Garment customization management system and data processing method thereof

Abstract

According to the garment customization management system and the data processing method thereof, high-precision and personalized garment customization is realized by integrating data acquisition, intelligent design and production management. The system comprises a client terminal module, a data acquisition module, a data processing module, an intelligent design module, a production management module and a background management module. 3D human body scanning and wearable equipment acquire body type data, and a data processing module performs cleaning, standardization and noise processing on the data to generate standardized data. And the intelligent design module generates a personalized design scheme and recommends the fabric based on deep learning and a K-means algorithm. And the production management module converts the design scheme into a production instruction and transmits the production instruction to production equipment in real time through an MQTT protocol, so that automatic production is realized. The background management module monitors orders and production progress in real time. According to the method, the customization efficiency and accuracy are improved, and the problems of large traditional customization error, insufficient individuation and the like are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of clothing, and in particular to a clothing customization management system and a data processing method thereof. Background Art

[0002] With the growing demand for personalized consumption, traditional clothing customization has gradually exposed some obvious problems, especially in terms of design personalization, efficiency improvement and data processing accuracy. Traditional clothing customization methods usually rely on manual measurement and traditional design methods, which not only causes measurement errors and inaccurate design, but also greatly reduces customization efficiency.

[0003] Limitations of traditional clothing customization: Traditional clothing customization usually relies on manual measurement of the customer's body shape, which is subject to measurement errors and uncertainty caused by manual operation. Due to the large differences in customer body shapes, manual calculation and adjustment alone often fail to meet the customer's personalized needs, resulting in unsatisfactory design results. At the same time, the traditional customization process is inefficient and difficult to achieve large-scale customized production.

[0004] Complexity of body shape data collection and processing: The collection of body shape data usually relies on traditional body measurement tools, and different measurement methods and measurement personnel may lead to inconsistent data. In addition, body shape data often contains noise or outliers, and needs to go through tedious data cleaning, standardization and processing processes in order to generate ergonomic clothing design solutions. However, in existing clothing customization systems, data processing often lacks precise cleaning and standardization steps, resulting in low accuracy of the generated design solutions.

[0005] Lack of intelligent design: Currently, most clothing customization systems on the market still use traditional design methods, where designers manually modify clothing drawings or templates according to the customer's body shape, which is not only inefficient but also has limited space for personalized design. Although some clothing customization systems have introduced computer-aided design (CAD) tools, these tools still do not fully combine the customer's body shape data for optimized design and lack intelligent and personalized recommendation systems.

[0006] Disconnection between production and customization process: In the traditional clothing customization process, there is a time lag and inaccurate information transmission between the generation of design solutions and production execution. Many systems fail to achieve real-time synchronization of order information and dynamic adjustment of production tasks, resulting in delays and inefficiency in the production process.

[0007] Therefore, how to combine modern information technology, especially data acquisition technology, intelligent design algorithms and automated production technology, to optimize the clothing customization process, improve the personalization and accuracy of the design, and solve the inefficiency and inaccuracy problems in traditional customization methods has become a technical problem that needs to be solved urgently.

[0008] In view of this, the inventor specially designed a clothing customization management system and a data processing method thereof, and this case was thus generated. Summary of the invention

[0009] 1. Technical issues to be resolved The purpose of this application is to provide a clothing customization management system and a data processing method thereof, which at least solves the technical problem of how to generate personalized design solutions through accurate data collection, processing and intelligent design algorithms in the clothing customization process.

[0010] (II) Technical solution In order to solve the above technical problems, the present invention provides the following technical solutions: This application provides a clothing customization management system, including: The customer terminal module is used to receive and process the personalized customization demand information input by the customer and generate an order; A data collection module, used to collect the customer's body shape data through 3D body scanning equipment and wearable measurement devices; The data processing module is used to clean, standardize, process noise and convert the collected body shape data to generate standardized data that can be used by the intelligent design module; Intelligent design module, which is used to generate personalized clothing design solutions based on customer needs and body shape data, and make fabric recommendations; Production management module, used to convert personalized design plans into production instructions and control production equipment to produce clothing; Backstage management module, used to manage customer information, order status and production progress.

