Personalized recommendation system based on deep learning under social network

A social network and recommendation system technology, applied in the field of personalized recommendation system, can solve problems such as cold start of recommendation system, poor quality of recommendation system recommendation, failure of recommendation system to give good recommendation results, etc., to solve cold start problem and improve The effect of recommending accuracy and reducing time overhead

Active Publication Date: 2017-09-08
TONGJI UNIV
View PDF4 Cites 35 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At the same time, when a new user logs in to an e-commerce service platform based on a social network, the recommendation system cannot give good recommendation results due to the lack of background or interest data related to the new user. This is the recommendation system in

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 system based on deep learning under social network
  • Personalized recommendation system based on deep learning under social network
  • Personalized recommendation system based on deep learning under social network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] Based on the technical solutions of the present invention, detailed embodiments are given below in conjunction with the accompanying drawings.

[0027] The specific implementation of step 1 (training sample set generation) in the offline learning module is as follows:

[0028] The present invention randomly selects 5000 existing users in the recommendation system, and for each user u i (1≤i≤5000), select u i recently purchased a i items and never purchased b i items, where a i The value of is 1 / 2 of the quantity of all items purchased by u, b i The value is a i 20 times of b i =20×a i , so as to get "user-item" pairs.

[0029] For each "user-item" pair (u, g), the present invention first obtains u's user feature list C(u), including: (1) u's demographic features u.D registered in the recommendation system, including age, Address, gender, occupation, income, education level, marriage, whether there are children, (2) u’s social network characteristics u.S, incl...

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 system based on deep learning under a social network. The system mainly comprises an offline learning module and an online recommendation module. The offline learning module firstly generates a training sample seat to construct a deep convolutional neural network learning module with an attention mechanism and carries out iterative optimization on parameters in the learning module; and the online recommendation module carries out real-time item recommendation on a newly-registered user based on the learning model obtained through training. Compared with the prior art, the system has the advantages of high accuracy, fast speed and simplicity and easiness in implementation and can be effectively applied to the fields, such as electronic commerce, public opinion monitoring, intelligent transportation and medical treatment and health.

Description

technical field [0001] The invention relates to the technical field of information recommendation, in particular to a deep learning-based personalized recommendation system under social networks. Background technique [0002] The informal concept of the recommendation system is the definition given by Resnick and Varian in 1997: "It uses e-commerce websites to provide customers with product information and suggestions, and helps users decide what products to buy, and simulates salespeople to help guide The process by which a user completes an online purchase". [0003] The recommendation system can dig out the user's potential favorite content, reduce the interference of useless information on the user, and enable the user to quickly find the products they want to buy, the news they are interested in, and potential friends on the Internet. And these recommendation results are dynamic, because the user's interest changes with time and scene changes, the final recommendation ...

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): G06F17/30G06Q50/00
CPCG06F16/9535G06Q50/01
Inventor 黄震华程久军孙剑向阳
Owner TONGJI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap