Sock customization design method based on intelligent optimization algorithm

Abstract

The invention relates to the technical field of sock customization design, in particular to a sock customization design method based on an intelligent optimization algorithm, and the method comprises the steps: obtaining basic information data, posture data and historical purchase data of a customer; the three kinds of data are input into a sock preference prediction model, a sock preference feature set is obtained through recognition, and a sock preference degree set of the customer is calculated and comprises multiple preference degree parameters such as color, size, pattern, function, material and thickness. Based on the sock preference degree set, constructing a first sock design optimization objective function, performing optimization analysis on the objective function by using a particle swarm algorithm to obtain a first sock customization design parameter set, performing sock design according to the design parameter set and recommending to customers, and adjusting design parameters according to feedback data. And obtaining a second sock customization design parameter set. According to the method, precise sock customization design is achieved through an intelligent optimization algorithm, and the satisfaction degree of customers can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of socks customization design, and in particular to a socks customization design method based on an intelligent optimization algorithm. Background Art

[0002] Socks are an essential clothing item in daily life, but with the continuous improvement of the quality of life, people's aesthetic standards are also constantly improving, and the importance of sock styles is increasing. Therefore, socks should not only have basic warmth value, but also meet people's more style needs.

[0003] Traditional sock manufacturers find it difficult to meet the customized demands of different groups of people for elements such as size, color and pattern in sock design, which easily leads to customer satisfaction issues.

[0004] Therefore, a sock customization design method based on intelligent optimization algorithm is proposed. Summary of the invention

[0005] The purpose of the present invention is to provide a sock customization design method based on an intelligent optimization algorithm. The present invention relates to the technical field of sock customization design, and specifically to a sock customization design method based on an intelligent optimization algorithm. The present invention obtains the basic information data, body shape data and historical purchase data of customers; inputs the three data into a sock preference prediction model, identifies a sock preference feature set, and calculates the customer's sock preference set, including multiple preference parameters such as color, size, pattern, function, material and thickness. Based on the sock preference set, a first sock design optimization objective function is constructed, and the objective function is optimized and analyzed using a particle swarm algorithm to obtain a first sock customization design parameter set, and socks are designed and recommended to customers according to the design parameter set, and the design parameters are adjusted according to the feedback data to obtain a second sock customization design parameter set. The method realizes accurate sock customization design through an intelligent optimization algorithm, which helps to improve customer satisfaction.

[0006] To achieve the above object, the present invention provides the following technical solutions: A method for customizing socks based on an intelligent optimization algorithm, comprising: S10. Obtain the customer's first basic information data, second body shape data and first historical hosiery purchase data; S20. Input the three types of data into the socks preference prediction model, and sequentially pass through the preprocessing layer, preference feature extraction layer, preference analysis layer and output layer of the socks preference prediction model; the preference feature extraction layer performs analysis through a deep neural network to obtain a socks preference feature set; the preference analysis layer obtains the customer's socks preference set based on the socks preference feature set, and the socks preference set includes a color preference set, a size preference set, a pattern preference set, a material preference set and a thickness preference set; S30. constructing a first sock design optimization objective function according to the sock preference set and a preset objective function optimization threshold, optimizing and analyzing the first sock design optimization objective function based on a particle swarm algorithm to obtain multiple sets of sock optimization parameters, and constructing a first sock customization design parameter set according to the multiple sets of sock optimization parameters; S40. Design socks according to the first sock customization design parameter set, recommend the designed socks to customers, obtain customers' recommended socks feedback data, and obtain customers' first sock design satisfaction based on the recommended socks feedback data, and adjust the first sock customization design parameter set based on the first sock design satisfaction and sock customization design constraint conditions to obtain a second sock customization design parameter set.

[0007] Preferably, the first basic information data includes age, gender and occupation; the second body shape data includes shoe size, height and body shape; the first historical sock purchase data includes multi-element data of each sock purchased by the customer, including color, pattern, size, material, function and thickness as well as customer evaluation data of each sock.

[0008] Preferably, the socks preference prediction model includes a preprocessing layer, a socks preference feature extraction layer, a preference degree analysis layer and an output layer; The preprocessing layer is used to preprocess the first basic information data, the second body shape data and the first historical socks purchase data to obtain the second basic information data, the third body shape data and the second historical socks purchase data; the preprocessing includes data cleaning, normalization and one-hot encoding; The preference feature extraction layer is used to identify the second basic information data, the third body shape data and the second historical socks purchase data through a deep neural network to obtain the socks preference feature set; the socks preference feature set includes a color preference feature set, a size preference feature set, a pattern preference feature set, a material preference feature set, a function preference feature set and a thickness preference feature set; The preference analysis layer is used to obtain a customer's socks preference set according to the socks preference feature set, wherein the socks preference set includes a color preference set, a size preference set, a pattern preference set, a material preference set, a function preference set, and a thickness preference set; The output layer is used to output the socks preference set.