[0011] In a further embodiment, the intelligent design module further comprises: Style recommendation unit, which uses deep learning model and collaborative filtering algorithm based on customer body features to recommend personalized clothing styles; Fabric recommendation unit, based on K-means clustering algorithm, recommends the most suitable fabric according to customer needs; The design optimization unit uses parametric modeling and finite element analysis to optimize clothing design, making the design more in line with the customer's body shape and comfort requirements.

[0012] In a further solution, real-time data transmission between modules is also included through the WebSocket protocol, which is used for data synchronization and instant update between modules.

[0013] In a further solution, the production management module transmits the production instructions generated by the intelligent design module to the production equipment in real time through the MQTT protocol to control the automation and accuracy of the production process.

[0014] In a further solution, the data processing module includes a data synchronization unit, which supports two modes: real-time streaming data transmission and scheduled batch uploading. Real-time streaming data transmission is used for instant transmission of customer body shape data, and scheduled batch uploading is used for regular uploading of production data.

[0015] In a further solution, the background management module provides order status monitoring, customer data management and production progress tracking functions, and provides a visual interface for system administrators to manage and adjust orders and production tasks.

[0016] The present application also provides a data processing method for a clothing customization management system, comprising the following steps: S10 Data Collection: Collect customer’s body data through 3D body scanning equipment and wearable measurement devices; S20 data cleaning: Use the Z-score algorithm to remove outliers that exceed the set threshold range to ensure data accuracy; S30 Data standardization: The Min-Max normalization method is used to convert the collected body shape data into a standardized range of 0 to 1; S40 Data conversion: Convert the cleaned and standardized body shape data into JSON format for processing and application in subsequent modules.

[0017] In a further embodiment, the S20 data cleaning step also includes noise processing, which smoothes the body shape data through a Gaussian filtering algorithm to remove noise caused by measurement errors or equipment interference for data accuracy.

[0018] (III) Beneficial effects Compared with the prior art, the present invention has the following beneficial effects: Precise and efficient data processing: Real-time collection of body shape data through 3D scanning and wearable devices, combined with Z-score cleaning, Min-Max standardization and Gaussian filtering noise processing, significantly improves data accuracy and consistency, overcoming the problems of large errors and inconsistent data in traditional manual measurement.

[0019] Personalized intelligent recommendation: This system uses deep learning and collaborative filtering algorithms to make personalized clothing design recommendations based on the customer's body characteristics and needs. At the same time, it uses the K-means clustering algorithm to match the most suitable fabrics to ensure the personalization and comfort of the design, solving the problems of low personalization and inaccurate recommendations in existing technologies.

[0020] Efficient production management and real-time control: Production instructions are transmitted to production equipment in real time through the MQTT protocol, realizing automated docking from design to production, significantly improving production efficiency and response speed, and overcoming the problems of delayed production instruction transmission and low production efficiency in traditional customization processes.

[0021] Comprehensive background management and real-time monitoring: The system integrates background management modules, providing order status monitoring, production progress tracking and visual management, making the management of the entire customization process more efficient and transparent, and improving user experience and management efficiency.

[0022] The specific implementation modes of the present invention are further described in detail below in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In the attached picture: Figure 1 The figure is a schematic diagram of the composition of a clothing customization management system in one embodiment of the present invention.

[0024] Figure 2 The present invention is a flowchart of a data processing method of a clothing customization management system in one embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. The following embodiments are used to illustrate the present invention.

[0026] The present invention provides a clothing customization management system and a data processing method thereof, which solves the problems of low precision, low efficiency and lack of personalization in traditional customization systems. The system ensures the accuracy, efficiency and personalization of the clothing customization process by intelligently controlling the collection, processing, standardization, design and production management of customer body data.

[0027] Example 1 The present invention discloses a clothing customization management system. Figure 1 FIG. 1 is a schematic diagram of the composition of a clothing customization management system in one embodiment of the present invention; please refer to FIG. Figure 1 The clothing customization management system is mainly composed of the following modules: 1. Customer terminal module: used to receive personalized customization demand information (such as clothing style, fabric preference, etc.) input by customers and generate corresponding customization orders.

