Method and device for search recommendation based on search term and search engine

Abstract

The invention provides a method and a device for search recommendation based on a search term and a search engine. The method comprises the steps that multiple candidate recommendation objects are acquired; the similarity between every two candidate recommendation objects is acquired; the candidate recommendation objects are classified according to the similarity to generate multiple clusters; and the search term input by a user is received, and the candidate recommendation object relevant to the search term is acquired from the clusters to serve as a recommendation result. The technical scheme overcomes the defect that in the prior art, a recommendation result is excessively generalized; the clusters are utilized to divide the recommendation result, each cluster is accurately described through a knowledge map, valuable information is provided, the selected recommendation result better conforms to the search habit and search demand of the user, the recommendation result is more accurate and more professional, and the satisfaction of the user is improved.

Description

technical field [0001] The invention relates to the technical field of the Internet, in particular to a method, device and search engine for search recommendation based on search terms. Background technique [0002] With the continuous development of Web technology, the creation and sharing of Internet information has become easier and easier, and the extreme explosion of information has made it more and more difficult for people to find the information they need. Search recommendation technology has emerged as the times require. Search recommendation technology The significance of is to guide users to find the information and information they need faster and more accurately. [0003] Existing search recommendation descriptions generally use "related xx" where xx is some category with no information, such as "person", "movie", etc., and the recommendation results of different categories are mixed together; for example, in the current If you search for "Transformers" in a se...

AI Technical Summary

Problems solved by technology

[0003] Existing search recommendation descriptions generally use "related xx" where xx is some category with no information, such as "person", "movie", etc., and the recommendation results of different categories are mixed together; for example, in the current If you search for "Transformers" in a search engine, the search engine will recommend "related characters", including movie actors and comic characters. Difference

[0004] Not only that, the existing search recommendations are mostly based on Collaborative Filtering or AssociationRules, which are characterized by a small number of results and lack of focus, resulting in a mismatch between recommended results and user intentions

For example, if you search for "Jiuzhaigou" in the existing search engine, the search engine will display "relevant attractions" recommendations, which are basically some popular national attractions that have little relationship with "Jiuzhaigou". Such a search recommendation scheme does not meet the user's search needs. makes little sense to the user

Images