[0009] Preferably, the socks preference feature is used to represent the correlation between the customer's historical purchase data and the customer's basic information data and body data; the socks preference feature set includes preference features, basic information influence coefficients and body data influence coefficients; and the socks preference degree set of each socks preference feature set is obtained according to the basic information influence coefficients and the body data influence coefficients.

[0010] Preferably, the hosiery preference feature set is: ; in, Represents a set of socks preference features; Represents a set of color preference features; Represents a set of size preference features; represents a set of pattern preference features; Represents a set of material preference features; Represents a set of functional preference features; represents the thickness preference feature set; Indicates the first Color preference characteristics; Indicates the size preference feature set size preference characteristics; Indicates the first Pattern preference features; Indicates the first Material preference characteristics; Indicates the first Functional preference features; represents the thickness preference feature set. Thickness preference characteristics; Indicates the first The basic information data influence coefficient of each color preference feature; Indicates the first The influence coefficient of body shape data on the color preference characteristics; Indicates the size preference feature set The basic information data influence coefficient of each size preference feature; Indicates the size preference feature set The influence coefficient of body data on size preference characteristics; Indicates the first The basic information data influence coefficient of each pattern preference feature; Indicates the first The influence coefficient of body data on the pattern preference characteristics; Indicates the first The basic information data influence coefficient of each material preference feature; Indicates the first The influence coefficient of body data of material preference characteristics; Indicates the first The basic information data influence coefficient of each functional preference feature; Indicates the first The influence coefficient of body shape data on the functional preference characteristics; represents the thickness preference feature set. Basic information data influence coefficient of thickness preference characteristics; represents the thickness preference feature set. The influence coefficient of body shape data on the thickness preference characteristics.

[0011] Preferably, the socks preference set is: ; in, represents the preference set of socks; Represents a color preference set; Indicates the first The preference of each color preference feature; Represents a set of size preferences; Indicates the size preference set The preference of each size preference feature; represents the pattern preference set; Indicates the first The preference of each pattern preference feature; Represents a material preference set; Indicates the first The preference of each material preference feature; Represents a set of functional preferences; Indicates the first The preference of each functional preference feature; represents the thickness preference set; Indicates the thickness preference set The preference of each thickness preference feature; Indicated by natural constant An exponential function with base .

[0012] Preferably, the first hosiery design optimization objective function is: ; in, represents the first hosiery product design optimization objective function; Indicates the weight of color preference; Indicates The preference of each color preference feature; Indicates the weight of size preference; Indicates The preference of each size preference feature; Indicates the influence weight of pattern preference; Indicates The preference of each pattern preference feature; Indicates the weight of material preference; Indicates The preference of each material preference feature; Indicates the weight of function preference; Indicates The preference of each functional preference feature; Indicates the thickness preference influence weight; Indicates The preference of each thickness preference feature; Represents the preset objective function optimization threshold.

[0013] Preferably, the recommended socks feedback data includes color satisfaction, pattern satisfaction, size satisfaction, function satisfaction, thickness satisfaction and material satisfaction.

[0014] Preferably, the first socks design satisfaction is: ; in, Indicates the satisfaction with the design of the first hosiery product; represents the number of parameter groups in the first socks customization design parameter set; Indicates that customers Color satisfaction of socks designed by group parameters; Indicates that customers Size satisfaction of hosiery designed by group parameters; Indicates that customers Pattern satisfaction of group parameter designed socks; Indicates that customers The material satisfaction of the socks is designed by group parameters; Indicates that customers Functional satisfaction of group parameter designed socks; Indicates that customers Set of parameters to design thickness satisfaction of socks.

[0015] Preferably, the constraints for the custom design of socks are: ; in, Indicates the constraints of sock customization design; Indicates the satisfaction with the design of the first hosiery product; Indicates the threshold of satisfaction with socks design; Represents the first set of custom design parameters for socks Any parameter group .

[0016] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention obtains the first basic information data, the second body shape data and the first historical socks purchase data of the customer; inputs these three data into the socks preference prediction model, and passes through the preprocessing layer, the preference feature extraction layer, the preference analysis layer and the output layer of the socks preference prediction model; the preference feature extraction layer analyzes through a deep neural network to obtain a socks preference feature set; the preference analysis layer obtains the customer's socks preference set according to the basic information data influence coefficient and the body shape data influence coefficient in the socks preference feature set, and the socks preference set includes a color preference set, a size preference set, a pattern preference set, a material preference set and a thickness preference set; the method effectively interprets the customer's inclination for each preference feature through a detailed analysis of the customer's basic information data and body shape data, and provides a data basis for the subsequent optimization of socks customization design, thereby further improving the customer's satisfaction with the socks customization design.