[0028] 2. Data collection module: collect customers’ body data (such as height, chest circumference, waist circumference, hip circumference, etc.) through 3D body scanning equipment and wearable measuring devices.

[0029] 3. Data processing module: perform data cleaning, standardization, noise processing and format conversion on the collected body shape data to generate standardized data for use in subsequent modules.

[0030] 4. Intelligent design module: Based on customer needs and body shape data, it uses deep learning algorithms and collaborative filtering algorithms to generate personalized clothing design solutions and recommend the most suitable fabrics.

[0031] 5. Production management module: convert the generated personalized design plan into production instructions, and automate the production of clothing through production equipment.

[0032] 6. Backstage management module: responsible for managing customer information, order status and production progress, and providing real-time monitoring and adjustment interface.

[0033] System architecture design The system architecture is modular, and each module interacts with each other through standard interfaces. The data flow is as follows:

[0034] The client terminal module receives client demands through the input interface, generates order information, and transmits it to the data acquisition module.

[0035] The customer body shape data collected by the data collection module is transmitted to the data processing module in real time through the data synchronization unit for processing.

[0036] The data processing module performs data cleaning, standardization, noise processing and format conversion to ensure the accuracy and consistency of the data, and transmits the processed data to the intelligent design module.

[0037] The intelligent design module generates personalized design solutions based on customer needs and body shape data, and transmits them to the production management module for production instruction conversion and production control.

[0038] The production management module transmits production instructions to production equipment in real time through the MQTT protocol to ensure the accuracy and automation of production.

[0039] The backend management module provides real-time monitoring of orders and production progress, and provides administrators with visual management functions.

[0040] The workflow of the entire system is as follows: 1. Data collection: The customer inputs the required information through the terminal device, and the data collection module uses 3D scanning and wearable measurement devices to obtain the customer's body data (such as height, weight, chest circumference, waist circumference, hip circumference, etc.).

[0041] 2. Data cleaning and standardization: The data processing module cleans the collected data (using the Z-score algorithm to remove outliers), standardizes (using the Min-Max normalization method) and performs noise processing (using the Gaussian filtering algorithm to remove errors).

[0042] 3. Intelligent design: The intelligent design module recommends personalized clothing styles based on the customer's body shape data and needs through deep learning algorithms, and uses the K-means clustering algorithm to recommend fabrics and optimize clothing design to suit the customer's body shape and comfort requirements.

[0043] 4. Production instruction generation: The intelligent design plan is converted into production instructions through the production management module, and transmitted to the production equipment in real time through the MQTT protocol to control the production process.

[0044] 5. Backstage management and monitoring: The backstage management module tracks orders and production progress in real time, and provides administrators with a visual monitoring and management interface.

[0045] Data flow and module collaboration Data collection and transmission: The data collection module uses 3D scanning equipment and wearable devices to collect customer body data, and transmits the collected data to the data processing module in real time through the WebSocket protocol.

[0046] Data processing and standardization: The data processing module performs data cleaning (outlier removal), standardization (Min-Max normalization), noise processing (Gaussian filtering) and format conversion (converting to JSON format) on the collected body shape data.

[0047] Specifically, data cleaning uses the Z-score algorithm: in: is the Z-score of the ith data point; is the i-th body shape data; is the mean of the data set D; is the standard deviation of the data set D.

[0048] The standardization adopts the Min-Max normalization method: in: is the normalized data value; and are the minimum and maximum values ​​of data set D respectively.

[0049] Noise processing is done using a Gaussian filtering algorithm: in, is the filtered data, is the Gaussian weight, and the Gaussian function is usually used as the weight function: Through this algorithm, high-frequency noise in the data (such as mutation values ​​caused by equipment errors) is smoothed out, while the effective components of the data are retained. Intelligent design and recommendation: The intelligent design module uses collaborative filtering algorithms and deep learning models to recommend clothing styles based on the customer's body shape data and needs; recommends fabrics through the K-means clustering algorithm, and optimizes the design through parametric modeling and finite element analysis.

