Method, device and equipment for building model for luggage design

Abstract

This application relates to the field of bag design technology, and particularly to a method, apparatus, and equipment for building models for bag design. The method includes: determining the shape features of bag components; determining paper grid parameters based on the component shape features; obtaining core structural features and at least one variable component feature based on the paper grid parameters; determining the compatibility probability between the core structural features and the core structural features and the at least one variable component feature; generating at least one bag design model based on the compatibility probability; and obtaining a bag optimization model based on the at least one bag design model. Therefore, the bag design model building method provided by this application can solve the problem that existing technologies cannot achieve quantitative prediction of the process feasibility of different component combinations during the design stage, thus making it difficult to get rid of the dependence on physical prototyping.

Description

Technical Field

[0001] This application belongs to the field of bag design technology, and in particular relates to a method, apparatus and equipment for model building for bag design. Background Technology

[0002] Bag design is a professional field centered on bag product development, encompassing styling, structural planning, and material selection. It includes techniques such as hand-drawn sketches, computer-aided design, and virtual reality 3D modeling. The process includes design drafting, pattern breaking down, material cutting, and sewing.

[0003] However, existing bag design methods still suffer from the following technical shortcomings: First, the design process heavily relies on manual drafting or basic CAD tools, requiring designers to repeatedly adjust dimensions, proportions, and component positions, resulting in long design cycles and a high risk of errors. Second, the process from three-dimensional finished products to flat pattern cutting (i.e., "cutting out the pattern") lacks digital support, heavily relying on the experience of craftsmen, making it difficult to quickly respond to diverse market demands, especially the flexible combination of different sizes and functional components in customized scenarios. Third, the high degree of coupling between various bag components makes design resources difficult to reuse, while the frequent modification requests from customers in OEM orders, often seemingly minor, actually... The unique nature of bags as flexible material composites will trigger passive adjustments to the production chain; fourth, existing modular designs mostly focus on physical connection structures, and the modular concept only extends to the user end (such as replaceable zippers or wheels), without being integrated into the design and production ends. This results in designers lacking systematic modular tools at the beginning of the design process, and being unable to predict the sewing feasibility and stress coordination of different component combinations; fifth, in the small-batch, fast-turnaround production model, orders are characterized by small batches, many batches, and R&D cycles compressed to days or even hours, making the "experience-based" design process that relies on physical sampling difficult to adapt.

[0004] Therefore, given that bags combine the complexity of flexible materials with the load-bearing requirements of rigid structures, existing bag design technologies cannot quantitatively predict the feasibility of combining different components during the design phase, thus making it difficult to break free from the reliance on physical prototypes. Summary of the Invention

[0005] This application provides a method, apparatus, and equipment for building a model for bag design, which can solve the problem that the prior art cannot achieve quantitative prediction of the process feasibility of different component combinations in the design stage, thus making it difficult to get rid of the dependence on physical prototyping.

[0006] In a first aspect, embodiments of this application provide a method for constructing a model for bag design, including: Determine the shape characteristics of the bag's components; wherein, the shape characteristics of the components include the three-dimensional configuration of the front and back panels, the circumference of the main body, the curvature of the corners, and / or the direction of the zipper; The paper grid parameters are determined based on the shape characteristics of the components; wherein, the paper grid parameters refer to the geometric dimensions and tolerances of the cut pieces of each component of the bag; The core structural features and at least one variable component feature are obtained based on the paper grid parameters; wherein, the core structural features refer to the geometric dimensions of the core structure of the bag, and the variable component features refer to the geometric dimensions of the zipper, handle, or decorative part; The compatibility probability between at least one variable component of the bag and the core structure is determined based on the core structural features and the features of at least one variable component; wherein, the compatibility probability is used to quantify the process feasibility of different component combinations; At least one bag design model is generated based on the compatibility probability; wherein each bag design model includes a combination of the core structure and at least one variable component; Based on the at least one bag design model, a bag optimization model is obtained.

[0007] The technical solutions described in this application embodiment have at least the following technical effects: The bag design model construction method provided in this application involves: determining the shape features of bag components; determining paper grid parameters based on the component shape features; obtaining core structural features and at least one variable component feature based on the paper grid parameters; determining the compatibility probability between the at least one variable component and the core structure based on the core structural features and the at least one variable component feature; generating at least one bag design model based on the compatibility probability; and obtaining an optimized bag model based on the at least one bag design model. Therefore, the bag design model construction method provided in this application defines components such as zippers and handles as independent modules, and quickly generates variations by adjusting their geometric dimensions (such as length and width), supporting personalized customization and improving design efficiency. Generating multiple design models based on compatibility probability provides consumers with more choices and helps reduce customization costs. Automatically selecting effective combinations through compatibility probability helps improve design quality. Decoupling the basic framework from functional components supports independent iteration and reuse of components.

[0008] In one possible implementation of the first aspect, determining the compatibility probability between at least one variable component of the bag and the core structure based on the core structural features and the at least one variable component features includes: Based on the core structural features and the features of at least one variable component, calculate the probability of the layer thickness passing at multiple preset connection points of each variable component and the core structure; wherein, the probability of the layer thickness passing refers to whether multiple layers of material can pass through the sewing process smoothly at multiple preset connection points of the bag without producing defects; The tear probability at the stress point is obtained based on the force direction of each variable component at each preset connection point. Based on the characteristics of the variable components of each zipper, the corresponding minimum radius of curvature is calculated by sampling along the installation curve; The corresponding zipper fit is determined based on the minimum radius of curvature described above; The corresponding compatibility probability is obtained based on the probability of passing through each layer thickness, the probability of tearing at each stress point, and / or the zipper fit.

