A method for automatically generating design schemes based on handbags

Abstract

The present invention relates to the field of artificial intelligence technology, and in particular to an automatic generation method based on a handbag design scheme. The method comprises the following steps: constructing a three-dimensional structure model for design history data to obtain a three-dimensional structure model; performing time series change migration to obtain a variable force structure dynamic model; performing multimodal learning of thermal gradients on the three-dimensional structure model for handbag temperature test data to obtain a thermal state model set; performing brightness level contrast evaluation on handbag shooting image data and handbag design image data to obtain contrast data; performing printing material adaptability analysis on handbag printing material data to obtain printing material adaptability data; performing design decision tree learning migration on the thermal state model set to obtain a design decision tree model; performing heat loss decision pruning processing on the design decision tree model to obtain a handbag automatic design model. The present invention achieves an intelligent and automatic generation effect based on a handbag design scheme.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an automatic generation method based on a handbag design scheme. Background Art

[0002] With the development of society and the increasing demand for personalized products, as a common packaging tool, handbags also need to provide more diversified and creative design solutions. At the same time, the demand for takeout and packaged food has become a living habit for more people with people's fast-paced life. However, the design of traditional food handbags is usually based on hand-drawing or simple computer-aided design software. The design process is relatively time-consuming and lacks personalized customization capabilities. In addition, due to the subjective consciousness and experience limitations of designers, traditional design methods cannot fully consider the sustainability of materials, the strength and stability of structures, and the influence of printing and decoration. Especially for foods that need to be insulated, the design of handbags is affected by many factors such as printing appearance, material bearing capacity, vibration of handbags when delivering takeout or packaging, and insulation effect and cost. As a result, the generation of handbag design solutions is not only easily affected by subjective factors, but also difficult to balance various factors. Summary of the invention

[0003] In order to solve the above technical problems, the present invention proposes an automatic generation method based on a handbag design scheme to solve at least one of the above technical problems.

[0004] To achieve the above object, the present invention provides a method for automatically generating a handbag design scheme, comprising the following steps:

[0005] Step S1: Acquire historical design data of a handbag; construct a three-dimensional structure model for the historical design data to obtain a three-dimensional structure model; perform temporal change migration based on the three-dimensional structure model to obtain a variable force structure dynamic model;

[0006] Step S2: Acquire the thermal conductivity index data of the handbag material and the handbag temperature test data; perform multi-modal learning of thermal gradient on the three-dimensional structure model according to the thermal conductivity index data of the handbag material and the handbag temperature test data, so as to obtain a thermal state model set;

[0007] Step S3: Acquire the photographed image data of the handbag, the printed material data of the handbag, and the designed image data of the handbag; perform brightness level contrast evaluation on the photographed image data of the handbag and the designed image data of the handbag, thereby obtaining contrast data; perform printing material adaptability analysis on the printed material data of the handbag according to the contrast data, thereby obtaining printing material adaptability data;

[0008] Step S4: Based on the variable force structure dynamic model and according to the printed material adaptability data, the thermal state model set is subjected to design decision tree learning migration to obtain a design decision tree model; the design decision tree model is subjected to heat loss decision pruning to obtain a handbag automatic design model.

[0009] The present invention can obtain a variable force structure dynamic model by using the design history data of the handbag to construct a three-dimensional structure model and perform time-series change migration. By obtaining the design history data of the handbag, valuable experience and knowledge can be obtained from past designs. These data contain information on different design styles, structural forms and material selections. By constructing a three-dimensional structure model for the design history data, the design elements of the handbag can be converted into a computable model representation. By performing time-series change migration based on the three-dimensional structure model, the mechanical changes of the handbag during use can be simulated. By obtaining the thermal conductivity index data and temperature test data of the handbag material, a thermal state model of the handbag can be established. This model can reflect the thermal conductivity characteristics of the handbag under different temperature conditions and provide useful information for subsequent design decisions. By performing multi-modal learning of thermal gradients on the three-dimensional structure model, the thermal state model set can be combined with the three-dimensional structure model. This helps to comprehensively consider the structure and thermal conductivity characteristics of the handbag, provide more accurate and comprehensive data support for the automatic design model, and analyze and evaluate the handbag from a visual perspective by obtaining the photographed image data, printed material data and design image data of the handbag. This helps to understand the appearance characteristics, pattern design and printing effects of handbags. By evaluating the brightness level contrast of the image data and design image data of handbags, the contrast characteristics of handbags can be quantified. This provides a basis for the subsequent analysis of the adaptability of printed materials, ensuring that the contrast of printed materials matches the design image. By performing adaptability analysis on the printing material data of handbags through contrast data, the most suitable printing material selection can be determined. This helps to ensure the quality and consistency of printing effects and improve the brand image and market competitiveness of handbags. By learning and transferring the design decision tree based on the variable force structure dynamic model and the printing material adaptability data, the design process can be transformed into a decision tree form. This helps to systematically consider various design elements and constraints, improve the accuracy and efficiency of design decisions, and perform heat loss decision pruning on the design decision tree model to eliminate design solutions that do not meet the heat loss requirements. This helps to ensure the thermal performance and insulation effect of handbags during use, improve product quality and user experience. Through the above steps, the automatic design model of handbags is finally obtained. This model can automatically generate a handbag design solution that meets the requirements according to user needs and input parameters. This greatly improves design efficiency and innovation while reducing design costs and cycles. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A schematic diagram of the steps of the method for automatically generating a handbag design scheme according to the present invention;

[0011] Figure 2 Detailed implementation flow chart of step S1;

[0012] Figure 3 It is a schematic diagram of the detailed implementation steps of step S13. DETAILED DESCRIPTION

[0013] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0014] The present application example provides a method for automatically generating a handbag design scheme. The execution subject of the method for automatically generating a handbag design scheme includes but is not limited to the following: mechanical equipment, data processing platform, cloud server node, network upload device, etc. equipped with the system can be regarded as the general computing node of the present application, and the data processing platform includes but is not limited to: at least one of an audio and image management system, an information management system, and a cloud data management system.

[0015] See also Figures 1 to 3 The present invention provides a method for automatically generating a handbag design scheme, comprising the following steps:

[0016] Step S1: Acquire historical design data of a handbag; construct a three-dimensional structure model for the historical design data to obtain a three-dimensional structure model; perform temporal change migration based on the three-dimensional structure model to obtain a variable force structure dynamic model;

[0017] Step S2: Acquire the thermal conductivity index data of the handbag material and the handbag temperature test data; perform multi-modal learning of thermal gradient on the three-dimensional structure model according to the thermal conductivity index data of the handbag material and the handbag temperature test data, so as to obtain a thermal state model set;

[0018] Step S3: Acquire the photographed image data of the handbag, the printed material data of the handbag, and the designed image data of the handbag; perform brightness level contrast evaluation on the photographed image data of the handbag and the designed image data of the handbag, thereby obtaining contrast data; perform printing material adaptability analysis on the printed material data of the handbag according to the contrast data, thereby obtaining printing material adaptability data;

[0019] Step S4: Based on the variable force structure dynamic model and according to the printed material adaptability data, the thermal state model set is subjected to design decision tree learning migration to obtain a design decision tree model; the design decision tree model is subjected to heat loss decision pruning to obtain a handbag automatic design model.