[0050] The basic model for deep learning recommendation is: in: is the predicted output of the model; and They are the weight matrix and bias term of the network respectively; X is the input customer body shape feature. After training, the model can generate personalized recommended clothing styles.

[0051] The objective function of the K-means clustering algorithm is: in: is the i-th data point (i.e., the customer’s body shape characteristics); It is the central production instruction generation and transmission of the jth cluster; K is the number of clusters; By minimizing the objective function J, the K-means algorithm clusters the customer body shape data into the most appropriate cluster, thereby recommending suitable fabrics.

[0052] After the intelligent design plan is generated, production instructions are generated through the production management module and transmitted to the production equipment in real time through the MQTT protocol for automated production.

[0053] Backstage management and monitoring: The backstage management module monitors order status, customer data and production progress, and provides a visual management interface for system administrators.

[0054] Embodiment 2 Corresponding to the above-mentioned clothing customization management system, the present invention further discloses a data processing method for the clothing customization management system. Figure 2This is a flow chart of a data processing method of a clothing customization management system in one embodiment of the present invention; please refer to Figure 2 , the data processing method comprises the following steps: S10 Data Collection: Collect the customer’s body data through 3D body scanning equipment and wearable measuring devices, including three-dimensional spatial data such as height, chest circumference, waist circumference, and hip circumference.

[0055] S20 Data cleaning: Use the Z-score algorithm to remove outliers that exceed the set threshold range to ensure data accuracy.

[0056] S30 Data standardization: The Min-Max normalization method is used to standardize the collected body shape data to a range of 0 to 1 to ensure data consistency.

[0057] S40 Data conversion: Convert the cleaned and standardized body shape data into JSON format for processing and application in subsequent modules.

[0058] Furthermore, the S20 data cleaning step also includes noise processing, which smoothes the body shape data through a Gaussian filtering algorithm to remove noise caused by measurement errors or equipment interference, so as to improve the accuracy of the data.

[0059] Algorithms and models Deep learning and collaborative filtering algorithms: The intelligent design module uses deep learning and collaborative filtering algorithms to recommend clothing styles based on the customer's historical behavior and body shape data. This method can provide more accurate personalized recommendations based on the user's personal characteristics and preferences.

[0060] K-means clustering algorithm: In the fabric recommendation process, the K-means clustering algorithm is used to select the most suitable fabric based on customer needs and body shape data to ensure the comfort and aesthetics of the clothing.

[0061] Data cleaning and standardization technology: Use the Z-score algorithm to remove abnormal data and the Gaussian filter algorithm to remove noise to ensure the accuracy and stability of data processing.

[0062] Embodiment 3: Generate clothing customization plan based on personalized needs.

[0063] Customer A accesses the clothing customization platform through a mobile terminal device, enters personal body data and customized clothing requirements (for example, a business suit is needed, and the fabric selection is mainly comfortable and breathable). Customer A's body data is collected in real time through 3D body scanning equipment and wearable measurement devices, including height, chest circumference, waist circumference, hip circumference, etc. The collected data is transmitted to the data processing module in the system through the WebSocket protocol for further processing.

[0064] Steps: Data collection: Customer A uses a mobile terminal to connect to a 3D body scanning device to scan and collect body shape data. During the data collection process, the collection of body shape data can be expressed as a vector:

[0065] in: h is the height of the customer; c is chest circumference; for waist circumference; b is the hip circumference.

[0066] After the device synchronously collects data, it transmits it to the data processing module in real time through the WebSocket protocol. This part can be represented by the real-time nature of data transmission:

[0067] in, is the size of the packet, is the time of data transmission.

[0068] Data processing: In the data processing module, the collected raw data is first cleaned. The Z-score algorithm is used to remove abnormal values ​​in data such as height and chest circumference (such as unreasonable values ​​caused by measurement errors). Then, the Min-Max normalization method is used to standardize all data to the range of 0 to 1.

