sheet. For example, for tasks mainly relying on the shape of two-dimensional geometric contours to generate process sheets, CNN can be preferentially selected. Divide the labeled data into a training set (accounting for 60%-80%), a validation set (accounting for 10%-20%), and a test set (accounting for 10%-20%). The training set enables the model to learn the mapping relationship between two-dimensional geometric contours and customized process sheets. The validation set is used to evaluate the model performance and adjust hyperparameters during training, and the test set is used to evaluate the generalization ability of the trained model. And determine training parameters such as the learning rate, number of iterations, batch size, etc. Input the training set data into the model, and use the backpropagation algorithm to calculate the loss between the predicted result and the actual process sheet (such as using the mean square error loss function for regression tasks), and adjust the model weights and biases according to the loss, and iterate continuously. Evaluate the trained model with the test set, and calculate indicators such as the accuracy, recall rate, and mean square error of predicting process sheet parameters, such as evaluating the prediction accuracy of seam width and counting the prediction accuracy of sewing stitch types. Optimize the model according to the evaluation results. If there is overfitting, use regularization, increase the data volume, or stop training early to improve; if there is underfitting, increase the model complexity, such as increasing the number of network layers and adjusting the convolutional kernel size. After multiple optimizations, obtain the optimal model for actual process sheet generation.

[0073] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0074] Corresponding to the method for automatically generating 3D simulation and process sheets for clothing customization based on artificial intelligence described in the above embodiments, an embodiment of the present application also provides a system for automatically generating 3D simulation and process sheets for clothing customization based on artificial intelligence. Each unit of this system can implement each step of the method for automatically generating 3D simulation and process sheets for clothing customization based on artificial intelligence. Figure 4 The block diagram of the system for automatically generating 3D simulation and process sheets for clothing customization based on artificial intelligence provided by the embodiment of the present application is shown. For the convenience of description, only the parts related to the embodiment of the present application are shown.

[0075] Referring to Figure 4 , the system for automatically generating 3D simulation and process sheets for clothing customization based on artificial intelligence includes: An acquisition unit, configured to acquire clothing customization parameters; A modeling unit, configured to perform three-dimensional parameter modeling based on the clothing customization parameters to determine a three-dimensional fitting model corresponding to the clothing customization parameters; A partitioning unit, configured to perform discrete grid partitioning on the three-dimensional fitting model to obtain a first triangular mesh topology corresponding to the three-dimensional fitting model; An iteration unit, configured to perform physical constraint iteration on the first triangular mesh topology based on the clothing customization parameters to obtain a second triangular mesh topology corresponding to the three-dimensional fitting model; A generation unit, configured to obtain a customized process sheet corresponding to the clothing customization parameters based on the second triangular mesh topology.

[0076] It should be noted that for the information interaction, execution process, etc. between the above systems / units, since they are based on the same concept as the method embodiment of the present application, for their specific functions and the technical effects brought, reference can be specifically made to the method embodiment part, and details are not described here again.

[0077] Those skilled in the art can clearly understand that for the convenience and conciseness of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the system is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in a processing unit, or each unit module exists physically alone, or two or more unit modules are integrated in one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of the present application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiment, and details are not described here again.

[0078] The embodiment of the present application also provides an electronic device. Figure 5 It is a schematic structural diagram of the electronic device provided by an embodiment of the present application. As Figure 5 shown, the electronic device 6 in this embodiment includes: at least one processor 60 ( Figure 5 only one is shown), at least one memory 61 ( Figure 5 only one is shown), and a computer program 62 stored in the at least one memory 61 and executable on the at least one processor 60. When the processor 60 executes the computer program 62, the electronic device 6 implements the steps in any of the above embodiments of the method for automatically generating 3D simulation and process sheets for clothing customization based on artificial intelligence, or the functions of each unit in the above system embodiments.

[0079] Exemplarily, the computer program 62 can be divided into one or more units. The one or more units are stored in the memory 61 and executed by the processor 60 to complete the present application. The one or more units can be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program 62 in the electronic device 6.

[0080] The electronic device 6 can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The electronic device may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art can understand that Figure 5 merely examples of the electronic device 6, which do not constitute a limitation to the electronic device 6. It may include more or fewer components than shown in the figure, or combine some components, or different components. For example, it may also include input / output devices, network access devices, buses, etc.

