E-commerce platform management method suitable for children's shoes and related equipment

Abstract

The invention relates to the technical field of e-commerce, in particular to an e-commerce platform management method suitable for children's shoes and related equipment, comprising the following steps: extracting contour and curvature features through foot images, classifying foot types and evaluating foot arch fitness, combining shoe style structure data and user foot matching degree, calculating fitness score, and calculating the fitness score; and evaluating inventory risks, calculating recommendation degree scores, adjusting display priorities, and generating a recommended commodity list. According to the method, accurate shoe style matching is achieved by analyzing the user foot image and extracting key features in combination with the foot arch curvature, the matching degree of the user foot contour and the shoe style design is evaluated, the comfort and adaptability are ensured, the commodity refunding and changing problems are effectively reduced through structural adaptation degree scoring, the commodity warehousing time and the warehousing period are combined, the inventory risk is recognized, and the user experience is improved. And timely inventory adjustment is supported, overstock of unsalable commodities is reduced, inventory management is optimized, and platform operation efficiency and user shopping experience are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of e-commerce, and in particular to an e-commerce platform management method and related equipment suitable for children's shoes. Background Art

[0002] The field of e-commerce technology includes various methods and systems for realizing commodity transactions, service provision and information dissemination through computer networks. The core content of the field of e-commerce technology is the optimization and management of transaction processes based on the network environment, including key links such as commodity display, user interaction, order processing, payment settlement, logistics tracking and after-sales service. The e-commerce system promotes the digitalization, platformization and intelligent development of the industry through the combination of data collection, information processing, customer behavior analysis and platform management strategies. It is widely used in multiple industries such as retail, manufacturing, cross-border trade, etc. With the increasing trend of consumer personalization and vertical segmentation of commodities, e-commerce platforms are gradually evolving towards professional and customized management models to adapt to the diverse characteristics of commodities and user needs.

[0003] Among them, the e-commerce platform management method suitable for children's shoes refers to the characteristics of complex category management, strong size adaptability and differentiated needs of parent users in the online sales of children's shoes products. By constructing logical rules for product classification, configuring size recommendation models and establishing a user behavior label system, it can achieve structured management of product information, accurate product matching and personalized recommendation display. This method establishes a children's shoe attribute database based on data processing means, integrates product life cycle management specifications and inventory dynamic update mechanism, and combines the front-end page management interface configuration system to manage product online, collect user behavior records and classify product labels, thereby assisting the platform to complete automated operation process setting and category optimization.

[0004] Existing technologies mainly rely on product classification and size recommendations, but fail to deeply analyze user foot characteristics and the structural adaptability of shoes, resulting in insufficient response of the recommendation system to personalized needs. Return and exchange problems often occur due to size or design mismatches. Inventory management relies on static data updates and forecasts, lacks real-time monitoring of product life cycles and inventory risks, and is unable to adjust strategies in time to cope with changes in market demand, resulting in inventory backlogs or out-of-stock phenomena, which reduces the platform's ability to operate accurately and user satisfaction, and makes it difficult to meet increasingly personalized consumer needs. Summary of the invention

[0005] In order to solve the technical problems existing in the prior art, the embodiment of the present invention provides an e-commerce platform management method and related equipment applicable to children's shoes. The technical solution is as follows: In order to achieve the above object, the present invention adopts the following technical solution, an e-commerce platform management method suitable for children's shoes, comprising the following steps: S1: Call multi-angle foot images, extract the contour edge pixels of the sole and instep, calculate the outer edge curvature change features at multiple positions on the sole, classify and identify the user's foot structure type using a support vector machine, and output the foot type classification label; S2: Call the foot type classification label, extract the arch contour curve of the side foot image to identify the arch structure features, compare with the standard arch grade table to obtain the structure grade label, combine with the sole rigidity score to identify the matching degree between the shoe model and the user's arch structure, and output the arch fitness information; S3: Call the arch fitness information, extract the structural design data of the shoe model and compare with the user's foot contour features, evaluate the matching degree of each part, and combine with the arch fitness to calculate the shoe model structure fitness score; S4: Extract the warehousing time of children's shoes products, calculate the storage days, and use the DBSCAN clustering algorithm to identify the inventory risk level of each product according to the storage cycle and sales trend data; S5: Call the inventory risk level and the shoe model structure fitness score, through dynamic weight allocation and non-linear coupling calculation, superimpose the storage cycle parameter and the inventory turnover rate gradient, obtain the recommendation score value, and generate a list of recommended products.

[0006] As a further solution of the present invention, the foot type classification label includes the sole contour type, instep contour type, and overall foot structure classification. The arch fitness information includes the arch curvature matching degree, arch structure grade, and fitness calculation result. The shoe model structure fitness score includes the forefoot structure matching degree, heel structure matching degree, and instep space matching degree. The inventory risk level includes the overdue risk level, short-term inventory level, and normal inventory level. The recommendation score includes the shoe model structure fitness score, dynamic weight allocation list, and final recommendation priority.

[0007] As a further solution of the present invention, the steps of calling multi-angle foot images, extracting the contour edge pixels of the sole and instep, calculating the outer edge curvature change features at multiple positions on the sole, classifying and identifying the user's foot structure type using a support vector machine, and outputting the foot type classification label are specifically as follows: S101: Obtain the multi-angle foot image data uploaded by the user, call the sole image and instep image, use the image gray distribution detection method to extract the contour edge pixel sequence of the sole area and instep area, calculate the contour change rate at each position, and combine with the position information to generate the foot contour change rate sequence; S102: Call the foot contour change rate sequence, calculate the curvature change feature values at multiple positions by dividing the sliding window with a fixed step size, perform the second derivative operation on the change rate values within each window, identify the outer edge curvature change characteristics at each position according to the change trend, and establish the sole local feature quantity including the local change rate interval and the curvature change trend; The outer edge curvature change feature is calculated based on the second derivative of the sequence of foot contour change rates within a fixed-step sliding window, and is divided and set as follows: a high convex section where it is greater than 0.03 / mm², a deep concave section where it is less than -0.03 / mm², and a gentle section in between. S103: According to the local feature quantity of the sole, use a support vector machine to identify and classify the categories of each local feature of the user's foot, and output the label of the user's foot structure type, including the width and narrowness of the foot type, the length ratio of the foot type, and the curvature label of the outer contour of the sole, to obtain the foot type classification label.

