Unlock instant, AI-driven research and patent intelligence for your innovation.

Garment matching recommendation method based on graph model

A recommendation method and graph model technology, applied in neural learning methods, biological neural network models, design optimization/simulation, etc.

Pending Publication Date: 2022-08-09
ZHENGZHOU UNIVERSITY OF LIGHT INDUSTRY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Then, factors such as the price factor of clothing, the emotional tendency of other people wearing it, the user's own preferences, and the attendance scene that matches the clothing are factors that have not been comprehensively considered in previous research.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Garment matching recommendation method based on graph model
  • Garment matching recommendation method based on graph model
  • Garment matching recommendation method based on graph model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0071] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a 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 those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0072] refer to Figure 1-3 , the present invention provides a method for recommending clothing matching based on a graph model, comprising the following steps:

[0073] Step 1: Collect multiple sets of clothing data. Select a complete set of clothing data of different genders, ages, occupations, skin colors, and different scenarios that have been matched. For example, a complete set of clothing includes a single piece of clothing su...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a clothes matching recommendation method based on a graph model, and relates to the technical field of clothes matching recommendation, and the method comprises the following steps: collecting a plurality of groups of clothes data; preprocessing the multiple groups of costume data, and converting numeric numbers, texts, pictures and the like in the costume data into structured data to obtain a data set; constructing a costume matching graph model according to the data set; constructing a plurality of feature models according to the graph model; carrying out weighted combination on the plurality of feature models and establishing a multi-modal scoring model; parameters in the multi-modal scoring model are trained through a deep learning optimization algorithm, a recommendation model is output, and costume matching prediction is carried out according to the recommendation model. The method can recommend clothes matching schemes suitable for styles and colors for the user to select according to the image, temperament, attendance occasions, wearing preferences and the like of the wearer.

Description

technical field [0001] The invention relates to the technical field of clothing matching recommendation, in particular to a method for recommending clothing matching based on a graph model. Background technique [0002] Clothing is inseparable from people's lives. With the development of the modern clothing industry, there are countless types and brands of clothing, which leads to the rapid growth of clothing data. However, the massive clothing data also increases the user's demand for retrieval and matching. A suitable outfit can enhance a person's beauty and display personality. However, not everyone has a strong fashion sense. "How do I wear a suitable and beautiful outfit to a party?" has become a daily headache for many people. Not only does it encompass a clear concept of fashion compatibility that requires an understanding of the complex interplay between human creativity and fashion expertise, but it also takes into account the impact of economic factors on clothin...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F30/27G06N3/04G06N3/08
CPCG06F30/27G06N3/08G06N3/045Y02P90/30
Inventor 尚松涛史雯隽陶红伟李祖贺韩继辉
Owner ZHENGZHOU UNIVERSITY OF LIGHT INDUSTRY