A method and a device for extracting keywords from a document text

Abstract

The embodiment of the invention provides a method and a device for extracting keywords from document text. The method comprises the following steps: obtaining a word vector corresponding to a title ofa target document; extracting keywords from the text of the target document to obtain at least one candidate keyword of the text of the document; acquiring a word vector corresponding to each candidate keyword; for each candidate keyword, determining the similarity between the word vector corresponding to the candidate keyword and the word vector corresponding to the title; determining candidatekeywords whose similarity satisfies preset conditions as final keywords of the target document body. When the document body keyword extracted by the embodiment of the invention is used for searching the target document, the body keyword consistent with the subject of the target document can be accurately obtained.

Description

technical field [0001] The invention relates to the field of natural language processing, in particular to a method and device for extracting keywords from document text. Background technique [0002] With the development of the information age and the explosive growth of text information on the Internet, how to effectively organize, classify and retrieve a large amount of information has become an issue that most Internet users are more and more concerned about. Keywords highly summarize the main content of the text, and it is obvious that the method of extracting keywords is the core issue of information retrieval. At the same time, keyword extraction plays a vital role in automatic literature, information retrieval, text classification, text clustering, etc. [0003] At present, the document text keyword extraction method mainly includes four steps: 1. Use the word segmentation tool to perform word segmentation processing on the document text to obtain the words in the d...

AI Technical Summary

Problems solved by technology

[0004] Obviously, the document text keyword extraction method in the prior art only extracts keywords from the document text, and the extraction results may have keyword results that are not related to the subject of the document.

Images