[0020] The present invention can obtain a variable force structure dynamic model by using the design history data of the handbag to construct a three-dimensional structure model and perform time-series change migration. By obtaining the design history data of the handbag, valuable experience and knowledge can be obtained from past designs. These data contain information on different design styles, structural forms and material selections. By constructing a three-dimensional structure model for the design history data, the design elements of the handbag can be converted into a computable model representation. By performing time-series change migration based on the three-dimensional structure model, the mechanical changes of the handbag during use can be simulated. By obtaining the thermal conductivity index data and temperature test data of the handbag material, a thermal state model of the handbag can be established. This model can reflect the thermal conductivity characteristics of the handbag under different temperature conditions and provide useful information for subsequent design decisions. By performing multi-modal learning of thermal gradients on the three-dimensional structure model, the thermal state model set can be combined with the three-dimensional structure model. This helps to comprehensively consider the structure and thermal conductivity characteristics of the handbag, provide more accurate and comprehensive data support for the automatic design model, and analyze and evaluate the handbag from a visual perspective by obtaining the photographed image data, printed material data and design image data of the handbag. This helps to understand the appearance characteristics, pattern design and printing effects of handbags. By evaluating the brightness level contrast of the image data and design image data of handbags, the contrast characteristics of handbags can be quantified. This provides a basis for the subsequent analysis of the adaptability of printed materials, ensuring that the contrast of printed materials matches the design image. By performing adaptability analysis on the printing material data of handbags through contrast data, the most suitable printing material selection can be determined. This helps to ensure the quality and consistency of printing effects and improve the brand image and market competitiveness of handbags. By learning and transferring the design decision tree based on the variable force structure dynamic model and the printing material adaptability data, the design process can be transformed into a decision tree form. This helps to systematically consider various design elements and constraints, improve the accuracy and efficiency of design decisions, and perform heat loss decision pruning on the design decision tree model to eliminate design solutions that do not meet the heat loss requirements. This helps to ensure the thermal performance and insulation effect of handbags during use, improve product quality and user experience. Through the above steps, the automatic design model of handbags is finally obtained. This model can automatically generate a handbag design solution that meets the requirements according to user needs and input parameters. This greatly improves design efficiency and innovation while reducing design costs and cycles.

[0021] In this embodiment, reference Figure 1 The above is a schematic diagram of the steps of the method for automatically generating a handbag design scheme according to the present invention. The method for automatically generating a handbag design scheme according to the present invention comprises the following steps:

[0022] Step S1: Acquire historical design data of a handbag; construct a three-dimensional structure model for the historical design data to obtain a three-dimensional structure model; perform temporal change migration based on the three-dimensional structure model to obtain a variable force structure dynamic model;

[0023] In this embodiment, by collecting the design history data of the handbag, which includes the design schemes and related parameters of various handbags. Then, based on these design history data, a three-dimensional structural model of the handbag is constructed. The three-dimensional structural model describes the three-dimensional shape and components of the handbag. Next, based on the three-dimensional structural model, a time-series change migration is performed, and the changes of the handbag during use are considered to obtain a variable force structure dynamic model. This dynamic model can describe the deformation and mechanical properties of the handbag under different conditions.

[0024] Step S2: Acquire the thermal conductivity index data of the handbag material and the handbag temperature test data; perform multi-modal learning of thermal gradient on the three-dimensional structure model according to the thermal conductivity index data of the handbag material and the handbag temperature test data, so as to obtain a thermal state model set;

[0025] In this embodiment, the thermal conductivity index data of the handbag material are collected, which describe the thermal conductivity of the handbag material. At the same time, the temperature test of the handbag is performed to obtain the temperature data of the handbag in actual use. Then, the thermal conductivity index data of the handbag material is used to perform multimodal learning on the handbag temperature test data, so as to learn the thermal gradient distribution characteristics of the handbag. This learning process can consider the influence of the thermal conductivity characteristics of different materials on the temperature distribution. Finally, a thermal state model set is obtained to describe the thermal state of the handbag under different conditions.

[0026] Step S3: Acquire the photographed image data of the handbag, the printed material data of the handbag, and the designed image data of the handbag; perform brightness level contrast evaluation on the photographed image data of the handbag and the designed image data of the handbag, thereby obtaining contrast data; perform printing material adaptability analysis on the printed material data of the handbag according to the contrast data, thereby obtaining printing material adaptability data;

[0027] In this embodiment, by collecting the photographed image data of the handbag, the printed material data of the handbag, and the design image data of the handbag, the brightness level and contrast of the photographed image data and the design image data of the handbag are evaluated to obtain contrast data. This evaluation process can be used to measure the brightness and contrast intensity of the image. According to the contrast data, the printed material data of the handbag is analyzed to determine the compatibility between the printed material and the background.

[0028] Step S4: Based on the variable force structure dynamic model and according to the printed material adaptability data, the thermal state model set is subjected to design decision tree learning migration to obtain a design decision tree model; the design decision tree model is subjected to heat loss decision pruning to obtain a handbag automatic design model.

[0029] In this embodiment, the learning migration of the design decision tree is performed based on the previously obtained variable force structure dynamic model and the adaptability data of the printed material. This process will consider the deformation characteristics, mechanical properties and adaptability of the handbag to formulate a design decision tree model. The design decision tree model can be based on different needs and conditions. Finally, the design decision tree model is subjected to heat loss decision pruning, and branches whose heat loss speed does not meet the optimal decision basis of the decision tree are pruned.

[0030] In this embodiment, reference Figure 2 The above is a schematic flow chart of the detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include:

[0031] Step S11: Acquire handbag design history data;

[0032] Step S12: constructing a three-dimensional structure model for the design history data, thereby obtaining a three-dimensional structure model;

[0033] Step S13: performing a three-layer finite element analysis based on the three-dimensional structure model, thereby obtaining structural force finite element data;

[0034] Step S14: performing time-series migration on the three-dimensional structure model according to the structural force finite element data to obtain a variable force structure dynamic model.

[0035] The embodiment of the present invention collects the design history data of the handbag. These data may include various design schemes, parameters and related information of the handbag, specifically including the design scheme of the handbag, including the selection and parameter setting of design variables such as different styles, shapes, sizes and structures, material information, including the type of material used by the handbag, material characteristics, thickness, strength and other related information, structural parameters, recording the structural parameters of the handbag, such as the bottom support method, side fixing method, handle type, connection method, etc., functional requirements, including the functional requirements of the handbag, such as load-bearing capacity, ease of use, waterproof performance, wear resistance, etc., printing design, recording the printing design requirements of the handbag, such as printing patterns, texts, logos and corresponding printing positions and sizes. By acquiring the design history data, a knowledge base based on past design experience can be established, and the collected design history data can be used to construct a three-dimensional structural model. The three-dimensional structural model describes the three-dimensional shape and composition structure of the handbag. By converting the design history data into a three-dimensional structural model, the geometric shape and structural characteristics of the handbag can be better understood. Using the constructed three-dimensional structural model, a three-layer finite element analysis is performed. This analysis method divides the structure of the handbag into different layers, including the outer layer, the filling layer and the inner layer. Through finite element analysis, the stress and deformation of the handbag under stress can be simulated, and the structural stress finite element data can be obtained. These data can be used to evaluate the structural strength and stability of the handbag. Based on the structural stress finite element data obtained previously, the three-dimensional structure model is migrated in time series. This process considers the changes of the handbag during use, such as load, deformation and other factors, and applies them to the three-dimensional structure model to obtain a variable force structure dynamic model. This model can describe the changes in the deformation and mechanical properties of the handbag under different conditions, providing a basis for subsequent design decisions and optimization.

[0036] The present invention first collects historical data of handbag design. These data include samples of handbags designed in the past, related documents and records, to represent detailed data in the historical design scheme of the handbag, including materials, structures, shapes, appearances, and application indicators, and uses the historical data of handbag design to construct a three-dimensional structural model. By converting the design history data into a computable model representation, the structural characteristics and construction methods of the handbag can be better understood. The three-dimensional structural model provides an accurate description of the design elements of the handbag, and a three-layer finite element analysis is performed based on the three-dimensional structural model constructed previously. Finite element analysis is a commonly used engineering analysis method, which can infer the stress conditions of the entire structure by discretizing the structure into a finite number of units and calculating the stress and deformation conditions of each unit. By performing a three-layer finite element analysis, the force distribution and finite element data of the handbag structure can be obtained, and the three-dimensional structural model can be migrated in a time series by using the previously obtained structural force finite element data. By simulating the mechanical changes of the handbag during use, a variable force structure dynamic model can be obtained. This model can reflect the response and behavior of the handbag under different stress conditions, providing an important basis for subsequent design optimization and performance evaluation. By analyzing the dynamic model of variable force structure, we can better understand the structural characteristics and force mechanism of the handbag, so as to make reasonable design improvements and optimizations.