[0009] In one possible implementation of the first aspect, calculating the stacking thickness probability of each variable component and the core structure at multiple preset connection points based on the core structural features and the at least one variable component features includes: Based on the core structural features and the features of at least one variable component, multiple sets of material stacking thicknesses and mating surfaces are determined at multiple preset connection points between each variable component and the core structure; wherein, the material stacking thickness includes the thickness of each layer of material stacking; Calculate the corresponding size fit probability and sewing success probability based on the material stack thickness and the mating surface of each group; Determine the radius of curvature or rotation angle at each preset connection point of each of the variable components; The neutral interlayer spacing of the inner and outer layers is determined based on the total thickness of the material stack at each preset connection point of each of the variable components. Calculate the potential matching score for each variable component based on the radius of curvature, the rotation angle, and / or the neutral layer spacing of each variable component; The corresponding layer thickness passing probability is obtained based on the size adaptation probability, the sewing pass probability, and the ease matching score.

[0010] In one possible implementation of the first aspect, determining the paper grid parameters based on the component shape features includes: The shape features of the component are mapped to the paper grid parameter space to generate initial paper grid parameters; wherein, the paper grid parameter space contains the planar unfolded coordinates of each piece, and the initial paper grid parameters refer to the two-dimensional geometric parameters of each piece; Based on the initial paper grid parameters, multiple feature vectors within a preset parameter range are determined; The high-frequency design features are obtained based on the aforementioned feature vectors; The paper grid parameters are obtained based on the high-frequency design features.

[0011] In one possible implementation of the first aspect, determining multiple feature vectors within a preset parameter range based on the initial paper grid parameters includes: Multiple candidate paper grid parameters are obtained by performing multi-objective optimization based on the initial paper grid parameters; The corresponding cutting piece interference probability and alignment deviation probability are determined based on the parameters of each candidate paper grid. The corresponding design conflict probability is obtained based on the interference probability of each piece and the alignment deviation probability of each piece. All candidate paper grid parameters whose design conflict probability is less than a first preset threshold are converted into feature vectors.

[0012] In one possible implementation of the first aspect, obtaining the bag optimization model based on the at least one bag design model includes: The influence weights of each piece of the at least one bag design model on the overall structural stability are determined by parameter sensitivity analysis. Cut pieces whose influence weight is lower than the second preset threshold are identified as candidate cut pieces; Predict the optimization probability of each of the candidate cut pieces; The candidate cut pieces with optimization probabilities greater than a third preset threshold are adjusted to obtain the bag optimization model.

[0013] In one possible implementation of the first aspect, predicting the optimization probability of each of the candidate cut pieces includes: Obtain historical design parameters; The optimization probability of each candidate piece is predicted based on the historical design parameters.

[0014] In one possible implementation of the first aspect, determining the component shape features of the bag includes: Obtain the design requirements for the bag; wherein, the design requirements include the overall volume, the number, shape, location, and volume of each internal compartment; The component shape characteristics are determined based on the design requirements.

[0015] Secondly, embodiments of this application provide a model building apparatus for bag design, comprising: The first feature module is used to determine the shape features of the bag's components; wherein, the component shape features include the three-dimensional configuration of the front and back panels, the circumference of the main body, the curvature of the corners, and / or the direction of the zipper; The paper grid parameter module is used to determine the paper grid parameters based on the shape characteristics of the component; wherein, the paper grid parameters refer to the geometric dimensions and tolerances of the cut pieces of each component of the bag; The second feature module is used to obtain core structural features and at least one variable component feature based on the paper grid parameters; wherein, the core structural feature refers to the geometric dimensions of the core structure of the bag, and the variable component feature refers to the geometric dimensions of a zipper, handle, or decorative part; A compatibility probability module is used to determine the compatibility probability between at least one variable component of the bag and the core structure based on the core structural features and the features of the at least one variable component; wherein, the compatibility probability is used to quantify the process feasibility of different component combinations; A bag design model module is used to generate at least one bag design model based on the compatibility probability; wherein each bag design model includes a combination of the core structure and at least one variable component; The bag optimization model module is used to obtain a bag optimization model based on the at least one bag design model.

[0016] Thirdly, embodiments of this application provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method as described in any one of the first aspects above.

[0017] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in any of the first aspects above.

[0018] Fifthly, embodiments of this application provide a computer program product that, when run on an electronic device, causes the electronic device to perform the method described in any one of the first aspects above.

[0019] It is understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart illustrating a method for constructing a model for bag design according to an embodiment of this application; Figure 2This is a schematic diagram of the implementation process of steps S400 and S410 in the bag design model construction method provided in an embodiment of this application; Figure 3 This is a schematic diagram illustrating the implementation process of steps S100, S200, and S220 in a bag design model construction method provided in an embodiment of this application. Figure 4 This is a schematic diagram of the implementation process of steps S600 and S630 in the bag design model construction method provided in an embodiment of this application; Figure 5 This is a schematic diagram showing the zipper fit degree corresponding to the curvature radius of different zipper models in the bag design model construction method provided in an embodiment of this application; Figure 6 This is a schematic diagram of the optimization probability of candidate cut pieces in a bag design model construction method provided in an embodiment of this application; Figure 7 This is a schematic diagram of the structure of the bag design model building device provided in the embodiments of this application; Figure 8 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0022] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0023] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0024] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0025] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0026] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0027] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0028] The relevant technologies suffer from the following technical shortcomings: First, the design process heavily relies on manual drafting or basic CAD tools, requiring designers to repeatedly adjust dimensions, proportions, and component positions, resulting in long design cycles and a high risk of errors. Second, the process from three-dimensional finished products to flat cutting (i.e., "cutting out the pattern") lacks digital support, heavily relying on the experience of craftsmen, making it difficult to quickly respond to diverse market demands, especially the flexible combination of different sizes and functional components in customized scenarios. Third, the high degree of coupling between various components of the bags makes design resources difficult to reuse, while the frequent modification requests from customers in OEM orders, often seemingly minor, can lead to significant issues due to the complexity of the bag manufacturing process. The unique nature of bags as flexible material composites has triggered passive adjustments to the production chain; fourth, existing modular designs mostly focus on physical connection structures, with the modular concept only extending to the user end (such as replaceable zippers or wheels), but not being integrated into the design and production ends. This results in designers lacking systematic modular tools at the beginning of the design process, making it impossible to predict the sewing feasibility and stress coordination of different component combinations; fifth, in the small-batch, fast-turnaround production model, orders are characterized by small batches, many batches, and R&D cycles compressed to days or even hours, making the "experience-based" design process that relies on physical sampling difficult to adapt.

