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

Matrix decomposition recommendation algorithm fusing multi-dimensional social information

A matrix factorization and social information technology, applied in the field of matrix factorization recommendation algorithms, can solve problems such as incomplete social information, achieve diverse recommendations, realize personalized recommendations, and improve data sparsity and cold start problems.

Pending Publication Date: 2022-08-05
中电万维信息技术有限责任公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Obviously, the social information established with only one social relationship is not complete

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
  • Matrix decomposition recommendation algorithm fusing multi-dimensional social information
  • Matrix decomposition recommendation algorithm fusing multi-dimensional social information
  • Matrix decomposition recommendation algorithm fusing multi-dimensional social information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The MFDSI algorithm proposed by the present invention is mainly divided into three steps: (1) Based on the user item score and trust relationship data set, establish the direct social relationship, indirect social relationship and time-weighted interest relationship between users, and combine the three It adopts multi-layer network fusion representation. (2) According to the structural characteristics of the interaction between users, the global similarity and local similarity of users in the multi-layer network are established. (3) Combining global and local similarity with matrix factorization to obtain user's recommendation list.

[0043] 1 Using a multi-layer network to represent various relationships between users

[0044] In the matrix decomposition recommendation literature involving social information, the social relationship between users is represented by a single-layer social network, and the social relationship between users is summarized as direct relation...

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 relates to the technical field of data processing, in particular to a matrix decomposition recommendation algorithm fusing multi-dimensional social information. And fusing and representing different social relations of the plurality of single-layer networks by using the multi-layer network. Then, according to the characteristics of the multi-layer network, the global similarity and the local similarity between the users are established; and finally, combining the global and local similarities with matrix decomposition to obtain a recommendation list of the user. In the multi-layer network, different layers correspond to different social relations, the same community is in different layers, and user preferences are similar, so that the problems of data sparsity and cold start can be improved, and diversified recommendation and personalized recommendation can be realized.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a matrix decomposition recommendation algorithm integrating multi-dimensional social information. Background technique [0002] With the advent of the era of big data, the exponential growth of network data has caused the problem of information overload. In order to obtain valuable information and meet the personalized needs of users, recommender systems are proposed. Among many recommendation models, matrix factorization has become the preferred model for a large number of researchers to build recommendation systems due to its simplicity, easy expansion, and high recommendation accuracy. Since the matrix factorization recommendation system only uses a single data source of user ratings for items, it is easy to cause a series of problems such as low recommendation efficiency and cold start. Therefore, relevant researchers introduce additional information, such as implic...

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): G06Q30/06G06Q50/00G06F16/9536
CPCG06Q30/0631G06Q50/01G06F16/9536
Inventor 田毅张秀娟王珂许建雯刘凡刘鹏涛
Owner 中电万维信息技术有限责任公司
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