[0037] In this embodiment, reference Figure 3 The above is a schematic flow chart of detailed implementation steps of step S13. In this embodiment, the detailed implementation steps of step S13 include:

[0038] Step S131: performing a bearing capacity analysis of the contact between the bottom of the handbag and the support surface based on the three-dimensional structure model, thereby obtaining first bearing capacity data;

[0039] Step S132: performing a bearing capacity analysis of the handle connection point based on the three-dimensional structure model, thereby obtaining second bearing capacity data;

[0040] Step S133: performing fixed constraint analysis of different material properties on the first bearing capacity data, thereby obtaining fixed constraint data;

[0041] Step S134: performing rotation constraint analysis of different material properties on the second bearing capacity data, thereby obtaining rotation constraint data;

[0042] Step S135: performing key structural mesh division on the three-dimensional structure model according to the fixed constraint data and the rotation constraint data, thereby obtaining structural mesh discrete data, wherein the key structural mesh division includes the sealing structure division of the elastic modulus extreme point and the yield strength extreme point, the handle hole structure division and the folding structure division;

[0043] Step S136: performing a three-layer finite element analysis on the structural mesh discrete data to obtain structural force finite element data, wherein the three-layer finite element analysis includes a thermal insulation layer finite element analysis, a heat insulating layer finite element analysis and an outer layer finite element analysis.

[0044] The embodiment of the present invention uses a well-established three-dimensional structural model to perform a bearing capacity analysis of the bottom of the handbag in contact with the support surface. By applying appropriate loads and boundary conditions, the mechanical behavior of the handbag when the bottom contacts the support surface is simulated. The results obtained by the analysis include data such as stress, deformation and bearing capacity of the bottom contact area, thereby obtaining first bearing capacity data. Using the three-dimensional structural model, a bearing capacity analysis of the handle connection point is performed. By simulating the force condition of the handle connection point, the strength and stability of the connection point can be evaluated. This analysis considers factors such as the connection mode and material properties of the handle and the bag body, and obtains second bearing capacity data, including information such as stress, deformation and bearing capacity of the connection point. Based on the first bearing capacity data, a fixed constraint analysis of different material properties is performed. This analysis considers the influence of different material properties such as stiffness and strength on the fixed constraint effect of the bottom contacting the support surface. By analyzing the obtained fixed constraint data, the influence of material selection on bearing capacity and stability can be better understood, and a basis for optimal design can be provided. Using the second bearing capacity data, a rotation constraint analysis of different material properties is performed. This analysis considers the influence of different material properties such as stiffness and strength on the rotation constraint effect of the handle connection point. By analyzing the rotation constraint data obtained, we can better understand the impact of material selection on the stability and reliability of the connection points and provide guidance for design optimization. According to the fixed constraint data and the rotation constraint data, the three-dimensional structure model is divided into key structural meshes. This step includes dividing the model into different mesh units to more accurately simulate the key structural parts of the handbag. The key structural mesh division can include dividing the sealing structure, handle hole structure and folding structure of the elastic modulus extreme point and yield strength extreme point, and performing mesh discretization for subsequent finite element analysis. Using the structural mesh discretization data, a three-layer finite element analysis is performed. This analysis includes independent finite element analysis of the three layers of the handbag, including the insulation layer, the thermal insulation layer and the outer layer. By applying appropriate loads and boundary conditions, the stress conditions of the handbag in actual use are simulated. The results obtained by the analysis can obtain data such as the force distribution, stress concentration area and deformation of the structure, so as to evaluate the structural performance and reliability of the handbag.

[0045] The present invention first analyzes the bearing capacity of the bottom of the handbag in contact with the support surface by using a three-dimensional structure model. By considering the contact force and the force condition between the bottom and the support surface, the first bearing capacity data can be calculated. These data can help evaluate the stability and load bearing capacity of the bottom structure of the handbag when placing or carrying items. Using the three-dimensional structure model, the bearing capacity of the handle connection point of the handbag is analyzed. By considering the force condition and load transfer mechanism at the handle connection point, the second bearing capacity data can be calculated. These data can help evaluate the stability and bearing capacity of the handle connection point of the handbag during use, so as to ensure that the handbag can withstand the expected load and maintain structural integrity. Fixed constraint analysis of different material properties is performed on the first bearing capacity data. Fixed constraint data can be obtained by considering the rigidity, strength and constraint conditions of different materials. These data can help evaluate the constraint condition when the bottom of the handbag contacts the support surface, so as to determine the appropriate material and structural design, and ensure that the bottom structure can remain stable and reliable when subjected to force. Rotation constraint analysis of different material properties is performed on the second bearing capacity data. Rotation constraint data can be obtained by considering the elasticity and rotation constraint conditions of different materials. These data can help evaluate the rotational constraints of the handle connection points of the handbag to determine the appropriate materials and designs to ensure that the handle connection points can withstand the expected rotational force when the handbag is in use and maintain the stability of the structure. According to the fixed constraint data and the rotational constraint data, the key structural mesh of the three-dimensional structure model is divided. The key structural mesh division includes the sealing structure, the handle hole structure and the folding structure. By dividing the structural mesh, the complex handbag structure can be decomposed into discrete mesh units to provide an accurate model for the subsequent finite element analysis. Using the structural mesh discrete data, a three-layer finite element analysis is performed. The three-layer finite element analysis includes the finite element analysis of the insulation layer, the heat insulation layer and the outer layer. By performing finite element analysis on each layer, the stress conditions of the handbag structure at different levels can be calculated, including stress and deformation. These structural force finite data can be used to evaluate the structural performance and stability of the handbag.

[0046] Preferably, the specific steps of step S136 are:

[0047] Performing three-layer stress distribution correlation analysis on the discrete data of the structural grid, thereby obtaining stress distribution correlation data, wherein the stress distribution correlation data includes insulation layer stress distribution correlation data, heat insulation layer stress distribution correlation data and outer layer stress distribution correlation data;

[0048] Performing thermal stress analysis on the thermal insulation layer stress distribution correlation data and the heat insulation layer stress distribution correlation data when different internal and external temperatures change, thereby obtaining thermal stress correlation data, wherein the thermal stress analysis includes deformation analysis and stress distribution analysis;

[0049] Perform material combination clustering on the thermal stress correlation data and the outer layer stress distribution correlation data to obtain stress distribution clustering data, wherein the material combination clustering includes material category clustering, material thickness clustering and material density clustering;

[0050] A three-layer finite element analysis is performed on the structural grid discrete data according to the stress distribution clustering data to obtain the structural force finite element data, wherein the three-layer finite element analysis includes the insulation layer finite element analysis, the heat insulation layer finite element analysis and the outer layer finite element analysis.