[0029] Therefore, given that bags combine the complexity of flexible materials with the load-bearing requirements of rigid structures, existing bag design technologies cannot quantitatively predict the feasibility of combining different components during the design phase, thus making it difficult to break free from the reliance on physical prototypes.

[0030] To address the aforementioned problems, this application provides a method, apparatus, and device for constructing a bag design model. The method involves: determining the shape features of bag components; determining paper grid parameters based on the component shape features; obtaining core structural features and at least one variable component feature based on the paper grid parameters; determining the compatibility probability between the core structural features and the core structural features; generating at least one bag design model based on the compatibility probability; and obtaining an optimized bag model based on the at least one bag design model. Therefore, the bag design model construction method provided by this application defines components such as zippers and handles as independent modules, and quickly generates variations by adjusting their geometric dimensions (such as length and width), supporting personalized customization and improving design efficiency. Generating multiple design models based on compatibility probability provides consumers with more choices and helps reduce customization costs. Automatically selecting effective combinations through compatibility probability helps improve design quality. Decoupling the basic framework from functional components supports independent iteration and reuse of components.

[0031] The bag design model construction method provided in this application embodiment can be applied to electronic devices. In this case, the electronic device is the execution subject of the bag design model construction method provided in this application embodiment. This application embodiment does not impose any restrictions on the specific type of electronic device.

[0032] For example, electronic devices can be tablets, laptops, ultra-mobile personal computers (UMPCs), netbooks, desktop computers, laptops, handheld computing devices, etc., but are not limited to these.

[0033] To better understand the bag design model construction method provided in the embodiments of this application, the specific implementation process of the bag design model construction method provided in the embodiments of this application will be described by way of example below.

[0034] Figure 1 This illustration shows a schematic flowchart of a method for building a bag design model according to an embodiment of this application. The method for building a bag design model includes: S100, Determine the shape characteristics of the bag's components. These component shape characteristics include the three-dimensional configuration of the front and back panels, the circumference of the main body, the curvature of the corners, and / or the direction of the zipper.

[0035] It's understandable that the front / rear three-dimensional configuration can be quantified as the Gaussian curvature and mean curvature of a surface. Overall body circumference: Extract the closed outline of the bag at its maximum width, calculate its perimeter and offset relative to a reference surface (such as the handle surface). Corner curvature: Extract the outline at the corners, fit it to an arc, and obtain the radius of curvature. Zipper trajectory: Extract the trajectory curve of the zipper centerline, which can be represented by a series of three-dimensional spatial points and their tangent vectors.

[0036] For example, the shape features of bag components can be extracted from design drawings or physical objects.

[0037] For example, a bag component feature library can be established, and the shape features of bag components can be selected from the bag design library according to the user's design requirements. Instance segmentation models such as YOLO can be used to train a large number of bag design drawings (such as renderings and three-view drawings) to automatically identify and segment components such as the front panel, back panel, main body, corners, and zippers of various bags, thus obtaining a bag component feature library. Alternatively, a 3D scanner can be used to scan physical prototypes or clay models to obtain point cloud data. Based on the point cloud data, NURBS surfaces can be reconstructed in reverse engineering software (such as Geomagic or CATIA), and the NURBS surfaces can be segmented into independent components (front panel, back panel, main body, etc.). For each segmented component, its geometric features can be extracted to obtain a bag component feature library.

[0038] S200, determine the paper pattern parameters based on the shape characteristics of the components. The paper pattern parameters refer to the geometric dimensions and tolerances of the cut pieces for each component of the bag.

[0039] For example, the three-dimensional component shape features can be mapped onto a two-dimensional plane to obtain the geometric dimensions of each component piece of the bag. This can be achieved by dividing a non-developable surface into several strip-shaped regions, approximating each region with a ruled surface (such as a cylindrical surface or other developable surface), dividing these ruled surfaces into triangular meshes, and unfolding each ruled surface onto the same plane to obtain the unfolded surface, which is the geometric dimension of each component piece of the bag. Furthermore, based on the physical properties of each component piece (such as the elongation of leather and the shrinkage of canvas) and the relevant sewing processes (such as webbing and binding), a preset tolerance corresponding to each component piece can be obtained.

[0040] S300, based on the paper grid parameters, obtain the core structural features and at least one variable component feature. The core structural features refer to the geometric dimensions of the bag's core structure, while the variable component features refer to the geometric dimensions of zippers, handles, or decorative elements.

[0041] Understandably, core structural features include: frame geometry: such as the length, width, and height of the bag; for a hard-sided case with a frame, the core structure includes the cross-sectional shape and length of the four side borders (top, bottom, left, and right); key structural points, such as the coordinates of the pull rod's fixing point, the coordinates of the wheel mounting holes, and the contact surface between the base and the ground. Variable component features: zipper geometry includes the total zipper length, zipper head type, and the installation position curve of the zipper stop. Handle geometry includes the handle's width, height, radius of curvature of the grip portion, and the distance between the mounting holes connecting it to the case body. Decorative parts such as logo plates, metal corner protectors, and decorative webbing refer to their external outline in terms of geometry.

[0042] For example, core structural features can be obtained by mapping paper pattern parameters, and the installation position of variable components (such as a zipper installed at the opening of the main body) can be determined based on the core structural features. Based on the installation position, the geometric dimensions of the relevant cut pieces (such as the length and width of the zipper installation position) are extracted from the paper pattern parameters to obtain the variable component features.

[0043] S400, determine the compatibility probability between at least one variable component of the bag and the core structure based on the core structural features and at least one variable component feature. The compatibility probability is used to quantify the process feasibility of different component combinations.

