3D Printing Model Adjustment Analysis Method and System for a Cycling Shoe

Abstract

The present invention discloses a method and system for adjusting and analyzing a 3D printing model of a cycling shoe, which relates to the technical field of cycling shoe design. The method includes: obtaining initial three-dimensional graphic data and initial printing parameters of an initial 3D printing model designed for a cycling shoe; wherein, the initial three-dimensional graphic data includes initial structural parameters, initial triangular facet data and initial texture information; the initial printing parameters include printing material, printing layer thickness, printing temperature, printing speed, support structure and printing path; analyzing the initial three-dimensional graphic data and the initial printing parameters of the initial 3D printing model according to the foot shape data and cycling dynamics parameters of the cyclist to obtain an adaptability analysis result; adjusting the initial three-dimensional graphic data and the initial printing parameters according to the adaptability analysis result; outputting a 3D printing model of the cycling shoe adjusted to match the cyclist.

Description

Technical Field

[0001] This application relates to the technical field of cycling shoe design. Specifically, it relates to a method and system for adjusting and analyzing 3D printing models of cycling shoes. Background Art

[0002] Cycling shoes, especially bicycle cycling shoes, are specialized footwear designed for cycling. They usually have a hard sole to more effectively transfer the rider's pedaling force to the pedals, thereby improving cycling efficiency. The design of cycling shoes needs to consider comfort, breathability, support, and durability to meet the needs of long-distance cycling. 3D printing technology, also known as additive manufacturing technology, is a process of constructing three-dimensional objects by adding materials layer by layer. In the design and manufacturing field of cycling shoes, 3D printing technology allows designers to create complex geometries, achieve personalized customization, and quickly iterate designs, thus shortening the product development cycle.

[0003] Although 3D printing technology has brought revolutionary changes to the design and manufacturing of cycling shoes, in practical applications, the design of 3D printing models for cycling shoes still faces some challenges. The most prominent problem is experience dependence: existing technologies rely heavily on designers' experience and intuition when designing 3D printing models for cycling shoes. This design method lacks systematic analysis and optimization, which may lead to low design efficiency and it is difficult to ensure the optimization of the design.

[0004] For the above problems, no effective solutions have been proposed yet. Summary of the Invention

[0005] Embodiments of this application provide a method and system for adjusting and analyzing 3D printing models of cycling shoes to solve the above technical problems.

[0006] This application provides a method for adjusting and analyzing 3D printing models of cycling shoes, including: obtaining the initial three-dimensional graphic data and initial printing parameters of the initial 3D printing model designed for cycling shoes; where the initial three-dimensional graphic data includes initial structure parameters, initial triangular facet data, and initial texture information; the initial printing parameters include printing material, printing layer thickness, printing temperature, printing speed, support structure, and printing path; analyzing the initial three-dimensional graphic data and initial printing parameters of the initial 3D printing model according to the rider's foot shape data and cycling dynamics parameters to obtain an adaptability analysis result; adjusting the initial three-dimensional graphic data and the initial printing parameters according to the adaptability analysis result; outputting the adjusted 3D printing model of the cycling shoe that matches the rider.

[0007] The present application provides a 3D printing model adjustment and analysis system for cycling shoes, including: an initial 3D printing information acquisition module, configured to acquire initial three-dimensional graphic data and initial printing parameters of an initial 3D printing model designed for cycling shoes; wherein, the initial three-dimensional graphic data includes initial structure parameters, initial triangular facet data, and initial texture information; the initial printing parameters include printing material, printing layer thickness, printing temperature, printing speed, support structure, and printing path; a rider adaptability analysis module, configured to analyze the initial three-dimensional graphic data and the initial printing parameters of the initial 3D printing model according to the foot shape data and cycling dynamics parameters of the rider to obtain an adaptability analysis result; a printing information adjustment module, configured to adjust the initial three-dimensional graphic data and the initial printing parameters according to the adaptability analysis result; and an adapted 3D printing model output module, configured to output a 3D printing model of a cycling shoe that is adjusted and matched to the rider.