[0051] The embodiment of the present invention uses the discrete data of the structural grid to perform a three-layer stress distribution correlation analysis. According to the structural force finite element data obtained by the three-layer finite element analysis, the stress distribution of each layer can be obtained by performing stress analysis on the grids of different levels. This analysis can provide stress distribution correlation data of the thermal insulation layer, the heat insulation layer and the outer layer, so as to further understand the stress conditions and mutual influence of each layer. The thermal stress analysis when different internal and external temperatures change is performed using the stress distribution correlation data of the thermal insulation layer and the stress distribution correlation data of the heat insulation layer. Considering the thermal expansion and heat conduction effects caused by temperature changes, the deformation and stress distribution of the structure under different temperature conditions are analyzed. This analysis can obtain thermal stress correlation data, including deformation analysis and stress distribution analysis, so as to evaluate the stability and reliability of the structure under temperature changes. The cluster analysis of material combinations is performed using the thermal stress correlation data and the outer layer stress distribution correlation data. According to the characteristics of the material type, thickness and density, the structures of different material combinations are classified. Through cluster analysis, stress distribution cluster data can be obtained to further understand the stress distribution of different material combinations and provide guidance for structural optimization. Based on the stress distribution clustering data, a three-layer finite element analysis is performed on the structural mesh discrete data. This analysis includes independent finite element analysis of the thermal insulation layer, the heat insulation layer, and the outer layer. By applying appropriate loads and boundary conditions, the stress conditions of the handbag in actual use are simulated. The results obtained from the analysis can obtain data such as the stress distribution of the structure, the stress concentration area, and the deformation, so as to evaluate the structural performance and reliability of the handbag.

[0052] The present invention firstly performs a three-layer stress distribution correlation analysis on the discrete data of the structural grid. By analyzing the stress distribution of each layer, stress distribution correlation data can be obtained, including stress distribution correlation data of the thermal insulation layer, the heat insulation layer and the outer layer. These data can be used to evaluate the stress distribution of each layer structure when subjected to force, and assist in optimizing the structural design and material selection. Thermal stress analysis is performed when different internal and external temperatures change for the stress distribution correlation data of the thermal insulation layer and the stress distribution correlation data of the heat insulation layer. By considering the thermal expansion and heat conduction effects caused by temperature changes, thermal stress correlation data can be calculated. These data include deformation analysis and stress distribution analysis, which are used to evaluate the thermal stress of the structure under different temperature conditions to ensure the stability and safety of the structure when the temperature changes. , Material combination clustering analysis is performed using the thermal stress correlation data and the outer layer stress distribution correlation data. By clustering material combinations with similar stress distribution characteristics, stress distribution clustering data can be obtained. These data can help evaluate the influence of different material combinations on stress distribution, and provide a reference for optimizing material selection and structural design. According to the stress distribution clustering data, a three-layer finite element analysis is performed on the discrete data of the structural grid. The analysis includes finite element analysis of the insulation layer, thermal insulation layer and outer layer. Through finite element analysis, the stress conditions of the structure in each layer can be calculated, including stress and deformation. These structural force finite element data can be used to evaluate the performance and stability of the structure.

[0053] Preferably, the specific steps of step S2 are:

[0054] Step S21: Acquire the thermal conductivity index data of the handbag material and the handbag temperature test data;

[0055] Step S22: constructing a three-layer heat conduction state matrix for the handbag temperature test data according to the heat conduction index data of the handbag material, thereby obtaining a three-layer heat conduction state matrix;

[0056] Step S23: performing heat conduction space structure analysis according to the three-layer heat conduction state matrix, thereby obtaining heat conduction space data;

[0057] Step S24: extracting the conduction boundary and conduction path features of the heat conduction space data, thereby obtaining heat conduction boundary data and heat conduction path data;

[0058] Step S25: performing a gas permeability regression analysis at the sealing point according to the heat conduction boundary data, thereby obtaining gas permeability regression data;

[0059] Step S26: Perform multimodal learning of thermal gradients on the three-dimensional structure model according to the three-layer heat conduction state matrix, gas permeation regression data, and heat conduction path data, thereby obtaining a thermal state model set.

[0060] The embodiment of the present invention needs to obtain the thermal conductivity index data of the materials used in the handbag, such as thermal conductivity and thermal diffusivity. These data can be obtained through technical documents provided by the material supplier or laboratory tests. In addition, it is necessary to perform a temperature test on the handbag. A temperature sensor or an infrared thermal imager can be used to measure the temperature change of the handbag under different conditions, and the temperature test data of the handbag is processed to construct a three-layer thermal conduction state matrix. According to the structural layering of the handbag, the handbag is divided into a thermal insulation layer, a heat insulation layer and an outer layer, and the thermal conduction state matrix of each layer is calculated respectively. The thermal conduction state matrix reflects the thermal conduction characteristics and temperature distribution of each layer of material. Perform a thermal conduction spatial structure analysis. By analyzing the thermal conduction relationship and heat flow distribution between the layers, the thermal conduction spatial data is obtained, including information such as the thermal conduction channel, thermal conduction path and thermal conduction resistance between the layers. , Extract the conduction boundary and conduction path features. The conduction boundary refers to the interface between the layers, and the conduction path refers to the path of heat conduction in the handbag. By extracting the thermal conduction boundary data and the thermal conduction path data, the distribution of the channels and paths of heat conduction can be further understood. Perform gas permeability regression analysis at the seal. Through testing or simulation, obtain the gas permeability data at the seal, and perform regression analysis with the heat conduction boundary data to establish a gas permeability regression model. This model can be used to predict the gas permeability at the seal and perform multi-modal learning of thermal gradients on the three-dimensional structure model of the handbag. By comprehensively analyzing and learning the data of multiple modes, a thermal state model set is obtained. This model set can provide the temperature distribution and thermal characteristics of the handbag under different heat conduction states.

[0061] The present invention first collects the thermal conductivity index data of the handbag material, which are used to describe the thermal conductivity performance of the material. At the same time, the handbag temperature test is carried out to obtain the temperature data under actual use. According to the thermal conductivity index data of the handbag material, combined with the handbag temperature test data, a three-layer thermal conductivity state matrix is ​​constructed. This step divides the interior of the handbag into three layers, analyzes the thermal conductivity conditions between the layers, and constructs the thermal conductivity state matrix. The three-layer thermal conductivity state matrix is ​​used to perform thermal conductivity spatial structure analysis. By analyzing the thermal conductivity characteristics between different layers, thermal conductivity spatial data is obtained to describe the thermal conductivity conditions and heat distribution inside the handbag. The conduction boundary and conduction path characteristics in the thermal conduction spatial data are extracted. By analyzing the boundary conditions and conduction paths of thermal conduction, thermal conduction boundary data and thermal conduction path data are obtained, which are used to further analyze the thermal conduction behavior and influencing factors inside the handbag. The thermal conduction boundary data is used to perform gas permeability regression analysis at the seal. By analyzing the relationship between the thermal conduction boundary and gas permeation, gas permeation regression data is obtained to evaluate the performance and characteristics of the handbag in terms of sealing. According to the three-layer heat conduction state matrix, gas permeation regression data and heat conduction path data, the three-dimensional structure model of the handbag is subjected to multimodal learning of thermal gradient. By learning the thermal state changes between different modes, a set of thermal state models is obtained to describe the thermal behavior and thermal performance of the handbag under different use conditions. These models can be used to optimize the design and improve the thermal performance of the handbag. Specifically, a model suitable for thermal gradient learning is designed. Deep learning models (such as convolutional neural networks, recurrent neural networks) or traditional machine learning models (such as support vector machines, random forests) can be selected as basic models. The input of the model includes multimodal data, and the output is the temperature distribution and thermal characteristics of the handbag under different heat conduction states. Feature-level fusion and decision-level fusion can be used to fuse multimodal data, and the thermal response state under different thermal conditions can be represented by a state matrix.

[0062] Preferably, the specific steps of step S22 are:

[0063] Step S221: clustering the test environment temperature of the bag temperature test data to obtain environment temperature clustering data;

[0064] Step S222: performing a temperature distribution time series analysis of different material densities, thicknesses and characteristics on the temperature test data of the handbag according to the ambient temperature clustering data and the thermal conductivity index data of the handbag material, thereby obtaining temperature distribution time series data;

[0065] Step S223: clustering the time series temperature of the items in the bag on the temperature distribution time series data, thereby obtaining time series temperature cluster distribution data;

[0066] Step S224: constructing a thermal environment memory network for the time series temperature cluster distribution data to obtain a thermal environment memory model;

[0067] Step S225: constructing a three-layer heat conduction state matrix based on the thermal environment memory model to obtain a three-layer heat conduction state matrix, wherein the three-layer heat conduction state matrix construction includes the heat preservation layer, the heat insulation layer and the outer layer.

