Clothing 3D printing design method and system based on knowledge graph
By using a knowledge graph-based 3D printing design method for clothing, user data is acquired, user preferences are analyzed, and personalized clothing design solutions are generated. This solves the problem that uniform design solutions cannot stimulate users' desire to buy, thereby increasing clothing sales.
Patent Information
- Application Number
- CN202510972344.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-15
- Publication Date
- 2025-10-28
AI Technical Summary
In the prior art, each user may have different preferences for clothing styles, colors, and patterns. If clothing is produced according to a unified design, it may not arouse the purchasing desire of some users, thereby affecting the sales of clothing.
By using a knowledge graph-based approach, user ID information is obtained, user clothing data is extracted and analyzed, the user's preferred clothing styles, colors and patterns are determined, and 3D printing files of clothing that match the user's preferences are generated.
Personalized clothing design solutions increased users' desire to buy and boosted clothing sales.
Smart Images
Figure CN120850768A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of clothing design technology, specifically to a knowledge graph-based method and system for 3D printing clothing design. Background Technology
[0002] Clothing is an indispensable part of human life, serving as both a practical necessity and a vehicle for expressing culture and individuality. Clothing encompasses garments, shoes, hats, accessories, and more, but primarily refers to clothing. Originally used for modesty and warmth, it gradually developed functions such as decoration and identification.
[0003] Each user may have different preferences for clothing styles, colors, and patterns. If clothing is produced according to a uniform design scheme, it may not arouse the purchasing desire of some users, thereby affecting the sales of clothing. Summary of the Invention
[0004] To address the aforementioned technical problems, a knowledge graph-based 3D printing design method and system for clothing is provided. This technical solution solves the problem mentioned in the background that each user may have different preferences for clothing styles, colors, and patterns. If clothing is produced according to a uniform design scheme, it may not arouse the purchasing desire of some users, thereby affecting clothing sales.
[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows: A knowledge graph-based 3D printing design method for clothing includes: Get user ID information; Data extraction and processing are performed on the database system using user ID information as a feature to obtain all user-related data; Using clothing information as a reference, perform intersection processing on all user-related data to obtain the user's clothing data; The system counts user clothing data and compares and analyzes different types of user clothing data to determine user preferred clothing styles. Feature data extraction processing is performed on the user's clothing data to determine relevant data on the user's preferred clothing; wherein, the relevant data on the user's preferred clothing includes clothing color, clothing fabric, and clothing pattern; Input user-preferred clothing styles and related data into a clothing knowledge graph to generate 3D clothing printing files.
[0006] Preferably, the step of counting user clothing data and comparing and analyzing different types of user clothing data to determine the user's preferred clothing style specifically includes the following steps: Extract and process user clothing data to obtain the purchase time of the user's clothing; Perform repeatability analysis on the purchase time of users' clothing to obtain the number of clothing items worn by each user; By comparing and analyzing user clothing data and data on different types of clothing, we can determine the user's preferred clothing styles.
[0007] Preferably, the step of performing a repeatability analysis on the purchase time of the user's clothing to obtain the quantity of clothing for the user specifically includes the following steps: Determine and process the purchase time of the user's clothing; If there are clothing data with the same purchase time in the user's clothing data, the clothing data with the same purchase time is verified to obtain the number of clothing items in the user's clothing data. If there is no clothing data with the same purchase time in the user's clothing purchase time, the purchase time of the user's clothing is counted to obtain the number of the user's clothing; wherein, the number of the user's clothing is the same as the number of purchase times of the user's clothing.
