Topic detection method and device for case-related public opinions

A topic detection and public opinion technology, applied in the computer field, can solve problems such as high algorithm overhead, dimension disaster, and sparse data features, and achieve the effects of improving efficiency, reducing overhead, and high accuracy

Pending Publication Date: 2021-02-26
CAPITAL NORMAL UNIVERSITY
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Existing topic detection methods do not consider case element information, but only perform topic detection on public opinion texts. Since there are many similar words invol

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
  • Topic detection method and device for case-related public opinions
  • Topic detection method and device for case-related public opinions
  • Topic detection method and device for case-related public opinions

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0061]Example two

[0062]figure 2 This is a schematic flow chart of the topic detection method of public opinion involved in another embodiment of this application, such asfigure 2 As shown, the method includes:

[0063]S1. Vector representation based on key elements of the case.

[0064]S11. Obtaining the data set.

[0065]The source of the text data in the data set can be a network communication platform, a portal website, and an information service platform. The network communication platform uses the Internet as a platform for communication and sharing, and comprehensively utilizes network carriers to achieve the exchange of ideas between the two parties, such as Weibo, Tieba, forums, BLOG (blog) and other network communication carriers.

[0066]Online text data refers to the information published by users or officials on the online platform. Online text data includes content published by users or officials themselves, as well as comments and forwarding content of users or officials to other ...

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 belongs to the technical field of computers, and particularly relates to a topic detection method and device for case-related public opinions. The topic detection method for the case-related public opinions comprises the steps of obtaining public opinion text data containing case public opinion texts; based on predetermined case element information and the position of the keyword inthe case public opinion text, determining an additional weight of the keyword; obtaining text vector representation of the public opinion text data according to the additional weight and a basic weight determined based on a TFIDF algorithm; conducting dimensionality reduction on the text vector representation through an auto-encoder, and obtaining low-dimensional text vector representation; and based on the low-dimensional text vector representation, clustering by adopting a spectral clustering algorithm to determine topics of the case public opinion text. When topic detection is carried out through the method, the detection efficiency and the detection accuracy are high, and the public opinions involved in the case can be captured in time.

Description

technical field [0001] The application belongs to the field of computer technology, and specifically relates to a method and device for detecting topics of public opinion involved in a case. Background technique [0002] Topic Detection and Tracking (TDT) is a technology in the field of natural language processing. It takes massive information flow as the research object, and detects and captures information that users are interested in by monitoring and extracting news topics. Due to the large amount of information in the network, the information related to the topic is often scattered in different places, and distributed in many different places at different times, so it is difficult for people to fully grasp the information of the event only by relying on these isolated information. In this case, topic detection technology emerges as the times require, which can help people integrate scattered information and organize information on the same topic as a whole for people to...

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): G06F16/35G06K9/62G06F40/284G06F40/289G06N3/04G06N3/08
CPCG06F16/355G06F40/284G06F40/289G06N3/08G06N3/045G06F18/23213
Inventor 刘杰王佳薇冀俊宇
Owner CAPITAL NORMAL UNIVERSITY
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