Application search method and server

Abstract

The invention discloses an application search method and a server. The method comprises the steps of constructing an application tag database, wherein the application tag database comprises tag systems of all applications; constructing a search word tag database, wherein the search word tag database comprises tag systems of a plurality of search words; constructing a tag knowledge base; receiving a current search word uploaded by a client, and obtaining the tag system of the current search word according to the search word tag database; based on the tag knowledge base, calculating semantic correlation between the tag system of the current search word and the tag system of each application; and when the semantic correlation between the tag system of the current search word and the tag system of one application meets a preset condition, returning related information of the application to the client for performing display. According to the scheme, the tag systems of the applications are matched with the tag systems of the search words based on the tag knowledge base, namely, user intentions and the applications are mapped to a same semantic space, so that the problem in semantic matching of the search words and the applications is solved and an application search function is effectively realized.

Description

technical field [0001] The invention relates to the technical field of the Internet, in particular to an application search method and server. Background technique [0002] App search engine is a mobile software application search engine service that provides app search and download on mobile phones, such as 360 Mobile Assistant, Tencent App Store, Google Play, Appstore, etc. With the development of the mobile Internet, the number of mobile apps has increased rapidly. Taking 360 Mobile Assistant as an example, there are millions of apps. Construct the query description, use the search engine to analyze the user's query intent based on the search query, map the user's intent to the app, and accurately find the app. This is the application scenario of the functional search technology. [0003] When we analyzed the user query session, we found that the query input by the user tends to use the functions or categories of the app they want to construct the query query. This is an...

AI Technical Summary

Problems solved by technology

[0004] The traditional functional search technology solution is based on manual labeling and keyword matching retrieval technology. Manual labeling and classification of app types and manual sorting of query intent types have high accuracy, but low recall and coverage rates, which can only cover popular apps and applications. Its type, the cost of manual labeling to obtain classification and labeling is very high, the workload is heavy, time-consuming and labor-intensive

[0005] Traditional keyword matching-based retrieval algorithms, when associated tags are used to express related semantics, cannot recall related apps due to word mismatch. The general solution is to mine synonyms and use synonyms to supplement semantic matching. However, in the vertical field of apps, synonyms are Very sparse. We have tried to mine synonyms but the results are very poor. One of the characteristics of the vertical search field is that the query requirements are narrow and the ambiguity is small

For example, when a user searches for a query "find a restaurant", it is semantically related to app tags such as "group buying, gourmet food, takeaway, discount, o2o, foodie", but there is no synonym coverage. There is a semantic gap between the user query and the app, which cannot satisfy the user. Search requirements, poor user search experience

Images