[0008] Preferably, the step of verifying clothing data purchased at the same time using the user's clothing data to obtain the user's clothing quantity specifically includes the following steps: Data extraction and processing of users' clothing data based on the same purchase time is performed to obtain clothing images purchased at the same time. Perform judgment processing on clothing images purchased at the same time; If there is only one image of clothing purchased at the same time, the clothing data purchased at the same time will be recorded repeatedly. Any clothing data purchased at the same time will be retained, and the purchase time of the user's clothing will be recounted to obtain the number of clothing items for the user. If there are more than one image of clothing purchased at the same time, compare the images of clothing purchased at the same time to determine whether they are the same image. If the clothing images purchased at the same time are the same image, the clothing data purchased at the same time will be recorded repeatedly. Any clothing data purchased at the same time will be retained, and the purchase time of the user's clothing will be recounted to obtain the number of clothing items for the user. If clothing images purchased at the same time are not the same image, then the clothing data purchased at the same time is not duplicate data. The clothing data purchased at the same time is retained, and the purchase time of the user's clothing is recounted to obtain the number of clothing items for the user.
[0009] Preferably, the step of comparing and analyzing the number of user's clothing items and the data on different types of clothing to determine the user's preferred clothing style specifically includes the following steps: Extract and process the user's clothing data to obtain images of all the user's clothing. Based on clothing type, classify all clothing images of the user to obtain different types of clothing data; Count the different types of clothing data of users to obtain the number of different types of clothing for several groups of users; The number of different types of clothing for several groups of users and the number of clothing items for each user are calculated and processed to obtain the proportion coefficients of different types of clothing for several groups. Based on the maximum value function, the proportion coefficients of several different types of clothing are sorted and the maximum value among the proportion coefficients of several different types of clothing is determined. Set the clothing style corresponding to the maximum value among several groups of different types of clothing proportion coefficients as the user's preferred clothing style.
[0010] Preferably, the step of extracting feature data from the user's clothing data to determine the relevant data on the user's preferred clothing includes the following steps: Count all clothing images in the user's clothing data to obtain the number of clothing of different colors; Based on the maximum value function, the quantities of clothing of different colors are sorted to determine the maximum value of each color. Set the color of the clothing corresponding to the maximum number of different colored clothing items as the user's preferred clothing color; Extract and process the user's clothing data to obtain all the clothing's factory parameters; The intersection of all garment manufacturing parameters is processed to obtain the frequency of occurrence of different fabrics; Based on the maximum value function, the frequency of occurrence of different fabrics is sorted to determine the maximum frequency of occurrence of different fabrics; Set the clothing fabric corresponding to the maximum number of times different fabrics appear as the user's preferred clothing fabric. Extract and process the user's clothing data to obtain all clothing patterns; All clothing patterns are categorized according to pattern type to determine different types of clothing patterns; The user's clothing data is extracted and processed based on different types of clothing patterns to determine the frequency of occurrence of different types of clothing patterns; Based on the maximum value function, the occurrence frequency of different types of clothing patterns is sorted to determine the maximum occurrence frequency of different types of clothing patterns; Set the clothing pattern corresponding to the maximum frequency of occurrence of different types of clothing patterns as the user's preferred clothing pattern.
[0011] Preferably, the step of inputting user-preferred clothing styles and related data into a clothing knowledge graph to generate clothing 3D printing files specifically includes the following steps: Input the user's preferred clothing style into the clothing knowledge graph to determine the node position of the user's preferred clothing style; The relevant data on users' preferred clothing are compared and analyzed with the subsequent child nodes of the node containing the user's preferred clothing style to determine the design scheme for the user's clothing. Convert user clothing design schemes into clothing 3D printing files.
[0012] Preferably, the step of comparing and analyzing the relevant data of user's preferred clothing with the subsequent child nodes of the node containing the user's preferred clothing style to determine the design scheme of the user's clothing specifically includes the following steps: The subsequent child nodes of the nodes containing the user's preferred clothing color, preferred clothing fabric, preferred clothing pattern, and preferred clothing style are judged and processed respectively. If the child nodes of the node containing the user's preferred clothing style contain the same data as the user's preferred clothing color, preferred clothing fabric, and preferred clothing pattern, then generate a design scheme for the user's clothing. If the subsequent child nodes of the node containing the user's preferred clothing style do not completely contain the user's preferred clothing color, fabric, or pattern, select data that is less than the number of non-existent data as input data to regenerate the user's clothing design scheme.
