Induction method of news event information

Abstract

The invention discloses a news event information induction method, comprising: collecting news materials, creating a news database; obtaining all news texts of a target event from the news database, performing heat analysis, obtaining inflection point news texts, and extracting the inflection point news texts and save the event information in the inflection point news text; wherein, the method of obtaining the news text of the inflection point includes: counting the heat values ​​of all news texts, sorting according to the chronological order of news text release, constructing a graph of the heat value changing with time, and taking all extremes of the graph The news text corresponding to the big point is the news text of the inflection point, and the popularity value is the sum of page views of the news and the number of independent visitors to the website. The method of the present invention accurately reflects the development trend of the news event by selecting the news text when the target news event is at a critical node, that is, the inflection point news text, for summary analysis and processing.

Description

technical field [0001] The invention relates to the field of information extraction, in particular to a news event information induction method. Background technique [0002] In recent years, with the rapid development and popularization of computer and information technology, people rely more and more on the Internet to collect information about target news events. Although the previous information extraction systems can help users retrieve a large amount of target information to a certain extent, due to the shackles brought about by the era of information explosion, users often directly retrieve a large number of relevant information surrounding the target event. In order to obtain useful information, the user needs to further filter the information; in addition, the event is in a dynamic development with the change of time, and it is difficult for the existing information extraction system to search for the target event. Trends are emerging, which inevitably brings a lot...

AI Technical Summary

Problems solved by technology

Although the previous information extraction systems can help users retrieve a large amount of target information to a certain extent, due to the shackles brought about by the era of information explosion, users often directly retrieve a large number of relevant information surrounding the target event. In order to obtain useful information, the user needs to further filter the information; in addition, the event is in a dynamic development with the change of time, and it is difficult for the existing information extraction system to search for the target event. Trends are emerging, which inevitably brings a lot of trouble to the process of analyzing target events for users

Images