Response method, terminal and storage medium

Abstract

The embodiment of the invention discloses a response method, a terminal and a storage medium. The response method comprises the steps of determining a first target character corresponding to a first moment through voice recognition processing at the first moment; determining a first prediction intention and a to-be-pushed answer according to the first target text, wherein the to-be-pushed answer is used for responding to the voice information; determining a second target character and a second prediction intention corresponding to a second moment through voice recognition processing, wherein the second moment is the next continuous moment of the first moment; judging whether a preset response condition is met or not according to the first prediction intention and the second prediction intention; and if it is judged that the preset response condition is met, performing response processing according to the to-be-pushed answer.

Description

technical field [0001] The present invention relates to the technical field of terminals, in particular to a response method, a terminal and a storage medium. Background technique [0002] With the rapid development of the mobile Internet, speech recognition and related technologies have become one of the most natural and efficient means of human-computer interaction, widely used in voice dialing, voice navigation, smart home control, voice search, dictation data entry and other scenarios. Speech recognition refers to the process of converting audio data into text information by obtaining useful information from audio data and using related technologies to identify audio data. [0003] In practical applications, when performing speech recognition for large-scale speech signal input, the speech recognition, intent recognition, and answer assembly are often performed after the user has finished speaking, and then the answer processing is performed according to the assembled an...

AI Technical Summary

Problems solved by technology

[0003] In practical applications, when performing speech recognition for large-scale speech signal input, the speech recognition, intent recognition, and answer assembly are often performed after the user has finished speaking, and then the answer processing is performed according to the assembled answer. It affects the processing efficiency of response processing; and when performing intent recognition, a single recognition intent leads to the loss of user intent, reducing the accuracy of response processing

Images