[0013] Furthermore, a knowledge graph-based 3D printing design system for clothing is proposed to implement the aforementioned knowledge graph-based 3D printing design method for clothing, including: The solution design terminal is used to control various modules to perform time analysis, data calculation, comparison and judgment on all user-related data, and generate clothing 3D printing files; the solution design terminal is also used to control data transmission and information interaction between various modules. A database system for storing all user-related data; The data extraction module is used to extract and process all user-related data to obtain the user's clothing data. A repeatability analysis module is used to perform time analysis and judgment processing on the purchase time of user clothing to determine the quantity of user clothing. The clothing style determination module is used to perform feature analysis processing on all clothing images of the user to determine the user's preferred clothing style. The design data determination module is used to perform feature analysis on the user's clothing data to determine relevant data on the user's preferred clothing. The print file generation module performs information matching processing on the clothing knowledge graph based on the user's preferred clothing style and related data to generate a 3D printing file for clothing.
[0014] Compared with existing technologies, this invention provides a knowledge graph-based 3D printing design method and system for clothing, which has the following beneficial effects: This invention processes user clothing data through time analysis, image comparison, and data judgment to determine the user's preferred clothing styles and related data. Then, based on the user's preferred clothing styles and related data, it matches information from a clothing knowledge graph to generate 3D printing files for clothing. This method, by processing and analyzing user clothing data to determine the user's preferred clothing data and producing clothing based on the user's preferred clothing data, stimulates the user's desire to purchase and increases clothing sales. Attached Figure Description
[0015] Figure 1 This is a flowchart illustrating steps S100-S600 in a knowledge graph-based 3D printing design method for clothing proposed in this invention. Figure 2 This is a structural block diagram of a knowledge graph-based 3D printing design system for clothing proposed in this invention. Detailed Implementation
[0016] The following description is intended to disclose the invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art.
[0017] Reference Figure 1 As shown, a knowledge graph-based 3D printing design method for clothing includes: S100, Obtain user ID information; S200. Using user ID information as a feature, perform data extraction and processing on the database system to obtain all user-related data; S300: Using clothing information as a reference, perform intersection processing on all user-related data to obtain the user's clothing data; S400: Count the user's clothing data and compare and analyze the data of different types of clothing to determine the user's preferred clothing style. S500: Perform feature data extraction processing on the user's clothing data to determine relevant data on the user's preferred clothing; wherein, the relevant data on the user's preferred clothing includes clothing color, clothing fabric, and clothing pattern. S600: Input the user's preferred clothing style and related data into the clothing knowledge graph to generate clothing 3D printing files; Those skilled in the art will understand that each user may have different preferences for clothing styles, colors, and patterns. If clothing is produced according to a uniform design scheme, it may not stimulate the purchasing desire of some users. Therefore, data extraction and comparison are performed on user clothing data to determine the user's preferred clothing styles (i.e., preferred clothing styles), colors, and patterns. Then, the user's preferred clothing styles and related data are input into a clothing knowledge graph. The clothing knowledge graph generates corresponding user clothing design schemes. Finally, clothing is produced according to the user's clothing design schemes. These clothing styles conform to the user's aesthetics, stimulate the user's consumption desire, and thus increase clothing sales.
