A method and system for completing a semantically incomplete corpus

Abstract

The invention provides a method and a system for completing semantically incomplete corpus. The method comprises the following steps: obtaining a semantically complete corpus sample library; accordingto the corpus sample library, establishing an audio library, a semantic slot and a regular expression library; obtaining a semantically intact corpus sample library; obtaining a semantically intact corpus sample library. Acquiring user voice; Matching the user voice and the audio library; When the matching result is consistent, determining a part of speech corresponding to the matching participleaccording to the semantic slot, wherein the matching participle is a participle matching with the audio library in the user voice; Comparing the part of speech of the matching participle with the regular expression library, and completing the incomplete components in the user speech according to the regular expression in the regular expression library to obtain a supplementary full-text version;A semantic analysis is performed according to the complement text. The invention intelligently identifies the true user intention by completing the incomplete components in the corpus.

Description

technical field [0001] The invention relates to the technical field of speech recognition, in particular to a method and system for complementing semantically incomplete corpus. Background technique [0002] With the rapid development of the Internet, people's lives are becoming more and more intelligent, so people are becoming more and more accustomed to using smart terminals to fulfill various needs. Moreover, with the increasing maturity of artificial intelligence-related technologies, the intelligence of various terminals is also getting higher and higher. As one of the mainstream communication applications of human-computer interaction in smart terminals, voice interaction is increasingly favored by users. [0003] The smart terminal recognizes the voice input by the user, and then takes corresponding measures. Therefore, the accuracy of the voice input by the user through the terminal seriously affects the feedback made by the smart terminal. [0004] Due to accident...

AI Technical Summary

Problems solved by technology

[0004] Due to accidents that may occur during the user input voice, for example, part of the voice input is accidentally interrupted or part of the voice is not captured by the microphone, as well as the interference of the external environment, such as the environment is too noisy to intelligently recognize part of the voice. Incomplete components make it difficult to accurately identify the user's true intentions

[0005] In addition, for low-grade students, because they are in the initial stage of learning, in the process of language expression, language components are often incomplete and intentions are vague, which makes it difficult for voice recognition products to intelligently recognize the real user intentions

Images