[0017] 2. The present invention constructs a first sock design optimization objective function according to a sock preference set and a preset objective function optimization threshold, optimizes and analyzes the first sock design optimization objective function based on a particle swarm algorithm, obtains multiple groups of sock optimization parameters, and constructs a first sock customization design parameter set based on the multiple groups of sock optimization parameters. This method improves the effectiveness of sock customization design by constructing the first sock design optimization objective function and optimizing the design based on a particle swarm optimization algorithm, thereby further improving customer satisfaction with the sock customization design.

[0018] 3. The present invention designs socks according to a first set of customized sock design parameters, recommends the designed socks to customers, obtains customer feedback data on recommended socks, and obtains customer satisfaction with the first sock design based on the recommended sock feedback data, and adjusts the first set of customized sock design parameters based on the first sock design satisfaction and customized sock design constraints to obtain a second set of customized sock design parameters. The method recommends sock designs based on the optimized first set of customized sock design parameters, reflects customer satisfaction with socks based on feedback data, and makes effective adjustments based on the satisfaction, thereby improving the comprehensiveness of customized sock design and further improving customer satisfaction with customized sock design. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A schematic diagram of a process flow of a socks customization design method based on an intelligent optimization algorithm provided by an embodiment of the present invention; Figure 2 A schematic diagram of the structure of a socks preference prediction model provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] Embodiment 1 In order to improve customer satisfaction, a sock manufacturer A applied a sock customization design method based on intelligent optimization algorithm; Reference Figure 1 , is a flow chart of a socks customization design method based on an intelligent optimization algorithm provided by an embodiment of the present invention, which specifically includes: S10. Obtain the customer's first basic information data, second body shape data and first historical hosiery purchase data; Further, the first basic information data includes age, gender and occupation; the second body shape data includes shoe size, height and body shape; the first historical socks purchase data includes multi-element data of each sock purchased by the customer, including color, pattern, size, material, function and thickness and customer evaluation data of each sock; wherein the evaluation data is a scoring evaluation of the color, pattern, size, function, thickness and material of the purchased socks; the full score is 10 points; wherein the pattern includes geometric pattern, text pattern, letter pattern, cartoon pattern and no pattern, etc.; the function includes sweat absorption, warmth retention and waterproof, etc.; the material includes wool, cotton and nylon, etc.; the body shape is analyzed according to the IBM index; the shoe size is expressed according to the Chinese size; the sock size is expressed according to the length of the socks; some basic information data body shape data are shown in Table 1; some historical purchase data are shown in Table 2; Table 1 Basic information data of part body data table

[0022] Table 2 Partial historical purchase data

[0023] S20. Input the three types of data into the socks preference prediction model, and sequentially pass through the preprocessing layer, preference feature extraction layer, preference analysis layer and output layer of the socks preference prediction model; the preference feature extraction layer performs analysis through a deep neural network to obtain a socks preference feature set; the preference analysis layer obtains the customer's socks preference set based on the socks preference feature set, and the socks preference set includes a color preference set, a size preference set, a pattern preference set, a material preference set and a thickness preference set; Furthermore, the socks preference prediction model includes a preprocessing layer, a socks preference feature extraction layer, a preference analysis layer and an output layer; the structural schematic diagram of the socks preference prediction model is as follows: Figure 2 As shown; The preprocessing layer is used to preprocess the first basic information data, the second body shape data and the first historical socks purchase data to obtain the second basic information data, the third body shape data and the second historical socks purchase data; the preprocessing includes data cleaning, normalization and one-hot encoding; specifically, it includes one-hot encoding of gender, normalization of age, height, shoe size and size, thickness and customer evaluation data of each sock; The preference feature extraction layer is used to identify the second basic information data, the third body shape data and the second historical socks purchase data through a deep neural network to obtain the socks preference feature set; the socks preference feature set includes a color preference feature set, a size preference feature set, a pattern preference feature set, a material preference feature set, a function preference feature set and a thickness preference feature set; The specific identification process of the socks preference feature set includes: first, converting the occupation in the basic information data, the body shape in the body shape data, and the color, pattern, material, and function data in the multi-element data of each sock purchased by the customer into a vector representation; and splicing the pre-processed data into a comprehensive feature vector, and training through a deep neural network to learn the basic information data influence coefficient and the body shape data influence coefficient of each feature in each preference feature, the basic information data influence coefficient is used to represent the influence of the customer's basic information data on the preference feature; the body shape data influence coefficient is used to represent the influence of the customer's body shape data on the preference feature; and outputting the preference feature set.

[0024] The preference analysis layer is used to obtain a customer's socks preference set according to the socks preference feature set, wherein the socks preference set includes a color preference set, a size preference set, a pattern preference set, a material preference set, a function preference set, and a thickness preference set; The output layer is used to output the socks preference set.

[0025] Furthermore, the sock preference feature is used to represent the correlation between the customer's historical purchase data and the customer's basic information data and body data; the sock preference feature set includes preference features, basic information influence coefficients and body data influence coefficients; and the sock preference degree set of each sock preference feature set is obtained based on the basic information influence coefficients and the body data influence coefficients.