[0018] Example 1 S400. The process of counting user clothing data and comparing and analyzing different types of user clothing data to determine user preferred clothing styles includes the following steps: S401. Extract and process the user's clothing data to obtain the purchase time of the user's clothing; S402. Perform repeatability analysis on the purchase time of the user's clothing to obtain the number of clothing items purchased by the user. S403. Compare and analyze the user's clothing data and the user's clothing data of different types to determine the user's preferred clothing style; Specifically, S402, performing a repeatability analysis on the purchase time of user clothing to obtain the quantity of clothing worn by the user, includes the following steps: S4021. Determine and process the purchase time of the user's clothing; S4022. If there are clothing data with the same purchase time in the user's clothing purchase data, verify the clothing data with the same purchase time through the user's clothing data to obtain the number of clothing items in the user's clothing. S4023. If there is no clothing data with the same purchase time in the user's clothing purchase time, count the purchase time of the user's clothing to obtain the number of the user's clothing; wherein, the number of the user's clothing is the same as the number of purchase times of the user's clothing. It is understandable that some users may purchase multiple items of clothing at the same time, or the same item of clothing may be recorded multiple times at the same time, resulting in identical purchase times. In order to more accurately determine the user's preferred clothing style, it is necessary to determine the number of clothing items purchased by the user. Therefore, it is necessary to conduct a duplicate analysis of the user's clothing purchase time to determine whether the same item of clothing has been recorded multiple times at the same time. If so, the data should be removed to obtain the actual number of clothing items purchased by the user.
[0019] Specifically, S4022, verifying clothing data purchased at the same time based on the user's clothing data to obtain the user's clothing quantity, includes the following steps: S40221. Extract and process the user's clothing data based on the same purchase time to obtain clothing images purchased at the same time; S40222, Perform judgment and processing on clothing images purchased at the same time; S40223. If there is only one image of clothing purchased at the same time, the clothing data purchased at the same time is recorded repeatedly. Any clothing data purchased at the same time is retained, and the purchase time of the user's clothing is recounted to obtain the number of clothing items for the user. S40224. If there is more than one image of clothing purchased at the same time, compare the images of clothing purchased at the same time to determine whether the images of clothing purchased at the same time are the same image. S40225. If the clothing images purchased at the same time are the same image, the clothing data purchased at the same time are recorded repeatedly. Any clothing data purchased at the same time is retained, and the purchase time of the user's clothing is recounted to obtain the number of the user's clothing. S40226. If the clothing images purchased at the same time are not the same image, then the clothing data purchased at the same time is not duplicate data. The clothing data purchased at the same time is retained, and the purchase time of the user's clothing is recounted to obtain the number of the user's clothing. Understandably, if there are identical purchase times, it is necessary to verify whether the purchase of the same item of clothing has been recorded multiple times. The most direct way to determine this is to compare the images of the purchased clothing. If the images are identical, it means that the purchase of the same item of clothing has been recorded multiple times, and the purchase time of the user's clothing needs to be adjusted before counting. If the images are different, it means that the user purchased multiple items of clothing at the same time, and there is no need to adjust the purchase time of the user's clothing; the counting can be performed directly to determine the number of items purchased by the user.
[0020] Specifically, S403 involves comparing and analyzing the number of clothing items a user owns and the data on different types of clothing to determine the user's preferred clothing styles. This includes the following steps: S4031. Extract and process the user's clothing data to obtain all clothing images of the user; S4032. Based on clothing type, classify all clothing images of the user to obtain different types of clothing data of the user. S4033. Perform counting processing on the different types of clothing data of users to obtain the quantity of different types of clothing of users in several groups; S4034. Calculate and process the quantity of different types of clothing for several groups of users and the quantity of clothing for each user to obtain the proportion coefficient of different types of clothing for several groups. S4035. Based on the maximum value function, sort the proportion coefficients of several different types of clothing and determine the maximum value among the proportion coefficients of several different types of clothing. S4036. Set the clothing style corresponding to the maximum value among several groups of different types of clothing proportion coefficients as the user's preferred clothing style. It is understandable that users may buy a variety of clothing styles, but among these styles, there will be clothing styles that users like the most (i.e., clothing styles that users prefer). The clothing styles that users like the most are the ones that they buy the most. Therefore, by determining the proportion coefficient of different types of clothing, we can determine the clothing styles that users prefer.