[0008] Based on the embodiments provided in the present application, acquire the initial three-dimensional graphic data and the initial printing parameters of the initial 3D printing model designed for cycling shoes; wherein, the initial three-dimensional graphic data includes initial structure parameters, initial triangular facet data, and initial texture information; the initial printing parameters include printing material, printing layer thickness, printing temperature, printing speed, support structure, and printing path; analyze the initial three-dimensional graphic data and the initial printing parameters of the initial 3D printing model according to the foot shape data and cycling dynamics parameters of the rider to obtain an adaptability analysis result; adjust the initial three-dimensional graphic data and the initial printing parameters according to the adaptability analysis result; and output a 3D printing model of a cycling shoe that is adjusted and matched to the rider. By means of an automated adjustment and analysis method to assist designers in adjusting and optimizing the model, it is possible to reduce the dependence on personal experience, improve design efficiency and product quality, and make the 3D printing model design of cycling shoes more accurate and efficient; promote the technological progress in the field of cycling shoe design and manufacturing, and provide cycling shoe products with better performance and more in line with personalized needs for riders. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, form a part of this application, and the illustrative embodiments and descriptions thereof are used to explain this application and do not constitute an improper limitation to this application. In the drawings:

[0010] Figure 1 is a flowchart of an optional 3D printing model adjustment and analysis method for cycling shoes according to an embodiment of the present application;

[0011] Figure 2 is a structural diagram of an optional 3D printing model adjustment and analysis system for cycling shoes according to an embodiment of the present application.

[0012] The realization, functional features and advantages of the present invention will be further described in conjunction with the embodiments with reference to the accompanying drawings. Detailed implementation manners

[0013] In order to enable those skilled in the art of this technology to better understand the solution of this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this application.

[0014] Optionally, as Figure 1 shown, this application provides a method for adjusting and analyzing a 3D printing model of a cycling shoe, including:

[0015] S101, obtaining the initial three-dimensional graphic data and initial printing parameters of the initial 3D printing model designed for the cycling shoe; wherein, the initial three-dimensional graphic data includes initial structure parameters, initial triangular patch data and initial texture information; the initial printing parameters include printing material, printing layer thickness, printing temperature, printing speed, support structure and printing path;

[0016] S102, analyzing the initial three-dimensional graphic data and initial printing parameters of the initial 3D printing model according to the foot shape data and cycling dynamics parameters of the cyclist to obtain an adaptability analysis result;

[0017] S103, adjusting the initial three-dimensional graphic data and initial printing parameters according to the adaptability analysis result;

[0018] S104, outputting the adjusted 3D printing model of the cycling shoe that matches the cyclist.

[0019] Based on the embodiments provided in this application, the initial three-dimensional graphic data and initial printing parameters of the initial 3D printing model designed for the cycling shoe are obtained; wherein, the initial three-dimensional graphic data includes initial structure parameters, initial triangular patch data and initial texture information; the initial printing parameters include printing material, printing layer thickness, printing temperature, printing speed, support structure and printing path; the initial three-dimensional graphic data and initial printing parameters of the initial 3D printing model are analyzed according to the foot shape data and cycling dynamics parameters of the cyclist to obtain an adaptability analysis result; the initial three-dimensional graphic data and initial printing parameters are adjusted according to the adaptability analysis result; the adjusted 3D printing model of the cycling shoe that matches the cyclist is output. By means of an automated adjustment and analysis method to assist designers in adjusting and optimizing the model, the dependence on personal experience is reduced, the design efficiency and product quality are improved, making the 3D printing model design of cycling shoes more accurate and efficient; promoting the technological progress in the field of cycling shoe design and manufacturing, and providing cycling shoe products with better performance and more in line with personalized needs for riders.

[0020] Analyze the initial 3D graphic data and initial printing parameters of the initial 3D printing model according to the foot type data and cycling kinetics parameters of the cyclist, and obtain the adaptability analysis result, which is configured to:

[0021] Use 3D scanning technology to obtain the foot type data of the cyclist; among them, the foot type data includes the length, width, dorsal height and arch height of the foot;

[0022] Collect the cycling kinetics parameters of the cyclist through a motion capture system; among them, the cycling kinetics parameters include pedaling force, frequency and foot position;

[0023] Extract foot type features from the foot type data of the cyclist, and establish the first correlation relationship between the foot type features and the initial structural parameters;

[0024] Extract cycling kinetics features from the cycling kinetics parameters of the cyclist; establish the second correlation relationship between the cycling kinetics features and the initial structural parameters;

[0025] According to the first correlation relationship and the second correlation relationship, analyze the initial 3D graphic data and initial printing parameters of the initial 3D printing model, and obtain the adaptability analysis result.