[0069] Then, the Gaussian filter algorithm is used to process the noise, smooth the data, and remove the interference caused by measurement errors and environmental factors. Finally, the processed data is converted into JSON format for use in subsequent modules.

[0070] Intelligent design and recommendation: The processed data is transmitted to the intelligent design module. This module first uses the deep learning algorithm and collaborative filtering algorithm to recommend suitable suit styles (such as slim fit, standard fit, etc.) based on the body characteristics of customer A. Then, based on the customer's demand for fabric comfort, the K-means clustering algorithm is used to recommend fabrics with strong breathability and high comfort. The specific model of the deep learning algorithm can be expressed by the following formula:

[0071] in: The preference for the recommended clothing style; They are the weights and bias terms of the deep learning model respectively; is the customer's body shape data, as input feature; is the activation function (such as ReLU or Sigmoid).

[0072] This formula expresses the process of recommending personalized clothing styles based on the customer's body data and needs.

[0073] Production management and control: The personalized design scheme generated by the intelligent design module is transmitted to the production management module. The module converts the design scheme into production instructions and transmits the instructions to the production equipment in real time through the MQTT protocol to start automated production.

[0074] Backstage management and tracking: Throughout the entire process, the backstage management module provides order status monitoring, customer data management and production progress tracking functions to ensure that every step from design to production of custom clothing is monitored in real time.

[0075] Technical effect: Through this embodiment, customer A can obtain personalized clothing design based on personal body shape and needs in a shorter period of time, and optimize the design plan through intelligent algorithms, thereby improving customer satisfaction.

[0076] Example 4: Clothing customization production management and personalized recommendation.

[0077] Customer B inputs his body data (such as weight, height, chest circumference, waist circumference, etc.) and basic requirements for clothing styles through the clothing customization platform. The platform collects customer B's body data through the data collection module and generates a personalized design plan based on the data. Customer B wants to customize a sports casual wear with good elasticity.

[0078] Steps: Data collection and transmission: Customer B uses a wearable measurement device to collect data and transmit the data to the system. The data is transmitted to the data processing module in the system via the WebSocket protocol. Assume that the relationship between data transmission time and data volume can be expressed by the following formula:

[0079] in: is the data transmission time; is the total size of the data; is the transfer rate.

[0080] Data cleaning and standardization: In the data processing module, the Z-score algorithm is first used to clean the collected body shape data and remove outliers (such as extreme data caused by measurement errors). Subsequently, the Min-Max normalization method is used to standardize the data.

[0081] Noise processing and data formatting: For the collected data, the Gaussian filtering algorithm is used for noise processing to remove data noise caused by environmental factors and equipment errors. The cleaned and standardized data is converted into JSON format for easy use in subsequent modules.

[0082] Smart design and style recommendation: The cleaned and standardized data is transmitted to the smart design module. This module uses a deep learning algorithm based on the customer's body shape characteristics to recommend suitable sports and leisure styles for customer B. Based on the customer's demand for elastic fabrics, the system uses the K-means clustering algorithm to recommend fabrics with good elasticity from the database.

[0083] Production instruction generation and execution: The optimized design plan and fabric recommendation are transmitted to the production management module, specific production instructions are generated, and transmitted to the production equipment through the MQTT protocol to start the production of personalized clothing. The production instructions optimize the automated production process through the PID control system to ensure production accuracy. The formula for PID control is:

[0084] in: To control output, determine the adjustment of production equipment; is the target production state (clothing design parameters); The current production status.

[0085] Through PID control, the system automatically adjusts the production process to ensure the precise production of each custom garment.

[0086] Backstage management and monitoring: The entire order process is monitored in real time. The backstage management module provides a visual management interface, which allows administrators to check the status of customer orders at any time and make adjustments and optimizations.

