Method and equipment for extracting core keywords based on query sequence cluster

Abstract

The invention aims to provide a method and equipment for extracting core keywords based on a query sequence cluster. The method comprises the following steps of: acquiring the query sequence cluster by the extracting equipment, wherein the query sequence cluster comprises a plurality of query sequences and each query sequence corresponds to at least one same user clicked search result; and extracting the core keywords corresponding to the query sequence cluster from the query sequence cluster. Compared with the prior art, search requirements of users of the query sequences input to the query sequence cluster are acquired, and more appropriate search suggestions or more relevant search results or the like can be supplied to the users according to the core keywords, so that the users acquire better search experience. Furthermore, when a lexicon does not contain the core keywords, the core keywords can be used as new words and added into the lexicon for each application.

Description

technical field [0001] The invention relates to the technical field of natural language processing, in particular to a technology for extracting core keywords based on query sequence clusters. Background technique [0002] Most of the existing word segmentation technologies use dictionaries or semantic analysis to segment sentences or fragments. However, the number of words included in the dictionary is limited, and new words emerge in an endless stream on the Internet, and the update speed of the dictionary is much lower than that in the Internet. The speed at which new words are updated makes word segmentation according to the dictionary unable to meet actual needs. Segmentation of sentences or fragments based on semantic analysis involves machine learning, and the diversification of language expressions and the colloquialism of Internet languages ​​in the Internet make the results of word segmentation through semantic analysis unsatisfactory. [0003] When there are a la...

AI Technical Summary

Problems solved by technology

[0002] Most of the existing word segmentation technologies use dictionaries or semantic analysis to segment sentences or fragments. However, the number of words included in the dictionary is limited, and new words emerge in an endless stream on the Internet, and the update speed of the dictionary is much lower than that in the Internet. The speed of updating new words makes it impossible to meet actual needs according to dictionary word segmentation

Segmentation of sentences or fragments based on semantic analysis involves machine learning, and the diversification of language expressions and colloquial Internet language in the Internet make the result of word segmentation through semantic analysis unsatisfactory.

[0003] When there are a large number of search needs for the same search results clicked by users on the network, these search needs often reflect the same theme, but due to the different expressions of search users, semantic analysis often cannot correctly reflect this search demand. At the same time, the search demand for the search results clicked by a large number of the same users is often a hot spot at that time. Therefore, the core keyword corresponding to the search demand may also be a new word that does not exist in the dictionary, which leads to It is also impossible to extract the corresponding core keywords from these search requirements according to the dictionary

Images