Recommendation method based on improved PageRank and comprehensive impact

A recommended method and influential technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve the problems of insufficient refinement and scientificity of indicators, and achieve avoidance of omission, accuracy and high reliability Effect

Active Publication Date: 2019-01-25
HANGZHOU DIANZI UNIV
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional PageRank lacks this part. Existing previous studies have proposed the idea of ​​adding influence indicators. Some researchers directly select specific big V users for research, which is obviously a bit too general; some researchers set several measures Indicators, but the indicators are not detailed and scientific enough, so the impact indicators need to be evaluated more comprehensively

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
  • Recommendation method based on improved PageRank and comprehensive impact
  • Recommendation method based on improved PageRank and comprehensive impact
  • Recommendation method based on improved PageRank and comprehensive impact

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The user recommendation method based on the improved version of the directed graph PageRank and the comprehensive assessment of microblog influence provided by the present invention is mainly divided into four steps:

[0047] (1) The Python crawler crawls the Sina Weibo dataset; (2) The directed graph model is established on the basis of the attention relationship and interaction relationship through the dataset; (3) The weighted probability transfer matrix is ​​obtained by adding the comprehensive index evaluation matrix; ( 4) Markov iterative convergence to obtain the final PR value and perform Top-N recommendation.

[0048] (1) Python crawler crawls Sina Weibo dataset

[0049] The Python crawler crawls about 2,000 users on Sina Weibo and the hundreds of thousands of fans derived from it, as well as the following user data set. This module needs to crawl four data tables: ①User_info table (user information table) ②Follows table (user attention table )③Followers (fan ...

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 recommendation method based on directed graph improved PageRank and comprehensively evaluating microblog impact. The method comprises the following steps: (1) a Python crawler crawling a Sina microblog data set; (2) building a directed graph model based on the relationship of interest and interaction through data set; 3) adding a comprehensive index evaluation matrix to obtain a weighted probability transfer matrix; (4) performing Markov iterative convergence to get the final PR value and Top-N Recommendation. Compared with the traditional method, the method of the invention can effectively avoid the limitation and inaccuracy caused by paying attention to the relationship modeling only, or the evaluation index is too single, and realize the determination of the influential user with more accuracy and higher reliability in the data range.

Description

technical field [0001] The invention belongs to the technical field of social media user recommendation, and in particular relates to a user recommendation method based on an improved version of PageRank of a directed graph and a comprehensive evaluation of microblog influence. Background technique [0002] Microblog has become the most popular mass information dissemination medium nowadays, users can easily complete various information acquisition, production, sharing and dissemination through the microblog platform. Another great charm of Weibo is that you can meet more friends in this virtual network. Taking Sina Weibo as an example, users can find like-minded users through the system-recommended users in the "People You May Be Interested in" module. people. But in fact, the existing Weibo does not recommend users who really have influence on Weibo. Most of the recommended users are salesmen or micro-businesses, and people are less likely to really start paying attention...

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): G06F16/9535G06Q50/00
CPCG06Q50/01
Inventor 黄彬彬何馥芸沈艳婷杨泽彬
Owner HANGZHOU DIANZI 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