[0087] Technical effect: Through this embodiment, customer B can quickly obtain personalized sports and leisure clothing design according to his personal body shape and needs, and the production process is automated, ensuring the customization, comfort and production efficiency of the clothing. In summary, the clothing customization management system of the present invention significantly improves the accuracy and efficiency of clothing customization by combining data processing and intelligent design. The use of deep learning and collaborative filtering algorithms makes personalized recommendations more accurate, and customers can choose the most suitable clothing styles and fabrics according to their body characteristics, thereby improving customer satisfaction. Compared with the prior art, the present invention effectively eliminates the data inconsistency problem in the traditional customized clothing system through cleaning, standardization and noise processing technology in data processing. The application of the intelligent design module makes the clothing customization process more intelligent, reduces manual intervention, and improves design accuracy. The present invention can be widely used in the clothing customization industry, promote the intelligent transformation of the traditional clothing industry, provide consumers with efficient and personalized customized clothing services, meet the growing demand for personalized customization, and has high industrial value and application prospects.

[0088] The present invention is described above by way of example in conjunction with the accompanying drawings. It is obvious that the specific implementation of the present invention is not limited to the above-mentioned method. As long as various non-substantial improvements are made using the method concept and technical solution of the present invention, or the concept and technical solution of the present invention are directly applied to other occasions without improvement, they are all within the protection scope of the present invention.

Claims

1. A clothing customization management system, characterized in that: include: The customer terminal module is used to receive and process the personalized customization demand information input by the customer and generate an order; A data collection module, used to collect the customer's body shape data through 3D body scanning equipment and wearable measurement devices; The data processing module is used to clean, standardize, process noise and convert the collected body shape data to generate standardized data that can be used by the intelligent design module; Intelligent design module, which is used to generate personalized clothing design solutions based on customer needs and body shape data, and make fabric recommendations; Production management module, used to convert personalized design plans into production instructions and control production equipment to produce clothing; Backstage management module, used to manage customer information, order status and production progress.

2. A clothing customization management system according to claim 1, characterized in that: The intelligent design module also includes: Style recommendation unit, which uses deep learning model and collaborative filtering algorithm based on customer body features to recommend personalized clothing styles; Fabric recommendation unit, based on K-means clustering algorithm, recommends the most suitable fabric according to customer needs; The design optimization unit uses parametric modeling and finite element analysis to optimize clothing design, making the design more in line with the customer's body shape and comfort requirements.

3. A clothing customization management system according to claim 1, characterized in that: It also includes real-time data transmission between modules through the WebSocket protocol, which is used for data synchronization and instant update between modules.

4. A clothing customization management system according to claim 1, characterized in that: The production management module transmits the production instructions generated by the intelligent design module to the production equipment in real time through the MQTT protocol to control the automation and accuracy of the production process.

5. A clothing customization management system according to claim 1, characterized in that: The data processing module includes a data synchronization unit, which supports two modes: real-time streaming data transmission and scheduled batch uploading. The real-time streaming data transmission is used for instant transmission of customer body shape data, and the scheduled batch uploading is used for regular uploading of production data.

6. A clothing customization management system according to claim 1, characterized in that: The backend management module provides order status monitoring, customer data management and production progress tracking functions, and provides a visual interface for system administrators to manage and adjust orders and production tasks.

7. A clothing customization management system according to claim 1, characterized in that: The 3D human body scanning equipment and the wearable measuring device are used to collect the three-dimensional spatial data of the customer's height, weight, chest circumference, waist circumference, and hip circumference.

8. A data processing method for the clothing customization management system according to claim 1, characterized in that: The following steps are involved: S10 Data Collection: Collect customer’s body data through 3D body scanning equipment and wearable measurement devices; S20 data cleaning: Use the Z-score algorithm to remove outliers that exceed the set threshold range to ensure data accuracy; S30 Data standardization: The Min-Max normalization method is used to convert the collected body shape data into a standardized range of 0 to 1; S40 Data conversion: Convert the cleaned and standardized body shape data into JSON format for processing and application in subsequent modules.

9. The data processing method of a clothing customization management system according to claim 8, characterized in that: The S20 data cleaning step also includes noise processing, which smoothes the body shape data through a Gaussian filtering algorithm to remove noise caused by measurement errors or equipment interference, so as to improve the accuracy of the data.

Images