A semantic analysis method and system

Abstract

The invention belongs to the field of semantic recognition, and discloses a semantic analysis method and system. The method includes: obtaining a corpus; extracting corpus with clear sentence structure from the corpus; generating regular expressions according to the extracted corpus; The corpus is trained as a training sample to obtain a semantic analysis model; the voice information input by the user is obtained; the matching degree between the voice information and the regular expression is calculated; if the matching degree between the voice information and any regular expression is greater than the preset threshold, the matching degree is passed The regular expression that is greater than the preset threshold analyzes the semantics of the voice information; if the matching degree is less than the preset threshold, the semantics of the voice information is analyzed through the semantic analysis model. In the present invention, when the user statement is clear, the semantic analysis is performed through regular expressions, which can improve the speed of semantic analysis; when the user statement cannot be analyzed with regular expressions, the semantic analysis is performed through the semantic analysis model to improve the success rate of semantic analysis and reduce the case of misparsing.

Description

technical field [0001] The invention belongs to the technical field of semantic recognition, in particular to a semantic analysis method and system. Background technique [0002] With the rapid development of smart terminals and network technology, people are more and more accustomed to using smart terminals to fulfill various needs. Voice input relevant knowledge points in the device, search for corresponding answers and knowledge explanations, so as to provide learning guidance for users. [0003] At present, in human-computer interaction scenarios, accurate understanding of semantics is the basis for making correct responses. However, because primary school students often get the language order and logic upside down in the process of speaking, some sentences that are easy to obtain specific features are easy to parse, while some sentences that cannot obtain their specific features are likely to cause semantic parsing failure, which makes the user experience. Poor, not c...

AI Technical Summary

Problems solved by technology

However, because primary school students often get the language order and logic upside down in the process of speaking, some sentences that are easy to obtain specific features are easy to parse, while some sentences that cannot obtain their specific features are likely to cause semantic parsing failure, which makes the user experience. Poor, not conducive to product promotion and use

Images