[0008] As a further solution of the present invention, the steps of calling the foot type classification label, extracting the arch contour curve of the side image of the foot to identify the arch structure feature, comparing with the standard arch grade table to obtain the structure grade label, and combining the sole rigidity score to identify the matching degree between the shoe model and the user's arch structure, and outputting the arch adaptability information are specifically as follows: S201: Call the foot type classification label, obtain the side image of the user's foot, based on the Canny edge detection algorithm, extract the boundary points of the arch area, collect the contour curve data in the order of the boundary points, fit the contour curve using the least squares method, calculate the curvature change value, and generate the arch curvature change sequence; S202: Based on the arch curvature change sequence, sample the curvature nodes at a fixed interval, analyze the curvature change range and trend, extract the bending degree and structure extension features, and call the curvature interval reference value in the standard arch grade table to obtain the arch structure grade label; The standard arch grade table divides the arch with a curvature greater than 0.045 / mm² into a high arch foot, the arch between 0.025 / mm² and 0.045 / mm² into a normal foot, and the arch less than 0.025 / mm² into a flat foot by statistically calculating the average value of the arch curvature change; S203: According to the arch structure grade label, calculate the difference between the sole rigidity score of the shoe model and the center value of the target interval based on the sole rigidity score of each shoe model, and combine the normalization process to obtain the adaptability score and establish the arch adaptability information.

[0009] As a further solution of the present invention, the steps of calling the arch adaptability information, extracting the structural design data of the shoe model to compare with the user's foot contour features, evaluating the matching degree of each part, and combining the arch adaptability to calculate the shoe model structure adaptability score are specifically as follows: S301: Call the arch adaptability information, extract the forefoot width, heel thickness, and instep space height parameters of each shoe model, and based on the foot contour feature point data, respectively match the corresponding shoe model structure parameters, calculate the size difference degree between each part, and obtain the part size difference values of each shoe model and the user's foot at the forefoot, heel, and instep positions; S302: Based on the part size difference value, use the normalization method to standardize multiple part difference values into a unified interval. Combine the importance factor weight table of the target shoe model for each part structure, calculate the average score of each standardized difference value and the corresponding structure importance weight, and obtain the shoe model structure matching degree score of the shoe model in the structure dimension; The importance factor weight table assigns 0.45, 0.35, and 0.20 to the forefoot width, heel thickness, and instep height respectively. After standardizing each part size difference value, multiply it by the corresponding value and sum them respectively as the shoe model structure matching degree score; S303: According to the shoe model structure matching degree score, combine the arch adaptability information to calculate the shoe model structure adaptability score corresponding to each shoe model.

[0010] As a further solution of the present invention, the steps of extracting the warehousing time of children's shoes products, calculating the warehousing days, and identifying the inventory risk level of each product using the DBSCAN clustering algorithm according to the warehousing cycle and sales trend data are specifically as follows: S401: Obtain the warehousing time data of children's shoes products, calculate the difference between the warehousing time of each product and the current time, obtain the warehousing duration information, and generate the warehousing time interval value; S402: Based on the warehousing time interval value, by comparing with the preset benchmark warehousing cycle interval level list, match the warehousing cycle level label of each children's shoes product, and obtain the warehousing cycle classification label corresponding to each product; S403: Call the warehousing cycle classification label, analyze the sales trend of each children's shoes product according to the sales data of each children's shoes product, and calculate the inventory risk level of each children's shoes product.

[0011] As a further solution of the present invention, the steps of calling the inventory risk level and the shoe model structure adaptability score, obtaining the recommendation score value through dynamic weight allocation and non - linear coupling calculation, and superimposing the warehousing cycle parameter and the inventory turnover rate gradient to generate a recommended product list are specifically as follows: S501: Call the inventory risk level and the shoe model structure adaptability score, obtain the recommendation score value through dynamic weight allocation and non - linear coupling calculation, superimpose the warehousing cycle parameter and the inventory turnover rate gradient, and generate a product score list; S502: Based on the product score list, sort the children's shoes products according to the scores, extract the ranking number of each product, and adjust the display priority of each children's shoes on the user recommendation interface to obtain the display priority number of each children's shoes product; S503: Build a product list for the user recommendation interface according to the display priority numbers, and map the basic information of each children's shoe product to the list, including the shoe model name, shoe model picture, sole rigidity score, and fitness score, to obtain a recommended product list.

[0012] On the other hand, an e-commerce platform management device applicable to children's shoes is provided. This device is applied to an e-commerce platform management method applicable to children's shoes. The device includes: A foot structure recognition module that calls the multi-angle foot image data uploaded by the user, extracts the contour edge pixels in the sole and instep images, and based on the extracted sole outer edge curvature change characteristics, uses a support vector machine model to classify and identify the user's foot structure type, generates a foot type classification label, and transfers it to the arch fitness analysis module; An arch fitness analysis module that calls the foot type classification label, extracts the arch contour curve in the side view image of the foot, performs curve fitting, calculates the arch curvature change sequence, extracts the arch structure characteristics, compares them with the standard arch grade table, obtains the arch structure grade label, combines the sole rigidity scores of multiple shoe models, evaluates the matching degree between the shoe model and the user's arch structure, generates arch fitness information, and transfers it to the shoe model structure matching module; A shoe model structure matching module that calls the arch fitness information, extracts the structural design data of each shoe model, including the forefoot width, heel thickness, and instep space height parameters, compares them with the user's foot contour feature data, evaluates the size matching degree of each structural part respectively, combines the arch fitness, calculates the shoe model structure fitness score, generates shoe model structure fitness score data, and transfers it to the product recommendation generation module; An inventory risk assessment module that extracts the warehousing time information of children's shoe products, calculates the storage days of each product, compares the storage time interval with the preset benchmark storage cycle interval grade list to determine the storage cycle classification label, combines the sales trend information, obtains the inventory risk level of each children's shoe product, generates inventory risk level data, and transfers it to the product recommendation generation module; A product recommendation generation module that calls the inventory risk level and the shoe model structure fitness score, through dynamic weight allocation and non-linear coupling calculation, superimposes the storage cycle parameters and the inventory turnover rate gradient, dynamically adjusts the display priority of products on the user recommendation interface according to the scoring results, and generates a recommended product list.

[0013] The beneficial effects brought by the technical solution provided in the embodiments of the present invention at least include: By analyzing the user's foot images and extracting key features, accurate shoe matching can be achieved according to the foot structure type and arch curvature. By carefully comparing the user's foot contour with the shoe design data, the matching degree of each part is evaluated to ensure a high degree of fit between the shoe and the user in terms of comfort and adaptability. The structural adaptability scoring method combines arch features to effectively reduce the return and exchange problems caused by inappropriate shoes. By analyzing the product warehousing time and storage cycle, the inventory risks of products are identified to support the platform in making timely inventory adjustments, reducing the backlog of slow-moving products, optimizing inventory management, and improving the platform operation efficiency and user shopping experience through precise matching and dynamic inventory adjustment. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0015] Figure 1 It is a schematic diagram of the working process of the present invention; Figure 2 It is a system flowchart of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] The following describes the technical solutions in the present invention with reference to the drawings.

[0017] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "example" in the present invention should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, the use of the word "example" is intended to present concepts in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one of the two.

[0018] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, their intended meanings are the same. "(of)", "corresponding", and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, their intended meanings are the same.

[0019] In the embodiments of the present invention, sometimes subscripts such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, their intended meanings are the same.

[0020] To make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments.