[0068] The embodiment of the present invention collects the temperature test data of the handbag, including the temperature measurement results of different parts of the handbag structure at different ambient temperatures, including at least the temperature measurement of the sealing part of the handbag, between multiple layers, and the parts where the loaded items and the outer layer are in contact with the environment, and clusters the temperature test data using a clustering algorithm (such as K-means, hierarchical clustering, etc.), and classifies the test data of similar temperatures into one category. Combined with the thermal conductivity index data of the handbag material, the temperature test data under each ambient temperature cluster is analyzed, and according to the material density, thickness and other characteristics of the handbag, combined with heat transfer theory and numerical methods, a model is established or an existing model is used to simulate the temperature distribution of the handbag under different thermal conduction states, and the simulated or predicted temperature distribution is compared and verified with the actual temperature test data, thereby obtaining the temperature distribution time series data. The temperature distribution time series data is processed to extract key features, such as temperature change rate and temperature peak value. The extracted features are clustered using a clustering algorithm to classify similar temperature time series into one category. According to the clustering results, the time series temperature cluster distribution data is obtained, that is, different time series temperature distributions are classified into several clusters, and the time series temperature cluster distribution data is used to build a thermal environment memory network. Models such as recurrent neural networks (RNN) or long short-term memory networks (LSTM) can be used to train the time series temperature cluster distribution data using the constructed thermal environment memory network to learn the time series characteristics and patterns of the thermal environment, optimize and adjust the structure and parameters of the thermal environment memory network, so as to improve its fitting ability and prediction performance for the time series temperature cluster distribution data. According to the structure and material properties of the handbag, the inferred temperature distribution data is decomposed into three heat conduction state matrices: thermal insulation layer, heat insulating layer and outer layer, and the heat conduction state matrix of the thermal insulation layer is constructed: according to the temperature distribution data inferred by the thermal environment memory model, the temperature distribution characteristics inside the thermal insulation layer are extracted and modeled, according to the temperature distribution data inferred by the thermal environment memory model, the temperature distribution characteristics inside the thermal insulation layer are extracted and modeled, according to the temperature distribution data inferred by the thermal environment memory model, the temperature distribution characteristics of the outer layer are extracted and modeled, the heat conduction state matrices of the thermal insulation layer, heat insulating layer and outer layer are integrated to obtain a three-layer heat conduction state matrix, which describes the temperature distribution and thermal characteristics of the handbag under different heat conduction states.

[0069] The present invention firstly performs cluster analysis of the test environment temperature for the handbag temperature test data. By clustering similar environment temperature data, environment temperature cluster data is obtained, which is used to further analyze the temperature change of the handbag under different environment temperatures. The environment temperature cluster data and the thermal conductivity index data of the handbag material are used to perform a time series analysis of the temperature distribution of different material densities, thicknesses and characteristics on the handbag temperature test data. By analyzing the influence of different parameters on the temperature distribution, the time series data of the temperature distribution changing with time is obtained, which is used to describe the dynamic change of the temperature inside the handbag. The time series temperature cluster analysis of the handbag items is performed on the temperature distribution time series data. By clustering similar time series temperature data, the time series temperature cluster distribution data is obtained, which is used to reveal the temperature change characteristics of the items inside the handbag in different time periods. The time series temperature cluster distribution data is used to construct a thermal environment memory network. The network can capture the temperature distribution characteristics of the handbag under different environment temperature and time conditions, and establish a thermal environment memory model, which is used to predict and simulate the temperature distribution of the handbag in the future environment. The thermal environment memory model is used to construct a three-layer heat conduction state matrix. This step involves constructing a thermal conductivity matrix for the bag's insulation layer, thermal insulation layer, and outer layer to describe the thermal conductivity characteristics between different layers. Through this matrix, we can understand the thermal conductivity behavior and heat distribution of different layers inside the bag in more detail.

[0070] Preferably, the specific steps of step S3 are:

[0071] Step S31: Acquire the photographed image data of the handbag and the design image data of the handbag;

[0072] Step S32: performing HSV pixel clustering grouping on the bag image data to obtain color pixel clustering data;

[0073] Step S33: constructing a local binary texture feature map for the image data of the handbag, thereby obtaining texture map data;

[0074] Step S34: performing brightness level contrast evaluation on the handbag design image data according to the texture map data and the color pixel clustering data, thereby obtaining contrast data;

[0075] Step S35: Acquire the printing material data of the handbag;

[0076] Step S36: Perform printing material suitability analysis on the handbag printing material data according to the contrast data, thereby obtaining printing material suitability data.

[0077] The embodiment of the present invention can obtain the captured image data of the handbag by using a camera, a scanner and other devices to collect the data, obtain the design image data of the handbag, obtain the design file or image of the handbag from the designer or relevant department, and perform image preprocessing on the captured image data of the handbag, including denoising, adjusting brightness and contrast and other operations, convert the preprocessed image data into the HSV color space, extract the hue, saturation and brightness information of the image, cluster the color pixels using a clustering algorithm, classify the pixels of similar colors into one category, and obtain color pixel clustering data according to the clustering results, that is, group the pixels in the image according to color. The captured image data of the handbag is preprocessed, including denoising, adjusting brightness and contrast, etc. The preprocessed image data is converted into a grayscale image, and the grayscale image is processed using a local binarization algorithm (such as the Otsu algorithm, the adaptive threshold algorithm, etc.) to obtain a binarized image. A texture feature map is constructed based on the binarized image. Feature extraction can be performed using methods such as local binary patterns (LBP) and histogram of oriented gradients (HOG) to obtain texture map data, which reflects the texture characteristics of the handbag image. The design image data of the handbag is preprocessed, including denoising, adjusting brightness and contrast, and the design image is evaluated using an appropriate evaluation method (such as a brightness level contrast evaluation algorithm) to obtain contrast data. Contact the printing material supplier or relevant department to obtain relevant information on the printing materials of the handbag, including material type, characteristics, optical parameters, etc., to ensure that the obtained printing material data is consistent with the design and manufacturing requirements of the handbag. The contrast data is compared and analyzed with the data of printed materials for handbags to evaluate the suitability of printed materials. The brightness level and color information in the contrast data are considered and compared with the characteristics of the printed materials. Appropriate analysis methods and indicators, such as similarity comparison and color matching, are used to evaluate the suitability of printed materials. Based on the analysis results, the printing material suitability data is obtained to determine whether the selected printing material is suitable for the production of handbags.

[0078] The present invention first collects the photographed image data and the design image data of the handbag. By photographing the actual image of the handbag and obtaining the design image of the handbag, a data basis is provided for the subsequent printing characteristics of the appearance of the handbag. HSV (hue, saturation, brightness) pixel clustering and grouping are performed for the photographed image data of the handbag. By clustering pixels with similar color features, color pixel clustering data is obtained, which is used to further analyze the color distribution of the handbag. A local binary texture feature map is constructed for the photographed image data of the handbag. Texture map data is obtained by extracting the texture features of the image and performing local binarization processing. These data can reveal the texture distribution of the surface of the handbag and provide a basis for subsequent texture feature analysis. The texture map data and color pixel clustering data are used to evaluate the brightness level and contrast of the design image data of the handbag. Contrast data is obtained by analyzing the brightness difference and contrast level of the image. These data can be used to measure the visual effect and recognizability of the handbag design. Relevant data of the printing material used for the handbag is obtained. This data can include the color, glossiness, transparency and other characteristics of the printed material, providing a basis for the subsequent analysis of the suitability of the printed material. Use contrast data to perform a suitability analysis on the printed material used for the tote bag. By comparing the contrast data and the characteristics of the printed material, the degree of match between the printed material and the tote bag design can be evaluated. This data can be used to guide the selection of appropriate printing materials to ensure that the printing effect of the tote bag meets expectations.

