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

Personalized recommended method based on picture under social network and system thereof

A technology of social network and recommendation method, applied in the field of graph-based personalized recommendation method and its system, which can solve problems such as dependence on document form and inappropriateness

Inactive Publication Date: 2011-01-12
PEKING UNIV
View PDF0 Cites 50 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The content-based recommendation method is the earliest recommendation method. Recommendations are made based on the similarity between the document content and the user's interests. A big disadvantage of this method is that it depends on the form of the document. If it is a resource such as video news, there is no way to express it. This method is not suitable for

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 recommended method based on picture under social network and system thereof
  • Personalized recommended method based on picture under social network and system thereof
  • Personalized recommended method based on picture under social network and system thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] In order to make the above objects, features and advantages of the present invention more comprehensible, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0023] refer to figure 1 , figure 1 It is a flow chart of the steps of the graph-based personalized recommendation method under the social network of the present invention, and the method includes the following steps after obtaining the user's rating information and labeling information on resources:

[0024] The information acquisition step 110 is to obtain the user's rating information and labeling information on resources; the similarity calculation step 120 is to calculate the similarity between users and users based on the labeling information; the social network undirected graph construction step 130 is based on The score information, the similarity between the user and the user construct a weighted social network undirecte...

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 recommended method based on a picture under a social network and a system thereof. The method comprises: obtaining scoring information and label marking information to resource of users; based on the label marking information, calculating similarity between the users; based on the marking information and the similarity between the users, building a weighted social network undirected graph; determining the probability from a vertex to be recommended in the social network undirected graph to each reset vertex by a random walk method; sorting the vertex of a representative item in the vertexes according to the probability; and according to the sorting, generating the personalized recommended item list. The invention can accurately provide the personalized recommendation relevant to user preferences to different users by introducing the similarity.

Description

technical field [0001] The invention relates to the technical field of knowledge mining, in particular to a graph-based personalized recommendation method and system thereof under social networks. Background technique [0002] Social network is an important part of web2.0. If the meaning of the Internet is to connect computers together, then the purpose of social networks is to connect people together. Traditional e-commerce, network media and other systems are also gradually moving towards social network structures. Traditional websites began to support users to establish friendships, including direct selection of trusted friends, or individualized labeling of items. Users on Taobao can share their favorite products with friends, and can also tag the products they like, so that more people can find this product through this tag. Sharing and passing among friends has become a new medium of data dissemination. How to use the relationship between people in social networks ...

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): G06Q30/00G06F17/30
Inventor 张铭王子琪
Owner PEKING UNIV
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