[0044] For example, the core structure and variable components can be defined as nodes in a graph, and the assembly constraints between them (such as fitting, alignment, and insertion) can be defined as edges. The weight of the edge represents the tightness of the assembly constraint. For each assembly constraint, a compatibility scoring function is defined, such as compatibility score S = max(0, 1 − A). 目标 |A 实际 -A 目标 |). The compatibility probability is obtained by weighting the compatibility scores of each assembly constraint.

[0045] S500 generates at least one bag design model based on compatibility probability. Each bag design model includes a combination of a core structure and at least one variable component.

[0046] For example, for combinations obtained through compatibility probability, the API of CAD software can be automatically invoked to assemble and combine the core structural model with randomly selected variable component models to generate at least one bag design model.

[0047] S600, obtains a bag optimization model based on at least one bag design model.

[0048] For example, a model can be selected from at least one bag design model and determined as the bag optimization model according to the bag optimization objective.

[0049] It is understandable that the optimization goals of luggage can include: minimizing the overall weight of the luggage; minimizing the deformation of the luggage when fully loaded; minimizing the material and processing costs of all components; and maximizing the internal usable space while meeting the external dimensional constraints.

[0050] In one possible implementation, please refer to Figure 2 S400, determining the compatibility probability between at least one variable component of the bag and the core structure based on the core structural features and at least one variable component feature, including: S410, based on the core structural features and at least one variable component feature, calculate the probability of layer thickness passing at multiple preset connection points between each variable component and the core structure. The probability of layer thickness passing refers to whether multiple layers of material can successfully pass through the sewing process at multiple preset connection points of the bag without producing defects.

[0051] For example, N random samples can be taken from each connection point j. During each sampling, the total stack thickness T_j is randomly generated based on the thickness distribution of each material layer, and the maximum sewing thickness T_max of the sewing machine is randomly generated based on the sewing machine's capacity distribution. The number of times T_j ≤ T_max is satisfied, M, is counted, and the stack thickness pass probability P_j = M / N.

[0052] S420, the tear probability of the stress point is obtained according to the force direction of each variable component at each preset connection point.

[0053] For example, a feature vector of connection points can be constructed: for each connection point, key features (including connection type, material combination, geometric dimensions, force direction and estimated load size) are extracted. For a new design, the similarity (such as Euclidean distance or cosine similarity) between it and the feature vector of historical connection points in the historical design database is calculated. The top K most similar data are taken, and the success rate among them is counted as the tear probability of the stress point.

[0054] S430 calculates the corresponding minimum radius of curvature by sampling along the installation curve based on the variable component characteristics of each zipper.

[0055] For example, the installation trajectory of the zipper centerline can be obtained from the variable component features; this trajectory is a three-dimensional spatial curve. Sampling is performed on this three-dimensional spatial curve at a certain density (e.g., every 5 mm) to obtain a series of sampling points. For each sampling point, the curvature of that point is calculated using its immediate and neighboring points. The radius of curvature is the reciprocal of the curvature. By iterating through all sampling points, the minimum radius of curvature is found.

[0056] S440 determines the corresponding zipper fit based on each minimum radius of curvature.

[0057] For example, the minimum allowable bending radius (R_allow) for each zipper model can be obtained. When the minimum radius of curvature (R_min) is greater than or equal to the minimum allowable bending radius, the zipper can bend naturally with low internal stress, and the zipper fit is 1. When the minimum radius of curvature is less than the minimum allowable bending radius, the zipper is forced to bend excessively, generating internal compressive stress, and the zipper fit decreases sharply as the radius of curvature decreases. An exponential penalty function can be used: zipper fit G = exp(-α × (R_allow - R_min) / R_allow), where α is the penalty factor (which can be 2~5). Figure 5 As shown. The minimum permissible bending radius for different zipper models can be obtained by consulting the product technical manuals published by the zipper manufacturers.

[0058] S450, the corresponding compatibility probability is obtained based on the pass probability of each layer thickness, the tear probability of each stress point and / or the fit of each zipper.

[0059] For example, the compatibility probability can be obtained by weighting the layer thickness with the probability of tearing at the stress point and / or the zipper fit.

[0060] In traditional craftsmanship, the difficulty of sewing at the junctions of multiple materials relies entirely on the experience of master craftsmen, making it prone to defects such as broken needles, skipped stitches, and wrinkles during mass production. These problems often only become apparent after the finished product is produced. Through steps S410 to S450, a probabilistic model quantifies the risk of zipper thickness variations during the design phase, transforming implicit technological challenges into explicit data. This elevates the reliability of the product structure from a qualitative description to a quantitative probabilistic value, quantifying the feasibility of zipper assembly and resolving design blind spots caused by insufficient curvature leading to zipper damage or jamming. A scientific, transparent, and adjustable comprehensive evaluation framework is provided, making the trade-offs between different design objectives well-founded.

[0061] Optionally, please refer to Figure 2 S410, based on the core structural features and at least one variable component feature, calculate the stacking thickness probability of each variable component and the core structure at multiple preset connection points, including: S411, based on the core structural features and at least one variable component feature, determine multiple sets of material stack thicknesses and mating surfaces at multiple preset connection points between each variable component and the core structure. The material stack thickness includes the thickness of each layer of material in the stack.

[0062] For example, the thickness of each layer of material in the material stack can be obtained from the technical specifications or industry standards provided by the supplier.

[0063] It is understandable that the types of mating surfaces include full fit, sliding fit, and point contact.

[0064] For example, all contact areas of the "variable component-core structure" can be traversed. All preset connection points requiring analysis are automatically identified based on assembly constraints (such as "handle mounting holes" and "zipper stops"), and a unique ID is generated for each connection point. The mating surface type is determined based on the connection method between the two material layers. The material stack thickness T_j at connection point j is the sum of the thicknesses of all layers. Since the thicknesses of each layer are independent, the distribution of T_j can be obtained through convolution. If all layers are normally distributed, then T_j is also normally distributed, with a mean equal to the sum of the means of all layers and a variance equal to the sum of the variances of all layers.

