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

Personalized recommendation method based on generative adversarial network

A recommendation method and generative technology, applied in the field of recommendation based on deep learning, to achieve the effect of effective preference, good purchase situation, and model stability

Active Publication Date: 2021-10-15
ANHUI AGRICULTURAL UNIVERSITY
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to provide a personalized recommendation method based on a generative confrontation network to solve the problems existing in the deep learning of the prior art when implementing product recommendation

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
  • Personalized recommendation method based on generative adversarial network
  • Personalized recommendation method based on generative adversarial network
  • Personalized recommendation method based on generative adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0023] The present invention is a personalized recommendation method based on a generative confrontation network, which utilizes users' comments on items to obtain specific purchases of items by users, and then uses encoders to capture user preferences for items in combination with the origin of the items and random variables. Use the decoder to predict what the user will buy. Using the predicted items that the user will purchase, the user's purchase of the item and the place of origin of the item, the discriminator constructed by the fully connected layer is used to judge the authenticity of the predicted item that the user will purchase. Finally, calculate the correlation coefficient between the items predicted to be purchased by the user and the real items, and select the item with the highest correlation coefficient for recommendation.

[0024] Suc...

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 personalized recommendation method based on a generative adversarial network, and the method comprises the steps of obtaining the specific purchase condition of a user for an article through employing the comment condition of the user for the article, capturing the preference of the user for the article through employing an encoder in combination with the production place of the article and a random variable, and predicting the article to be purchased by the user through employing a decoder; judging the authenticity of the predicted article to be purchased by the user by using a discriminator constructed by a full connection layer according to the predicted article to be purchased by the user, the purchase condition of the article by the user and the place of origin of the article; and finally, calculating and predicting correlation coefficients between articles to be purchased by the user and real articles, and selecting the article with the highest correlation coefficient for recommendation.

Description

technical field [0001] The invention relates to the field of recommendation methods based on deep learning, in particular to a personalized recommendation method based on a generative confrontation network. Background technique [0002] With the continuous development of information technology, the data on the network has shown an explosive growth. It is difficult for people to extract the information they need from the massive information, and it is impossible to judge the authenticity of the information. In order to solve the problem of information overload, personalized recommendation technology has emerged. Its main idea is to help users obtain information that they may be interested in in a timely manner, which has the characteristics of "thousands of people and thousands of faces". The recommendation system not only solves the problem that users are difficult to choose, but also can discover the potential needs of users by analyzing the characteristics of users' behavi...

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): G06Q30/02G06N3/04G06N3/08
CPCG06Q30/0255G06Q30/0251G06N3/08G06N3/048G06N3/045Y02T10/40
Inventor 吴国栋杨宇刘玉良汪菁瑶范维成毕海娇朱文涛
Owner ANHUI AGRICULTURAL UNIVERSITY
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