[0026] Furthermore, according to the first correlation relationship and the second correlation relationship, analyze the initial 3D graphic data and initial printing parameters of the initial 3D printing model, and obtain the adaptability analysis result, which is configured to:

[0027] Establish the vector representation of foot type features and cycling kinetics features in a multi-dimensional space;

[0028] Through the radial basis function, map the vector representation of foot type features in the multi-dimensional space and the vector representation of cycling kinetics features in the multi-dimensional space to an extended dimensional space to obtain an extended foot type vector and an extended cycling kinetics vector;

[0029] Construct a transaction dataset based on the extended foot type vector and the extended cycling kinetics vector;

[0030] Use the Relim algorithm to mine frequent item sets from the transaction dataset; among them, the frequent item sets represent the combined patterns of foot type features and cycling kinetics features;

[0031] For each frequent item set, use a gradient boosting tree to construct a tree-based model; among them, each tree-based model is used to predict the configuration of structural parameters according to foot type features and cycling kinetics features;

[0032] Among them, the objective function of the gradient boosting tree Among them, n is the total number of samples; i is the cumulative index; ω i is the weight of the i-th sample; y iis the actual structural parameter of the i-th sample; is the predicted structural parameter of the i-th sample; γ is the regularization parameter; represents the complexity of the tree model; f t (x i ) represents the prediction function of the t-th tree for the i-th sample;

[0033] For each tree-based model, calculate the correlation degree between the predicted structural parameter and the initial structural parameter;

[0034] Based on the correlation degree between the predicted structural parameter and the initial structural parameter of each tree-based model, fuse the prediction results of all tree-based models to obtain the fused prediction result;

[0035] Update the first correlation relationship based on the fused prediction result; Update the second correlation relationship based on the fused prediction result;

[0036] According to the updated first correlation relationship and the updated second correlation relationship, analyze the initial three-dimensional graphic data and the initial printing parameters of the initial 3D printing model to obtain the adaptability analysis result.

[0037] Optionally, as Figure 2 shown, the present application provides a 3D printing model adjustment analysis system for cycling shoes, including:

[0038] An initial 3D printing information acquisition module 201, configured to acquire the initial three-dimensional graphic data and the initial printing parameters of the initial 3D printing model designed for cycling shoes; wherein, the initial three-dimensional graphic data includes initial structural parameters, initial triangular patch data and initial texture information; the initial printing parameters include printing material, printing layer thickness, printing temperature, printing speed, support structure and printing path;

[0039] A rider adaptability analysis module 202, configured to analyze the initial three-dimensional graphic data and the initial printing parameters of the initial 3D printing model according to the foot shape data and the cycling dynamics parameters of the rider to obtain the adaptability analysis result;

[0040] A printing information adjustment module 203, configured to adjust the initial three-dimensional graphic data and the initial printing parameters according to the adaptability analysis result;

[0041] An adapted 3D printing model output module 204, configured to output the 3D printing model of the cycling shoes adjusted to match the rider.

[0042] Further, the rider adaptability analysis module analyzes the initial three-dimensional graphic data and the initial printing parameters of the initial 3D printing model according to the foot shape data and the cycling dynamics parameters of the rider to obtain the adaptability analysis result, and is configured to:

[0043] Use 3D scanning technology to obtain the foot shape data of the rider; among them, the foot shape data includes the length, width, height of the instep, and height of the arch of the foot;

[0044] Collect the rider's cycling kinetics parameters through a motion capture system; among them, the cycling kinetics parameters include pedaling force, frequency, and the position of the foot;

[0045] Extract the foot shape features from the rider's foot shape data, and establish the first correlation relationship between the foot shape features and the initial structural parameters;

[0046] Extract the cycling kinetics features from the rider's cycling kinetics parameters; establish the second correlation relationship between the cycling kinetics features and the initial structural parameters;

[0047] According to the first correlation relationship and the second correlation relationship, analyze the initial three-dimensional graphic data and initial printing parameters of the initial 3D printing model to obtain the adaptability analysis result.