[0065] S412, calculate the corresponding size fit probability and sewing success probability based on the stacking thickness and mating surface of each group of materials.

[0066] As can be understood, the size fit probability refers to the probability that the total thickness of all material layers at the connection point can fit the reserved installation space or mold slot. The sewing success probability refers to the probability that the sewing machine needle can successfully penetrate all material layers without breaking or being damaged.

[0067] For example, the maximum penetrable thickness of the sewing machine can be obtained, the thickness distribution of each layer can be determined based on the mating surface and the material stack thickness, the thickness of each layer of material can be randomly generated based on the thickness distribution of each layer, it can be determined whether the material stack thickness meets the constraints (reserved installation space or mold slot, maximum penetrable thickness) and the counter can be updated to obtain the corresponding size fit probability and sewing success probability. The maximum penetrable thickness of the sewing machine can be obtained by consulting the sewing equipment technical manual or relevant national standards.

[0068] S413, determine the radius of curvature or rotation angle at each preset connection point of each variable component.

[0069] For example, for each preset connection point, the principal curvature of the surface containing that point (usually the outer or inner surface of a bag) and the normal curvature along a specific direction (such as the direction of force or the direction of the seam) can be extracted from the 3D model. For curved surfaces, the radius of curvature along the principal curvature direction at that point is taken. For corners, the corner can be approximated as an arc, the radius of which is the radius of curvature at that point. The tangent vectors of the two sides containing the preset connection point can be obtained to calculate the corner angle.

[0070] S414, determine the neutral interlayer spacing of the inner and outer layers based on the total thickness of the material stack at each preset connection point of each variable component.

[0071] It is understandable that the neutral layer spacing refers to the difference in distance from the neutral layer of different material layers to the bending center axis.

[0072] For example, in bag manufacturing, it is typically assumed that the neutral layer of each material is located at the center of its thickness. Therefore, the distance d_i from the center of curvature to each neutral layer can be approximated as: d_i = R + (h_1 + ... + h_{i-1}) + (h_i / 2), where R is the radius of curvature on the inner side of the bend, and h_i is the thickness of the i-th material layer. The neutral layer spacing refers to the distance difference Δd = d_{i+1} - d_i between two adjacent neutral layers, which is approximately equal to the average thickness of the two layers (h_i + h_{i+1}) / 2.

[0073] S415, calculate the potential matching score for each variable component based on its radius of curvature, rotation angle, and / or neutral layer spacing.

[0074] As you can understand, ease of sewing or splicing refers to the amount of length that the outer layer of material needs to have compared to the inner layer in order to make the multiple layers of material fit together smoothly after bending. This difference in length is called ease of sewing.

[0075] For example, when the material is bent at an angle θ (radians) along an arc with a radius of curvature R (inner radius), the length difference (required ease) between the outer and inner layers can be: ΔL_needed = θ × Δd_total. Where Δd_total is the distance between the outermost and innermost neutral layers, and θ is the angular radius. Each material combination has a maximum achievable shear potential ΔL_max, and the shear potential matching score S_ease = 1 - (ΔL_needed / ΔL_max).

[0076] S416, based on the fit probability of each size, the sewing pass probability of each size, and the matching score of each ease amount, the corresponding layer thickness pass probability is obtained.

[0077] For example, the corresponding layer thickness pass probability can be obtained by weighted summing of the fit probability of each size, the sewing pass probability, and the elongation matching score.

[0078] Through steps S411 to S416 above, the comprehensive pass probability under material thickness fluctuations and machine capability fluctuations is given, which helps to avoid batch scrapping due to batch fluctuations. A theoretical calculation model for the feed rate is established and matched with the process capability, enabling designers to predict and optimize the flatness at corners during the design phase.

[0079] In one possible implementation, please refer to Figure 3 S200, Determine the paper grid parameters based on the shape characteristics of the components, including: S210: Map the shape features of the component to the paper grid parameter space to generate initial paper grid parameters. The paper grid parameter space contains the planar unfolded coordinates of each piece, and the initial paper grid parameters refer to the two-dimensional geometric parameters of each piece.

[0080] It is understandable that the initial paper grid parameters include the two-dimensional geometric parameters of various cut pieces within the paper grid parameter space.

[0081] For example, a 3D surface model (such as a NURBS surface) can be discretized into a mesh composed of a large number of triangular facets. Each triangle has a definite side length and angle in 3D space. The unfolding process from 3D to 2D is considered as an energy minimization problem. The total energy E_total is defined as the sum of the deformation energies of all triangles during the unfolding process. The most common energy term is the stretching energy, which is the difference between the side length of the 2D triangle and the corresponding side length in 3D. Using optimization algorithms such as gradient descent and L-BFGS, the coordinates of all mesh vertices in the 2D plane are iteratively adjusted to minimize the total energy E_total. When the energy converges, the resulting 2D mesh is an approximately isometric unfolding of the 3D surface. The boundary contour, internal vertex coordinates, and key feature points (such as fold lines and opening positions) of the 2D mesh are output in a parameterized form to form the initial grid parameters.

[0082] S220 determines multiple feature vectors within a preset parameter range based on the initial paper grid parameters.

[0083] For example, the two-dimensional geometric parameters of the cut pieces within the preset parameter range in the initial paper grid parameters can be converted into the corresponding feature vectors.

[0084] S230, high-frequency design features are obtained based on each eigenvector.

[0085] For example, the first k eigenvectors can be selected so that their cumulative variance contribution rate reaches a high level (e.g., 95% or 99%). These k eigenvectors represent the overall changes in shape (low frequency). The remaining eigenvectors (k+1 to M) are high-frequency design features.

[0086] S240, the paper grid parameters are obtained based on the high-frequency design characteristics.