[0079] Preferably, the specific steps of step S36 are:

[0080] Step S361: Perform printing correlation feature analysis on the handbag printing material data to obtain color permeability data, glossiness data and texture data;

[0081] Step S362: performing durability evaluation on the handbag printing material data to obtain durability evaluation data, wherein the durability evaluation includes material durability evaluation, printed product adhesion evaluation and coating adhesion evaluation;

[0082] Step S363: performing printing adhesion uniformity matching and printing adhesion distortion matching on the glossiness data and the texture data according to the contrast data, thereby obtaining printing adhesion matching data;

[0083] Step S364: performing contrast time series difference analysis on the print adhesion matching data and the color permeability data according to the durability evaluation data, thereby obtaining contrast time series difference data;

[0084] Step S365: Perform printing material adaptability analysis on the handbag printing material data according to the contrast time series difference data, so as to obtain printing material adaptability data.

[0085] The embodiment of the present invention analyzes the printing-related characteristics of the handbag printing material data, including key characteristics such as color permeability, glossiness and texture. For color permeability, the interaction between the dye or ink of the printing material and the material is analyzed to evaluate whether the color penetrates into the material and obtain corresponding color permeability data. For glossiness, a gloss meter or related equipment is used to measure the glossiness of the printing material to obtain corresponding glossiness data. For texture, a texture meter or related method is used to evaluate the texture characteristics of the printing material to obtain corresponding texture data. Material durability evaluation is performed to examine the durability of the printing material, including indicators such as scratch resistance and wear resistance, and tests are performed according to relevant standards or test methods to obtain material durability evaluation data. Print adhesion evaluation is performed to evaluate the adhesion between the printed material and the material, including indicators such as peel strength and adhesion, and the corresponding test method is used to evaluate to obtain print adhesion evaluation data. Coating adhesion evaluation is performed. If the printing material has a coating, the adhesion between the coating and the material is evaluated, including indicators such as coating peel strength and adhesion, and the coating adhesion evaluation data is obtained by using relevant test methods. Based on the contrast data obtained previously, the gloss data and texture data are matched for printing adhesion uniformity. The gloss data is analyzed to compare the gloss differences in different areas, evaluate the uniformity of printing adhesion, and obtain printing adhesion uniformity matching data. The texture data is analyzed to compare the texture differences in different areas, evaluate the distortion of printing adhesion, and obtain printing adhesion distortion matching data. Using the previously obtained durability evaluation data, it is compared with the printing adhesion matching data for contrast analysis, and the contrast differences of printing adhesion at different time points or under different conditions are compared to evaluate the stability and consistency of printing adhesion. The durability evaluation data and the color permeability data are analyzed for contrast time series difference to detect the changes in color permeability at different time points or under different conditions. Based on the previously obtained contrast time series difference data, the printing material adaptability analysis is performed on the handbag printing material data, and the differences in printing adhesion performance of different material samples are compared to evaluate the adaptability of printing materials. The trends and patterns in the contrast time series difference data are analyzed to determine the adaptability of different materials under different printing conditions.

[0086] The present invention firstly performs printing correlation feature analysis on the handbag printing material data, and extracts relevant data such as color permeability, glossiness and texture. These data can describe the color permeability, surface brightness and texture richness of the printing material on the handbag, and provide more detailed information for the subsequent printing material adaptability analysis. The handbag printing material data is subjected to durability evaluation, including material durability evaluation, printed product adhesion evaluation and coating adhesion evaluation. Durability evaluation data is obtained by evaluating the durability of the printing material, the adhesion of the printed product to the material and the adhesion of the coating. These data can evaluate the performance and stability of the printing material under long-term use and environmental conditions. Based on the contrast data, the glossiness data and the texture data are matched for printing adhesion uniformity and printing adhesion distortion. The printing adhesion matching data is obtained by comparing the consistency of the glossiness and texture of the printing material with the contrast data. These data can evaluate the adhesion uniformity and adhesion distortion of printing in different areas. Using the durability evaluation data, the printing adhesion matching data and the color permeability data are subjected to contrast time series difference analysis. By comparing the contrast data at different time points, the changes in printing adhesion and color penetration over time are revealed, and the contrast time series difference data are obtained. These data can be used to analyze the change trend and quality stability of printed products during use. According to the contrast time series difference data, the printing material data of the handbag is analyzed for printing material adaptability. By analyzing the relationship between the contrast time series difference data and the characteristics of the printing material, the adaptability of the printing material to the handbag is evaluated. Taking into account the printing material adaptability data, durability evaluation data and contrast time series difference data, the printing material of the handbag is comprehensively analyzed. By weighing these data, the final adaptability evaluation result of the handbag printing material is obtained. This result can guide the consideration of the balance between its matching with the handbag design, durability and visual effect when selecting suitable printing materials.

[0087] Preferably, the specific steps of step S4 are:

[0088] Step S41: performing load-bearing and printing adaptability genetic forest analysis based on the variable force structure dynamic model and the printing material adaptability data, thereby obtaining load-bearing printing adaptability analysis data;

[0089] Step S42: performing sealing gas permeability analysis of different earthquake intensities and different vibration durations based on the variable force structure dynamic model, thereby obtaining vibration gas permeability data;

[0090] Step S43: performing heat exchange distribution flow rate analysis on the vibration gas permeability data based on the thermal state model set, thereby obtaining heat flow rate distribution data;

[0091] Step S44: performing design decision tree learning migration on the thermal state model set and the bearer printing adaptation analysis data to obtain a design decision tree model;

[0092] Step S45: performing heat loss decision pruning processing on the design decision tree model according to the heat flow rate distribution data, thereby obtaining an automatic design model for handbags.

[0093] The embodiment of the present invention establishes a dynamic model based on a variable force structure, considers the structural characteristics of the handbag and the variable force load, simulates the load-bearing process, and combines the printing material adaptability data. The printing material adaptability data is used as the input of the genetic forest analysis, and the load-bearing capacity and printing adaptability are analyzed using a genetic algorithm or related technology. In the genetic forest analysis, through an iterative and optimization process, load-bearing printing adaptability analysis data is obtained to evaluate the influence of different printing materials and structural parameters on the handbag. The dynamic model based on the variable force structure is used to simulate the deformation of the handbag under different earthquake intensities and vibration durations. Combined with the sealing gas permeability test data, the gas permeability of the handbag under vibration conditions is analyzed, and the influence of different earthquake intensities and vibration durations on the deformation degree and gas permeation path of the handbag seal is considered to obtain the corresponding vibration gas permeability data. A thermal state model set is established, and factors such as the temperature difference inside and outside the handbag, gas temperature distribution and heat conduction are considered. The thermal state model set is used to analyze the heat exchange process in the vibration gas permeability data. The gas velocity distribution in the handbag is considered. According to the model calculation results, the heat flow velocity distribution data in the vibration gas penetration process is obtained, which is used to evaluate the heat conduction inside the handbag. The thermal state model set and the previously obtained load-bearing printing adaptation analysis data are used as training sets. The decision tree learning algorithm in machine learning is applied. The decision tree learning algorithm is used to learn and transfer the thermal state model set and the load-bearing printing adaptation analysis data to construct a design decision tree model. The design decision tree model can be used to predict suitable printing materials, structural parameters and heat conduction characteristics according to the given handbag design requirements and conditions, so as to optimize the design of the handbag. Based on the heat flow velocity distribution data and the design decision tree model, heat loss decision pruning is performed. This means that according to the design requirements and conditions of the handbag, those decision branches that perform poorly in the heat flow velocity distribution data are pruned, and after pruning, an optimized automatic design model for the handbag is obtained. The model can automatically recommend suitable printing materials, structural parameters, thermal conductivity characteristics, etc. based on the input design requirements and conditions to achieve the optimal design of the handbag.