[0026] Furthermore, the hosiery preference feature set is: ; in, Represents a set of socks preference features; Represents a set of color preference features; Represents a set of size preference features; represents a set of pattern preference features; Represents a set of material preference features; Represents a set of functional preference features; represents the thickness preference feature set; Indicates the first Color preference characteristics; Indicates the size preference feature set size preference characteristics; Indicates the first Pattern preference features; Indicates the first Material preference characteristics; Indicates the first Functional preference features; represents the thickness preference feature set. Thickness preference characteristics; Indicates the first The basic information data influence coefficient of each color preference feature; Indicates the first The influence coefficient of body shape data on the color preference characteristics; Indicates the size preference feature set The basic information data influence coefficient of each size preference feature; Indicates the size preference feature set The influence coefficient of body data on the size preference characteristics; Indicates the first The basic information data influence coefficient of each pattern preference feature; Indicates the first The influence coefficient of body data on the pattern preference characteristics; Indicates the first The basic information data influence coefficient of each material preference feature; Indicates the first The influence coefficient of body data of material preference characteristics; Indicates the first The basic information data influence coefficient of each functional preference feature; Indicates the first The influence coefficient of body shape data on the functional preference characteristics; represents the thickness preference feature set. Basic information data influence coefficient of thickness preference characteristics; represents the thickness preference feature set. The influence coefficient of body shape data on the thickness preference characteristics.

[0027] Furthermore, the socks preference set is: ; in, represents the preference set of socks; Represents a color preference set; Indicates the first The preference of each color preference feature; Represents a set of size preferences; Indicates the size preference set The preference of each size preference feature; represents the pattern preference set; Indicates the first The preference of each pattern preference feature; Represents a material preference set; Indicates the first The preference of each material preference feature; Represents a set of functional preferences; Indicates the first The preference of each functional preference feature; represents the thickness preference set; Indicates the thickness preference set The preference of each thickness preference feature; Indicated by natural constant An exponential function with base .

[0028] This embodiment obtains the customer's first basic information data, second body shape data and first historical socks purchase data; inputs these three data into the socks preference prediction model, through the preprocessing layer, preference feature extraction layer, preference analysis layer and output layer of the socks preference prediction model; the preference feature extraction layer analyzes through a deep neural network to obtain a socks preference feature set; the preference analysis layer obtains the customer's socks preference set according to the basic information data influence coefficient and the body shape data influence coefficient in the socks preference feature set, and the socks preference set includes a color preference set, a size preference set, a pattern preference set, a material preference set and a thickness preference set; the method effectively interprets the customer's inclination for each preference feature through a detailed analysis of the customer's basic information data and body shape data, provides a data basis for the subsequent optimization of socks customization design, and further improves the customer's satisfaction with the socks customization design.

[0029] S30. constructing a first sock design optimization objective function according to the sock preference set and a preset objective function optimization threshold, optimizing and analyzing the first sock design optimization objective function based on a particle swarm algorithm to obtain multiple sets of sock optimization parameters, and constructing a first sock customization design parameter set according to the multiple sets of sock optimization parameters; Further, the particle swarm optimization parameters include the preference values ​​of multiple preference features in the socks preference set, which are combined and constructed, including multiple combination parameters of color preference, pattern preference, size preference, function preference, thickness preference and material preference; and a first socks customization design parameter set is constructed; Furthermore, the first hosiery design optimization objective function is: ; in, represents the first hosiery product design optimization objective function; Indicates the weight of color preference; Indicates The preference of each color preference feature; Indicates the weight of size preference; Indicates The preference of each size preference feature; Indicates the influence weight of pattern preference; Indicates The preference of each pattern preference feature; Indicates the weight of material preference; Indicates The preference of each material preference feature; Indicates the weight of function preference; Indicates The preference of each functional preference feature; Indicates the thickness preference influence weight; Indicates The preference of each thickness preference feature; Represents the preset objective function optimization threshold.

[0030] This embodiment constructs a first sock design optimization objective function according to a sock preference set and a preset objective function optimization threshold, optimizes and analyzes the first sock design optimization objective function based on a particle swarm algorithm, obtains multiple groups of sock optimization parameters, and constructs a first sock customization design parameter set based on the multiple groups of sock optimization parameters. This method improves the effectiveness of sock customization design by constructing a first sock design optimization objective function and optimizing the design based on a particle swarm optimization algorithm, thereby further improving customer satisfaction with the sock customization design.

[0031] S40. Design socks according to the first sock customization design parameter set, recommend the designed socks to customers, obtain customers' recommended socks feedback data, and obtain customers' first sock design satisfaction based on the recommended socks feedback data, and adjust the first sock customization design parameter set based on the first sock design satisfaction and sock customization design constraint conditions to obtain a second sock customization design parameter set.