[0021] Please refer to Figure 1 , the present invention provides a technical solution, an e-commerce platform management method applicable to children's shoes, including the following steps: S1: Call multi-angle foot images, extract the contour edge pixels of the sole and instep, calculate the outer edge curvature change features at multiple positions on the sole, classify and identify the foot structure type of the user using a support vector machine, and output a foot type classification label; S2: Call the foot type classification label, extract the arch contour curve of the side image of the foot to identify the arch structure features, compare with the standard arch grade table to obtain the structure grade label, and combine the sole rigidity score to identify the matching degree between the shoe model and the user's arch structure, and output the arch fitness information; S3: Call the arch fitness information, extract the structural design data of the shoe model and compare with the foot contour features of the user, evaluate the matching degree of each part, and combine the arch fitness to calculate the shoe model structure fitness score; S4: Extract the warehousing time of children's shoes products, calculate the storage days, and use the DBSCAN clustering algorithm to identify the inventory risk level of each product according to the storage cycle and sales trend data; S5: Call the inventory risk level and the shoe model structure fitness score, through dynamic weight allocation and non-linear coupling calculation, superimpose the storage cycle parameter and the inventory turnover rate gradient, obtain the recommendation score value, and generate a recommended product list.

[0022] The foot type classification label includes the sole contour type, instep contour type, and overall foot structure classification. The arch fitness information includes the arch curvature matching degree, arch structure grade, and fitness calculation result. The shoe model structure fitness score includes the forefoot structure matching degree, heel structure matching degree, and instep space matching degree. The inventory risk level includes the overdue risk level, short-term inventory level, and normal inventory level. The recommendation score includes the shoe model structure fitness score, dynamic weight allocation list, and final recommendation priority.

[0023] Please refer to Figure 1 , the steps of calling multi-angle foot images, extracting the contour edge pixels of the sole and instep, calculating the outer edge curvature change features at multiple positions on the sole, classifying and identifying the foot structure type of the user using a support vector machine, and outputting a foot type classification label specifically include: S101: Obtain the multi-angle foot image data uploaded by the user, call the sole image and instep image, use the image gray distribution detection method to extract the contour edge pixel sequence of the sole area and instep area, calculate the contour change rate at each position, and combine the position information to generate a foot contour change rate sequence; Obtain the multi - angle foot image data uploaded by the user. First, perform normalization processing on all images. Load the sole image and the dorsal foot image at a fixed resolution of 500×500 pixels respectively. For the sole image, sequentially detect the gray - scale values of the pixel points in each row, extract the points with gray - scale values between 80 and 180, and record their corresponding row and column coordinates. For example, when scanning the 200th row, if the columns with gray - scale values in the allowable range are from the 150th column to the 160th column, record these points as the preliminary boundary of the sole. Subsequently, for the dorsal foot image, use a gray - scale range of 90 to 190, and similarly extract the edge coordinates to complete the extraction of the two sets of edge - point sets; After that, from the extracted point sets, calculate the square root of the sum of the squares of the differences in the abscissa and ordinate for every two consecutive points to obtain the contour change rate. For example, if the change rate between points (120, 220) and (122, 223) is a 2 - pixel difference horizontally and a 3 - pixel difference vertically, the change rate is approximately 3.606. After processing all points in sequence, a change - rate sequence is formed. For example , and combine it with the position index to form the complete foot contour change - rate data for subsequent feature extraction; Table 1 Gray - scale Range Table for Extracting Sole and Dorsal Foot Images As shown in Table 1, by setting different gray - scale ranges, the contour boundaries of the sole and dorsal foot can be accurately extracted, laying a foundation for the calculation of the change rate.

[0024] S102: Call the foot contour change - rate sequence. By dividing a sliding window with a fixed step size, calculate the curvature change feature values at multiple positions. Perform a second - order derivative operation on the change - rate values within each window, and identify the outer - edge curvature change characteristics at each position according to the change trend to establish the sole local feature quantity including the local change - rate interval and the curvature change trend; The specific formula for identifying the outer - edge curvature change characteristics at each position according to the change trend is: ; Calculate the local curvature change feature value; Among them, represents the local curvature change feature value within the position window, represents the second - order difference value of the change - rate sequence at the position, represents the change - rate value at the position, represents the change - rate value at the position, is the index position of the local sequence within the sliding window, is the current calculation position index, is the radius of the sliding window, is the The contour pixel coordinate value of the position, is the contour pixel coordinate value of the position, is the standardized reference length parameter, is the total number of samples included in the sliding window centered at the current index ; is the current calculation position index number shifted forward by one position, is the current calculation position index number shifted backward by one position, is the absolute value of the rate of change value at the position; Formula: ; Detailed explanation of the formula and the derivation process of formula calculation: The formula is used to calculate the local curvature change characteristic value of the plantar contour at the position. The obtained result is used to identify the outer edge curvature change characteristic at this position, and then establish the plantar local feature quantity including the local change rate interval and the curvature change trend; Parameter meaning and setting value: is the second-order difference value of the rate of change sequence at the position, and the calculation method is , where is the rate of change value at the position, is the rate of change value at the position, is the rate of change value at the position. Set , , , then ; is the sum of the absolute values of all rates of change within the range of the window radius centered at . The sliding window radius is set to 5. Set the values to be: 0.012, 0.014, 0.016, 0.018, 0.020, 0.022, 0.024, 0.026, 0.028, 0.030, 0.032, ; is the total number of samples in the sliding window. Substitute it into , then ; is the contour pixel coordinate value at the position, is the contour pixel coordinate value at the position. Set , , then ; is the standardized reference length parameter, set to 10; Substitute the parameters into the formula for calculation: ; ; ; ; Substitute the above calculation results into the formula: ; The result indicates that the local curvature change eigenvalue within the position window is small, indicating that the plantar contour change at this position is relatively gentle. The result is used to identify the outer edge curvature change characteristics at this position, and then a plantar local feature quantity including a local change rate interval and a curvature change trend is established.

[0025] The outer edge curvature change characteristic is based on the calculation result of the second derivative of the foot contour change rate sequence within a fixed-step sliding window, and is divided and set according to a high convex section greater than 0.03 / mm², a deep concave section less than -0.03 / mm², and a gentle section between the two; S103: According to the plantar local feature quantity, use a support vector machine to identify and classify the category of each local feature of the user's foot, and output the user's foot structure type label, including the width and narrowness of the foot type, the length ratio of the foot type, and the plantar outer contour curvature label, to obtain the foot type classification label; After extracting all window local feature quantities, perform an encoding operation on each feature quantity, and assign fixed digital encodings to the change rate interval and the smoothness trend respectively. For example, the gentle interval is set to 0, the medium interval is set to 1, the severe interval is set to 2, the curvature change trend with increasing fluctuation is set to 1, the curvature change trend with decreasing fluctuation is set to 2, and the stable is set to 0. The feature quantity of each window corresponds to form a group of encodings. For example, if the change rate interval of a window is medium and the curvature change trend is increasing fluctuating, the encoding is ; Subsequently, all window encodings are integrated into a feature matrix as the classification input to train a support vector machine model. The classification criteria are based on the width of the foot type (e.g., a foot width greater than 10 cm is defined as wide), the length ratio of the foot type (foot length divided by foot width greater than 3.0 is defined as slender), and the curvature of the outer contour of the sole (more than 60% of the medium change interval is marked as medium curvature) for three-label classification. For example, if a user's foot width is 10.8 cm, foot length is 32 cm, and the medium change accounts for 70% in the change interval, the final classification labels are wide, slender, and medium curvature, which are used as the output results; Table 2 Encoding Rules for Local Foot Features As shown in Table 2, by defining standard feature encodings, the unity and accuracy of the classification process can be ensured, facilitating model training and prediction output.

