Recommend system solution method for fusing social information

A technology of social information and recommendation system, applied in the field of personalized recommendation, it can solve the problems of long time and reduced user experience, and achieve the effect of improving the accuracy of recommendation

Inactive Publication Date: 2017-02-08
TIANJIN UNIV
View PDF0 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Users spend more and more time choosing the information or products they want, which leads to a decrease in user experience

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
  • Recommend system solution method for fusing social information
  • Recommend system solution method for fusing social information
  • Recommend system solution method for fusing social information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] The basic idea of ​​the present invention is: in the entire recommendation system, for a specific user i, there may be very little rating data on commodities, and if the user is a new user, it is impossible to effectively make recommendations based on historical rating data . Therefore, social network information is added to the recommendation system, so that the available data sources are not only the user's rating data on the product, but also the user's personal information, social network (friends, personal dynamics, recent attention, etc.) information. Through the information accumulated in the social network, a more comprehensive and detailed feature extraction is performed on the user, and the feature correction of the target user is performed through the extracted user social network feature. And the historical score data of the user's friends is introduced as the reference data for product recommendation to the user. The present invention will be further descr...

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 present invention relates to a recommend system solution method for fusing social information. The method comprises: selecting the users' scores for goods in a period of time, and taking the users' scores for goods, the user friend relation information and the user own features as a data set; performing statistics of the number of all the users and all the goods, constructing the user-goods real score matrix, selecting the part of score data at will and taking the score data as a training set, and constructing a user friend matrix and a user owner feature matrix; calculating the similarity between the users and the friends; employing a latent semantic model, generating the user feature matrix and the goods feature matrix, and obtaining a predicated score through multiplying the matrix; and calculating the root-mean-square error (RMSE) between the predicated score and the real score, and adding the similarity between the users to take as the weight of the social information for the error. The gradient descent algorithm is employed to perform iteration updating of the user features and the goods. The new user's recommend accuracy can be effectively improved.

Description

technical field [0001] The invention relates to a personalized recommendation technology, in particular to a recommendation system method for fusing social information. Background technique [0002] With the rapid development of the Internet, the resulting data is also increasing exponentially. Users spend more and more time choosing the information or products they want, which leads to a decrease in user experience. For information overload, there are currently two solutions: search and personalized recommendation. [0003] The personalized recommendation system is based on the user's historical behavior and purchase records and other information to construct personalized user characteristics and commodity characteristics for specific users. Screen products based on user characteristics and recommend products that are similar to user characteristics. At present, personalized recommendation systems have been widely used in various fields of the Internet, such as Amazon's ...

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): G06Q30/06G06Q30/02
CPCG06Q30/0631G06Q30/0201
Inventor 成石王宝亮毛陆虹常鹏
Owner TIANJIN 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