Method for extracting events from news

A news and event technology, applied in computer components, special data processing applications, instruments, etc., can solve problems such as flooding, inability to select and digest massive information, and information loss

Inactive Publication Date: 2018-06-22
CHENGDU REMARK TECH CO LTD +1
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] With the continuous development of computer network technology, the acquisition of online information has become one of the main ways for people to know events. As a main form of network information resources, news portals at home and abroad will generate a large number of news every moment. News, people often fall into an embarrassing situation. On the one hand, the huge amount of information they receive cannot be selected and digested, and they are submerged in the complicated information. On the other hand, the information is lost, and it is difficult for people to find the information they really need; Accurately obtaining the required information is the urgent need of people for network information nowadays

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
  • Method for extracting events from news
  • Method for extracting events from news

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] Such as figure 1 As shown, this embodiment provides a method for extracting events from news, and the method specifically includes the following steps:

[0026] S01. Obtain an original news data set related to a target topic; including a news ID, a news title and a news content.

[0027] S02. Extract the abstract of the news as the event, and perform numerical conversion on the news text respectively.

[0028] Numerical transformations include:

[0029] Step 2.1, training the doc2vec model: segment the news title and news content into words, for example, the result of word segmentation of "today's weather is really good" is "today", "day", "day", "qi", "true" , "OK"; use the news title and news content with good word classification, respectively train the doc2vec model of the title and the doc2vec model of the content, and save it locally;

[0030] Step 2.2. Convert text into vectors: For any new piece of news, first segment the title and content, and use the above-t...

Embodiment 2

[0039] Such as figure 2 As shown, this embodiment provides a method for extracting events from news. On the basis of the above embodiments, it further provides a specific method for determining the event that news belongs to in the news box according to the similarity. Correspondingly, the method specifically include:

[0040] S11. Obtain an original news data set related to the target topic; including news ID, news title and news content;

[0041] S12. Extracting the summary of the news as the related event, and numerically converting the news text respectively;

[0042] Numerical transformations include:

[0043] Step 2.1, training the doc2vec model: segment the news title and news content into words, for example, the result of word segmentation of "today's weather is really good" is "today", "day", "day", "qi", "true" , "OK"; use the news title and news content with good word classification, respectively train the doc2vec model of the title and the doc2vec model of the ...

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 method for extracting events from news. The method comprises the steps that summary information in the news is extracted to serve as affiliated events, news text is subjectedto numeric conversion to obtain vector representation of the text, the degree of similarity of the news is calculated by means of a clustering method, and on the basis of the degree of similarity, the news is classified rapidly according to the affiliated events; the news belonging to the same event can be clustered together easily and effectively, new heat of the news is obtained, and subsequentpublic opinion monitoring is facilitated. By means of the method, mass news information can be classified easily, rapidly and effectively, guidance is provided for public opinion analysis, the monitoring strength of public opinions is further improved, and decision support and public opinion guidance can be made in time.

Description

technical field [0001] The invention relates to the technical field of computer network communication, in particular to a method for extracting events from news. Background technique [0002] With the continuous development of computer network technology, the acquisition of online information has become one of the main ways for people to know events. As a main form of network information resources, news portals at home and abroad will generate a large number of news every moment. News, people often fall into an embarrassing situation. On the one hand, the huge amount of information they receive cannot be selected and digested, and they are submerged in the complicated information. On the other hand, the information is lost, and it is difficult for people to find the information they really need; Acquiring the required information efficiently is the urgent need of people for network information nowadays. In this case, it is necessary to automatically and effectively cluster ...

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): G06F17/27G06K9/62
CPCG06F40/279G06F18/23
Inventor 范艳艳李源
Owner CHENGDU REMARK TECH CO LTD
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