[0032] Furthermore, the recommended socks feedback data includes color satisfaction, pattern satisfaction, size satisfaction, function satisfaction, thickness satisfaction and material satisfaction.

[0033] Furthermore, the first socks design satisfaction is: ; in, Indicates the satisfaction with the design of the first hosiery product; represents the number of parameter groups in the first socks customization design parameter set; Indicates that customers Color satisfaction of socks designed by group parameters; Indicates that customers Size satisfaction of hosiery designed by group parameters; Indicates that customers Pattern satisfaction of group parameter designed socks; Indicates that customers The material satisfaction of the socks is designed by group parameters; Indicates that customers Functional satisfaction of socks designed by group parameters; Indicates that customers Set of parameters to design thickness satisfaction of socks.

[0034] Furthermore, the constraints of the socks customization design are: ; in, Indicates the constraints of sock customization design; Indicates the satisfaction with the design of the first hosiery product; Indicates the threshold of satisfaction with socks design; Represents the first set of custom design parameters for socks Any parameter group .

[0035] If the socks customized design constraint conditions are not met, the unsatisfied parameter group is adjusted, mainly adjusting each characteristic parameter therein, including color, pattern, size, function, thickness and material; until the socks customized design constraint conditions are met, a second socks customized design parameter set is obtained.

[0036] This embodiment designs socks according to the first sock customization design parameter set, and recommends the designed socks to customers, obtains customers' recommended socks feedback data, and obtains customers' satisfaction with the first sock design based on the recommended sock feedback data, and adjusts the first sock customization design parameter set based on the first sock design satisfaction and sock customization design constraints to obtain a second sock customization design parameter set. This method recommends sock designs based on the optimized first sock customization design parameter set, reflects customers' sock satisfaction based on feedback data, and makes effective adjustments based on the satisfaction, thereby improving the comprehensiveness of the sock customization design and further improving customers' satisfaction with the sock customization design.

[0037] In order to compare the customer satisfaction of the socks customization design method based on the intelligent optimization algorithm proposed in this embodiment and the traditional socks design method, multiple comparative experiments were conducted, mainly through method 1 and method 2. Method 1 is the socks customization design method based on the intelligent optimization algorithm proposed in this embodiment, and method 2 is the traditional socks design method. Satisfaction data feedback was conducted on multiple customers respectively, and the average satisfaction comparison data was obtained as shown in Table 3; Table 3 Comparison of customer satisfaction of different socks design methods

[0038] As shown in Table 3, the socks customization design method based on the intelligent optimization algorithm proposed in this embodiment shows certain effectiveness in the socks customization design.

[0039] The present invention obtains the basic information data, body shape data and historical purchase data of the customer; inputs these three data into the socks preference prediction model, identifies the socks preference feature set, and calculates the customer's socks preference set, including multiple preference parameters such as color, size, pattern, function, material and thickness. Based on the socks preference set, a first socks design optimization objective function is constructed, and the objective function is optimized and analyzed using a particle swarm algorithm to obtain a first socks customization design parameter set. Socks are designed and recommended to customers based on the design parameter set, and the design parameters are adjusted based on the feedback data to obtain a second socks customization design parameter set. The method realizes accurate socks customization design through an intelligent optimization algorithm, which helps to improve customer satisfaction.

[0040] Embodiment 2 In order to improve customer satisfaction, sock manufacturer B applied a sock customization design method based on intelligent optimization algorithm; Reference Figure 1 , is a flow chart of a socks customization design method based on an intelligent optimization algorithm provided by an embodiment of the present invention, which specifically includes: S10. Obtain the customer's first basic information data, second body shape data and first historical hosiery purchase data; Further, the first basic information data includes age, gender and occupation; the second body shape data includes shoe size, height and body shape; the first historical socks purchase data includes multi-element data of each sock purchased by the customer, including color, pattern, size, material, function and thickness and customer evaluation data of each sock; wherein the evaluation data is a scoring evaluation of the color, pattern, size, function, thickness and material of the purchased socks; the full score is 10 points; the body shape is analyzed according to the IBM index; the pattern includes geometric pattern, text pattern, letter pattern, cartoon pattern and no pattern, etc.; the function includes sweat absorption, warmth preservation and waterproof, etc.; the material includes wool, cotton and nylon, etc.; the body shape is analyzed according to the IBM index; the shoe size is expressed according to the Chinese size; the sock size is expressed according to the length of the socks; some basic information data body shape data are shown in Table 4; Table 4 Part of basic information data body data table

[0041] Some historical purchase data are shown in Table 5; Table 5 Partial historical purchase data

