Case public opinion abstract generation method based on case element sentence association graph convolution

A technology of associating graphs and sentences, applied in neural learning methods, biological neural network models, instruments, etc., to achieve the effect of improving effectiveness

Active Publication Date: 2020-06-26
KUNMING UNIV OF SCI & TECH
View PDF9 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a case public opinion summary generation method based on the case element sentence association graph convolution, solves the problem of how to integrate the case public opinion summary into domain knowledge and cross-document sentence correlation, and improves the effectiveness of the case public opinion summary generation method

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
  • Case public opinion abstract generation method based on case element sentence association graph convolution
  • Case public opinion abstract generation method based on case element sentence association graph convolution
  • Case public opinion abstract generation method based on case element sentence association graph convolution

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0067] Embodiment 1: as Figure 1-2 As shown, the method for generating case public opinion summaries based on the convolution of case element sentence association graphs includes:

[0068] Step1, the collection of experimental corpus and the construction of data sets;

[0069] Using a crawler based on the Scrapy framework, using the case name as a keyword to collect case public opinion news from Baidu News (https: / / news.baidu.com / ), Sogou News (https: / / news.sogou.com / ), etc., after Data cleaning and manual screening to obtain news texts related to different cases. The experimental training corpus collected 500 news documents related to 50 cases, including 13133 sentences. The 10 news texts related to each case constitute a text cluster, manually write a reference abstract for each text cluster, use the ROUGE value method to calculate the score of each sentence, and divide the sentences into 10 categories from 0 to 9 according to the score. training label. The training set...

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 relates to a case public opinion abstract generation method based on case element sentence association graph convolution, and belongs to the technical field of natural language processing. According to the method, case elements and words are fused to construct a sentence association graph based on the case elements to represent an association relationship between sentence informationand sentences; an association relationship between sentence information and sentences is learned by using a graph convolutional neural network, and the sentences are classified to obtain an importance score of each sentence; sentences are sorted according to importance, and abstracts are obtained through duplication elimination and sequential relation adjustment. According to the invention, important information is obtained from a plurality of news texts related to a specific case and is used as a brief abstract of the news texts. The method plays an important role in quickly mastering the public opinion situation by related personnel, and solves the problem of how to integrate domain knowledge and cross-document sentence association relationships for case public opinion abstracts.

Description

technical field [0001] The invention relates to a case public opinion summary generation method based on case element sentence correlation graph convolution, and belongs to the technical field of natural language processing. Background technique [0002] Case public opinion refers to Internet public opinion related to the case. Compared with general news public opinion, case public opinion is sensitive and specific, and has greater social influence. Case public opinion summaries can extract important information from case-related news texts, thereby simplifying the length of news texts and helping users obtain key information about public opinion events from a large amount of public opinion data, which plays an important role in the monitoring and timely processing of case public opinion. [0003] Case public opinion summarization is essentially a domain-specific multi-document summarization task. In the research of multi-document summarization, the key issue is to evaluate ...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F40/216G06F40/211G06F40/284G06F16/35G06N3/04G06N3/08
CPCG06F16/355G06N3/08G06N3/045
Inventor 余正涛韩鹏宇黄于欣高盛祥郭军军王振晗
Owner KUNMING UNIV OF SCI & TECH
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