[0021] Example 2 S500. The process of extracting feature data from user clothing data to determine relevant data regarding user clothing preferences includes the following steps: S5010: Count all clothing images in the user's clothing data to obtain the number of clothing of different colors; S5011. Based on the maximum value function, sort the quantities of clothing of different colors and determine the maximum value of the quantities of clothing of different colors. S5012. Set the color of the clothing corresponding to the maximum number of different colored clothing items as the user's preferred clothing color. S5020: Extract and process the user's clothing data to obtain all the factory parameters of the clothing. S5021. Perform intersection processing on all garment factory parameters to obtain the occurrence count of different fabrics; S5022. Based on the maximum value function, sort the occurrence frequency of different fabrics and determine the maximum value of the occurrence frequency of different fabrics. S5023. Set the clothing fabric corresponding to the maximum number of times different fabrics appear as the user's preferred clothing fabric. S5030: Extract and process the user's clothing data to obtain all clothing patterns; S5031. Classify all clothing patterns according to pattern type to determine different types of clothing patterns; S5032. Extract and process user clothing data according to different types of clothing patterns to determine the frequency of occurrence of different types of clothing patterns; S5033. Based on the maximum value function, sort the occurrence frequency of different types of clothing patterns and determine the maximum occurrence frequency of different types of clothing patterns; S5034. Set the clothing pattern corresponding to the maximum occurrence frequency of different types of clothing patterns as the user's preferred clothing pattern. It is understandable that different users may have different preferences for clothing colors, fabrics, and patterns. For example, some users may prefer purple, so purple will be the most common color in the clothing they buy. Similarly, this also reveals the preferred fabrics and patterns of clothing.
[0022] Example 3 S600. Inputting user-preferred clothing styles and related data into the clothing knowledge graph to generate clothing 3D printing files specifically includes the following steps: S601. Input the user's preferred clothing style into the clothing knowledge graph and determine the node position of the user's preferred clothing style. S602. Compare and analyze the relevant data of the user's preferred clothing with the subsequent child nodes of the node where the user's preferred clothing style is located to determine the design scheme of the user's clothing. S603: Convert the user's clothing design into clothing 3D printing files.
[0023] Specifically, S602 involves comparing and analyzing the data related to the user's preferred clothing with the subsequent child nodes of the node containing the user's preferred clothing style to determine the design scheme for the user's clothing. This includes the following steps: S6021. The subsequent child nodes of the nodes containing the user's preferred clothing color, user's preferred clothing fabric, user's preferred clothing pattern, and user's preferred clothing style are judged and processed respectively. S6022. If the subsequent child nodes of the node containing the user's preferred clothing style contain the same data as the user's preferred clothing color, preferred clothing fabric, and preferred clothing pattern, generate a design scheme for the user's clothing. S6023. If the subsequent child nodes of the node containing the user's preferred clothing style do not completely contain the user's preferred clothing color, the user's preferred clothing fabric, or the user's preferred clothing pattern, select data that is less than the number of non-existent data as input data and regenerate the user's clothing design scheme. Understandably, the clothing knowledge graph contains design data for various garments. Therefore, by inputting user-preferred clothing styles and related data, corresponding clothing design schemes can be generated. However, when certain data is missing from the clothing knowledge graph, it is necessary to reselect the user's preferred clothing data. For example, if purple is not among the user's preferred clothing styles, but purple is their favorite color, then a new preferred color must be selected. For instance, if the user's favorite color is purple and their second favorite is red, then red can be used as input data and matched with the clothing knowledge graph to generate a clothing design scheme for the user.
[0024] Reference Figure 2 As shown, a knowledge graph-based 3D clothing printing design system is used to implement the knowledge graph-based 3D clothing printing design method described above, including: The solution design terminal is used to control various modules to perform time analysis, data calculation, comparison and judgment on all user-related data, and generate clothing 3D printing files; the solution design terminal is also used to control data transmission and information interaction between various modules. A database system for storing all user-related data; The data extraction module is used to extract and process all user-related data to obtain the user's clothing data. A repeatability analysis module is used to perform time analysis and judgment processing on the purchase time of user clothing to determine the quantity of user clothing. The clothing style determination module is used to perform feature analysis processing on all clothing images of the user to determine the user's preferred clothing style. The design data determination module is used to perform feature analysis on the user's clothing data to determine relevant data on the user's preferred clothing. The print file generation module performs information matching processing on the clothing knowledge graph based on the user's preferred clothing style and related data to generate a 3D printing file for clothing.
