Search demand analysis method and device

Abstract

The invention provides a search requirement analysis method and device. The method comprises the steps of obtaining a search term and obtaining multiple associated terms corresponding to the search term; extracting the characters of the search term to serve as primitive characters, and extracting the characters of the multiple associated terms to serve as associated characters; acquiring search requirements according to the primitive characters and the associated characters. By the adoption of the method, the search requirements of a user can be obtained accurately, so that search results better meeting the requirements of the user are provided by a search engine according to the search requirements of the user; in this way, the accuracy of search is improved, and the recall rate of search is increased. Furthermore, due to the fact that search requirement analysis is irrelevant to languages, switching between different languages can be achieved conveniently, and using is more convenient.

Description

technical field [0001] The present invention relates to the field of search technology, in particular to a search demand analysis method and device. Background technique [0002] Traditional keyword matching search engines, because they only segment the search word query and use the obtained keywords to search in the index data, do not really fully understand the user's search intention, resulting in the retrieved results only containing the search words Keyword results may not necessarily meet the user's search needs. For example, query "Andy Lau's picture", in the traditional search engine, the two keywords "Andy Lau" and "picture" will be used to search the index data respectively, and the search results will only contain the keyword "Andy Lau" or the keyword "picture". " data, not the data resources of "Andy Lau pictures" that users really want to get. [0003] Therefore, search engines that can perform search demand analysis are playing an increasingly important role ...

AI Technical Summary

Problems solved by technology

Although the accuracy of template matching is very high, the retrieval results are not comprehensive enough and the recall rate is very low, and template mining relies on a lot of human work, which requires template mining for each type of demand, which is a heavy workload and cannot be transferred between languages; However, the method of using query retrieval results to train machine learning models depends entirely on the accuracy of the retrieval results, and the accuracy is difficult to guarantee, resulting in the accuracy of the search results obtained based on the trained and its learning model cannot be guaranteed.

Images