Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Fashionable clothing intelligent matching and recommending method based on visual combination relation learning

A combination relationship and recommendation method technology, applied in the field of artificial intelligence, can solve the problems of inability to process new clothing products, inability to intelligently understand user clothing matching intentions and scenarios, and high cost

Active Publication Date: 2020-07-10
UNIV OF SCI & TECH OF CHINA
View PDF8 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Most of the traditional methods are based on the generation and recommendation of clothing collocation schemes based on expert experience, but this method relies too much on human experience and data labeling (each time requires experts to assist in recommendation), and the cost is very high. The processing of new clothing products can only complete the reproduction of the original clothing scheme, and cannot intelligently understand the user's clothing matching intention and scene

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
  • Fashionable clothing intelligent matching and recommending method based on visual combination relation learning
  • Fashionable clothing intelligent matching and recommending method based on visual combination relation learning
  • Fashionable clothing intelligent matching and recommending method based on visual combination relation learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0022] For the training samples, the overall representation vector is extracted through the pre-built neural network model. Based on the neural network, the model uses computer vision technology to intelligently analyze clothing image information, extract clothing aesthetic features, and further model the interrelationship between clothing collocations. With visual consistency, etc., mining the visual correlation of clothing collocation and the complementary compatibility of categories, the preferred implementation method is as follows:

[0023] 1) Extract the visual information of each garment.

[0024] According to the information obtained in step 1, it is first necessary to extract visual information from clothing pictures, that is, to convert the pictures into feature vectors that can be recognized, understood and calculated by the computer.

[0025] In the embodiment of the present invention, the visual representation vector x of clothing is obtained through a pre-trained...

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 fashionable garment intelligent matching and recommending method based on visual combination relation learning. According to the method, aiming at extraction of clothing visual information and modeling of multi-clothing visual compatibility and a mutual influence relationship, clothing can be intelligently matched, matching scores among the clothing are obtained, matchingcategory analysis is further assisted, missing parts in current matching can be intelligently identified, and missing single items are subjected to targeted prediction; through a model training and optimization strategy, the model can learn expert experience in a self-adaptive manner, and can intelligently generate beautiful clothes matching for a user.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to an intelligent matching and recommendation method for fashion clothing based on visual combination relationship learning. Background technique [0002] Clothing is an indispensable part of people's daily life. A good set of clothing can not only improve the user's self-confidence, but also feedback the user's personality preference to a certain extent. However, in daily life, most people can match a suitable and beautiful outfit, especially for those who have no sense of beauty and related experience. At the same time, based on the learning of clothing matching relationships, it can further help the recommendation system to better recommend clothing matching solutions for users. [0003] Most of the traditional methods are based on the generation and recommendation of clothing collocation schemes based on expert experience, but this method relies too much on huma...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/535G06F16/583G06N3/04G06N3/08
CPCG06F16/535G06F16/583G06N3/08G06N3/045Y02P90/30
Inventor 陈恩红刘淇李徵吴李康侯旻
Owner UNIV OF SCI & TECH OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com