[0087] For example, the base shape can be the mean shape determined based on the initial paper grid parameters, or it can be a shape reconstructed from low-frequency principal components. The base shape is modified according to the high-frequency features to obtain the final paper grid parameters.

[0088] Through steps S210 to S240 above, statistical learning can automatically identify and separate these high-frequency details, allowing them to be retained in the final paper pattern. This helps avoid subsequent assembly difficulties caused by the loss of details (such as zippers not fitting properly or stiff three-dimensional shapes).

[0089] Optionally, please refer to Figure 3 S220, determine multiple feature vectors within a preset parameter range based on the initial paper grid parameters, including: S221, Multiple candidate paper grid parameters are obtained by performing multi-objective optimization based on the initial paper grid parameters.

[0090] For example, based on the initial paper grid parameters, a multi-objective evolutionary algorithm such as NSGA-II (non-dominated sorting genetic algorithm) or MOPSO (multi-objective particle swarm optimization algorithm) can be used to iteratively search in the variable space, continuously generate new cut piece shapes, evaluate their performance on the three objectives, and output a set of non-dominated solutions, that is, all solutions on the Pareto front, to obtain multiple candidate paper grid parameters.

[0091] S222, determine the corresponding cutting piece interference probability and alignment deviation probability based on the parameters of each candidate paper grid.

[0092] For example, for each candidate paper grid parameter, a three-dimensional stitching simulation can be performed on all its pieces (using a mass-spring model or the finite element method). During the stitching process, the penetration between the triangular meshes of different pieces is detected in real time. Due to fluctuations in material and sewing (such as seam shrinkage rate and worker error), interference occurs randomly. Using the Monte Carlo method: key parameters in the sewing process (such as seam allowance width and seam shrinkage rate) are randomly sampled, and N stitching simulations are performed, counting the number of interferences M. Then the probability of piece interference P = M / N.

[0093] S223, the corresponding design conflict probability is obtained based on the interference probability of each cut piece and the alignment deviation probability of each piece.

[0094] For example, the corresponding design conflict probability can be calculated based on the interference probability of each piece and the alignment deviation probability of each piece, such as design conflict probability P_conflict=1-(1-P_collision)×(1-P_misalign).

[0095] S224, convert all candidate paper grid parameters whose design conflict probability is less than the first preset threshold into feature vectors.

[0096] For example, the parameters of all candidate paper grids with a design conflict probability less than a first preset threshold can be standardized and converted into feature vectors.

[0097] Through steps S221 to S224, the probability of design conflict can be used to determine the likelihood of problems occurring in production, allowing for targeted optimization and driving continuous improvement in design quality. It can automatically filter high-quality designs from a large pool of candidate designs and extract feature vectors representing "excellent genes," reducing the number of physical prototyping attempts and trial-and-error costs.

[0098] In one possible implementation, please refer to Figure 4 S600, Based on at least one bag design model, a bag optimization model is obtained, including: S610, through parameter sensitivity analysis, determine the influence weight of each piece of at least one bag design model on the overall structural stability.

[0099] For example, Sobol sequence or Latin hypercube sampling methods can be used to generate N sets of sample points in the parameter space (the combination of all fabric piece thicknesses). Each set of sample points corresponds to a specific combination of fabric piece thicknesses. For each set of sample points, a finite element simulation is run to calculate the corresponding output response. The total variance of the output response is decomposed into the variance contributed by each input parameter individually and the variance contributed by the interaction between parameters, and the first-order influence index of each fabric piece is obtained. The first-order influence index of each fabric piece is determined as its influence weight on the overall structural stability.

[0100] S620, determine the cut pieces whose influence weight is lower than the second preset threshold as candidate cut pieces.

[0101] For example, all cut pieces in the bag model can be iterated through, and their influence weights can be compared with a second preset threshold. All cut pieces whose influence weights are less than the second preset threshold are marked as candidate cut pieces.

[0102] S630 predicts the optimization probability of each candidate piece of fabric.

[0103] For example, for a candidate fabric piece, possible optimization operation types and magnitudes can be defined. A fast response surface model or Kriging model can be built for the candidate fabric piece, taking the optimization operation parameters (such as new thickness) as input and outputting two key responses: weight reduction rate and local peak stress. A large number of optimization schemes are randomly generated within the operation space, and the surrogate model is used to quickly predict their weight reduction rate and local peak stress, determining whether they meet the conditions (e.g., weight reduction rate ≥ 5%). The proportion of schemes that meet the conditions out of the total number of schemes is counted, i.e., the optimization probability. Figure 6 As shown.

[0104] S640, adjust and optimize candidate cut pieces with a probability greater than the third preset threshold to obtain the bag optimization model.

[0105] For example, for each candidate cut piece with an optimization probability greater than a third preset threshold, the weight reduction rate (or cost minimization) can be maximized. This optimal parameter can be found on the surrogate model using a simple optimization algorithm (such as the golden section search) to obtain the bag optimization model.

[0106] Through steps S610 to S640, sensitivity analysis accurately identifies "non-critical" cut pieces that contribute little to structural stability, thus pinpointing the optimization target to the correct location and avoiding the risks associated with blind optimization. By constructing a surrogate model and Monte Carlo simulation, factors such as material fluctuations and manufacturing tolerances are taken into account, predicting the success probability of different optimization schemes. This transforms uncertainty into quantifiable risk indicators, providing a scientific basis for the final decision.

[0107] Optionally, please refer to Figure 4 S630 predicts the optimization probability of each candidate cut piece, including: S631, retrieve historical design parameters.

[0108] It is understandable that historical design parameters include the geometric characteristics of the cut pieces (such as area, perimeter, minimum radius of curvature, aspect ratio), optimization type (such as thinning, punching, material replacement), specific parameters of the optimization operation (such as the thickness after thinning, the size and location of the punching, the grade of the new material), and result labels (such as the pass rate in mass production).

[0109] For example, historical design parameters can be obtained from a historical design database. This database can be built based on existing company design archives, paper drawings, process records, or publicly available industry databases.

