Searching-based data recommendation method and device

Abstract

The invention provides a searching-based data recommendation method and device. The method comprises the following steps of: determining result types of one or more searching result items corresponding to a searching query; judging whether entity recommendation data of the searching query corresponding to the result types exist or not; if not, collecting the entity recommendation data of the searching query corresponding to the result types; and, when a target query coming from a user and matched with the searching query is received, obtaining the collected entity recommendation data of the searching query corresponding to the result types, and performing recommendation. By means of the embodiment of the invention, on the basis of the result types of the searching result items, data recommendation is carried out; types of recommendation data can be increased; therefore, the recommendation data is more diversified; furthermore, the real-time performance of the recommendation data is improved; and thus, the problem that the recommendation data is not in real time and relatively lags due to the fact that the recommendation data is obtained from offline data in the prior art can be solved.

Description

technical field [0001] The invention relates to the technical field of Internet applications, in particular to a search-based data recommendation method and device. Background technique [0002] With the rapid development of information technology, today's society has entered the era of information explosion, and people increasingly rely on the Internet to find the information they need. Therefore, retrieval has become an indispensable part of people's work and life. People usually use search engines to search. Search engines refer to collecting information from the Internet according to certain strategies and using specific computer programs. The system by which information is presented to the user. [0003] At present, graphic and text recommendations are displayed on the right side of the search results page presented to users, which can cover about 93% of the PV (Page View, page views) searched every day, and is currently the largest type of recommendation for searches....

AI Technical Summary

Problems solved by technology

However, at present, all recommended data and algorithm templates are technically calculated and uploaded offline data to the server and take effect. Newly generated knowledge graphs such as movies, TV dramas, and Internet terms on the Internet between two data updates cannot be identified. What, so there is a problem of poor diversity recommendation, which needs to be solved urgently

Images