Query word similarity calculation method and device, query word search method and device

Abstract

Disclosed are a method and a device for calculating similarity of search terms, and a searching method and device using the search terms. The method for calculating similarity of search terms comprises: determining a first characteristic vector set corresponding to a first search term and a second characteristic vector set corresponding to a second search term (S101); calculating characteristic similarity between the first characteristic vector set and the second characteristic vector set (S102); in the case that both the first search term and the second search term satisfy a preset condition, determining the characteristic similarity as search term similarity between the first search term and the second search term (S103). The similarity between the first characteristic vector set and the second characteristic vector set (the similarity of meanings between the first and second characteristic vector sets determined by a user) is used as the similarity between the first search term and the second search term. Therefore, the method can accurately determine the similarity between two search terms such that a server can quickly and accurately retrieve a webpage related to the search terms according to the similarity.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a query word similarity calculation method and device, query word search method and device. Background technique [0002] With the advancement of science and technology, the types of search applications are gradually increasing. In the process of using a search application, it is generally necessary to calculate the similarity between two query words. For example, when a user enters a query word (stnb) with less semantics in the search bar, it is necessary to obtain a query word with richer semantics (Despicable Milk Dad), so that the processor can quickly and accurately retrieve the webpage corresponding to the query word (stnb) based on the query word (Despicable Me Dad) with richer semantics. [0003] At present, there are many ways to calculate the similarity between two query words, for example: calculate the similarity probability between two query words accor...

AI Technical Summary

Problems solved by technology

Theoretically, the similarity of the two query words should be very high, but when using the existing technology to calculate the similarity of the characters of the two query words, the similarity is very low

This will result in an incorrect calculation of the similarity between the two query terms, which in turn will cause the processor to fail to quickly and accurately retrieve web pages related to the query term when using similarity for related searches

Images