A query string semantic requirements analysis method and device

Abstract

The invention relates to a semantic requirement analysis method and device for a query string. The method comprises the steps of conducting word segmentation on the received query string and obtaining a word-segmentation query string; obtaining candidate semantic templates matched with the word-segmentation query string from a semantic template library corresponding to the query string; calculating semantic scores of the candidate semantic templates, taking the candidate semantic template with the highest semantic score as an optimal semantic template, and constructing a retrieval scheme according to the optimal semantic template. The semantic requirement analysis method and device for the query string overcome shortcomings in the prior art, the retrieval scheme which more meets the actual demands of a user is provided for the user within a shorter time through semantic requirement analysis, the obtaining mode of the retrieval scheme is flexible and simple, fast and high in precision, and the user experiences are fundamentally improved.

Description

technical field [0001] The invention relates to the field of semantic analysis, in particular to a query string semantic requirement analysis method and device. Background technique [0002] At present, search query is already an important business for people to use map products. Through search query, people can realize the application requirements for specific destinations, life-related services, and route planning. Among them, the query string input by the user, especially the voice input query string whose proportion is gradually increasing, contains a large number of semantic requirements of the user and needs to be parsed by the search engine. The search query method used in the prior art is relatively simple, using relatively simple matching rules to obtain keywords matching the query string input by the user from the keyword vocabulary, and finally constructing a retrieval scheme based on the keywords. However, in the prior art, keywords are obtained by manual enumer...

AI Technical Summary

Problems solved by technology

However, the keywords in the prior art are obtained by manual enumeration, which makes it difficult for the keyword vocabulary to fully cover the query string input by the user, and it takes a long time to obtain the matching keywords

Obviously, the existing technology is difficult to obtain the matching query string according to the query string in a short time. This is the actual semantic demand retrieval scheme.

Images