[0025] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention. The scope of protection claimed by the appended claims and their equivalents is defined.
Claims
1. A knowledge graph-based 3D printing design method for clothing, characterized in that, include: Get user ID information; Data extraction and processing are performed on the database system using user ID information as a feature to obtain all user-related data; Using clothing information as a reference, perform intersection processing on all user-related data to obtain the user's clothing data; The system counts user clothing data and compares and analyzes different types of user clothing data to determine user preferred clothing styles. Feature data extraction processing is performed on the user's clothing data to determine relevant data on the user's preferred clothing; wherein, the relevant data on the user's preferred clothing includes clothing color, clothing fabric, and clothing pattern; Input user-preferred clothing styles and related data into a clothing knowledge graph to generate 3D clothing printing files.
2. The knowledge graph-based 3D printing design method for clothing according to claim 1, characterized in that, The process of counting user clothing data and comparing and analyzing different types of user clothing data to determine user preferred clothing styles specifically includes the following steps: Extract and process user clothing data to obtain the purchase time of the user's clothing; Perform repeatability analysis on the purchase time of users' clothing to obtain the number of clothing items worn by each user; By comparing and analyzing user clothing data and data on different types of clothing, we can determine the user's preferred clothing styles.
3. The knowledge graph-based 3D printing design method for clothing according to claim 2, characterized in that, The process of performing repeatability analysis on the purchase time of user clothing to obtain the quantity of clothing worn by the user specifically includes the following steps: Determine and process the purchase time of the user's clothing; If there are clothing data with the same purchase time in the user's clothing data, the clothing data with the same purchase time is verified to obtain the number of clothing items in the user's clothing data. If there is no clothing data with the same purchase time in the user's clothing purchase time, the purchase time of the user's clothing is counted to obtain the number of the user's clothing; wherein, the number of the user's clothing is the same as the number of purchase times of the user's clothing.
4. The knowledge graph-based 3D printing design method for clothing according to claim 3, characterized in that, The process of verifying clothing data purchased at the same time based on the user's clothing data to obtain the user's clothing quantity specifically includes the following steps: Data extraction and processing of users' clothing data based on the same purchase time is performed to obtain clothing images purchased at the same time. Perform judgment processing on clothing images purchased at the same time; If there is only one image of clothing purchased at the same time, the clothing data purchased at the same time will be recorded repeatedly. Any clothing data purchased at the same time will be retained, and the purchase time of the user's clothing will be recounted to obtain the number of clothing items for the user. If there are more than one image of clothing purchased at the same time, compare the images of clothing purchased at the same time to determine whether they are the same image. If the clothing images purchased at the same time are the same image, the clothing data purchased at the same time will be recorded repeatedly. Any clothing data purchased at the same time will be retained, and the purchase time of the user's clothing will be recounted to obtain the number of clothing items for the user. If clothing images purchased at the same time are not the same image, then the clothing data purchased at the same time is not duplicate data. The clothing data purchased at the same time is retained, and the purchase time of the user's clothing is recounted to obtain the number of clothing items for the user.
5. The knowledge graph-based 3D printing design method for clothing according to claim 2, characterized in that, The process of comparing and analyzing the number of clothing items and the different types of clothing worn by users to determine their preferred clothing styles includes the following steps: Extract and process the user's clothing data to obtain images of all the user's clothing. Based on clothing type, classify all clothing images of the user to obtain different types of clothing data; Count the different types of clothing data of users to obtain the number of different types of clothing for several groups of users; The number of different types of clothing for several groups of users and the number of clothing items for each user are calculated and processed to obtain the proportion coefficients of different types of clothing for several groups. Based on the maximum value function, the proportion coefficients of several different types of clothing are sorted and the maximum value among the proportion coefficients of several different types of clothing is determined. Set the clothing style corresponding to the maximum value among several groups of different types of clothing proportion coefficients as the user's preferred clothing style.