[0081] The processor 60 can be a Central Processing Unit (CPU), and the processor 60 can also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0082] The memory 61 may be an internal storage unit of the electronic device 6 in some embodiments, such as a hard disk or memory of the electronic device 6. The memory 61 may also be an external storage device of the electronic device 6 in some other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the electronic device 6. Further, the memory 61 may also include both the internal storage unit and the external storage device of the electronic device 6. The memory 61 is used to store an operating system, application programs, a BootLoader, data, and other programs, such as the program code of the computer program. The memory 61 may also be used to temporarily store data that has been output or will be output.

[0083] An embodiment of the present application also provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0084] An embodiment of the present application provides a computer program product, and when the computer program product runs on an electronic device, the electronic device implements the steps in any of the above method embodiments.

[0085] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above method embodiments of the present application, a computer program may be used to instruct relevant hardware to complete. The computer program may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps in the above method embodiments may be implemented. Among them, the computer program includes computer program code, and the computer program code may be in the form of source code, object code, an executable file, or some intermediate form, etc. The computer-readable medium may at least include: any entity or device capable of carrying the computer program code to an electronic device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk, or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium may not be an electrical carrier signal and a telecommunication signal.

[0086] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not described in detail or recorded in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0087] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0088] In the embodiments provided in this application, it should be understood that the disclosed 3D simulation and process sheet automatic generation system / electronic device and method based on artificial intelligence for clothing customization can be implemented in other ways. For example, the above-described embodiments of the 3D simulation and process sheet automatic generation system / electronic device based on artificial intelligence for clothing customization are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the systems or units can be in electrical, mechanical or other forms.

[0089] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0090] The above-described embodiments are only used to illustrate the technical solutions of this application, rather than to limit them; although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included in the protection scope of this application.

Claims

1. A method for 3D simulation and automatic generation of process sheets for clothing customization based on artificial intelligence, characterized in that: include: Get clothing customization parameters; Performing three-dimensional parameter modeling based on the clothing customization parameters to determine a three-dimensional fitting model corresponding to the clothing customization parameters; Performing discrete mesh division on the three-dimensional fitting model to obtain a first triangular mesh topology corresponding to the three-dimensional fitting model; Performing physical constraint iteration on the first triangular mesh topology based on the clothing customization parameters to obtain a second triangular mesh topology corresponding to the three-dimensional fitting model; Based on the second triangular mesh topology, a customization process sheet corresponding to the clothing customization parameters is obtained.

2. The method for automatic generation of 3D simulation and process sheet for clothing customization based on artificial intelligence according to claim 1, characterized in that: The performing three-dimensional parameter modeling based on the clothing customization parameters to determine the three-dimensional fitting model corresponding to the clothing customization parameters includes: Extracting human body size information and clothing style parameters based on the clothing customization parameters; Extracting anatomical features according to the human body size information, and determining a coordinate set of anatomical feature points corresponding to the human body size information; Constructing a human body mechanics model based on the anatomical feature point coordinate set to generate a dynamic body shape surface model corresponding to the human body size information; The clothing style parameters are mapped to the dynamic body shape surface model and differential coordinate deformation is performed to determine a three-dimensional fitting model corresponding to the clothing customization parameters.

3. The method for automatic generation of 3D simulation and process sheet for clothing customization based on artificial intelligence according to claim 2, characterized in that: The step of mapping the clothing style parameters to the dynamic body shape surface model and performing differential coordinate deformation to determine the three-dimensional fitting model corresponding to the clothing customization parameters includes: Decomposing the clothing style parameters by geometric features to obtain geometric constraint features corresponding to the clothing style parameters; Mapping the geometric constraint feature to the dynamic body surface model through geodesic projection to obtain a characteristic line path corresponding to the geometric constraint feature; A local deformation coordinate system is constructed based on the characteristic line path, and the dynamic body shape surface model is adjusted through differential coordinate deformation to determine a three-dimensional fitting model corresponding to the clothing customization parameters.

