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

Audience portrait forming method based on text mining

A text mining and portrait technology, which is applied in the field of underweight group portraits based on text mining, can solve the problems of unknown attributes that cannot be identified and mined, and achieve the effect of wide commercial application value and expanded application scope.

Inactive Publication Date: 2018-03-06
CHENGDU JINCHUANTIAN AGRI MACHINE MFG
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, there are the following defects: the existing technical solutions require a known user sample, and then perform machine learning through the behavior preferences of the user sample to analyze the user attributes of unknown users. The analysis of user attributes can only analyze the sample user attributes. Known attributes, unknown attributes cannot be identified and mined

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
  • Audience portrait forming method based on text mining
  • Audience portrait forming method based on text mining
  • Audience portrait forming method based on text mining

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] A text mining-based portrait method for heavy-weight groups includes first, text mining, and second, official account portraits.

[0041] 1. Text Mining

[0042] 1-1: Create a label master corpus, such as figure 1 as shown,

[0043] Step 1: Extract article samples, clean the samples, and clean out audio, video and pictures;

[0044] Step 2: Manual classification according to the tag class library;

[0045] Step 3: Perform dynamic clustering and fuzzy clustering on samples at the same time, and set cluster parameters;

[0046] Step 4: Perform semantic analysis, cluster feature analysis, modify cluster parameters, and density noise reduction in sequence to obtain the noise value M;

[0047] Step 5: Compare the noise value M with the threshold a, if the noise value M is less than the threshold a, go to step 6, if the noise value M is greater than or equal to the threshold a, go to step 3;

[0048] Step 6: Then perform model clustering, semantic analysis, class feature...

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 an audience portrait forming method based on text mining. The method includes the steps of text mining and public account portrait forming; by forming public account portraits with a tag corpus, the browse sample article attribute of each user can be formed, the weight of each preference class can be analyzed, and thus the user attribute of each user can be recognized, analyzed and mined.

Description

technical field [0001] The invention belongs to the field of Internet data mining, and in particular relates to a text mining-based portrait method for heavy-weight groups. Background technique [0002] China's Internet has formed a scale, and Internet applications are becoming more diversified. The Internet is changing people's study, work and lifestyle more and more profoundly. In network data analysis, being able to accurately know official account portraits and identify user attributes is an important prerequisite for accurate content promotion or advertising. At present, the existing technical solutions for identifying user attributes in the Internet are all based on user article samples. It is necessary to first collect a full amount of historical samples of users, sort out the data of sample users, sort out the sample database, and classify the sample database as a tag corpus. For example, a certain A corpus represents content such as "shopping", "fashion", "apparel...

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): G06F17/30G06F17/27
CPCG06F16/35G06F16/9535G06F40/289G06F40/30
Inventor 张钉
Owner CHENGDU JINCHUANTIAN AGRI MACHINE MFG
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

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