A Semantic Retrieval System and Method for Fuzzy Concepts

Abstract

The invention relates to a semantic retrieval system and method of vague concepts. The semantic retrieval system and method of the vague concepts are characterized in that the semantic retrieval system comprises an application layer composed of a human-computer interaction interface, a service logic layer and a data layer, wherein the service logic layer is composed of a preprocessing module, a query transformation module, a body expander, a query processing module and a customization processing module, and the data layer is composed of a plurality of index information bases; a user can submits a query request to the preprocessing module through the human-computer interaction interface for preprocessing, and an original retrieval word set is generated and submitted to the query transmission module; the query transformation module conducts vague concept transformation on the received retrieval word set to generate an expanded synonymous retrieval word set and a selectable semantic relativity retrieval word set which are then submitted to the query processing module and the customization processing module respectively; the query processing module retrieves the index information bases and submits retrieval results to the customization processing module; after the customization processing module processes the retrieval results and the selectable semantic relativity retrieval word set, submits the retrieval results and the selectable semantic relativity retrieval word set are submitted to the human-computer interaction interface.

Description

technical field

[0001] The invention relates to a retrieval system and method, in particular to a semantic retrieval system and method for fuzzy concepts. Background technique

[0002] With the popularization and application of network technology, the release of network information has become simple and fast. How to quickly locate the resources needed by users from a large amount of network information is a headache. In order to solve such problems, network retrieval technology emerges and develops rapidly. At present, most of the existing web search engines are based on keywords or text content retrieval. Although their recall rate can be guaranteed to a certain extent, the precision rate still cannot meet the needs of users, and these network A fatal flaw in all search engines is the lack of semantic analysis of retrieved content and the inability to fully express semantic information. Semantic-based retrieval methods can greatly improve the search results of traditiona...

Images