A multifunctional clothing splicing design method and system based on artificial intelligence

Abstract

The present invention relates to the technical field of intelligent clothing design. The present invention discloses a multifunctional clothing splicing design method and system based on artificial intelligence, including collecting users' personal information and historical purchase data to form a comprehensive user portrait; using an improved deep learning model to analyze the collected user data, identify the user's style tendencies and preferences, and generate splicing design suggestions; building a social platform to allow users to complete splicing design with designers, submit design requirements through interaction, and obtain real-time feedback and suggestions from designers; based on user feedback and design adjustments, generate and output the final splicing clothing design plan. This method is based on artificial intelligence, and through an improved deep learning model, the construction of a social platform, and iterative design driven by user feedback, a more efficient and personalized clothing design experience is achieved to meet the growing customization needs of users.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent clothing design, and in particular to a clothing splicing multifunctional design method and system based on artificial intelligence. Background Art

[0002] In the field of clothing design, with the growing personalized needs of consumers, customized design has become a new trend in the development of the industry. In recent years, the rapid development of artificial intelligence technology has brought revolutionary changes to clothing design. Traditional clothing design methods often rely on the subjective judgment and experience of designers, while modern technology can more accurately capture the personalized needs of users through data-driven design processes. In particular, deep learning models based on user data are widely used to analyze user behavior, predict style preferences, and thus guide clothing design.

[0003] However, the existing clothing design technology still has obvious shortcomings. First, although the existing technology can collect user information and form user portraits, when analyzing user data, it often lacks an in-depth understanding of user style tendencies and preferences, resulting in a deviation between design suggestions and actual user needs. Secondly, in the existing design process, the interaction between users and designers is relatively limited, it is difficult for users to participate in the design process, and it is difficult for designers to obtain real-time feedback from users, which limits the personalization and innovation of the design. In addition, the existing technology fails to effectively combine the interactive characteristics of social platforms to promote the joint creation of users and designers, thereby affecting the diversity and satisfaction of design solutions. The multifunctional design method of clothing splicing based on artificial intelligence proposed in our invention content has made beneficial explorations and innovations in these aspects, and is expected to significantly improve the personalization and interactivity of clothing design and meet the growing customization needs of users. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a multifunctional clothing splicing design method based on artificial intelligence, which can deeply analyze user data, accurately identify user style tendencies and preferences, obtain real-time feedback from users, effectively combine the interactive characteristics of social platforms, promote the joint creation of users and designers, and improve the diversity of design solutions and user satisfaction.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: a multifunctional clothing splicing design method based on artificial intelligence, comprising: collecting users' personal information and historical purchase data to form a comprehensive user portrait; using an improved deep learning model to analyze the collected user data, identify users' style tendencies and preferences, and generate splicing design suggestions; building a social platform to allow users to complete splicing design with designers, submit design requirements through interaction, and obtain real-time feedback and suggestions from designers; based on user feedback and design adjustments, generate and output the final splicing clothing design plan.

[0007] As a preferred solution of the multifunctional clothing splicing design method based on artificial intelligence described in the present invention, wherein: the forming of a comprehensive user portrait includes requiring the user to fill in a personal information form containing basic information, body shape, and style preferences when using the relevant application or platform for the first time, and automatically extracting the user's historical purchase data by integrating the e-commerce platform or consumption records to identify the user's consumption habits and trends;

[0008] Use data analysis tools to monitor user behavior on apps and websites, identify user interests and preferences, further understand user preferences by analyzing user stay time and interaction on different product pages, provide options to connect users' social media accounts, and extract style preferences and fashion attention information;

[0009] The collected data is stored in the user database, and the user portrait is updated regularly to continuously reflect the user's current interests and trends.

[0010] As a preferred solution of the artificial intelligence-based clothing splicing multifunctional design method described in the present invention, wherein: the analysis of the collected user data includes processing the collected data, using the K nearest neighbor interpolation method, and performing unique hot encoding on the category data;

[0011] The improved deep learning model is applied to analyze the user's style preference, and the user's historical interaction data is combined with real-time feedback to generate a personalized style feature vector for the user. The user feature vector U is expressed as:

[0012] U=[u1,u2,...,u n ]

[0013] Among them, u i is the numerical representation of the user on a specific feature, i = 1, 2, ..., n;

[0014] Train the user feature vector, reconstruct the user preference, and calculate the reconstruction error E:

[0015]

[0016] Among them, R(Ud ) represents the recommended style features reconstructed by the autoencoder, e is the number of samples, U′ is the user feature vector after training. By analyzing the reconstruction error, the user’s potential style tendency is identified and the user feature vector is optimized.