[0026] Please refer to Figure 1 , the steps of calling the foot type classification label, extracting the arch contour curve of the side foot image to identify the arch structure features, comparing with the standard arch grade table to obtain the structure grade label, and combining with the sole rigidity score to identify the matching degree between the shoe model and the user's arch structure and outputting the arch adaptability information specifically include: S201: Call the foot type classification label, obtain the side foot image of the user, based on the Canny edge detection algorithm, extract the boundary points of the arch area, collect the contour curve data according to the boundary point order, use the least squares method to fit the contour curve, calculate the curvature change value, and generate the arch curvature change sequence; Retrieve and load the side foot image of the corresponding user, unify the image size to 640×480 pixels, call the Canny edge detection operation, set the low threshold to 50 and the high threshold to 150, scan the image pixel by pixel, detect the edge contour line points of the arch area, and filter out the continuously distributed and arc-shaped boundary point set through the pixel position change rule. For example, the detected edge points continuously change from the 150th column of the 100th row to the 170th column of the 300th row. According to the arrangement order of the edge points, record the horizontal and vertical coordinates of each boundary point in turn, and at the same time arrange the boundary points in ascending order of row number to ensure the continuity of the contour curve. Subsequently, perform the least squares method fitting on all contour points, that is, by minimizing the sum of the squares of the vertical distances from all points to the fitting curve, obtain the optimal curve fitting parameters. After fitting, analyze the curvature change through the tangent slope change of each point on the fitting curve. The curvature change value is calculated by the differential tangent angle change of adjacent points. For example, if the tangent angles of two adjacent points are 10 degrees and 12 degrees respectively, the change amount is 2 degrees. Finally, organize the curvature change values of all boundary points into sequence data, such as the curvature change sequence , which is output as the arch curvature change sequence; Table 3 Example Table for Arch Area Boundary Point Collection and Curvature Change As shown in Table 3, by extracting boundary points point by point and calculating the curvature change, a complete arch curvature change sequence is formed for subsequent arch characteristic recognition.

[0027] S202: Based on the arch curvature change sequence, sample curvature nodes at fixed intervals, analyze the curvature change range and trend, extract the bending degree and structural extension characteristics, and call the curvature interval reference values in the standard arch grade table to obtain the arch structure grade label; It is set to sample 1 node for every 5 boundary points. For example, in the curvature change sequence , the curvature values of the 1st and 6th points are sampled in sequence to form a node curvature sequence , for the sampled node curvature data, its change range is statistically calculated, that is, the difference between the maximum curvature and the minimum curvature. For example, the change range in the above nodes is 0.03 - 0.03 = 0.00. Further, the curvature change trend is judged. By comparing the size relationship of adjacent node curvature values, if the value of the latter node is greater than that of the previous node, it is recorded as rising, otherwise it is recorded as falling. Subsequently, the curvature interval reference values specified in the standard arch grade table are called. Among them, the arch with a curvature mean greater than 0.045 / mm² is classified as a high-arched foot, the arch with a curvature mean between 0.025 / mm² and 0.045 / mm² is classified as a normal foot, and the arch with a curvature mean less than 0.025 / mm² is classified as a flat foot. For example, the actual sampled node curvature mean is 0.030 / mm², which belongs to the normal foot type. Finally, the corresponding arch structure grade label is output for subsequent shoe style adaptability analysis; Table 4 Arch Curvature Grade Standard Table As shown in Table 4, by performing standardized division according to the arch curvature change mean, the arch structure grade can be clarified, which is convenient for subsequent adaptability measurement; The standard arch grade table classifies the arch with a curvature greater than 0.045 / mm² as a high-arched foot, the arch with a curvature between 0.025 / mm² and 0.045 / mm² as a normal foot, and the arch with a curvature less than 0.025 / mm² as a flat foot by statistically calculating the arch curvature change mean; S203: According to the arch structure grade label, calculate the difference between the sole rigidity score of each shoe style and the center value of the target interval, and combine the normalization process to obtain the adaptability score and establish the arch adaptability information; According to the recognized arch structure level label, call the sole rigidity score data of each shoe in the shoe style database, determine the target interval center value for the user's belonging level, set 0.8 for high-arched feet, 0.5 for normal feet, and 0.3 for flat feet. For example, if the user is identified as having normal feet, the target interval center value is 0.5. Traverse each shoe style, subtract the sole rigidity score from the target center value, and take the absolute value to represent the preliminary difference. For example, if the sole rigidity score of a certain shoe style is 0.6, the preliminary difference is 0.1. To unify the difference comparison between different shoe styles, normalize all the preliminary difference values of the shoe styles. Adopt the minimum-maximum normalization method to linearly scale all the difference values to the 0-1 interval. The smaller the normalized difference value, the higher the fitness. Then, take 1 minus the normalized difference value to get the final fitness score. For example, if the normalized difference of a certain shoe style is 0.25, the fitness is 0.75. Finally, sort all the shoe styles according to the fitness score and recommend the list of shoe styles with the highest fitness to the user.

[0028] Table 5 Example Table of the Fit between Shoe Sole Rigidity and Arch As shown in Table 5, through the normalized calculation of the difference between the sole rigidity score and the arch level center value, the fitness of different shoe styles can be clarified, so as to carry out personalized recommendations.

[0029] Please refer to Figure 1 , call the arch fitness information, extract the structural design data of the shoe style, compare it with the user's foot contour features, evaluate the matching degree of each part, and combine the arch fitness to calculate the steps of the shoe style structure fitness score specifically include: S301: Call the arch fitness information, extract the forefoot width, heel thickness, and instep space height parameters of each shoe style, and based on the foot contour feature point data, respectively match the corresponding shoe style structure parameters, calculate the size difference degree between each part, and obtain the part size difference values of each shoe style and the user's foot at the forefoot, heel, and instep positions; For each shoe style, extract its structural parameter data, including three parameters: forefoot width, heel thickness, and instep space height. For example, the forefoot width of shoe style A is 98 mm, the heel thickness is 28 mm, and the instep space height is 65 mm. At the same time, call the user's foot contour feature point data, and extract the actual measured sizes through the feature points in the forefoot area, heel area, and the highest point area of the instep of the sole. For example, the user actually measures the forefoot width as 102 mm, the heel thickness as 30 mm, and the instep space height as 68 mm. Match the sizes of each part respectively, calculate the difference between the shoe style parameters and the user's corresponding part parameters, and the calculation formula is the user's size minus the shoe style size, and take the absolute value of the difference. For example, the forefoot width difference is mm, the heel thickness difference is mm, and the instep space height difference is mm to obtain the dimensional difference values between Shoe Model A and the user in each part. All shoe models are calculated according to the same logic, and finally a list of dimensional difference values for the forefoot, heel, and instep positions of each shoe model is formed. Table 6 Example Table of Dimensional Differences between Shoe Models and User's Foot Parts As shown in Figure 6, by calculating the dimensional differences between each part of the shoe model and the user's foot structure item by item, basic data can be provided for subsequent structural matching degree analysis.