[0048] Further, according to the first correlation relationship and the second correlation relationship, analyze the initial three-dimensional graphic data and initial printing parameters of the initial 3D printing model to obtain the adaptability analysis result, which is configured to:

[0049] Establish the vector representations of the foot shape features and cycling kinetics features in the multi-dimensional space;

[0050] Through the radial basis function, map the vector representation of the foot shape features in the multi-dimensional space and the vector representation of the cycling kinetics features in the multi-dimensional space to the extended dimensional space to obtain the extended foot shape vector and the extended cycling kinetics vector;

[0051] Construct a transaction dataset based on the extended foot shape vector and the extended cycling kinetics vector;

[0052] Use the Relim algorithm to mine the frequent item sets from the transaction dataset; among them, the frequent item sets represent the combined patterns of the foot shape features and cycling kinetics features;

[0053] For each frequent item set, use the gradient boosting tree to construct a tree-based model; among them, each tree-based model is used to predict the configuration of the structural parameters according to the foot shape features and cycling kinetics features;

[0054] Among them, the objective function of the gradient boosting tree Among them, n is the total number of samples; i is the cumulative index; ω i is the weight of the i-th sample; y i is the actual structural parameter of the i-th sample; is the predicted structural parameter of the i-th sample; γ is the regularization parameter; Represents the complexity of the tree model; f t (x i ) represents the prediction function of the t-th tree for the i-th sample;

[0055] For each tree-based model, calculate the correlation degree between the predicted structural parameters and the initial structural parameters;

[0056] Based on the correlation degree between the predicted structural parameters and the initial structural parameters of each tree-based model, fuse the prediction results of all tree-based models to obtain the fused prediction result;

[0057] Update the first association relationship based on the fused prediction result; Update the second association relationship based on the fused prediction result;

[0058] According to the updated first association relationship and the updated second association relationship, analyze the initial three-dimensional graphic data and the initial printing parameters of the initial 3D printing model to obtain the adaptability analysis result.

[0059] Furthermore, the initial structural parameters include the design parameters of the initial lock piece structure, the design parameters of the initial partition reinforcement belt, the design parameters of the initial asymmetric heel cup, the design parameters of the initial carbon fiber outsole, the design parameters of the initial arch support piece, and the design parameters of the initial metatarsal pad; the initial triangular patch data includes vertex data and edge data; the initial texture information includes UV coordinate information and material information; according to the updated first association relationship and the updated second association relationship, analyze the initial three-dimensional graphic data and the initial printing parameters of the initial 3D printing model to obtain the adaptability analysis result, which is configured to:

[0060] Define the initial structural parameter vector P = {p cleat , p reinforce , p heel , p sole , p arch , p ball}; where, p cleat represents the design parameters of the initial lock piece structure; p reinforce represents the design parameters of the initial partition reinforcement belt; p heel represents the design parameters of the initial asymmetric heel cup; p sole represents the design parameters of the initial carbon fiber outsole; p arch represents the design parameters of the initial arch support piece; p ball represents the design parameters of the initial metatarsal pad;

[0061] Initialize the probability distribution of the hidden variable; where, the probability distribution of the hidden variable represents the potential categories of the rider's foot shape and riding dynamics parameters;

[0062] Given the initial structural parameter vector P, calculate the posterior probability distributions of the foot type characteristics and riding dynamics characteristics for each design parameter;

[0063] According to the calculated posterior probability distributions, update the initial structural parameter vector P to maximize the log-likelihood function of the observed data H; where the observed data H includes foot type data and riding dynamics parameters;

[0064] Iteratively calculate the posterior probability distributions and update the initial structural parameter vector P until the initial structural parameter vector P converges to obtain the reference structural parameter vector;

[0065] where, P (k+1) = argmax P G(Z|H, P (k) ) × log G(H, Z|P (k) ); where, P (k+1) is the initial structural parameter vector P updated in the (k + 1)-th iteration; P (k) is the initial structural parameter vector P updated in the k-th iteration; G(Z|H, P (k) ) is the posterior probability of the hidden variable Z under the condition of the given observed data H and the parameter estimate P (k) in the k-th iteration; log G(H, Z|P (k) ) is the log-likelihood function used to calculate the logarithm of the joint probability of the observed data H and the latent class Z given the parameter P;

[0066] Based on the reference structural parameter vector, determine the adaptability analysis result.

[0067] Furthermore, given the initial structural parameter vector P, calculate the posterior probability distributions of the foot type characteristics and riding dynamics characteristics for each design parameter based on the following formula;

[0068]

[0069] where, G(Z|H, P) is the posterior probability of the hidden variable Z under the condition of the given observed data H and the current parameter estimate P, Z represents the latent class of the rider's foot type characteristics and dynamics characteristics, representing different combinations of foot type characteristics and riding dynamics characteristics; G(H, Z|P) represents the joint probability of the observed data H and the latent class Z given the parameter P; ∑ k G(H, Z k |P) represents the summation of the joint probabilities for all latent classes Z k for normalizing the posterior probability.