[0017] As a preferred solution of the multifunctional clothing splicing design method based on artificial intelligence described in the present invention, wherein: the generation of splicing design suggestions includes analyzing the current fashion trends, extracting popular elements and features, and the analysis results of the popular trends are used to evaluate the adaptability of the popular elements in the user's feature vector; according to the user's style preferences, the splicing styles that meet the user's characteristics are screened from the design library, and during the screening process, the compatibility between each splicing style and the user's characteristics is evaluated, so that the recommended style meets the user's personalized needs;

[0018] Based on the adaptability of popular elements and style matching obtained in the above steps, a comprehensive evaluation is conducted to form personalized design suggestions for users;

[0019] Design a suggestion scoring mechanism to determine the best recommendations.

[0020] As a preferred solution of the artificial intelligence-based clothing splicing multifunctional design method described in the present invention, wherein: the construction of the social platform includes using an improved matching algorithm to automatically match designers according to user portraits and recommend designers when users request. After receiving the user's design requirements, the designer confirms them through the instant messaging function and asks interactive questions based on the user's requirements;

[0021] A style feature extraction model F is established, wherein the style features include color, texture, and style elements:

[0022]

[0023] Among them, C i Indicates the color feature RGB value, T j represents texture features, j = 1, 2, ..., m, S l Represents style features, l = 1, 2, ..., p;

[0024] By adjusting the weight of each feature in the analysis system, a weighted feature vector W is formed, and the final feature output X is obtained:

[0025]

[0026] X=W T ·F

[0027] Among them, w C 、w T 、w Sare the color feature weight, texture feature weight, and style feature weight, respectively, and W T is the transpose of the weighted eigenvector matrix;

[0028] After the initial feedback, designers make adjustments based on user comments and feedback, forming a design iteration cycle. After each iteration, users can review the design updates and give their opinions to form the final design.

[0029] As a preferred solution of the multifunctional clothing splicing design method based on artificial intelligence described in the present invention, the final design includes collecting currently popular splicing style pictures, keywords, tags and user reviews on social platforms through crawler technology, pushing design inspiration, and collecting user feedback on different designs in the design discussion link for dynamic adjustment;

[0030] Setting r u For the user's feedback scores on different splicing designs u, set the feedback satisfaction threshold A:

[0031]

[0032] Where b is the number of splicing design solutions. If R ≥ A, it is confirmed that the satisfaction meets the requirements and enters the final solution stage;

[0033] Once the interaction between the user and the designer reaches a satisfactory level, the designer will generate the final stitching garment design plan, automatically generate detailed design documents, and provide formatting for users to download or share.

[0034] As a preferred solution of the multifunctional clothing splicing design method based on artificial intelligence described in the present invention, wherein: the generating and outputting of the final splicing clothing design scheme includes, after multiple rounds of user feedback and design adjustment, using a machine learning model to comprehensively analyze the collected user feedback data, design suggestions and market trends, and automatically generating the final splicing design scheme;

[0035] Output a complete design document, which includes: design drawings, splicing details, fabric instructions, color selection, size information; allow users to download the final design plan in different formats, supported formats include PDF, printable documents and image files, integrate social media sharing function, users can share splicing design plans, and after the final design is output, regularly track user satisfaction, regularly update the design model, adapt to user needs and market changes, form a closed-loop feedback mechanism, and ensure the efficiency of the design process.

[0036] Another object of the present invention is to provide a multifunctional clothing splicing design system based on artificial intelligence, which can provide an end-to-end personalized clothing design solution through the collaborative work of modules, ensuring that the design process is both efficient and meets the personalized needs of users.