[0110] S632, based on historical design parameters, predicts the optimization probability of each candidate piece.

[0111] For example, for the current candidate pattern piece, a feature set corresponding to the pattern piece's geometric features based on historical design parameters can be extracted to obtain a feature vector. The feature vector of the current candidate pattern piece is then input into a trained machine learning model (such as a logistic regression model, support vector machine model, etc.) to output the corresponding optimization probability.

[0112] Through the above steps S631 to S632, predictions based on historical data can more comprehensively evaluate the actual success rate of the optimization scheme. The machine learning model can use feature similarity to make analogical reasoning and give a reasonable probability estimate.

[0113] In one possible implementation, please refer to Figure 3 S100, Determine the shape characteristics of the bag's components, including: S110, Obtain the design requirements for the bag. The design requirements include the overall volume, the number, shape, location, and volume of each internal compartment.

[0114] For example, numerical values ​​can be entered via a form. For instance, the overall volume is 30L, the main pocket volume is 20L, and the front pocket volume is 5L, specifying the front pocket as a "3D pocket" with a depth of 50mm. For text-based requirement descriptions, key information can be extracted using a trained entity recognition model (such as BERT): computer compartment → size reference standard (e.g., 380mm × 260mm × 20mm); 30 liters → overall volume; front pocket → front pocket; backpack → style. This extracted information is then converted into structured data.

[0115] S120, determine the shape characteristics of the component according to design requirements.

[0116] For example, a basic bag template (such as a backpack, handbag, or rolling case) can be selected from a bag component feature library according to design requirements. This template defines the topological relationships between components (such as the front and back panels being connected by the body circumference, and the zipper being located at the opening). The overall volume and preset length-width-height ratio determine the length, width, and height of the bag. Based on the volume and position requirements of each section, the internal space is divided to determine the shape characteristics of the components.

[0117] Through the steps S110 to S120 above, the transformation from functional requirements to geometric features is automatically completed through requirement analysis and parameterized mapping, eliminating the ambiguity and inconsistency of manual transformation.

[0118] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0119] Corresponding to the bag design model construction method described in the above embodiments, this application also provides a bag design model construction device, the various modules of which can implement the various steps of the bag design model construction method. Figure 7 A structural block diagram of the bag design model building device provided in the embodiments of this application is shown. For ease of explanation, only the parts related to the embodiments of this application are shown.

[0120] Reference Figure 7 The device includes: The first feature module is used to determine the shape features of the bag's components; wherein, the component shape features include the three-dimensional configuration of the front and back panels, the circumference of the main body, the curvature of the corners, and / or the direction of the zipper; The paper grid parameter module is used to determine the paper grid parameters based on the shape characteristics of the component; wherein, the paper grid parameters refer to the geometric dimensions and tolerances of the cut pieces of each component of the bag; The second feature module is used to obtain core structural features and at least one variable component feature based on the paper grid parameters; wherein, the core structural feature refers to the geometric dimensions of the core structure of the bag, and the variable component feature refers to the geometric dimensions of a zipper, handle, or decorative part; A compatibility probability module is used to determine the compatibility probability between at least one variable component of the bag and the core structure based on the core structural features and the features of the at least one variable component; wherein, the compatibility probability is used to quantify the process feasibility of different component combinations; A bag design model module is used to generate at least one bag design model based on the compatibility probability; wherein each bag design model includes a combination of the core structure and at least one variable component; The bag optimization model module is used to obtain a bag optimization model based on the at least one bag design model.

[0121] It should be noted that the information interaction and execution process between the above modules are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, which will not be repeated here.

[0122] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above device can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0123] This application also provides an electronic device. Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 8 As shown, the electronic device 8 of this embodiment includes: at least one processor 80 ( Figure 8 Only one is shown in the image), at least one memory 81 ( Figure 8(Only one is shown in the image) and a computer program 82 stored in the at least one memory 81 and executable on the at least one processor 80, wherein when the processor 80 executes the computer program 82, it causes the electronic device 8 to perform the steps in any of the above-described embodiments of the bag design model construction method, or causes the electronic device 8 to perform the functions of each module / unit in the above-described device embodiments.

[0124] For example, the computer program 82 may be divided into one or more modules / units, which are stored in the memory 81 and executed by the processor 80 to complete this application. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program 82 in the electronic device 8.

[0125] The electronic device 8 can be a desktop computer, laptop, handheld computer, or cloud server, etc. This electronic device may include, but is not limited to, a processor 80 and a memory 81. Those skilled in the art will understand that... Figure 8 This is merely an example of electronic device 8 and does not constitute a limitation on electronic device 8. It may include more or fewer components than shown, or combine certain components, or different components, such as input / output devices, network access devices, buses, etc.

[0126] The processor 80 can be a Central Processing Unit (CPU), or it can 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 any conventional processor.

[0127] In some embodiments, the memory 81 may be an internal storage unit of the electronic device 8, such as a hard disk or memory of the electronic device 8. In other embodiments, the memory 81 may be an external storage device of the electronic device 8, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the electronic device 8. Furthermore, the memory 81 may include both internal and external storage units of the electronic device 8. The memory 81 is used to store the operating system, applications, bootloader, data, and other programs, such as the program code of the computer program. The memory 81 can also be used to temporarily store data that has been output or will be output.

[0128] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in any of the above method embodiments.

[0129] This application provides a computer program product that, when run on an electronic device, causes the electronic device to perform the steps in any of the above method embodiments.

[0130] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying 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. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0131] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0132] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0133] In the embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the electronic device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0134] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0135] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions 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 within the protection scope of this application.

