KR-102962762-B1 - Manufacturing and recommendation system for seamless women's clothing with optimal mixing ratio and sewing density

KR102962762B1KR 102962762 B1KR102962762 B1KR 102962762B1KR-102962762-B1

Abstract

The present invention relates to the field of convergence technology applying data processing and analysis technology to the clothing industry, and more specifically, to an intelligent clothing evaluation and recommendation system that organically combines physical manufacturing specification data of clothing with user feedback data collected from the actual market, objectively evaluates product quality based on this, and further optimizes the design of new products or recommends customized products to end consumers.

Inventors

송진호
이현지
김예진

Assignees

주식회사 자칼

Dates

Publication Date: 20260508
Application Date: 20250728

Claims (6)

In a system for evaluating and recommending products based on manufacturing specification data and market response data of clothing products, A data collection unit that collects raw data including the above manufacturing specification data and the above market response data from an external source; A manufacturing specification analysis module and a user feedback analysis module that extract and store structured physical characteristic data and market acceptance data from the above raw data; A data storage module for storing and managing the above-mentioned structured data; An analysis optimization module that generates a plurality of technical indices, including a wear comfort index, a compression-support index by area, and an overall product optimization score, based on the stored structured data; and A new product design module and a product recommendation module that derive manufacturing specifications for a new product or recommend an existing product to a user by utilizing the technical index generated above; Includes, The above analysis optimization module is, It is characterized by generating a wear comfort index that indicates the comfort of the material based on the physical properties of the fabric, and generating a part-specific compression-support index that indicates the compression and support force applied to specific body parts of the seamless garment. The generation of the above wear comfort index is, (a) A first step of obtaining the blending ratio for each of the plurality of individual materials constituting the fabric and the unique comfort coefficient of each material from the data storage module above, and calculating the weighted average comfort value of the entire fabric; (b) A second step of performing a non-linear sensitivity correction on the weighted average comfort value calculated above, wherein as the comfort value increases above a certain level, the influence of the change in the value on the final index is gradually reduced; (c) A third step of obtaining weight data per unit area of the fabric from the data storage module above, and calculating a weight penalty value based on the weight, wherein the penalty value increases as the weight increases but the rate of increase gradually decreases; and (d) A fourth step of generating a final wear comfort index by performing calculations to have a relationship that is directly proportional to the corrected comfort value and inversely proportional to the weight penalty value; Includes, The generation of the above-mentioned compression-support index by region is, (e) Step 5, which compares the actual sewing density of a specific part of the garment with the reference sewing density and calculates the relative compression strength by considering the intrinsic elastic modulus of the yarn; (f) Step 6, which generates a non-linear pressure intensity by modeling a non-linear sensory response in which the pressure felt by the human body increases exponentially as the sewing density increases, with respect to the relative pressure intensity calculated above; and (g) A seventh step of generating a final index by combining an area distribution correction coefficient, calculated by reflecting the effect of pressure concentration in a narrow area as the area ratio of the corresponding part decreases, with the non-linear compression strength; characterized by being performed including a seamless women's clothing manufacturing and recommendation system with optimal blend ratio and sewing density.
delete
In paragraph 1, The above manufacturing specification analysis module is, Receives a fabric specification text file from the above data collection unit, parses it to extract the above blending ratio and the above weight value per unit area, and The above analysis optimization module is, A seamless women's clothing manufacturing and recommendation system with optimal blend ratio and sewing density, characterized by obtaining the above-mentioned intrinsic comfort coefficient by querying a material property database that is defined in advance for each material and stored in the data storage module.
In paragraph 1, The above new product design module is, A step of receiving a target profile of a new product, including a target wear comfort index, through a user interface unit; A step of generating a plurality of virtual manufacturing specification combinations and simulating an expected wear comfort index by calling the analysis optimization module for each virtual combination; and A step of deriving an optimal combination of manufacturing specifications that satisfies the input target wear comfort index among the simulated indices and displaying it on the user interface unit; A seamless women's clothing manufacturing and recommendation system with optimal blend ratio and sewing density, further including
In paragraph 1, The above product recommendation module is, A step of receiving requirements related to "soft material" through a user interface unit; A step of querying the wear comfort index generated by the analysis optimization module for all products stored in the data storage module; and A step of filtering only products whose above-mentioned wear comfort index is above a preset threshold to generate a final recommendation list and displaying it on the user interface unit; A seamless women's clothing manufacturing and recommendation system with optimal blend ratio and sewing density, further including
In paragraph 1, The nonlinear sensitivity correction of the second step above is, It is intended to model the psychophysical response in which the human sense of comfort exhibits the characteristics of diminishing marginal utility, and The calculation of the weight penalty in the third step above is, This is intended to reflect the phenomenon where the rate of increase in the burden of weight increase decreases, and The operation of the above fourth step is, A seamless women's clothing manufacturing and recommendation system with optimal blend ratio and sewing density, characterized by combining into a ratio structure that evaluates the balance between a positive element, the texture of the material, and a negative element, the weight.