[0030] S302: Based on the dimensional difference values of the parts, use the normalization method to standardize multiple part difference values to a unified interval. Combine the importance factor weight table of the structure of each part of the target shoe model, calculate the average score of each standardized difference value and the corresponding structural importance weight, and obtain the shoe model structure matching degree score in the structural dimension. Based on the dimensional difference values of the parts calculated above, first perform normalization processing on the difference values of the forefoot, heel, and instep of each shoe model respectively. The normalization uses the minimum-maximum normalization method to linearly map the difference values to the [0,1] interval. For example, for the forefoot difference values of all shoe models, the maximum difference value is 5mm and the minimum difference value is 2mm. The normalized forefoot difference value is calculated according to the following logic: Taking the forefoot difference of 4mm of Shoe Model A as an example, the normalization calculation is Similarly, process the heel and instep difference values. Subsequently, call the structure importance factor weight table, assign weights of 0.45, 0.35, and 0.20 to the forefoot width, heel thickness, and instep space height respectively. Multiply the normalized difference value of each shoe model by the corresponding weight value to obtain the weighted difference value of each part respectively, and then sum to obtain the shoe model structure matching degree score. For example, the normalized differences of Shoe Model A are 0.6667 for the forefoot, 0.3333 for the heel, and 0.5 for the instep. The calculation process is as follows: Score of the forefoot: ; Score of the heel: ; Score of the instep: ; The final structure matching degree score of Shoe Model A is , and the scores of all shoe models are calculated in the same way and are used for subsequent integration with the arch adaptability. The importance factor weight table standardizes each part dimensional difference value, multiplies them by the corresponding values respectively and sums them, by assigning 0.45, 0.35, and 0.20 to the forefoot width, heel thickness, and instep space height respectively, as the shoe model structure matching degree score.

[0031] S303: Calculate the shoe model structure adaptability score corresponding to each shoe model based on the shoe model structure matching score and in combination with the arch adaptability information; Based on the structure matching scores of each shoe model in the structure dimension and in combination with the arch adaptability scores of the corresponding shoe models, comprehensively calculate the shoe model structure adaptability scores. In specific operations, first call the shoe model structure matching score and the arch adaptability score separately. Set the structure matching score of shoe model A to 0.5167 and the arch adaptability score to 0.75. To comprehensively consider the adaptability in both aspects, take the weighted average of the two. Among them, the weight of the arch adaptability is set to 0.6, and the weight of the structure matching is set to 0.4. The specific calculation steps are as follows: Multiply the arch adaptability score of 0.75 by 0.6 to get 0.45, multiply the structure matching score of 0.5167 by 0.4 to get 0.2067, and add the two to obtain the comprehensive adaptability score of 0.6567. Calculate the remaining shoe models in the same way. Sort the shoe models through the comprehensive adaptability scores to obtain a recommended list of shoe models that are most suitable for the user's foot shape and arch characteristics; Table 7 Example Table of Shoe Model Comprehensive Adaptability Scores As shown in Table 7, by comprehensively calculating the matching situations in both the arch and structure aspects, the overall adaptability of the shoe models can be accurately evaluated and personalized recommendations can be made.

[0032] Please refer to Figure 1 , call the arch adaptability information, extract the structural design data of the shoe models, compare with the user's foot contour characteristics, evaluate the matching degree of each part, and in combination with the arch adaptability, the steps to calculate the shoe model structure adaptability score specifically include: S401: Obtain the warehousing time data of children's shoes products, calculate the difference between the warehousing time of each product and the current time, obtain the warehousing duration information, and generate a warehousing time interval value; First, it is necessary to query the warehousing records of each children's shoes product through the warehousing management system, read the "warehousing time" field in each product record. In the example, take January 1, 2025 as the warehousing time of product A. Then call the system current time parameter and set it to April 29, 2025. Compare the warehousing time with the current time and perform the time difference calculation. Adopt subtracting the product warehousing timestamp (such as the timestamp of January 1, 2025 is 1735689600 seconds) from the current time timestamp (such as the timestamp of April 29, 2025 is 1751414400 seconds), and then divide the difference by 86400 seconds (i.e., the number of seconds in a day) to obtain the warehousing days. The calculation result is days, and after rounding, take 18 days. Execute the same steps for all products in batches to form a warehousing duration information set. Further, based on the warehousing days, construct a warehousing time interval value list. For example, the warehousing time of product B is December 15, 2024 (timestamp 1734211200 seconds), and the warehousing days are For the days, take 20 days, and organize the warehousing time interval values in the form of an array as days, etc., and then complete the generation of the warehousing time interval values.

[0033] S402: Based on the warehousing time interval values, by comparing with the preset reference warehousing cycle interval grade list, match the warehousing cycle grade label for each children's shoe product, and obtain the corresponding warehousing cycle classification label for each product; Read the warehousing days obtained in the previous step in sequence. For each warehousing day, call the preset reference warehousing cycle interval grade list for comparison. The list is set as follows: Table 8 Warehousing Cycle Interval Grade Table Taking Table 8 as a reference, read the warehousing days of Product A as 18 days. Determine that 18 is between 0 and 20, and match to Grade A. Read the warehousing days of Product B as 20 days. Determine that the boundary 20 belongs to the upper limit of Grade A and still classify it as Grade A; for the product with 25 days of warehousing, determine that it is between 21 and 40 and match to Grade B. And so on. For the product with 45 days of warehousing, by determining that 45 is between 41 and 60, classify it as Grade C. Complete the matching of the warehousing days of each product with the interval grade, generate the corresponding warehousing cycle classification label for each product, and finally form a corresponding list of children's shoe products to warehousing grade labels, such as Product A: Grade A, Product B: Grade A, Product C: Grade B, Product D: Grade B, Product E: Grade C.