[0037] As a preferred solution of the artificial intelligence-based clothing splicing multifunctional design system described in the present invention, it includes: a user portrait construction module, an intelligent design analysis module, a social collaboration platform module, and a design output and management module;

[0038] The user portrait building module is responsible for collecting detailed information about users from multiple data sources and building a comprehensive and dynamic user portrait through data analysis technology. The portrait will include the user's personal characteristics, shopping habits, style preferences and social behavior, providing accurate personalized information for subsequent design;

[0039] The intelligent design analysis module uses advanced machine learning and deep learning algorithms to analyze user portraits to identify and predict user style preferences, and combines current fashion trends and market data to provide users with tailored clothing design suggestions;

[0040] The social collaboration platform module provides an interactive collaboration environment for users and designers, allowing both parties to communicate and collaborate at all stages of the design process, supporting real-time feedback, design modification, and creative sharing, thereby enhancing user experience and improving design satisfaction;

[0041] The design output and management module is responsible for converting the final design solution into a deliverable format, managing the output of the entire design process, tracking user satisfaction, and collecting feedback for continuous improvement of design methods and system performance.

[0042] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, it implements the steps of a multifunctional clothing splicing design method based on artificial intelligence.

[0043] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the computer program implements the steps of a multifunctional clothing splicing design method based on artificial intelligence.

[0044] The beneficial effects of the present invention are as follows: by collecting and analyzing the user's personal information and historical purchase data, combined with an improved deep learning model, the user's style tendencies and preferences can be more accurately identified, thereby generating design suggestions that better meet the user's personalized needs. The constructed social platform allows users to interact directly with designers and complete the design together. The user's real-time feedback and design needs can directly affect the design process, improving the user's sense of participation and satisfaction.

[0045] The interactive cooperation model between users and designers helps to inspire new design inspirations, making the design solutions more diverse and innovative. Based on user feedback and design adjustments, the system can iteratively optimize the design solutions to ensure that the final output clothing design solutions not only meet user expectations but also have market competitiveness. Users can participate in the design process and experience more personalized services, which improves the overall user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0047] Figure 1 A schematic flow chart of a multifunctional clothing splicing design method based on artificial intelligence is provided for one embodiment of the present invention.

[0048] Figure 2 A schematic diagram of working modules of a clothing splicing multifunctional design system based on artificial intelligence is provided for one embodiment of the present invention. DETAILED DESCRIPTION

[0049] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0050] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0051] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0052] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0053] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, which are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0054] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0055] Example 1, reference Figure 1 , which is the first embodiment of the present invention, and provides a multifunctional clothing splicing design method based on artificial intelligence, comprising:

[0056] S1: Collect users’ personal information and historical purchase data to form a comprehensive user profile.

[0057] Furthermore, when users use the relevant application or platform for the first time, they are required to fill in a personal information form, including basic information (such as name, age, gender), body type (such as height, weight, size), style preferences (such as favorite color, style, brand), etc. By integrating e-commerce platforms or consumption records, users' historical purchase data, including purchase time, product category, brand, price range, etc., are automatically extracted;

[0058] Use data analysis tools to monitor user behavior on apps and websites, identify user interests and preferences, further understand user preferences by analyzing user stay time and interaction on different product pages, and provide options to connect to users' social media accounts to extract style preferences and fashion attention information;

[0059] The collected data is stored in the user database, and the user portrait is updated regularly to continuously reflect the user's current interests and trends.

[0060] S2: Use the improved deep learning model to analyze the collected user data, identify the user's style tendencies and preferences, and generate splicing design suggestions.

[0061] Furthermore, the collected data were processed and the K-nearest neighbor interpolation method was used to perform one-hot encoding on the categorical data;

[0062] The improved deep learning model is applied to analyze the user's style preference, and the user's historical interaction data is combined with real-time feedback to generate a personalized style feature vector for the user. The user feature vector U is expressed as:

[0063] U=[u1,u2,...,u n ]

[0064] Among them, u i is the numerical representation of the user on a specific feature, i = 1, 2, ..., n;

[0065] Train the user feature vector, reconstruct the user preference, and calculate the reconstruction error E:

[0066]

[0067] Among them, R(U d ) represents the recommended style features reconstructed by the autoencoder, e is the number of samples, U′ is the user feature vector after training. By analyzing the reconstruction error, the user’s potential style tendency is identified and the user feature vector is optimized.

