Method and device for extracting keywords in page

Abstract

The invention discloses a method and a device for extracting keywords in a page. The method comprises the following steps: performing character string analysis on the title content of the page to obtain candidate words, and constructing a candidate word search table by the obtained candidate words; performing page analysis on the page to obtain a character combination, and constructing a short string set by the obtained character combination; performing character string analysis on the short string set to obtain character strings, and constructing an original weight pool by the obtained character strings; performing weighted voting on the candidate words in the candidate word search table through the character strings according to the sequence of the quantities of words included in each character string in the original weight pool, and increasing the weight values of the candidate words if the character strings are consistent with the candidate words in the candidate word search table; sequencing according to the weighted values of the candidate words from large to small, and extracting a preset quantity of candidate words in the front as keywords according to the sequence. By adopting the method and the device, the universality of a keyword extraction technology can be enhanced, and a way for extracting the keywords is more intelligent and efficient.

Description

technical field [0001] The invention relates to the field of computer networks, and more specifically, to a method and device for extracting keywords in a page. Background technique [0002] With the development of the network, people can handle more and more things through the network. However, users need to use keywords as search content when facing various information queries. If the keywords in the page can be scientifically Extraction and application will improve the query effect with half the effort. [0003] The analysis and extraction of keywords in the existing technology needs to rely on prior knowledge, such as word segmentation, part-of-speech tagging, and stop word dictionary. These natural language processing logics need to accumulate thesaurus to carry out. Commonly used are statistical methods based on TF-IDF (term frequency-inverse document frequency, that is, a commonly used weighting technique for information retrieval and information mining), some based ...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem that the general keyword extraction in the prior art cannot work in an internationalized language, resulting in the low versatility, insufficient intelligence and low processing efficiency of the keyword extraction technology in the prior art, the embodiment of the present invention provides a A method and device for extracting keywords in a page

Images