[0094] The present invention firstly uses a variable force structure dynamic model and combines the printing material adaptability data to perform a genetic forest analysis of load-bearing and printing adaptability. By analyzing the adaptability and load-bearing capacity of the printing material, load-bearing printing adaptability analysis data is obtained. These data can be used to evaluate the adaptability and stability of the printing material during the load-bearing and printing process. Using the variable force structure dynamic model, the sealing gas permeability under different earthquake intensities and vibration durations is analyzed. By simulating the sealing gas permeability under different vibration conditions, the vibration gas permeability data is obtained. These data can be used to evaluate the air tightness and sealing effect of the handbag under a vibration environment to simulate the insulation effect of the handbag loaded with food when delivering takeout and packing takeout. Using the thermal state model set, the vibration gas permeability data is analyzed for heat exchange distribution flow rate. By analyzing the heat exchange of the gas in the handbag, the heat flow rate distribution data is obtained. These data can be used to evaluate the thermal characteristics and heat loss of the handbag under a vibration environment. Using the thermal state model set and the load-bearing printing adaptability analysis data, the learning migration of the design decision tree is performed. By analyzing the relationship between the thermal state model and the printing adaptability data, a design decision tree model is constructed. This model can be used to automatically make design decisions and select appropriate materials and printing methods based on the requirements and conditions of the handbag. According to the heat flow velocity distribution data, the design decision tree model is pruned for heat loss decisions. By analyzing the relationship between the heat flow velocity distribution and the design decision tree model, the structure and parameters of the decision tree model are optimized to obtain the automatic design model of the handbag. This model can automatically select appropriate materials and design solutions based on the needs and environmental conditions of the handbag to improve the thermal performance and energy saving effect of the handbag. Based on the automatic design model, users can input relevant parameters and use the automatic design model to output the corresponding CAD three-dimensional handbag structure and its design-related parameters after considering factors that cannot be directly generalized, such as cost, to clearly display the specific optimal design solution.

[0095] Preferably, the specific steps of step S44 are:

[0096] Step S441: performing three-layer thermal gradient adaptation on the bearing printing adaptation analysis data based on the thermal state model set, thereby obtaining thermal gradient adaptation data, wherein the three-layer thermal gradient adaptation includes material thermal gradient adaptation of the thermal insulation layer, the heat insulating layer and the outer layer, and sealing thermal gradient adaptation between the thermal insulation layer, the heat insulating layer and the outer layer;

[0097] Step S442: sorting the thermal gradient adaptation data by feature importance, thereby obtaining thermal gradient sequence data;

[0098] Step S443: constructing a tree diagram for the thermal gradient sequence data, thereby obtaining thermal gradient tree data;

[0099] Step S444: performing row design decision tree learning migration on the thermal state model set according to the thermal gradient tree data to obtain a design decision tree model.

[0100] The embodiment of the present invention performs three-layer thermal gradient adaptation based on the thermal state model set and the previously obtained load-bearing printing adaptation analysis data. This includes the thermal gradient adaptation of the thermal insulation layer, the heat insulating layer and the outer layer of the handbag, as well as the thermal gradient adaptation of the sealing between the thermal insulation layer, the heat insulating layer and the outer layer. In the adaptation process, factors such as the thermal conductivity, thickness and thermal conduction characteristics of different materials are considered, and the thermal gradient adaptation data is obtained through model calculation and optimization. These data reflect the thermal conductivity and adaptability of the handbag at different levels and regions. The thermal gradient adaptation data is sorted by feature importance to determine which thermal gradient features have the most important impact on the design of the handbag. A feature selection algorithm (such as a method based on information gain or a method based on regression coefficient) is used to sort the features in the thermal gradient adaptation data. According to the sorting results, the thermal gradient sequence data is obtained and arranged from high to low in importance for subsequent tree diagram construction and decision tree learning migration. Based on the thermal gradient sequence data, a tree diagram is constructed. A tree diagram is a graphical representation method used to display the hierarchical structure and association relationship in the data. In the tree diagram, the features in the thermal gradient sequence data are organized according to the hierarchy and association to form a tree structure. According to the construction result of the tree diagram, the thermal gradient tree data is obtained for the subsequent learning transfer of the design decision tree model. Using the thermal gradient tree data as input, the learning transfer of the row design decision tree is performed on the thermal state model set. Transfer learning is a machine learning method that transfers existing knowledge to new tasks. Here, by utilizing the information in the thermal gradient tree data, the thermal state model set is learned and transferred to obtain the design decision tree model. The design decision tree model can predict the appropriate insulation layer, thermal insulation layer and outer layer material according to the given thermal gradient characteristics and conditions to achieve the thermal adaptability design of the handbag.

[0101] The present invention firstly performs three-layer thermal gradient adaptation on the bearing printing adaptation analysis data by using the thermal state model set. This includes thermal gradient adaptation of the thermal insulation layer, the heat insulating layer and the outer layer material, and the sealing thermal gradient adaptation between the thermal insulation layer, the heat insulating layer and the outer layer. By analyzing and optimizing the thermal conductivity and thermal impedance of the material, the balanced distribution of the thermal gradient is achieved. In this way, the thermal performance and thermal insulation effect of the handbag can be improved, and the conduction and loss of heat can be prevented. The thermal gradient adaptation data is sorted by feature importance to determine the degree of influence of each feature on the thermal gradient adaptation. By analyzing the importance of each feature, it can be understood which factors play a key role in the thermal gradient adaptation. In this way, subsequent design decisions and optimization work can be guided to improve the thermal performance and thermal gradient adaptation effect of the handbag. A tree diagram is constructed for the thermal gradient sequence data to form thermal gradient tree data. The various factors of thermal gradient adaptation are organized and represented according to the hierarchical relationship to form a tree structure. In this way, the hierarchy of thermal gradient adaptation and the relationship between various factors can be clearly displayed. Through the thermal gradient tree data, the characteristics and optimization direction of thermal gradient adaptation can be better understood and analyzed. Based on the thermal gradient tree data, the learning migration of the design decision tree is carried out for the thermal state model set. By analyzing the relationship between the thermal gradient tree data and the thermal state model set, a design decision tree model is constructed. This model can automatically make design decisions and select appropriate materials and thermal gradient adaptation solutions based on the thermal gradient adaptation requirements and conditions of the handbag. By designing a decision tree model, the thermal performance and thermal gradient adaptation effect of the handbag can be optimized.