[0068] The improved weighted K-means clustering algorithm is used to cluster the user feature vector U and define the clustering quality Q:

[0069]

[0070] Among them, C q is the qth cluster, μ is the cluster center, |C| is the average cluster size of all samples, α is a fixed weight adjustment factor used to penalize uneven clustering, x is the clustering variable, and k is the number of clusters;

[0071] It should be noted that the current fashion trends are analyzed, popular elements and features are extracted, and the focus is on colors, fabrics, and design styles. This process involves extensive data collection and analysis of popular design styles on the market to identify popular trends that are suitable for most users. The analysis results of popular trends are used to evaluate the adaptability of popular elements in the user's feature vector:

[0072] P = f(T x ,U)

[0073] Among them, P represents the popular element T x In the adaptability score of user features, the function f is used to evaluate the matching degree between the popular elements and the user feature vector U.

[0074] According to the user's style preferences (such as casual, sports or formal occasions), stitching styles that meet the user's characteristics will be screened out from the design library. In this screening process, the compatibility between each stitching style and the user's characteristics is evaluated so that the recommended style meets the user's personalized needs. For example, if the user prefers a sports style, stitching styles that are energetic and comfortable will be recommended first. Stitching styles that meet the user's characteristics are screened out from the design library:

[0075] M=g(U,D1)

[0076] Among them, M represents the matching degree of the splicing style in the design library, D1 is the feature vector of the current splicing style, and the function g is used to calculate the compatibility between the user feature vector U and the design style feature vector.

[0077] Based on the adaptability of popular elements and style matching obtained in the above steps, a comprehensive evaluation is conducted to form personalized design suggestions for users. The design suggestions include the splicing elements preferred by users, and the design styles are combined with current fashion trends. The design suggestion scoring mechanism is used to determine the best recommendation.

[0078] S3: Build a social platform that allows users to complete splicing design with designers, submit design requirements through interaction, and obtain real-time feedback and suggestions from designers.

[0079] Furthermore, the improved matching algorithm is used to automatically match designers based on user portraits and recommend designers when users make requests. After receiving the user's design requirements, the designer confirms them through the instant messaging function and asks interactive questions based on the user's requirements;

[0080] Establish a style feature extraction model F, including color, texture, and style elements:

[0081]

[0082] Among them, C iRepresents the color feature RGB value, i = 1, 2, ..., n, T j represents texture features, j = 1, 2, ..., m, S l Represents style features, l = 1, 2, ..., p;

[0083] By adjusting the weight of each feature in the analysis system, a weighted feature vector W is formed, and the final feature output X is obtained:

[0084]

[0085] X=W T ·F

[0086] Among them, w C 、w T 、w S are the color feature weight, texture feature weight, and style feature weight, respectively, and W T is the transpose of the weighted eigenvector matrix;

[0087] After the initial feedback, designers make adjustments based on user comments and feedback, forming a design iteration cycle. After each iteration, users can review the design updates and give their opinions to form the final design.

[0088] It should be noted that, through crawler technology, popular splicing style pictures, keywords, tags and user reviews are collected on social platforms to push design inspiration, and user feedback on different designs is collected during the design discussion to make dynamic adjustments;

[0089] Setting r u For the user's feedback scores on different splicing designs u, set the feedback satisfaction threshold A:

[0090]

[0091] Where b is the number of splicing design solutions. If R ≥ A, it is confirmed that the satisfaction meets the requirements and enters the final solution stage;

[0092] Once the interaction between the user and the designer reaches a satisfactory level, the designer will generate the final stitching garment design plan, automatically generate detailed design documents, and provide formatting for users to download or share.

[0093] Furthermore, the weight adjustment formula of user feedback on design elements can be expressed as:

[0094]

[0095] Where v is the current weight of the design element, γ is the adjustment coefficient, s′ is the current feedback score, is the average of the feedback scores, δ is the weighting factor, D′ is the impact factor of the design element, and v new Adjusted weights for design elements.

[0096] S4: Based on user feedback and design adjustments, generate and output the final stitching clothing design plan.

[0097] Furthermore, after multiple rounds of user feedback and design adjustments, the machine learning model is used to comprehensively analyze the collected user feedback data, design suggestions and market trends to automatically generate the final splicing design plan;

[0098] Output a complete design document, which includes:

[0099] Design drawing: A clear schematic diagram of the splicing design, showing the overall look and details of the garment.