6. The knowledge graph-based 3D printing design method for clothing according to claim 1, characterized in that, The process of extracting feature data from user clothing data to determine relevant data on user clothing preferences includes the following steps: Count all clothing images in the user's clothing data to obtain the number of clothing of different colors; Based on the maximum value function, the quantities of clothing of different colors are sorted to determine the maximum value of each color. Set the color of the clothing corresponding to the maximum number of different colored clothing items as the user's preferred clothing color; Extract and process the user's clothing data to obtain all the clothing's factory parameters; The intersection of all garment manufacturing parameters is processed to obtain the frequency of occurrence of different fabrics; Based on the maximum value function, the frequency of occurrence of different fabrics is sorted to determine the maximum frequency of occurrence of different fabrics; Set the clothing fabric corresponding to the maximum number of times different fabrics appear as the user's preferred clothing fabric. Extract and process the user's clothing data to obtain all clothing patterns; All clothing patterns are categorized according to pattern type to determine different types of clothing patterns; The user's clothing data is extracted and processed based on different types of clothing patterns to determine the frequency of occurrence of different types of clothing patterns; Based on the maximum value function, the occurrence frequency of different types of clothing patterns is sorted to determine the maximum occurrence frequency of different types of clothing patterns; Set the clothing pattern corresponding to the maximum frequency of occurrence of different types of clothing patterns as the user's preferred clothing pattern.
7. The knowledge graph-based 3D printing design method for clothing according to claim 1, characterized in that, The process of inputting user-preferred clothing styles and related data into a clothing knowledge graph to generate 3D printing files specifically includes the following steps: Input the user's preferred clothing style into the clothing knowledge graph to determine the node position of the user's preferred clothing style; The relevant data on users' preferred clothing are compared and analyzed with the subsequent child nodes of the node containing the user's preferred clothing style to determine the design scheme for the user's clothing. Convert user clothing design schemes into clothing 3D printing files.
8. The knowledge graph-based 3D printing design method for clothing according to claim 7, characterized in that, The process of comparing and analyzing data related to user's preferred clothing styles with subsequent child nodes of the node containing the user's preferred clothing style to determine the design scheme for the user's clothing includes the following steps: The subsequent child nodes of the nodes containing the user's preferred clothing color, preferred clothing fabric, preferred clothing pattern, and preferred clothing style are judged and processed respectively. If the child nodes of the node containing the user's preferred clothing style contain the same data as the user's preferred clothing color, preferred clothing fabric, and preferred clothing pattern, then generate a design scheme for the user's clothing. If the subsequent child nodes of the node containing the user's preferred clothing style do not completely contain the user's preferred clothing color, fabric, or pattern, select data that is less than the number of non-existent data as input data to regenerate the user's clothing design scheme.
9. A knowledge graph-based 3D printing design system for clothing, used to implement the knowledge graph-based 3D printing design method for clothing as described in any one of claims 1-8, characterized in that, include: The solution design terminal is used to control various modules to perform time analysis, data calculation, comparison and judgment on all user-related data, and generate clothing 3D printing files; the solution design terminal is also used to control data transmission and information interaction between various modules. A database system for storing all user-related data; The data extraction module is used to extract and process all user-related data to obtain the user's clothing data. A repeatability analysis module is used to perform time analysis and judgment processing on the purchase time of user clothing to determine the quantity of user clothing. The clothing style determination module is used to perform feature analysis processing on all clothing images of the user to determine the user's preferred clothing style. The design data determination module is used to perform feature analysis on the user's clothing data to determine relevant data on the user's preferred clothing. The print file generation module performs information matching processing on the clothing knowledge graph based on the user's preferred clothing style and related data to generate a 3D printing file for clothing.