4. The method for automatic generation of 3D simulation and process sheet for clothing customization based on artificial intelligence according to claim 3, characterized in that: The step of mapping the geometric constraint feature to the dynamic body surface model through geodesic projection to obtain a feature line path corresponding to the geometric constraint feature includes: Identifying curvature-sensitive regions of the dynamic body shape surface model, and determining high-curvature region grids of the dynamic body shape surface model; A shortest path search is performed based on the geometric constraint feature and the high curvature area grid to obtain a characteristic line path corresponding to the geometric constraint feature.

5. The method for automatic generation of 3D simulation and process sheet for clothing customization based on artificial intelligence according to claim 3, characterized in that: The method of constructing a local deformation coordinate system based on the characteristic line path and adjusting the dynamic body shape surface model through differential coordinate deformation to determine the three-dimensional fitting model corresponding to the clothing customization parameters includes: The u-axis of the local coordinate system is defined based on the tangent direction of the characteristic line path, and the v-axis is defined based on the normal direction of the dynamic body surface model to construct a local deformation coordinate system; Generating differential coordinate constraints according to the local deformation coordinate system, calculating the average offset of the vertices of the dynamic body surface model relative to the neighborhood vertices, and obtaining a reference amount of differential coordinate deformation; A vertex displacement constraint equation is constructed by using the reference quantity, and the vertex displacement constraint equation is iteratively solved in the local deformation coordinate system to determine a three-dimensional fitting model corresponding to the clothing customization parameter.

6. The method for 3D simulation and automatic generation of process sheets for clothing customization based on artificial intelligence according to claim 1, characterized in that: The step of performing discrete mesh division on the three-dimensional fitting model to obtain a first triangular mesh topology corresponding to the three-dimensional fitting model includes: Perform triangulation based on the three-dimensional fitting model to generate an initial triangular mesh, and perform binary subdivision on triangular facets in the initial triangular mesh whose side length exceeds a preset threshold, until the side lengths of all triangular facets are less than or equal to the threshold; wherein the triangular facets are the basic constituent units in the initial triangular mesh; The mesh vertex distribution of the subdivided triangular mesh is optimized to obtain a first triangular mesh topology corresponding to the three-dimensional fitting model.

7. The method for 3D simulation and automatic generation of process sheets for clothing customization based on artificial intelligence according to claim 1, characterized in that: The performing physical constraint iteration on the first triangular mesh topology based on the clothing customization parameters to obtain a second triangular mesh topology corresponding to the three-dimensional fitting model includes: Based on the clothing customization parameters, anisotropic mechanical constraints are applied to the first triangular mesh topology and a projection dynamics equation is constructed, and the vertex displacement field is solved by local-global alternating iteration; wherein the local iteration is used to calculate the ideal displacement of the vertex under the action of elastic force and gravity, and the global iteration is used to correct the vertex position and update the mesh topology through implicit surface constraints; When the vertex displacement fields of consecutive preset number of iterations are all less than a preset convergence threshold, the iteration is stopped to obtain a second triangular mesh topology corresponding to the three-dimensional fitting model.

8. The method for 3D simulation and automatic generation of process sheets for clothing customization based on artificial intelligence as claimed in claim 2, characterized in that: The step of obtaining a customization process sheet corresponding to the clothing customization parameter based on the second triangular mesh topology includes: Generating a piece alignment mark on the second triangular mesh topology according to the anatomical feature point coordinate set, and flattening the second triangular mesh topology into a two-dimensional geometric contour by conformal mapping; The two-dimensional geometric contour is input into a process sheet generation model to obtain a customized process sheet corresponding to the clothing customization parameters; wherein the process sheet generation model is a pre-trained machine learning model.

9. The method for 3D simulation and automatic generation of process sheets for clothing customization based on artificial intelligence according to claim 8, characterized in that: The step of generating a piece alignment mark on the second triangular mesh topology according to the anatomical feature point coordinate set, and flattening the second triangular mesh topology into a two-dimensional geometric contour by conformal mapping includes: Generating a piece alignment mark on the second triangular mesh topology according to the anatomical feature point coordinate set, and determining a piece coordinate position corresponding to the piece alignment mark; The second triangular mesh topology is flattened into a two-dimensional geometric outline according to the coordinate position of the cutting piece corresponding to the cutting piece alignment mark.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 9 is implemented.

Images