Speech semantic recognition method, system, equipment and medium

Abstract

The invention provides a speech semantic recognition method, a system and a device and a medium. The method comprises the steps of obtaining a voice signal of a user; converting the voice signal into text data by using an automatic voice recognition technology; judging whether the text data accords with a preset sentence pattern, and if yes, responding according to a voice signal in the text data; and if not, processing and analyzing the text data by using a natural language to obtain a named entity, performing grammatical analysis on the text data to obtain an intention keyword, and obtaining an intention recognition result according to a relationship between the intention keyword and the named entity. By combining the named entity and the intention keyword in the voice information in the text data, the intention of the user can be accurately understood when the user does not adopt a verbal skill system for interaction, so that the semantic recognition accuracy and the user experience are improved.

Description

Technical field [0001] The present invention belongs to the field of speech recognition, and in particular, to a speech geographic identification method, a system, a device, and a medium. Background technique [0002] Currently, speech language identification technology applies more and more applications in electronic devices. Among them, speech language recognition technology is trained in advanced acoustic models by using acoustic and linguistic methods. Since the acoustic data is speech data. In actual products, speech language recognition technology is divided into two phases, namely voice recognition (ASR) and natural language processing (NLP); where voice recognition identifies the audio data into text data, and inputs text data as a natural voice processing. Data; during the NLP process, the gathered extraction is performed according to the set words, and finally reaches the effect of identifying the audio data. [0003] However, traditional voice functions, intelligence, ...

AI Technical Summary

Problems solved by technology

[0003] However, the traditional voice function is not as intelligent as a real person. The specific speaking skills and usage methods need to be learned by the user to use the voice function better, and the user is not willing to spend time and energy reading the manual, even if they are willing to read the manual. , many words are difficult to remember

Images