[0042] S20. Input the three types of data into the socks preference prediction model, and sequentially pass through the preprocessing layer, preference feature extraction layer, preference analysis layer and output layer of the socks preference prediction model; the preference feature extraction layer performs analysis through a deep neural network to obtain a socks preference feature set; the preference analysis layer obtains the customer's socks preference set based on the socks preference feature set, and the socks preference set includes a color preference set, a size preference set, a pattern preference set, a material preference set and a thickness preference set; Furthermore, the socks preference prediction model includes a preprocessing layer, a socks preference feature extraction layer, a preference analysis layer and an output layer; the structural schematic diagram of the socks preference prediction model is as follows: Figure 2 As shown; The preprocessing layer is used to preprocess the first basic information data, the second body shape data and the first historical socks purchase data to obtain the second basic information data, the third body shape data and the second historical socks purchase data; the preprocessing includes data cleaning, normalization and one-hot encoding; specifically, it includes one-hot encoding of gender, normalization of age, height, shoe size and size, thickness and customer evaluation data of each sock; The preference feature extraction layer is used to identify the second basic information data, the third body shape data and the second historical socks purchase data through a deep neural network to obtain the socks preference feature set; the socks preference feature set includes a color preference feature set, a size preference feature set, a pattern preference feature set, a material preference feature set, a function preference feature set and a thickness preference feature set; The specific identification process of the socks preference feature set includes: first, converting the occupation in the basic information data, the body shape in the body shape data, and the color, pattern, material, and function data in the multi-element data of each sock purchased by the customer into a vector representation; and splicing the pre-processed data into a comprehensive feature vector, and training through a deep neural network to learn the basic information data influence coefficient and the body shape data influence coefficient of each feature in each preference feature, the basic information data influence coefficient is used to represent the influence of the customer's basic information data on the preference feature; the body shape data influence coefficient is used to represent the influence of the customer's body shape data on the preference feature; and outputting the preference feature set.

[0043] The preference analysis layer is used to obtain a customer's socks preference set according to the socks preference feature set, wherein the socks preference set includes a color preference set, a size preference set, a pattern preference set, a material preference set, a function preference set, and a thickness preference set; The output layer is used to output the socks preference set.

[0044] Furthermore, the sock preference feature is used to represent the correlation between the customer's historical purchase data and the customer's basic information data and body data; the sock preference feature set includes preference features, basic information influence coefficients and body data influence coefficients; and the sock preference degree set of each sock preference feature set is obtained based on the basic information influence coefficients and the body data influence coefficients.

[0045] Furthermore, the hosiery preference feature set is: ; in, Represents a set of socks preference features; Represents a set of color preference features; Represents a set of size preference features; represents a set of pattern preference features; Represents a set of material preference features; Represents a set of functional preference features; represents the thickness preference feature set; Indicates the first Color preference characteristics; Indicates the size preference feature set size preference characteristics; Indicates the first Pattern preference features; Indicates the first Material preference characteristics; Indicates the first Functional preference features; represents the thickness preference feature set. Thickness preference characteristics; Indicates the first The basic information data influence coefficient of each color preference feature; Indicates the first The influence coefficient of body shape data on the color preference characteristics; Indicates the size preference feature set The basic information data influence coefficient of each size preference feature; Indicates the size preference feature set The influence coefficient of body data on the size preference characteristics; Indicates the first The basic information data influence coefficient of each pattern preference feature; Indicates the first The influence coefficient of body data on the pattern preference characteristics; Indicates the first The basic information data influence coefficient of each material preference feature; Indicates the first The influence coefficient of body data of material preference characteristics; Indicates the first The basic information data influence coefficient of each functional preference feature; Indicates the first The influence coefficient of body shape data on the functional preference characteristics; represents the thickness preference feature set. Basic information data influence coefficient of thickness preference characteristics; represents the thickness preference feature set. The influence coefficient of body shape data on the thickness preference characteristics.

[0046] Furthermore, the socks preference set is: ; in, represents the preference set of socks; Represents a color preference set; Indicates the first The preference of each color preference feature; Represents a set of size preferences; Indicates the size preference set The preference of each size preference feature; represents the pattern preference set; Indicates the first The preference of each pattern preference feature; Represents a material preference set; Indicates the first The preference of each material preference feature; Represents a set of functional preferences; Indicates the first The preference of each functional preference feature; represents the thickness preference set; Indicates the thickness preference set The preference of each thickness preference feature; Indicated by natural constant An exponential function with base .

[0047] S30. constructing a first sock design optimization objective function according to the sock preference set and a preset objective function optimization threshold, optimizing and analyzing the first sock design optimization objective function based on a particle swarm algorithm to obtain multiple sets of sock optimization parameters, and constructing a first sock customization design parameter set according to the multiple sets of sock optimization parameters; Further, the particle swarm optimization parameters include the preference values ​​of multiple preference features in the socks preference set, which are combined and constructed, including multiple combination parameters of color preference, pattern preference, size preference, function preference, thickness preference and material preference; and a first socks customization design parameter set is constructed; Furthermore, the first hosiery design optimization objective function is: ; in, represents the first hosiery product design optimization objective function; Indicates the weight of color preference; Indicates The preference of each color preference feature; Indicates the weight of size preference; Indicates The preference of each size preference feature; Indicates the influence weight of pattern preference; Indicates The preference of each pattern preference feature; Indicates the weight of material preference; Indicates The preference of each material preference feature; Indicates the weight of function preference; Indicates The preference of each functional preference feature; Indicates the thickness preference influence weight; Indicates The preference of each thickness preference feature; Represents the preset objective function optimization threshold.