[0100] Specific details of stitching: Describe the construction of the stitching part in detail, including sewing technology, interface treatment methods between different fabrics, etc.

[0101] Fabric Description: Provides detailed information on the selected material, including material properties, functional description (such as breathability, elasticity, etc.) and sustainability evaluation.

[0102] Color selection: List the color schemes of the selected colors and the occasions where they are suitable to ensure that users understand the design concept related to the visual effects.

[0103] Size information: Provide applicable size ranges and size guides to help users make appropriate choices and avoid size inaccuracies.

[0104] It allows users to download the final design plan in different formats. The supported formats include PDF, printable documents and image files. It integrates social media sharing function, and users can share splicing design plans. After the final design is output, user satisfaction is tracked regularly, and the design model is updated regularly to adapt to user needs and market changes, forming a closed-loop feedback mechanism to ensure the efficiency of the design process.

[0105] Embodiment 2, the second embodiment of the present invention, is different from the previous embodiment in that:

[0106] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the 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, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0107] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0108] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0109] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0110] Embodiment 3 is an embodiment of the present invention, which provides a multifunctional clothing splicing design system based on artificial intelligence, characterized in that it includes a user portrait construction module 100, an intelligent design analysis module 200, a social collaboration platform module 300, and a design output and management module 400;

[0111] The user portrait building module 100 is responsible for collecting detailed information of users from multiple data sources and building a comprehensive and dynamic user portrait through data analysis technology. The portrait will include the user's personal characteristics, shopping habits, style preferences and social behavior, providing accurate personalized information for subsequent design;

[0112] Intelligent design analysis module 200, which uses advanced machine learning and deep learning algorithms to analyze user portraits to identify and predict user style preferences, and combines current fashion trends and market data to provide users with tailored clothing design suggestions;

[0113] The social collaboration platform module 300 provides an interactive collaboration environment for users and designers, allowing both parties to communicate and collaborate at all stages of the design process, supporting real-time feedback, design modification, and creative sharing, enhancing user experience and improving design satisfaction;

[0114] The design output and management module 400 is responsible for converting the final design solution into a deliverable format, managing the output of the entire design process, tracking user satisfaction, and collecting feedback for continuous improvement of design methods and system performance.

[0115] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A multifunctional clothing splicing design method based on artificial intelligence, characterized by: include, Collect users’ personal information and historical purchase data to form a comprehensive user profile; Utilize the improved deep learning model to analyze the collected user data, identify the user’s style tendencies and preferences, and generate splicing design suggestions; Build a social platform that allows users to complete splicing design with designers, submit design requirements through interaction, and obtain real-time feedback and suggestions from designers; Based on user feedback and design adjustments, the final stitching garment design plan is generated and output.

2. The multifunctional clothing splicing design method based on artificial intelligence as claimed in claim 1, characterized in that: The formation of a comprehensive user profile includes requiring users to fill out a personal information form containing basic information, body type, and style preferences when using the relevant application or platform for the first time, automatically extracting the user's historical purchase data through the integration of e-commerce platforms or consumption records, and identifying the user's consumption habits and trends; Use data analysis tools to monitor user behavior on apps and websites, identify user interests and preferences, further understand user preferences by analyzing user stay time and interaction on different product pages, provide options to connect users' social media accounts, and extract style preferences and fashion attention information; The collected data is stored in the user database, and the user portrait is updated regularly to continuously reflect the user's current interests and trends.

3. A multifunctional clothing splicing design method based on artificial intelligence as claimed in claim 2, characterized in that: The analyzing the collected user data includes processing the collected data and performing one-hot encoding on the category data using a K-nearest neighbor interpolation method; The improved deep learning model is applied to analyze the user's style preference, and the user's historical interaction data is combined with real-time feedback to generate a personalized style feature vector for the user. The user feature vector U is expressed as: U=[u1,u2,...,u n ] Among them, u i is the numerical representation of the user on a specific feature, i = 1, 2, ..., n; Train the user feature vector, reconstruct the user preference, and calculate the reconstruction error E: Among them, R(U d ) represents the recommended style features reconstructed by the autoencoder, e is the number of samples, and U′ is the user feature vector after training; By analyzing the reconstruction error, the user's potential style tendency is identified and the user feature vector is optimized.