Description

Manufacturing and recommendation system for seamless women's clothing with optimal mixing ratio and sewing density The present invention relates to the field of convergence technology applying data processing and analysis technology to the clothing industry, and more specifically, to an intelligent clothing evaluation and recommendation system that organically combines physical manufacturing specification data of clothing with user feedback data collected from the actual market, objectively evaluates product quality based on this, and further optimizes the design of new products or recommends customized products to end consumers. Recently, there has been an increasing number of attempts to utilize artificial intelligence and big data technologies in the fashion and apparel industries. Existing technologies have primarily focused on recommending previously released clothing products by analyzing users' purchase history, search records, or physical activity levels. For example, the main approaches involved recommending clothing with elasticity suited to a user's activity level or suggesting styles similar to what the user wore in specific environments in the past. However, these prior art technologies have several obvious limitations. First, they treat clothing merely as a finished product and fail to utilize in their analysis fundamental manufacturing specifications that determine the garment's fit or functionality—such as key physical characteristics like specific fabric blend ratios or precise stitching densities applied differently to various body parts. Consequently, recommended products frequently fail to satisfy the subtle and complex comfort needs of actual users. Second, prior technologies were limited to recommending already produced products, failing to establish a virtuous cycle that analyzes the fundamental causes of a product's success or failure in the market based on data and incorporates the results into the design and development process of next-generation products. In other words, the disconnect between the design, manufacturing, sales, and feedback processes made it difficult to achieve continuous, data-driven product improvement and innovation. Therefore, there is a need for a new level of system that can objectively evaluate product value by integrally analyzing the intrinsic physical characteristics of clothing and actual market responses, and organically utilize this for new product development and sophisticated personalized recommendations. Figure 1 illustrates an overall relationship diagram according to the present invention. Figure 2 illustrates a flowchart between components according to the present invention. Figure 3 illustrates a flowchart of a method for generating a wear comfort index according to the present invention. Figure 4 illustrates a flowchart of a method for generating a compression-support index by region according to the present invention. Figure 5 illustrates a flowchart of a method for generating a comprehensive product optimization score according to the present invention. Hereinafter, various embodiments are described in more detail with reference to the attached drawings. The embodiments described in this specification may be modified in various ways. Specific embodiments may be depicted in the drawings and described in detail in the detailed description. However, specific embodiments disclosed in the attached drawings are intended only to facilitate understanding of various embodiments. Accordingly, the technical concept is not limited by specific embodiments disclosed in the attached drawings, and it should be understood that it includes all equivalents or substitutions that fall within the spirit and scope of the invention. Terms including ordinal numbers, such as first, second, etc., may be used to describe various components, but these components are not limited by the aforementioned terms. The aforementioned terms are used solely for the purpose of distinguishing one component from another. Functions related to artificial intelligence according to the present disclosure are operated through a processor and memory. The processor may be composed of one or more processors. In this case, the one or more processors may be general-purpose processors such as CPUs, APs, and DSPs (Digital Signal Processors), graphics-dedicated processors such as GPUs and VPUs (Vision Processing Units), or artificial intelligence-dedicated processors such as NPUs. The one or more processors control the processing of input data according to predefined operation rules or artificial intelligence models stored in memory. Alternatively, if the one or more processors are artificial intelligence-dedicated processors, the artificial intelligence-dedicated processors may be designed with a hardware structure specialized for processing a specific artificial intelligence model. The predefined rules of operation or artificial intelligence models are characterized by being created through lea