Method and device for determining similarity between inquiry sentence and webpage, terminal and server

Abstract

The embodiment of the invention discloses a method and a device for determining the similarity between an inquiry sentence and a webpage, a terminal and a server. The method comprises the following steps: translating a target inquiry sentence into at least one candidate sentence having similar semantics through a pre-created phrase translation model; determining the similarity between the target inquiry sentence and a webpage topic sentence according to the similarity between the at least one candidate sentence and the webpage topic sentence, wherein the webpage topic sentence is a webpage title or a sentence for describing major webpage content obtained by resolving webpage content based on a set algorithm. By adopting the technical scheme provided by the embodiment, the webpage recall rate of any inquiry sentence by a search engine can be increased, the search engine can return webpage sets with small differences specific to inquiry sentences having different representation forms but similar semantics, and the user satisfaction of an inquiry result is improved.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of data processing, and in particular to a method, a device, a terminal and a server for determining the similarity between a query statement and a web page. Background technique [0002] At present, when search engines provide users with search services, they usually first obtain the instructions entered by users in the search bar, generate query sentences based on the instructions, then calculate the correlation between the query sentences and a large number of web pages, and finally put the relevant Links corresponding to webpages with high reliability are presented to the user as the query result for the user to click to view. [0003] Since the ranking of web pages based on correlation calculation directly determines the quality of search engines and the quality of user experience, how to accurately and efficiently calculate the correlation between query statements and web page...

AI Technical Summary

Problems solved by technology

However, in the prior art, after obtaining the query sentence input by the user, no other processing is performed on the query sentence, but a hard matching method is adopted to directly calculate the correlation between the query sentence and the webpage, so that on the one hand, the search engine can identify the relevant query sentence. The recall rate of webpages related to the query statement is low; on the other hand, the webpage collection obtained by the search engine is quite different under the query sentences with different expressions but similar semantics, and the user search experience is poor.

Images