[0070] Furthermore, the 3D printing model adjustment analysis system for riding shoes further includes:

[0071] A user interface for receiving foot shape data and cycling kinetics parameters input by a cyclist and visually displaying the results of the fit analysis and the adjusted 3D printed model.

[0072] Furthermore, the 3D printing model adjustment analysis system for cycling shoes further includes:

[0073] An intelligent recommendation module for determining a target cycling shoe and customization options from a set of candidate cycling shoes based on the cyclist's foot shape data and cycling kinetics parameters.

[0074] It should be noted that in this application, the embodiments implemented on the side of the 3D printing model adjustment analysis system for cycling shoes can be mutually referred to the embodiments implemented on the side of the 3D printing model adjustment analysis method for cycling shoes, and will not be elaborated one by one in this application.

[0075] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structural or equivalent process transformations made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, are similarly included in the patent protection scope of the present invention.

Claims

1. A 3D printing model adjustment and analysis method for cycling shoes, characterized in that: include: Acquire initial three-dimensional graphic data and initial printing parameters of an initial 3D printing model designed for a cycling shoe; The initial three-dimensional graphics data includes initial structural parameters, initial triangular face data and initial texture information; Initial printing parameters include printing material, printing layer thickness, printing temperature, printing speed, support structure, and printing path; Based on the cyclist's foot shape data and cycling dynamics parameters, the cycling dynamics parameters include pedaling force, frequency and foot position; The initial three-dimensional graphic data and initial printing parameters of the initial 3D printing model are analyzed to obtain the adaptability analysis results, including: Extract foot shape features from the rider's foot shape data, and establish a first correlation relationship between the foot shape features and the initial structural parameters; extract riding dynamics features from the rider's riding dynamics parameters; and establish a second correlation relationship between the riding dynamics features and the initial structural parameters; According to the first association relationship and the second association relationship, the initial three-dimensional graphic data and the initial printing parameters of the initial 3D printing model are analyzed to obtain the adaptability analysis results, which include: Establish vector representations of foot shape features and cycling dynamics features in multidimensional space; map the vector representations of foot shape features in multidimensional space and the vector representations of cycling dynamics features in multidimensional space to the extended dimensional space through radial basis functions to obtain extended foot shape vectors and extended cycling dynamics vectors; construct a transaction data set based on the extended foot shape vectors and extended cycling dynamics vectors; use the Relim algorithm to mine frequent item sets from the transaction data set; wherein the frequent item sets represent the combination patterns of foot shape features and cycling dynamics features; for each frequent item set, use the gradient boosting tree to construct a tree-based model; wherein each tree-based model is used to predict the configuration of structural parameters according to foot shape features and cycling dynamics features; for each tree-based model, calculate the correlation between its predicted structural parameters and the initial structural parameters; based on the correlation between the structural parameters predicted by each tree-based model and the initial structural parameters, fuse the prediction results of all tree-based models to obtain a fused prediction result; The first association relationship is updated based on the fusion prediction result; the second association relationship is updated based on the fusion prediction result; According to the updated first association relationship and the updated second association relationship, the initial three-dimensional graphic data and the initial printing parameters of the initial 3D printing model are analyzed to obtain the adaptability analysis result; including: defining an initial structural parameter vector; initializing the hidden variable probability distribution; wherein the hidden variable probability distribution represents the potential category of the rider's foot shape and riding dynamics parameters; under the condition of a given initial structural parameter vector P, calculating the posterior probability distribution of the foot shape feature and the riding dynamics feature for each design parameter; According to the calculated posterior probability distribution, the initial structural parameter vector P is updated to maximize the log-likelihood function of the observed data H; wherein the observed data H includes foot shape data and riding dynamics parameters; the posterior probability distribution is calculated iteratively and the initial structural parameter vector P is updated until the initial structural parameter vector P converges to obtain a reference structural parameter vector; based on the reference structural parameter vector, the adaptability analysis result is determined; According to the adaptability analysis results, the initial three-dimensional graphic data and initial printing parameters are adjusted; Output a 3D printed model of the cycling shoe adjusted to match the rider.

