Key information extraction method and device, computer equipment and storage medium

Abstract

The invention discloses a key information extraction method and device, computer equipment and a medium, and the method comprises the steps of carrying out the crawling of a public opinion article from a self-media site based on a preset crawling mode, and obtaining a target article; performing format analysis on the target article to obtain a title and a main body of the target article; performing text information extraction on the text to obtain target text information; taking the title and the target text information as fusion features, taking the target article as basic features, and inputting the fusion features and the basic features into a preset keyword screening model for training to obtain an initial keyword candidate set; performing priority ranking on each keyword in the initial candidate set to obtain a target sequence with priorities from large to small, and selecting a preset number of keywords from the target sequence as target keywords; and generating key information based on the target keyword and the target article. According to the invention, the accuracy of key information extraction can be improved.

Description

technical field [0001] The invention relates to the field of data processing, in particular to a key information extraction method, device, computer equipment and media. Background technique [0002] The Internet can provide users with rich information resources. With the rapid development of Internet technology, more and more users obtain the information they want through the Internet. In order to facilitate users to obtain the latest information, self-media sites will add a large number of articles every day. How Finding the information you want from a large number of articles has become an urgent problem to be solved. [0003] In the existing method, article collection is performed according to the user's keywords or preset preference information by means of a collection of search engines, and then the first few sentences of each collected article are displayed to the user in the form of a snapshot. However, it is difficult to guarantee the accuracy of the generalization...

AI Technical Summary

Problems solved by technology

[0003] In the existing method, article collection is carried out according to the user's keywords or preset preference information through the collection of search engines, and then the first few sentences of each collected article are displayed to the user in the form of a snapshot. However, it is difficult to guarantee the accuracy of the generalization of the content of the article in this way, so that when the user browses, he still needs to click on the article one by one to read the information of the article, which consumes a lot of time. extraction method

Images