[0102] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0103] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0104] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for automatically generating a design scheme based on a handbag, characterized in that: The following steps are involved: Step S1: Acquire historical data of handbag design; A three-dimensional structural model is constructed for the design history data to obtain a three-dimensional structural model; based on the three-dimensional structural model, a time series change migration is performed to obtain a variable force structural dynamic model; Step S2: Acquire the thermal conductivity index data of the handbag material and the handbag temperature test data; According to the thermal conductivity index data of the handbag material, the temperature test data of the handbag is subjected to multimodal learning of the thermal gradient of the three-dimensional structure model, so as to obtain a thermal state model set; wherein step S2 includes the following steps: Step S21: Acquire the thermal conductivity index data of the handbag material and the handbag temperature test data; Step S22: constructing a three-layer heat conduction state matrix for the handbag temperature test data according to the heat conduction index data of the handbag material, thereby obtaining a three-layer heat conduction state matrix, wherein the three layers include a heat preservation layer, a heat insulating layer and an outer layer; Step S23: performing heat conduction space structure analysis according to the three-layer heat conduction state matrix, thereby obtaining heat conduction space data; Step S24: extracting the conduction boundary and conduction path features of the heat conduction space data, thereby obtaining heat conduction boundary data and heat conduction path data; Step S25: performing a gas permeability regression analysis at the sealing point according to the heat conduction boundary data, thereby obtaining gas permeability regression data; Step S26: performing multimodal learning of thermal gradient on the three-dimensional structure model according to the three-layer heat conduction state matrix, gas permeation regression data and heat conduction path data, thereby obtaining a thermal state model set; Step S3: Acquire the photographed image data of the handbag, the printed material data of the handbag, and the designed image data of the handbag; perform brightness level contrast evaluation on the photographed image data of the handbag and the designed image data of the handbag, thereby obtaining contrast data; perform printing material adaptability analysis on the printed material data of the handbag according to the contrast data, thereby obtaining printing material adaptability data; Step S4: Based on the variable force structure dynamic model and according to the printing material adaptability data, the thermal state model set is subjected to design decision tree learning migration to obtain a design decision tree model; the design decision tree model is subjected to heat loss decision pruning processing to obtain a handbag automatic design model; wherein step S4 includes the following steps: Step S41: performing load-bearing and printing adaptability genetic forest analysis based on the variable force structure dynamic model and the printing material adaptability data, thereby obtaining load-bearing printing adaptability analysis data; Step S42: performing sealing gas permeability analysis of different earthquake intensities and different vibration durations based on the variable force structure dynamic model, thereby obtaining vibration gas permeability data; Step S43: performing heat exchange distribution flow rate analysis on the vibration gas permeability data based on the thermal state model set, thereby obtaining heat flow rate distribution data; Step S44: performing design decision tree learning migration on the thermal state model set and the bearer printing adaptation analysis data to obtain a design decision tree model; Step S45: Perform heat loss decision pruning processing on the design decision tree model according to the heat flow rate distribution data, so as to obtain the automatic design model of the handbag.

2. The method for automatically generating a design scheme based on a handbag according to claim 1, characterized in that: The specific steps of step S1 are: Step S11: Acquire handbag design history data; Step S12: constructing a three-dimensional structure model for the design history data, thereby obtaining a three-dimensional structure model; Step S13: performing a three-layer finite element analysis based on the three-dimensional structure model, thereby obtaining structural force finite element data; Step S14: performing time-series migration on the three-dimensional structure model according to the structural force finite element data to obtain a variable force structure dynamic model.

3. The method for automatically generating a design scheme based on a handbag according to claim 2, characterized in that: The specific steps of step S13 are: Step S131: performing a bearing capacity analysis of the contact between the bottom of the handbag and the support surface based on the three-dimensional structure model, thereby obtaining first bearing capacity data; Step S132: performing a bearing capacity analysis of the handle connection point based on the three-dimensional structure model, thereby obtaining second bearing capacity data; Step S133: performing fixed constraint analysis of different material properties on the first bearing capacity data, thereby obtaining fixed constraint data; Step S134: performing rotation constraint analysis of different material properties on the second bearing capacity data, thereby obtaining rotation constraint data; Step S135: performing key structural mesh division on the three-dimensional structure model according to the fixed constraint data and the rotation constraint data, thereby obtaining structural mesh discrete data, wherein the key structural mesh division includes the sealing structure division of the elastic modulus extreme point and the yield strength extreme point, the handle hole structure division and the folding structure division; Step S136: performing a three-layer finite element analysis on the structural mesh discrete data to obtain structural force finite element data, wherein the three-layer finite element analysis includes a thermal insulation layer finite element analysis, a heat insulating layer finite element analysis and an outer layer finite element analysis.

4. The method for automatically generating a design scheme based on a handbag according to claim 3, characterized in that: The specific steps of step S136 are: Performing three-layer stress distribution correlation analysis on the discrete data of the structural grid, thereby obtaining stress distribution correlation data, wherein the stress distribution correlation data includes insulation layer stress distribution correlation data, heat insulation layer stress distribution correlation data and outer layer stress distribution correlation data; Performing thermal stress analysis on the thermal insulation layer stress distribution correlation data and the heat insulation layer stress distribution correlation data when different internal and external temperatures change, thereby obtaining thermal stress correlation data, wherein the thermal stress analysis includes deformation analysis and stress distribution analysis; Perform material combination clustering on the thermal stress correlation data and the outer layer stress distribution correlation data to obtain stress distribution clustering data, wherein the material combination clustering includes material category clustering, material thickness clustering and material density clustering; A three-layer finite element analysis is performed on the structural grid discrete data according to the stress distribution clustering data to obtain the structural force finite element data, wherein the three-layer finite element analysis includes the insulation layer finite element analysis, the heat insulation layer finite element analysis and the outer layer finite element analysis.

5. The method for automatically generating a design scheme based on a handbag according to claim 1, characterized in that: The specific steps of step S22 are: Step S221: clustering the test environment temperature of the bag temperature test data to obtain environment temperature clustering data; Step S222: performing a temperature distribution time series analysis of different material densities, thicknesses and characteristics on the temperature test data of the handbag according to the ambient temperature clustering data and the thermal conductivity index data of the handbag material, thereby obtaining temperature distribution time series data; Step S223: clustering the time series temperature of the items in the bag on the temperature distribution time series data, thereby obtaining time series temperature cluster distribution data; Step S224: constructing a thermal environment memory network for the time series temperature cluster distribution data to obtain a thermal environment memory model; Step S225: constructing a three-layer heat conduction state matrix based on the thermal environment memory model to obtain a three-layer heat conduction state matrix, wherein the three-layer heat conduction state matrix construction includes the heat preservation layer, the heat insulation layer and the outer layer.

6. The method for automatically generating a design scheme based on a handbag according to claim 1, characterized in that: The specific steps of step S3 are: Step S31: Acquire the photographed image data of the handbag and the design image data of the handbag; Step S32: performing HSV pixel clustering grouping on the bag image data to obtain color pixel clustering data; Step S33: constructing a local binary texture feature map for the image data of the handbag, thereby obtaining texture map data; Step S34: performing brightness level contrast evaluation on the handbag design image data according to the texture map data and the color pixel clustering data, thereby obtaining contrast data; Step S35: Acquire the printing material data of the handbag; Step S36: Perform printing material suitability analysis on the handbag printing material data according to the contrast data, thereby obtaining printing material suitability data.

7. The method for automatically generating a design scheme based on a handbag according to claim 6, characterized in that: The specific steps of step S36 are: Step S361: Perform printing correlation feature analysis on the handbag printing material data to obtain color permeability data, glossiness data and texture data; Step S362: performing durability evaluation on the handbag printing material data to obtain durability evaluation data, wherein the durability evaluation includes material durability evaluation, printed product adhesion evaluation and coating adhesion evaluation; Step S363: performing printing adhesion uniformity matching and printing adhesion distortion matching on the glossiness data and the texture data according to the contrast data, thereby obtaining printing adhesion matching data; Step S364: performing contrast time series difference analysis on the print adhesion matching data and the color permeability data according to the durability evaluation data, thereby obtaining contrast time series difference data; Step S365: Perform printing material adaptability analysis on the handbag printing material data according to the contrast time series difference data, so as to obtain printing material adaptability data.

8. The method for automatically generating a design scheme based on a handbag according to claim 1, characterized in that: The specific steps of step S44 are: Step S441: performing three-layer thermal gradient adaptation on the bearing printing adaptation analysis data based on the thermal state model set, thereby obtaining thermal gradient adaptation data, wherein the three-layer thermal gradient adaptation includes material thermal gradient adaptation of the thermal insulation layer, the heat insulating layer and the outer layer, and sealing thermal gradient adaptation between the thermal insulation layer, the heat insulating layer and the outer layer; Step S442: sorting the thermal gradient adaptation data by feature importance, thereby obtaining thermal gradient sequence data; Step S443: constructing a tree diagram for the thermal gradient sequence data, thereby obtaining thermal gradient tree data; Step S444: performing row design decision tree learning migration on the thermal state model set according to the thermal gradient tree data to obtain a design decision tree model.

Images