A Clustering Method for Search Tasks Based on Learning Output

Abstract

The invention provides a search process clustering method based on learning output, which belongs to the field of search engines. A search task clustering method based on Bayesian rose tree is used, and a query similarity measurement method based on learning output is used in the clustering process to achieve clustering of search tasks. The present invention makes up for the shortcomings of existing search task clustering methods that only focus on queries and clicks in the search process and ignore learning output. By considering learning output in the clustering process, the effect of search task clustering is improved.

Description

technical field [0001] The invention belongs to the field of search engines, in particular to a search task clustering method based on learning output. Background technique [0002] With the continuous improvement of the overall complexity of society, people are also facing more and more complex problems in their work and life. Search engines are one of the most common tools people use to solve everyday problems. As people use search engines more and more to solve complex problems encountered in work and life, researchers have also begun to pay attention to how to develop new search technologies to help people solve complex problems. [0003] One way to help people use search engines to solve complex problems is to identify search tasks by clustering queries in search logs that belong to the same search task. A method of clustering queries of a search task and identifying a search task is called a search task clustering method. Most of the existing search task clustering ...

AI Technical Summary

Problems solved by technology

The search task clustering method using the literature paradigm only focuses on the queries and clicks in the search task, ignoring the learning output, resulting in an unsatisfactory effect of search task clustering

Images