[0048] S40. Design socks according to the first sock customization design parameter set, recommend the designed socks to customers, obtain customers' recommended socks feedback data, and obtain customers' first sock design satisfaction based on the recommended socks feedback data, and adjust the first sock customization design parameter set based on the first sock design satisfaction and sock customization design constraint conditions to obtain a second sock customization design parameter set.

[0049] Furthermore, the recommended socks feedback data includes color satisfaction, pattern satisfaction, size satisfaction, function satisfaction, thickness satisfaction and material satisfaction.

[0050] Furthermore, the first socks design satisfaction is: ; in, Indicates the satisfaction with the design of the first hosiery product; represents the number of parameter groups in the first socks customization design parameter set; Indicates that customers Color satisfaction of socks designed by group parameters; Indicates that customers Size satisfaction of hosiery designed by group parameters; Indicates that customers Pattern satisfaction of group parameter designed socks; Indicates that customers The material satisfaction of the socks is designed by group parameters; Indicates that customers Functional satisfaction of group parameter designed socks; Indicates that customers Set of parameters to design thickness satisfaction of socks.

[0051] Furthermore, the constraints of the socks customization design are: ; in, Indicates the constraints of sock customization design; Indicates the satisfaction with the design of the first hosiery product; Indicates the threshold of satisfaction with socks design; Represents the first set of custom design parameters for socks Any parameter group .

[0052] If the socks customized design constraint conditions are not met, the unsatisfied parameter group is adjusted, mainly adjusting each characteristic parameter therein, including color, pattern, size, function, thickness and material; until the socks customized design constraint conditions are met, a second socks customized design parameter set is obtained.

[0053] In order to compare the customer satisfaction of the socks customization design method based on the intelligent optimization algorithm proposed in this embodiment and the traditional socks design method, multiple comparative experiments were conducted, mainly through method 1 and method 2. Method 1 is the socks customization design method based on the intelligent optimization algorithm proposed in this embodiment, and method 2 is the traditional socks design method. Satisfaction data feedback was conducted on multiple customers respectively, and the average satisfaction comparison data was obtained as shown in Table 6; Table 6 Comparison of customer satisfaction of different socks design methods

[0054] As shown in Table 6, the socks customization design method based on the intelligent optimization algorithm proposed in this embodiment shows certain effectiveness in the socks customization design.

[0055] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for customizing socks based on an intelligent optimization algorithm, characterized in that: include: S10. Obtain the customer's first basic information data, second body shape data and first historical hosiery purchase data; S20. Input the three types of data into the socks preference prediction model, and sequentially pass through the preprocessing layer, preference feature extraction layer, preference analysis layer and output layer of the socks preference prediction model; the preference feature extraction layer performs analysis through a deep neural network to obtain a socks preference feature set; the preference analysis layer obtains the customer's socks preference set based on the socks preference feature set, and the socks preference set includes a color preference set, a size preference set, a pattern preference set, a material preference set and a thickness preference set; S30. constructing a first sock design optimization objective function according to the sock preference set and a preset objective function optimization threshold, optimizing and analyzing the first sock design optimization objective function based on a particle swarm algorithm to obtain multiple sets of sock optimization parameters, and constructing a first sock customization design parameter set according to the multiple sets of sock optimization parameters; S40. Design socks according to the first sock customization design parameter set, recommend the designed socks to customers, obtain customers' recommended socks feedback data, and obtain customers' first sock design satisfaction based on the recommended socks feedback data, and adjust the first sock customization design parameter set based on the first sock design satisfaction and sock customization design constraint conditions to obtain a second sock customization design parameter set.

2. The method for customizing socks based on intelligent optimization algorithm according to claim 1, characterized in that: The first basic information data includes age, gender and occupation; the second body shape data includes shoe size, height and body shape; the first historical sock purchase data includes multi-element data of each sock purchased by the customer, including color, pattern, size, material, function and thickness, as well as customer evaluation data of each sock.

3. The method for customizing socks based on intelligent optimization algorithm according to claim 1, characterized in that: The socks preference prediction model includes a preprocessing layer, a socks preference feature extraction layer, a preference degree analysis layer and an output layer; The preprocessing layer is used to preprocess the first basic information data, the second body shape data and the first historical socks purchase data to obtain the second basic information data, the third body shape data and the second historical socks purchase data; the preprocessing includes data cleaning, normalization and one-hot encoding; The preference feature extraction layer is used to identify the second basic information data, the third body shape data and the second historical socks purchase data through a deep neural network to obtain the socks preference feature set; the socks preference feature set includes a color preference feature set, a size preference feature set, a pattern preference feature set, a material preference feature set, a function preference feature set and a thickness preference feature set; The preference analysis layer is used to obtain a customer's socks preference set according to the socks preference feature set, wherein the socks preference set includes a color preference set, a size preference set, a pattern preference set, a material preference set, a function preference set, and a thickness preference set; The output layer is used to output the socks preference set.