2. A 3D printing model adjustment and analysis system for cycling shoes, the system implementing the method according to claim 1, characterized in that: include: An initial 3D printing information acquisition module is used to acquire initial three-dimensional graphic data and initial printing parameters of an initial 3D printing model designed for cycling shoes; wherein the initial three-dimensional graphic data includes initial structural parameters, initial triangular face data and initial texture information; and the initial printing parameters include printing material, printing layer thickness, printing temperature, printing speed, support structure and printing path; The rider adaptability analysis module analyzes the initial three-dimensional graphic data and initial printing parameters of the initial 3D printed model according to the rider's foot shape data and riding dynamics parameters to obtain adaptability analysis results, including: Extracting foot shape features from the rider's foot shape data, and establishing a first correlation relationship between the foot shape features and the initial structural parameters; Extracting riding dynamics features from the riding dynamics parameters of the rider; establishing a second correlation relationship between the riding dynamics features and the initial structural parameters; According to the first association relationship and the second association relationship, the initial three-dimensional graphic data and the initial printing parameters of the initial 3D printing model are analyzed to obtain the adaptability analysis results, which include: Establish vector representation of foot shape characteristics and cycling dynamics characteristics in multi-dimensional space; By using radial basis functions, the vector representation of foot shape features in multidimensional space and the vector representation of cycling dynamics features in multidimensional space are mapped to the extended dimensional space to obtain an extended foot shape vector and an extended cycling dynamics vector; Construct a transaction dataset based on the extended foot shape vector and the extended cycling dynamics vector; The Relim algorithm is used to mine frequent item sets from the transaction dataset; frequent item sets represent the combination patterns of foot shape features and cycling dynamics features; For each frequent item set, a tree-based model is constructed using a gradient boosting tree; each tree-based model is used to predict the configuration of structural parameters based on foot shape characteristics and cycling dynamics characteristics; For each tree-based model, the correlation between its predicted structural parameters and the initial structural parameters was calculated; Based on the correlation between the structural parameters predicted by each tree-based model and the initial structural parameters, the prediction results of all tree-based models are fused to obtain a fused prediction result; The first association relationship is updated based on the fusion prediction result; the second association relationship is updated based on the fusion prediction result; According to the updated first association relationship and the updated second association relationship, the initial three-dimensional graphic data and the initial printing parameters of the initial 3D printing model are analyzed to obtain the adaptability analysis result; including defining the initial structural parameter vector Initialize the hidden variable probability distribution; wherein the hidden variable probability distribution represents the potential categories of the cyclist's foot type and cycling dynamics parameters; Given an initial structural parameter vector P, calculate the posterior probability distribution of foot shape characteristics and riding dynamics characteristics for each design parameter; According to the calculated posterior probability distribution, the initial structural parameter vector P is updated to maximize the log-likelihood function of the observed data H; wherein the observed data H includes foot shape data and riding dynamics parameters; Iteratively calculate the posterior probability distribution and update the initial structure parameter vector P until the initial structure parameter vector P converges to obtain a reference structure parameter vector; Determine the fit analysis result based on the reference structure parameter vector; A printing information adjustment module, used to adjust the initial three-dimensional graphic data and initial printing parameters according to the adaptability analysis results; The 3D printing model output module is adapted to output a 3D printing model of the cycling shoes adjusted to match the rider.

3. The 3D printing model adjustment and analysis system for cycling shoes according to claim 2, characterized in that: Given the initial structural parameter vector P, the posterior probability distribution of foot shape characteristics and riding dynamics characteristics for each design parameter is calculated based on the following formula; Where G(Z|H,P) is the posterior probability of the hidden variable Z given the observed data H and the current parameter estimate P. Z represents the latent class of the rider's foot shape and dynamics, representing different combinations of foot shape and cycling dynamics. G(H,Z|P) represents the joint probability of the observed data H and the latent class Z given the parameter P. k G(H,Z k |P) represents all potential classes Z k The joint probability sum is used to normalize the posterior probability.

4. The 3D printing model adjustment and analysis system for cycling shoes according to claim 3, characterized in that: The 3D printing model adjustment and analysis system for cycling shoes also includes: The user interface is used to receive the foot shape data and cycling dynamics parameters input by the rider, and to visually display the fitness analysis results and the adjusted 3D printed model.

5. The 3D printing model adjustment and analysis system for cycling shoes according to claim 4, characterized in that: The 3D printing model adjustment and analysis system for cycling shoes also includes: The intelligent recommendation module is used to determine target cycling shoes and customization options from a set of candidate cycling shoes according to the cyclist's foot shape data and cycling dynamics parameters.

Images