Offline semantic parsing method and system

Abstract

The invention discloses an offline semantic parsing method and system. The method comprises the steps of: obtaining a plurality of functional semantic fields corresponding to a plurality of language fields according to the plurality of language fields, and building a plurality of semantic classification fields skill _ id corresponding to the plurality of functional semantic fields in gram grammarcompiled contents of a language model; judging whether the current field has a plurality of corresponding semantic classification fields skill _ id or not, and if yes, acquiring the corresponding current semantic classification fields skill _ id according to the current field and semantic correspondence; and if not, acquiring a navigation information return field according to the current field anda local navigation analysis program. According to the method, skill _ id fields are added in a gram grammar compiling process, the classification of each statement is indicated, and while an identification result is given, the category of information, namely skill id, to which the current statement belongs is given. The semanteme of the corresponding category is directly positioned through skill_ id for analysis.

Description

technical field [0001] The invention relates to the field of voice recognition and its application. The invention specifically relates to an off-line semantic analysis method and system. Background technique [0002] Most of the existing semantic analysis schemes are based on repeated matching schemes to determine the final semantic results. In the existing scheme, after the recognition result is obtained, a relatively correct result is obtained by sequentially matching different offline semantics. [0003] It can be seen that the defect of the existing semantic analysis scheme is that, on the one hand, since the final semantics is based on sequential matching and comparison, a result with relatively high reliability is obtained, which means that even when identifying On the basis of correctness, there is no guarantee that the final semantic result must be the result that the user wants. [0004] On the other hand, it takes time to match and analyze semantics. In the case...

AI Technical Summary

Problems solved by technology

[0003] It can be seen that the defect of the existing semantic analysis scheme is that, on the one hand, since the final semantics is based on sequential matching and comparison, a result with relatively high reliability is obtained, which means that even when identifying On the basis of correctness, there is no guarantee that the final semantic result must be the result that the user wants

[0004] On the other hand, it takes time to match and analyze semantics. In the case of fewer offline semantics, the time spent is not outstanding. As the demand for offline semantics increases, there are more and more sayings and skills. The time will also increase accordingly. The richer the offline content, the longer the semantic analysis time will be, and the worse the user experience will be.

[0005] In the process of implementing this application, the inventor found that the root cause of the above-mentioned defects is that the recognition results in the above technologies do not contain semantic-related information, so that the only way to obtain the correct semantics is to sequentially analyze the offline semantics. match, compare

Images