4. The method for customizing socks based on an intelligent optimization algorithm according to claim 1, characterized in that: The hosiery preference feature is used to represent the correlation between the customer's historical purchase data and the customer's basic information data and body shape data; the hosiery preference feature set includes preference features, basic information influence coefficients and body shape data influence coefficients; A socks preference degree set of each socks preference feature set is obtained according to the basic information influence coefficient and the body shape data influence coefficient.

5. The method for customizing socks based on intelligent optimization algorithm according to claim 1, characterized in that: The hosiery preference feature set is: ； in, Represents a set of socks preference features; Represents a set of color preference features; Represents a set of size preference features; represents a set of pattern preference features; Represents a set of material preference features; Represents a set of functional preference features; represents the thickness preference feature set; Indicates the first Color preference characteristics; Indicates the size preference feature set size preference characteristics; Indicates the first Pattern preference features; Indicates the first Material preference characteristics; Indicates the first Functional preference features; represents the thickness preference feature set. Thickness preference characteristics; Indicates the first The basic information data influence coefficient of each color preference feature; Indicates the first The influence coefficient of body shape data on the color preference characteristics; Indicates the size preference feature set The basic information data influence coefficient of each size preference feature; Indicates the size preference feature set The influence coefficient of body data on the size preference characteristics; Indicates the first The basic information data influence coefficient of each pattern preference feature; Indicates the first The influence coefficient of body data on the pattern preference characteristics; Indicates the first The basic information data influence coefficient of each material preference feature; Indicates the first The influence coefficient of body data of material preference characteristics; Indicates the first The basic information data influence coefficient of each functional preference feature; Indicates the first The influence coefficient of body shape data on the functional preference characteristics; represents the thickness preference feature set. Basic information data influence coefficient of thickness preference characteristics; represents the thickness preference feature set. The influence coefficient of body shape data on the thickness preference characteristics.

6. The method for customizing socks based on intelligent optimization algorithm according to claim 5, characterized in that: The socks preference set is: ； in, represents the preference set of socks; Represents a color preference set; Indicates the first The preference of each color preference feature; Represents a set of size preferences; Indicates the size preference set The preference of each size preference feature; represents the pattern preference set; Indicates the first The preference of each pattern preference feature; Represents a material preference set; Indicates the first The preference of each material preference feature; Represents a set of functional preferences; Indicates the first The preference of each functional preference feature; represents the thickness preference set; Indicates the thickness preference set The preference of each thickness preference feature; Indicated by natural constant An exponential function with base .

7. The method for customizing socks based on intelligent optimization algorithm according to claim 1, characterized in that: The first hosiery design optimization objective function is: ； in, represents the first hosiery product design optimization objective function; Indicates the weight of color preference; Indicates The preference of each color preference feature; Indicates the weight of size preference; Indicates The preference of each size preference feature; Indicates the influence weight of pattern preference; Indicates The preference of each pattern preference feature; Indicates the weight of material preference; Indicates The preference of each material preference feature; Indicates the weight of function preference; Indicates The preference of each functional preference feature; Indicates the thickness preference influence weight; Indicates The preference of each thickness preference feature; Represents the preset objective function optimization threshold.

8. The method for customizing socks based on intelligent optimization algorithm according to claim 1, characterized in that: The recommended socks feedback data include color satisfaction, pattern satisfaction, size satisfaction, function satisfaction, thickness satisfaction and material satisfaction.

9. The method for customizing socks based on intelligent optimization algorithm according to claim 1, characterized in that: The satisfaction level of the first hosiery design is: ； in, Indicates the satisfaction with the design of the first hosiery product; represents the number of parameter groups in the first socks customization design parameter set; Indicates that customers Color satisfaction of socks designed by group parameters; Indicates that customers Size satisfaction of hosiery designed by group parameters; Indicates that customers Pattern satisfaction of group parameter designed socks; Indicates that customers The material satisfaction of the socks is designed by group parameters; Indicates that customers Functional satisfaction of group parameter designed socks; Indicates that customers Set of parameters to design thickness satisfaction of socks.

10. The method for customizing socks based on intelligent optimization algorithm according to claim 9, characterized in that: The constraints for the custom design of socks are: ； in, Indicates the constraints of sock customization design; Indicates the satisfaction with the design of the first hosiery product; Indicates the threshold of satisfaction with socks design; Represents the first set of custom design parameters for socks Any parameter group .

Images