Theme category analysis method based on focus attention

An analysis method and theme technology, applied in the field of big data, to achieve a good classification effect

Active Publication Date: 2019-09-20
成都冰鉴信息科技有限公司
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a subject category analysis method based on focus attention, to sol

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
  • Theme category analysis method based on focus attention
  • Theme category analysis method based on focus attention
  • Theme category analysis method based on focus attention

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] It is found through observation that when the subject boundary is blurred, keywords in the text play a decisive role in judging the subject category. Therefore, the present invention proposes a subject category analysis method based on focus attention.

[0045] Such as Figure 1-Figure 2 Shown is a subject category analysis method based on focus attention, including the following steps:

[0046] Step 1: Establish a client server and a central server, the client server is used to obtain the original text, and the client server communicates with the central server through the Internet;

[0047] Establish data preprocessing module, vector learning module, feature extraction module, attention calculation module, pooling module,

[0048] Step 2: The central server obtains the original text in the client server, and cleans and filters it through the data preprocessing module to generate preprocessed text. The specific steps are as follows:

[0049] Step A1: Obtain the text ...

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 topic category analysis method based on focus attention, which belongs to the technical field of big data. The method comprises the following steps that: a client server and a central server are established, the client server is used for acquiring an original text, and the client server is communicated with the central server through the Internet; and a data preprocessing module, a vector learning module, a feature extraction module, an attention calculation module and a pooling module are established in the central server. The technical problem of secondary topic division under the condition that topic feature differences are not obvious is solved. The local cyclic convolutional network provided by the invention not only can learn the word relationship between the text sequences, but also can extract the keywords and corresponding position information in the text, and a topic category analysis method based on focus attention is adopted, so that a good classification effect can still be obtained when the topic feature difference is not obvious.

Description

technical field [0001] The invention belongs to the technical field of big data, and in particular relates to a subject category analysis method based on focus. Background technique [0002] With the continuous increase of news data on the Internet, how to correctly classify news data according to its subject is particularly important for people to browse and search. At present, topic classification technology is widely used in the commercial field. When people browse news, they first filter according to categories, and then read related news. Common news classification categories include: sports, military, technology, entertainment, education, international, finance, etc. . The news about various companies on the Internet is also increasing day by day, and the news categories related to enterprises include: company information, announcement reports, product information, achievement awards, investment and financing, etc. In order to analyze the relevant category informatio...

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): G06F16/35G06F16/36G06N3/04
CPCG06F16/35G06F16/374G06N3/044G06N3/045
Inventor 顾凌云王洪阳严涵
Owner 成都冰鉴信息科技有限公司
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