Claims

1. A method for constructing a model for bag design, characterized in that, include: Determine the shape characteristics of the bag's components; wherein, the shape characteristics of the components include the three-dimensional configuration of the front and back panels, the circumference of the main body, the curvature of the corners, and / or the direction of the zipper; The paper grid parameters are determined based on the shape characteristics of the components; wherein, the paper grid parameters refer to the geometric dimensions and tolerances of the cut pieces of each component of the bag; The core structural features and at least one variable component feature are obtained based on the paper grid parameters; wherein, the core structural features refer to the geometric dimensions of the core structure of the bag, and the variable component features refer to the geometric dimensions of the zipper, handle, or decorative part; The compatibility probability between at least one variable component of the bag and the core structure is determined based on the core structural features and the features of at least one variable component; wherein, the compatibility probability is used to quantify the process feasibility of different component combinations; At least one bag design model is generated based on the compatibility probability; wherein each bag design model includes a combination of the core structure and at least one variable component; Based on the at least one bag design model, a bag optimization model is obtained.

2. The method for constructing a model for bag design as described in claim 1, characterized in that, Determining the compatibility probability between at least one variable component of the bag and the core structure based on the core structural features and the at least one variable component features includes: Based on the core structural features and the features of at least one variable component, calculate the probability of the layer thickness passing at multiple preset connection points of each variable component and the core structure; wherein, the probability of the layer thickness passing refers to whether multiple layers of material can pass through the sewing process smoothly at multiple preset connection points of the bag without producing defects; The tear probability at the stress point is obtained based on the force direction of each variable component at each preset connection point. Based on the characteristics of the variable components of each zipper, the corresponding minimum radius of curvature is calculated by sampling along the installation curve; The corresponding zipper fit is determined based on the minimum radius of curvature described above; The corresponding compatibility probability is obtained based on the probability of passing through each layer thickness, the probability of tearing at each stress point, and / or the zipper fit.

3. The method for constructing a model for bag design as described in claim 2, characterized in that, The step of calculating the stacking thickness probability of each variable component and the core structure at multiple preset connection points based on the core structural features and the features of at least one variable component includes: Based on the core structural features and the features of at least one variable component, multiple sets of material stacking thicknesses and mating surfaces are determined at multiple preset connection points between each variable component and the core structure; wherein, the material stacking thickness includes the thickness of each layer of material stacking; Calculate the corresponding size fit probability and sewing success probability based on the material stack thickness and the mating surface of each group; Determine the radius of curvature or rotation angle at each preset connection point of each of the variable components; The neutral interlayer spacing of the inner and outer layers is determined based on the total thickness of the material stack at each preset connection point of each of the variable components. Calculate the potential matching score for each variable component based on the radius of curvature, the rotation angle, and / or the neutral layer spacing of each variable component; The corresponding layer thickness passing probability is obtained based on the size adaptation probability, the sewing pass probability, and the ease matching score.

4. The method for constructing a model for bag design as described in claim 1, characterized in that, Determining the paper grid parameters based on the shape characteristics of the component includes: The shape features of the component are mapped to the paper grid parameter space to generate initial paper grid parameters; wherein, the paper grid parameter space contains the planar unfolded coordinates of each piece, and the initial paper grid parameters refer to the two-dimensional geometric parameters of each piece; Based on the initial paper grid parameters, multiple feature vectors within a preset parameter range are determined; The high-frequency design features are obtained based on the aforementioned feature vectors; The paper grid parameters are obtained based on the high-frequency design features.

5. The method for constructing a model for bag design as described in claim 4, characterized in that, The step of determining multiple feature vectors within a preset parameter range based on the initial paper grid parameters includes: Multiple candidate paper grid parameters are obtained by performing multi-objective optimization based on the initial paper grid parameters; The corresponding cutting piece interference probability and alignment deviation probability are determined based on the parameters of each candidate paper grid. The corresponding design conflict probability is obtained based on the interference probability of each piece and the alignment deviation probability of each piece. All candidate paper grid parameters whose design conflict probability is less than a first preset threshold are converted into feature vectors.

6. The method for constructing a model for bag design as described in claim 1, characterized in that, The step of obtaining a bag optimization model based on the at least one bag design model includes: The influence weights of each piece of the at least one bag design model on the overall structural stability are determined by parameter sensitivity analysis. Cut pieces whose influence weight is lower than the second preset threshold are identified as candidate cut pieces; Predict the optimization probability of each of the candidate cut pieces; The candidate cut pieces with optimization probabilities greater than a third preset threshold are adjusted to obtain the bag optimization model.

7. The method for constructing a model for bag design as described in claim 6, characterized in that, The prediction of the optimization probability of each of the candidate cut pieces includes: Obtain historical design parameters; The optimization probability of each candidate piece is predicted based on the historical design parameters.

8. The method for constructing a model for bag design as described in claim 1, characterized in that, The determination of the shape characteristics of the bag components includes: Obtain the design requirements for the bag; wherein, the design requirements include the overall volume, the number, shape, location, and volume of each internal compartment; The component shape characteristics are determined based on the design requirements.

9. A model-building device for bag design, characterized in that, include: The first feature module is used to determine the shape features of the bag's components; wherein, the component shape features include the three-dimensional configuration of the front and back panels, the circumference of the main body, the curvature of the corners, and / or the direction of the zipper; The paper grid parameter module is used to determine the paper grid parameters based on the shape characteristics of the component; wherein, the paper grid parameters refer to the geometric dimensions and tolerances of the cut pieces of each component of the bag; The second feature module is used to obtain core structural features and at least one variable component feature based on the paper grid parameters; wherein, the core structural feature refers to the geometric dimensions of the core structure of the bag, and the variable component feature refers to the geometric dimensions of a zipper, handle, or decorative part; A compatibility probability module is used to determine the compatibility probability between at least one variable component of the bag and the core structure based on the core structural features and the features of the at least one variable component; wherein, the compatibility probability is used to quantify the process feasibility of different component combinations; A bag design model module is used to generate at least one bag design model based on the compatibility probability; wherein each bag design model includes a combination of the core structure and at least one variable component; The bag optimization model module is used to obtain a bag optimization model based on the at least one bag design model.

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, it implements the method as described in any one of claims 1 to 8.

Images