A semantic-based query recommendation method and system

Abstract

The invention provides a semantic-based query recommendation method and system. The method comprises the steps of establishing a query concept binary diagram, establishing a query click URL binary diagram, combining the query concept binary diagram with the query click URL binary diagram according to query nodes to form a concept query click URL ternary diagram, and establishing three layers of random walk models; according to query terms input by users, calculating the walk possibility between the input query term nodes, and the concept nodes and the URL nodes based on the three layers of random walk models, arranging the input query term nodes from high to low based on the walk possibility to obtain a query recommendation list. The semantic-based query recommendation method and system provided by the invention aim to enhance the semantic relevance between the recommended query and the original query to recommend better queries for users so as to meet the query demands of users.

Description

technical field [0001] The invention relates to the field of information retrieval, in particular to a semantic-based query recommendation method and system. Background technique [0002] With the development of the times, the Internet has also developed vigorously around the world, and more and more people start to find the information they need on the Internet. With more and more information on the Internet, search engines have gradually become an indispensable tool for users to access network resources. Users input queries to search engines to reflect their information needs, and search engines acquire and analyze user queries and return Give users the information they need. But not every query, the user can get the desired result. This is because on the one hand, when users query certain information, they lack knowledge in this area, and it is difficult to construct a suitable query; on the other hand, due to search engine technical reasons, the search engine itself so...

AI Technical Summary

Problems solved by technology

[0006] First, the document-based method requires external documents, and the time complexity of global document analysis is high. Due to the limitation of natural language processing technology, the effect is not very good. Local document analysis is also a problem for how to accurately obtain query-related documents, and the calculation cost still big

[0007] Second, the session-based method needs to accurately divide the query log into sessions, and sessions are less than queries, and there is still a problem of information sparseness directly based on statistical information

The method based on click information is very dependent on the effect of search engines, and there are many noises and biases in the results of user clicks, and the query in the query log also has the problem of sparsity.

[0008] Third, traditional query recommendation methods generally only consider click information or just the query words themselves, and rarely consider the deep semantics behind the query words

For these queries, traditional methods are also difficult to give good query recommendations

Images