Method and system for identifying same user among different platforms

A user and platform technology, applied in character and pattern recognition, data processing applications, special data processing applications, etc., can solve the problems of uncommon accounts, difficult to judge whether two Weibo belong to the same user, etc., to achieve good development, high The effect of accuracy

Inactive Publication Date: 2015-12-23
ZHANGJIAGANG INST OF IND TECH SOOCHOW UNIV
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] In recent years, with the rapid development of the Internet, many Internet-connected applications are favored by users, and Internet-connected applications generally require users to log in, such as Weibo (Micro-blog), Twitter, Facebook, etc., Sina

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
  • Method and system for identifying same user among different platforms
  • Method and system for identifying same user among different platforms
  • Method and system for identifying same user among different platforms

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0040] Example one:

[0041] This embodiment provides a method for identifying the same user between different platforms, figure 1 The flowchart of this embodiment is shown, including:

[0042] Step S101: Collect a preset number of text information published by users on the first platform and the second platform;

[0043] Specify two platforms, such as Sina Weibo and Tencent Weibo, to collect a preset number of text messages posted by users of the two Weibo platforms. The specific collection process is as follows:

[0044] Step S201: construct a user queue;

[0045] Step S202: Select a user as a seed user and add it to the user queue;

[0046] Step S203: Take out a user from the user queue, grab the user profile information and published text information through the API provided by Weibo. The user profile information includes the followed user and the followed user, and the following Users and followed users are added to the user queue;

[0047] Step S204: Repeat the process of capturing...

Example Embodiment

[0062] Embodiment two:

[0063] This embodiment provides a system for identifying the same user between different platforms, figure 2 Shows a schematic structural diagram of this embodiment, including:

[0064] The collection module 101 is configured to collect a preset number of text information published by users on the first platform and the second platform;

[0065] The marking module 102 is used to mark a part of the text information;

[0066] The first sample acquisition module 103 is configured to use the labeled text information in the text information as a labeled sample, and use the unlabeled text information in the text information as a sample to be tested;

[0067] The second sample acquisition module 104 is configured to use the LDA model to extract topic features from the labeled samples and the samples to be tested, respectively perform cosine similarity calculations on the extracted topic features, and use the obtained similarity values ​​as training samples respectivel...

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 discloses a method and a system for identifying the same user among different platforms. The method comprises: collecting text information published by a user in two different platforms; labeling one part of the text information; using the labelled text information as labeled samples, using unlabeled text information as samples to be tested; respectively extracting topic features from the labeled sample and the sample to be tested by using an LDA model; respectively performing cosine similarity calculation on the extracted topic features; respectively using the obtained similarity values as training samples and test samples; training the training samples to obtain a classifier model by a using preset algorithm; classifying the test samples by using the classifier model; and determining if users corresponding to the test samples in the two different platforms are the same user. According to the method, users in two different platforms can be identified whether to be the same user or not by a text published by the user, and under the condition of the limited training samples, a higher accuracy rate is reached.

Description

technical field [0001] The invention relates to the field of natural language processing, in particular to a method and system for identifying the same user between different platforms. Background technique [0002] In recent years, with the rapid development of the Internet, many Internet-connected applications are favored by users, and Internet-connected applications generally require users to log in, such as Weibo (Micro-blog), Twitter, Facebook, etc., Sina Micro-blog, etc. Bo and Tencent Weibo are well-known microblog websites in China, but the accounts of different microblog websites are not common, and it is currently difficult to judge whether two microblogs of different microblog websites belong to the same user. Contents of the invention [0003] In view of this, the main purpose of the present invention is to provide a method and system for identifying the same user between different platforms, which can effectively identify whether users under two different plat...

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
IPC IPC(8): G06F17/30G06F17/27G06Q50/00G06K9/62
CPCG06F16/951G06Q50/01G06F40/205G06F18/2411
Inventor 李寿山王晶晶周国栋
Owner ZHANGJIAGANG INST OF IND TECH SOOCHOW 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