[0034] S403: Call the warehousing cycle classification label, analyze the sales trend of each children's shoe product according to the sales data of each children's shoe product, and calculate the inventory risk level of each children's shoe product; The specific formula for analyzing the sales trend of each children's shoe product is: ; Calculate the sales trend fluctuation value of each children's shoe product; Among them, represents the sales trend fluctuation value of the th children's shoe product, represents the th children's shoe product in the th time period, represents the th children's shoe product in the overall cycle, represents the th children's shoe product in the th time period, represents the th children's shoe product in the The inventory level within a time period represents the maximum inventory level of the th children's shoe product during the analysis period represents the th children's shoe product's median sales during the overall period represents the total number of time periods used for analysis represents the number or index of each children's shoe product represents the index of the time period; Formula: ; Detailed explanation of the formula and the derivation process of formula calculation: This formula is used to calculate the sales trend fluctuation value of each children's shoe product, and the result obtained is used to evaluate the sales stability and inventory risk level of the product; Meaning and set values of parameters: is the sales quantity, set as : [100, 120, 110, 130, 140, 150, 160, 170, 180, 190, 200, 210]; is the number of days in the storage cycle, set as [30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30]; is the inventory level, set as : [50, 60, 70, 80, 90, 100, 110, 120, 130, 140, 150, 160]; is the th children's shoe product's maximum inventory level during the analysis period, set as ; is the th children's shoe product's median sales during the overall period, set as ; The total number of time periods used for analysis, set as ; Substitute the parameters into the formula for calculation: Calculate the average sales quantity : ; Calculate the absolute deviation of the sales quantity from the average sales quantity : ; Calculation result: ; Calculate the square root of the storage cycle days : ; Calculate the inventory reverse difference item : ; Calculation result: ; Calculate the absolute deviation of the average sales quantity from the median sales : ; Substitute the above results into the formula for calculation : ; Calculation result: ; ; ; ; ; ; Result 55 indicates that the sales trend fluctuation value of the th children's shoes product is 55, indicating that the sales of this product fluctuate greatly during the analysis period, and there may be risks of inventory backlog or unstable sales. Combining the moving average method and the exponential smoothing method, fit the sales curve of the product, speculate on future sales conditions, and calculate the safety inventory level based on the predicted sales trend and the current inventory level, taking into account factors such as seasonal fluctuations, supply cycles, and sales volatility of the product. That is, to ensure that a certain sales capacity can still be maintained in the event of a supply chain interruption. Through the inventory risk level assessment standard, the products are divided into three levels: low risk, medium risk, and high risk. If the inventory of a product is much higher than the safety inventory level and the turnover rate is low, it can be classified as a high inventory risk level. Such products need special attention, including conducting promotions or adjusting sales strategies. On the contrary, if the inventory is close to or lower than the safety inventory and the turnover rate is high, it is a low-risk level product, indicating that the product has stable sales and sufficient inventory.

[0035] Please refer to Figure 1 , call the inventory risk level and shoe style structure fitness score, and through dynamic weight allocation and non-linear coupling calculation, superimpose the storage cycle parameters and the inventory turnover rate gradient to obtain the recommendation score value. The steps to generate the recommended product list specifically include: S501: Call the inventory risk level and the shoe style structure adaptability score, calculate through dynamic weight allocation and non-linear coupling, superimpose the warehousing cycle parameter and the inventory turnover rate gradient, obtain the recommendation score value, and generate a product score list; First, read the inventory risk level of each children's shoe product in the product database. Assume that the risk level of product A is low risk and that of product B is medium risk. Extract the shoe style structure adaptability score. Assume that the adaptability score of product A is 85 points and that of product B is 70 points. Then, perform dynamic weight allocation. Set the weight coefficient of the inventory risk level to 0.6 and the weight coefficient of the shoe style adaptability score to 0.4. When performing non-linear coupling calculation, first multiply the two weights by their corresponding score values. For example, for product A: the score assigned to the inventory risk level is 90, and the score for the shoe style adaptability is 85. Execute 、 , sum the two to get the total score of 88. When superimposing the warehousing cycle parameter, introduce the warehousing days gradient as an adjustment factor. Assume that the warehousing days gradient is assigned 0.95 (the standard is 0.95 within 20 days, 0.9 for 21 - 40 days, 0.85 for 41 - 60 days, and 0.8 for more than 60 days. The classification standard is shown in Table 2). The warehousing days of product A is 18 days, so the gradient is 0.95. The final recommendation score value is , similarly, for product B, the score of the inventory risk level is 75, and the score of the shoe style adaptability is 70. After weight processing, get 、 , the total score is 73, the warehousing days is 45 days, and the corresponding gradient is 0.85. The recommendation score value is , finally, batch calculate the recommendation score values of all products according to the above steps, and generate a product score list; Table 9 Warehousing Cycle and Warehousing Time Gradient Table As shown in Table 9, different ranges of warehousing days correspond to different gradients, which are used to adjust the recommendation score value.

[0036] S502: Based on the product score list, sort the children's shoe products according to the scores, extract the position number of each product, and adjust the display priority of each children's shoe in the user recommendation interface to obtain the display priority number of each children's shoe product; First, sort the recommendation score values according to the score size, and arrange all children's shoes products in descending order of scores. For the example products, product A scores 83.6 and product B scores 62.05. Product A ranks first and product B ranks second. Extract the position numbers of each product. During this process, set the starting value of the number to 1, and number them in descending order of scores in sequence. Product A is numbered 1 and product B is numbered 2. Subsequently, adjust the display priority of each pair of children's shoes in the user recommendation interface. By directly using the product position number as the interface priority order identifier, complete the number update. For example, product A has a display priority of 1 in the interface and product B has a priority of 2. In specific implementation, it is necessary to call the product display interface management module, read the recommendation position field, and replace the original field value with the currently obtained priority number. If there is a conflict situation in the original interface (such as an existing priority being occupied), then by comparing the scores of the existing product and the new product, the higher one covers the lower one. After performing the priority refresh operation, save the update. Finally, obtain the set of display priority numbers for each pair of children's shoes products.

[0037] S503: According to the display priority number, construct the product list of the user recommendation interface, and map the basic information of each pair of children's shoes to the list, including the shoe model name, shoe model picture, sole rigidity score, and fitness score, to obtain the recommended product list; First, traverse the product data table in ascending order of display priority, filter the corresponding product basic information fields. The field content includes the shoe model name, shoe model picture, sole rigidity score, and structural fitness score. Among them, the sole rigidity score is quantified according to a preset standard, and the rigidity score range is set to 0 - 100 points. Assume that the sole rigidity score of product A is 78 points and that of product B is 85 points. The fitness score calls the fitness score value obtained in S501. Product A is 85 points and product B is 70 points. Combine the filtered shoe model names such as "Light Step Children's Shoes Type A" and "Healthy Step Children's Shoes Type B", the shoe model picture paths such as " / images / A.jpg" and " / images / B.jpg", the sole rigidity score, and the fitness score into a structured data list, and map it to the recommended interface product list display module. In the display module, call the list generation interface and write the product entries in sequence according to the priority. Serial number 1 corresponds to product A and serial number 2 corresponds to product B. Finally, generate the recommended product list. Each row of this list displays the shoe model name, shoe model picture, sole rigidity score, and fitness score, and completes the construction of the recommended interface data.

