Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Mobile Internet user access mode representing and clustering method

A mobile Internet and user technology, applied in the Internet field, can solve problems such as large errors and unrealistic problems, and achieve the effects of increasing speed, high commercial value, and reducing costs

Inactive Publication Date: 2018-03-20
BEIJING UNIV OF POSTS & TELECOMM +1
View PDF6 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since there are hundreds of millions of users, it is unrealistic to use manual methods for clustering
It is difficult to cover everything by using simple rule classification made manually, and the error is large

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
  • Mobile Internet user access mode representing and clustering method
  • Mobile Internet user access mode representing and clustering method
  • Mobile Internet user access mode representing and clustering method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] In order to further understand the present invention, the present invention will be further introduced below in combination with implementation cases and implementation procedures. The following introduction is only an example of the method of the present invention, and does not mean that the present invention is only applicable to one situation of this example. On the contrary, the method described in the present invention can also be used in Internet user clustering tasks in different scenarios.

[0038] attached Figure 1 It is the overall flowchart of the present invention's implementation, and is the overall framework of the present invention's realization. It is introduced as follows in conjunction with specific examples below:

[0039] In step 101, the present invention first realizes the acquisition of domain name access sequences of mobile Internet users.

[0040] In this example, use the user domain name provided by the operator to access the recorded data. ...

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 provides a mobile Internet user access mode representing and clustering method. The method comprises that a domain name access sequence of mobile Internet users is acquired; preprocessing is performed on the mobile Internet domain name user access sequence, and training data and actual data of a preset data type are generated; a vector representation training module performs trainingon a training data set by using an algorithm; a user vector generation module performs generation calculation on the actual data by using a training model acquired by the training algorithm; APP domain name classification rules are set, and manual classification is performed according to belonging fields and purposes of domain names in the domain name access sequence; and a user vector clusteringmodule performs clustering and analysis on users by using an acquired user vector. The mobile Internet user clustering method provided by the invention is based on domain name access sequence data ofthe users, clustering for the users is achieved, and behavioral habits and characteristics of the users are extracted.

Description

technical field [0001] The invention relates to the technical field of the Internet, in particular to a mobile Internet user access pattern characterization and clustering method. Background technique [0002] Based on the doc2vec algorithm, it is applied to the clustering of mobile Internet users. The doc2vec algorithm was proposed for use in the field of natural language processing. It is an improvement based on the word2vec algorithm. With the wide application of natural language processing technology, the application scenarios of the doc2vec algorithm are also constantly being expanded. For the access records of mobile Internet users, a user identifier can be regarded as a paragraph identifier, and a specific domain name access sequence can be regarded as a sequence of words arranged in order, so that the The doc2vec algorithm is applied to the vector representation of mobile Internet users, and further user clustering and feature extraction can be performed based on ...

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): G06K9/62G06F17/30
CPCG06F16/951G06F18/23213
Inventor 吴晓非禹可李苒江万
Owner BEIJING UNIV OF POSTS & TELECOMM
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
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