A friend recommendation method and device

A friend recommendation and friend technology, applied in the Internet field, can solve the problems of low friend accuracy and single influencing factors, and achieve the effects of comprehensive coverage, comprehensive reference data, and improved accuracy

Active Publication Date: 2017-12-01
TENCENT TECH (SHENZHEN) CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the embodiments of the present invention is to provide a method for recommending friends to solve the problem in the prior art that the influencing factors considered when recommending friends are relatively single, making the accuracy of the recommended friends not high

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
  • A friend recommendation method and device
  • A friend recommendation method and device
  • A friend recommendation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0026] figure 1 The implementation flow of a friend recommendation method provided by the first embodiment of the present invention is shown, and the details are as follows:

[0027] In step S101, the user's data information is acquired, and the user's data information includes the user's personal attribute information and social network topology information.

[0028] The acquisition of the user's data information can be obtained by obtaining data such as the user's personal information, personal page, or user's offline chat records, including the user's age, gender, home address, work address, interest, occupation, etc. in the personal information, and also It can be obtained by obtaining the evaluation information of the user's friends on the user, etc.; the personal page can include the interactive information of the friends, and the interactive information of the friends includes the message content of other users on the page, the reply content to the message, and the numb...

Embodiment 2

[0045] figure 2 The implementation process of the friend recommendation method provided by the second embodiment of the present invention is shown, and the details are as follows:

[0046] In step S201, the user's data information is acquired, and the user's data information includes the user's personal attribute information and social network topology information.

[0047] Wherein, optionally, the user's social network topology information includes one or more of the following: the type of circle to which the user and the candidate recommended friend belong, the number of people in the circle, whether the user adds a new friend, whether the candidate recommended friend is The number of friends in the group newly added by the user, and the number of common friends between the user and the candidate recommended friends.

[0048] Optionally, the personal attribute information of the user includes one or more of the following: whether the gender of the user and the candidate re...

Embodiment 3

[0079] image 3 A schematic structural diagram of a device for recommending friends provided by the third embodiment of the present invention is shown, and details are as follows:

[0080] The device for recommending friends in the embodiments of the present invention includes:

[0081] The acquiring unit 301 is configured to acquire data information of the user, the data information of the user includes the user's personal attribute information and social network topology information;

[0082] A feature vector determining unit 302, configured to determine, according to the user's data information, a candidate recommended friend of the user and a feature vector of the candidate recommended friend, the feature vector including quantitative information of the user's personal attributes and social network Quantitative information on topology;

[0083] The score calculation unit 303 is used to calculate the score corresponding to the feature vector according to the neural networ...

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 is applicable to the Internet field, and provides a method and device for friend recommendation. The method includes: acquiring data information of a user; The feature vector of the friend, the feature vector includes the quantitative information of the user's personal attributes and the quantitative information of the social network topology; according to the model obtained in advance training, the score corresponding to the feature vector is calculated, and the score ranking of the user's friends is obtained ; According to the calculated score ranking of the user's friends, recommend friends to the user. In the embodiment of the present invention, the recommended reference data is more comprehensive by integrating the user's personal attribute information and topological network structure information. In addition, the user's personal data information is used to determine candidate recommended friends, so that the coverage of the recommended friends is more comprehensive, and the accuracy of the user's friend recommendation can be significantly improved.

Description

technical field [0001] The invention belongs to the field of the Internet, and in particular relates to a friend recommendation method and device. Background technique [0002] With the rapid development of social networks, the user base in social networks is also growing. For the needs of users to communicate and communicate, social network systems often recommend friends who may be interested. [0003] In the existing friend recommendation method, the general steps include: determining the candidate groups that the user may be interested in, sorting the candidate groups, and preferentially recommending the highest-ranked candidate groups to the user. Wherein, the method for sorting the candidate groups includes: sorting based on the number of common friends and sorting based on user attributes. [0004] The existing friend recommendation method can intelligently recommend friends who may be interested in for the user. However, since the influencing factors considered in ...

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 Patents(China)
IPC IPC(8): H04L12/58
Inventor 余建兴易玲玲贺鹏陈川
Owner TENCENT TECH (SHENZHEN) CO LTD
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