[0038] Please refer to Figure 2 , an e-commerce platform management device applicable to children's shoes. The e-commerce platform management device applicable to children's shoes is used to execute the above-mentioned e-commerce platform management method for children's shoes. The device includes: The foot structure recognition module calls the multi-angle foot image data uploaded by the user, extracts the contour edge pixels in the sole and instep images, and based on the extracted curvature change features of the outer edge of the sole, uses a support vector machine model to classify and identify the user's foot structure type, generates a foot type classification label and transfers it to the arch adaptation analysis module; The arch adaptation analysis module calls the foot type classification label, extracts the arch contour curve in the side image of the foot, performs curve fitting, calculates the arch curvature change sequence, extracts the arch structure features, compares them with the standard arch grade table, obtains the arch structure grade label, combines the sole rigidity scores of multiple shoe models, evaluates the matching situation between the shoe model and the user's arch structure, generates the arch adaptation degree information and transfers it to the shoe model structure matching module; The shoe model structure matching module calls the arch adaptation degree information, extracts the structural design data of each shoe model, including the forefoot width, heel thickness and instep space height parameters, compares them with the user's foot contour feature data, evaluates the size matching degree of each structural part respectively, combines the arch adaptation degree, calculates the shoe model structure adaptation degree score, generates the shoe model structure adaptation degree score data and transfers it to the commodity recommendation generation module; The inventory risk assessment module extracts the warehousing time information of children's shoes commodities, calculates the warehousing days of each commodity, compares the warehousing time interval with the preset benchmark warehousing cycle interval grade list, determines the warehousing cycle classification label, combines the sales trend information, obtains the inventory risk level of each children's shoes commodity, generates the inventory risk level data and transfers it to the commodity recommendation generation module; The commodity recommendation generation module calls the inventory risk level and the shoe model structure adaptation degree score, through dynamic weight allocation and non-linear coupling calculation, superimposes the warehousing cycle parameter and the inventory turnover rate gradient, dynamically adjusts the display priority of the commodity on the user recommendation interface according to the scoring result, and generates a recommended commodity list.

[0039] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that contains one or more collections of available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, or magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0040] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood by referring to the context before and after.

[0041] In the present invention, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following" or its similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0042] It should be understood that in various embodiments of the present invention, the magnitudes of the sequence numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0043] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0044] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described devices, apparatuses, and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0045] In several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be in an electrical, mechanical, or other form.

[0046] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0047] In addition, the functional units in each embodiment of the present invention can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0048] When the above-mentioned function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0049] As described above, the above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A management method for an e-commerce platform applicable to children's shoes, characterized in that, The method includes: S1: Call multi-angle foot images, extract the edge pixels of the sole and dorsal surface contours of the foot, calculate the outer edge curvature change features at multiple positions on the sole, classify and identify the foot structure type of the user using a support vector machine, and output a foot type classification label; S2: Call the foot type classification label, extract the arch contour curve of the lateral foot image to identify the arch structure features, compare with the standard arch grade table to obtain the structure grade label, and combine with the sole rigidity score to identify the matching degree between the shoe model and the user's arch structure, and output the arch adaptability information; S3: Call the arch adaptability information, extract the structural design data of the shoe model to compare with the foot contour features of the user, evaluate the matching degree of each part, and combine with the arch adaptability to calculate the shoe model structure adaptability score; S4: Extract the warehousing time of children's shoes products, calculate the storage days, and use the DBSCAN clustering algorithm to identify the inventory risk level of each product according to the storage cycle and sales trend data; S5: Call the inventory risk level and the shoe model structure adaptability score, through dynamic weight allocation and non-linear coupling calculation, superimpose the storage cycle parameter and the inventory turnover rate gradient to obtain a recommendation score value, and generate a list of recommended products.

2. The e-commerce platform management method applicable to children's shoes according to claim 1, wherein, The foot type classification label includes the sole contour type, dorsal surface contour type, and overall foot structure classification. The arch adaptability information includes the arch curvature matching degree, arch structure grade, and adaptability calculation result. The shoe model structure adaptability score includes the forefoot structure matching degree, heel structure matching degree, and dorsal surface space matching degree. The inventory risk level includes the overdue risk level, short-term inventory level, and normal inventory level; The recommendation score includes the shoe model structure adaptability score, dynamic weight allocation list, and final recommendation priority.

3. The e-commerce platform management method applicable to children's shoes according to claim 1, wherein, The steps of calling multi-angle foot images, extracting the edge pixels of the sole and dorsal surface contours of the foot, calculating the outer edge curvature change features at multiple positions on the sole, classifying and identifying the foot structure type of the user using a support vector machine, and outputting a foot type classification label are specifically as follows: S101: Obtain the multi-angle foot image data uploaded by the user, call the sole image and dorsal surface image, use the image gray distribution detection method to extract the edge pixel sequence of the sole area and dorsal surface area of the foot, calculate the contour change rate at each position, and combine with the position information to generate a foot contour change rate sequence; S102: Call the foot contour change rate sequence, calculate the curvature change feature values at multiple positions by dividing a sliding window with a fixed step size, perform a second-order derivative operation on the change rate values within each window, identify the outer edge curvature change characteristics at each position according to the change trend, and establish a sole local feature quantity including the local change rate interval and the curvature change trend; The outer edge curvature change feature is based on the second-order derivative calculation result of the foot contour change rate sequence within a sliding window with a fixed step size, and is divided and set according to greater than 0.03 / mm² as the high convex section, less than -0.03 / mm² as the deep concave section, and between the two as the gentle section; S103: According to the local plantar feature quantity, use a support vector machine to identify and classify the categories of each local feature of the user's foot, and output the label of the user's foot structure type, including the width and narrowness of the foot type, the length ratio of the foot type, and the curvature label of the plantar outer contour, to obtain the foot type classification label.

4. The e-commerce platform management method applicable to children's shoes according to claim 3, characterized in that The specific formula for identifying the change characteristics of the outer edge curvature at each position based on the change trend is: ； Calculate the local curvature change eigenvalue; Among them, represents the local curvature change eigenvalue within the position window, represents the second-order difference value of the position change rate sequence, represents the change rate value at the position, represents the change rate value at the position, is the index position of the local sequence within the sliding window, is the current calculation position index, is the sliding window radius, is the contour pixel coordinate value at the is the contour pixel coordinate value at the is the normalized reference length parameter, is the total number of samples included within the sliding window centered at the current index , is the current calculation position and the index number offset one position forward, is the current calculation position and the index number offset one position backward, is the absolute value of the change rate value at the position.