4. The multifunctional clothing splicing design method based on artificial intelligence as claimed in claim 3, characterized in that: The generating of the splicing design suggestion comprises: Analyze current fashion trends, extract popular elements and features, and use the analysis results of popular trends to evaluate the adaptability of popular elements in the user's feature vector; based on the user's style preferences, select stitching styles that meet the user's characteristics from the design library. During the screening process, evaluate the compatibility between each stitching style and the user's characteristics, so that the recommended style meets the user's personalized needs; Based on the adaptability of popular elements and style matching obtained in the above steps, a comprehensive evaluation is conducted to form personalized design suggestions for users; Design a suggestion scoring mechanism to determine the best recommendations.

5. The multifunctional clothing splicing design method based on artificial intelligence as claimed in claim 4, characterized in that: The construction of the social platform includes using an improved matching algorithm to automatically match designers according to user portraits and recommend designers when users make requests. After receiving the user's design requirements, the designer confirms them through an instant messaging function and asks interactive questions based on the user's requirements. A style feature extraction model F is established, wherein the style features include color, texture, and style elements: Among them, C i Indicates the color feature RGB value, T j represents texture features, j = 1, 2, ..., m, S l Represents style features, l = 1, 2, ..., p; By adjusting the weight of each feature in the analysis system, a weighted feature vector W is formed, and the final feature output X is obtained: X=W T ·F Among them, w C 、w T 、w S are the color feature weight, texture feature weight, and style feature weight, respectively, and W T is the transpose of the weighted eigenvector matrix; After the initial feedback, designers make adjustments based on user comments and feedback, forming a design iteration cycle. After each iteration, users can review the design updates and give their opinions to form the final design.

6. The multifunctional clothing splicing design method based on artificial intelligence as claimed in claim 5, characterized in that: The final design includes collecting currently popular splicing style pictures, keywords, tags and user reviews on social platforms through crawler technology, pushing design inspiration, and collecting user feedback on different designs during the design discussion session to make dynamic adjustments; Setting r u For the user's feedback scores on different splicing designs u, set the feedback satisfaction threshold A: Where b is the number of splicing design solutions. If R ≥ A, it is confirmed that the satisfaction meets the requirements and enters the final solution stage; Once the interaction between the user and the designer reaches a satisfactory level, the designer will generate the final stitching garment design plan, automatically generate detailed design documents, and provide formatting for users to download or share.

7. The multifunctional clothing splicing design method based on artificial intelligence as claimed in claim 6, characterized in that: Generating and outputting the final stitching clothing design plan includes, after multiple rounds of user feedback and design adjustments, using a machine learning model to comprehensively analyze the collected user feedback data, design suggestions and market trends, and automatically generating the final stitching design plan; Output a complete design document, including: design drawings, splicing details, fabric description, color selection, and size information; It allows users to download the final design plan in different formats. Supported formats include PDF, printable documents and image files. It integrates social media sharing functions to allow users to share and splice design plans. After the final design is output, user satisfaction is tracked regularly, and the design model is updated regularly to adapt to user needs and market changes, forming a closed-loop feedback mechanism.

8. A system using the artificial intelligence-based clothing splicing multifunctional design method as claimed in any one of claims 1 to 7, characterized in that: It includes user portrait building module, intelligent design analysis module, social collaboration platform module, and design output and management module; The user portrait building module is responsible for collecting detailed information about users from multiple data sources and building a comprehensive and dynamic user portrait through data analysis technology. The portrait will include the user's personal characteristics, shopping habits, style preferences and social behavior, providing accurate personalized information for subsequent design; The intelligent design analysis module uses advanced machine learning and deep learning algorithms to analyze user portraits to identify and predict user style preferences, and combines current fashion trends and market data to provide users with tailored clothing design suggestions; The social collaboration platform module provides an interactive collaboration environment for users and designers, allowing both parties to communicate and collaborate at all stages of the design process, supporting real-time feedback, design modification, and creative sharing, thereby enhancing user experience and improving design satisfaction; The design output and management module is responsible for converting the final design solution into a deliverable format, managing the output of the entire design process, tracking user satisfaction, and collecting feedback for continuous improvement of design methods and system performance.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images