5. The e-commerce platform management method applicable to children's shoes according to claim 3, characterized in that The steps of calling the foot type classification label, extracting the arch contour curve of the side view of the foot to identify the arch structure characteristics, comparing with the standard arch grade table to obtain the structure grade label, and combining the sole rigidity score to identify the matching degree between the shoe model and the user's arch structure, and outputting the arch adaptability information are specifically as follows: S201: Call the foot type classification label, obtain the side view image of the user's foot, based on the Canny edge detection algorithm, extract the boundary points of the arch area, collect the contour curve data in the order of the boundary points, fit the contour curve using the least squares method, calculate the curvature change value, and generate the arch curvature change sequence; S202: Based on the arch curvature change sequence, sample the curvature nodes at a fixed interval, analyze the curvature change range and trend, extract the bending degree and structure extension characteristics, and call the curvature interval reference value in the standard arch grade table to obtain the arch structure grade label; The standard arch grade table classifies the arch with a curvature greater than 0.045 / mm² as a high arch foot, the arch between 0.025 / mm² and 0.045 / mm² as a normal foot, and the arch less than 0.025 / mm² as a flat foot by statistically calculating the average value of the arch curvature change; S203: According to the arch structure grade label, calculate the difference between the sole rigidity score of the shoe model and the center value of the target interval based on the sole rigidity score of each shoe model, and combine the normalization process to obtain the adaptability score and establish the arch adaptability information.

6. The e-commerce platform management method applicable to children's shoes according to claim 5, characterized in that, The steps of calling the arch adaptability information, extracting the structural design data of the shoe model to compare with the user's foot contour characteristics, evaluating the matching degree of each part, and combining the arch adaptability to calculate the shoe model structure adaptability score are specifically as follows: S301: Call the arch adaptability information, extract the forefoot width, heel thickness, and instep space height parameters of each shoe model, and based on the foot contour feature point data, respectively match the corresponding shoe model structure parameters, calculate the size difference degree between each part, and obtain the part size difference values of each shoe model and the user's foot at the forefoot, heel, and instep positions; S302: Based on the part size difference values, use the normalization processing method to standardize multiple part difference values to a unified interval, and combine the importance factor weight table of the structure of each part of the target shoe model to calculate the average score of each standardized difference value and the corresponding structure importance weight, and obtain the shoe model structure matching degree score in the structure dimension; The importance factor weight table assigns 0.45, 0.35, and 0.20 to the forefoot width, heel thickness, and instep space height respectively. After standardizing each part size difference value, multiply and sum them with the corresponding values respectively as the shoe model structure matching degree score; S303: Calculate the shoe structure adaptability score for each shoe style based on the shoe style structure matching score and in combination with the arch adaptability information.

7. The e-commerce platform management method applicable to children's shoes according to claim 6, characterized in that, The steps of extracting the warehousing time of children's shoes products, calculating the warehousing days, and identifying the inventory risk level of each product according to the warehousing cycle and sales trend data by using the DBSCAN clustering algorithm are specifically as follows: S401: Obtain the warehousing time data of children's shoes products, calculate the difference between the warehousing time of each product and the current time, obtain the warehousing duration information, and generate the warehousing time interval value; S402: Based on the warehousing time interval value, by comparing with the preset list of benchmark warehousing cycle interval levels, match the warehousing cycle level label of each children's shoes product, and obtain the warehousing cycle classification label corresponding to each product; S403: Invoke the warehousing cycle classification label, analyze the sales trend of each children's shoes product according to the sales data of each children's shoes product, and calculate the inventory risk level of each children's shoes product.

8. The e-commerce platform management method applicable to children's shoes according to claim 7, characterized in that, The specific formula for analyzing the sales trend of each children's shoes product is: ； Calculate the sales trend fluctuation value of each children's shoes product; Among them, represents the sales trend fluctuation value of the th children's shoe product, represents the th children's shoe product in the th time period, represents the th children's shoe product's average sales quantity in the overall period, represents the th children's shoe product's warehousing cycle days corresponding to the warehousing cycle classification label in the th time period, represents the th children's shoe product's inventory level in the th time period, represents the th children's shoe product's maximum inventory level in the analysis period, represents the th children's shoe product's sales median in the overall period, represents the total number of time periods used for analysis, represents the number or index of each children's shoe product, represents the index of the time period.

9. The e-commerce platform management method applicable to children's shoes according to claim 7, characterized in that, The steps of invoking the inventory risk level and the shoe structure adaptability score, obtaining the recommendation score value through dynamic weight allocation and non-linear coupling calculation, and superimposing the warehousing cycle parameter and the inventory turnover rate gradient to generate the recommended product list are specifically as follows: S501: Invoke the inventory risk level and the shoe structure adaptability score, obtain the recommendation score value through dynamic weight allocation and non-linear coupling calculation, superimpose the warehousing cycle parameter and the inventory turnover rate gradient, and generate the product score list; S502: Based on the product score list, sort the children's shoes products according to the scores, extract the ranking number of each product, and adjust the display priority of each children's shoes in the user recommendation interface to obtain the display priority number of each children's shoes product; S503: According to the display priority number, construct the product list of the user recommendation interface, and map the basic information of each children's shoes product to the list, including the shoe style name, shoe style picture, sole rigidity score, and adaptability score, to obtain the recommended product list.

10. An e-commerce platform management device applicable to children's shoes, characterized in that, The device is used to implement the e-commerce platform management method for children's shoes according to any one of claims 1-9. The device includes: A foot structure recognition module, which invokes the multi-angle foot image data uploaded by the user, extracts the contour edge pixels in the sole and instep images, and based on the extracted sole outer edge curvature change feature, uses a support vector machine model to classify and identify the user's foot structure type, generates a foot type classification label, and transfers it to the arch adaptability analysis module; An arch adaptability analysis module, which invokes the foot type classification label, extracts the arch contour curve in the side view image of the foot, performs curve fitting, calculates the arch curvature change sequence, extracts the arch structure feature, compares it with the standard arch grade table, obtains the arch structure grade label, combines the sole rigidity scores of multiple shoe styles, evaluates the matching situation between the shoe style and the user's arch structure, generates the arch adaptability information, and transfers it to the shoe style structure matching module; The shoe style structure matching module calls the arch adaptability information, extracts the structural design data of each shoe style, including the forefoot width, heel thickness, and instep space height parameters, compares them with the user's foot contour feature data, evaluates the size matching degree of each structural part respectively, combines the arch adaptability, calculates the shoe style structure adaptability score, generates the shoe style structure adaptability score data and transmits it to the product recommendation generation module; The inventory risk assessment module extracts the warehousing time information of children's shoes products, calculates the storage days of each product, compares the storage time interval with the preset benchmark storage cycle interval grade list to determine the storage cycle classification label, combines the sales trend information, obtains the inventory risk level of each children's shoes product, generates the inventory risk level data and transmits it to the product recommendation generation module; The product recommendation generation module calls the inventory risk level and the shoe style structure adaptability score, through dynamic weight allocation and non-linear coupling calculation, superimposes the storage cycle parameter and the inventory turnover rate gradient, dynamically adjusts the display priority of products on the user recommendation interface according to the scoring result, and generates a recommended product list.

Images