Image output method and device of virtual character, equipment and storage medium

Abstract

The embodiment of the invention relates to the field of artificial intelligence, and discloses an image output method and device of a virtual character, equipment and a storage medium. The method comprises the following steps: when an interaction request of a target object is received, outputting a preset interaction response according to the interaction request, and collecting audio data and video data of the target object; extracting first voice data of the target object according to the audio data; acquiring second voice data corresponding to the target object according to the video data; determining target voice data of the target object according to the first voice data and the second voice data; obtaining target text information according to the target voice; performing semantic classification processing on the target text information by utilizing a semantic analysis model to obtain a classification result; obtaining a target response scheme according to the classification result, and generating response voice information and face image control information of the virtual character; and outputting response voice information, and controlling the display of the face state of the virtual character according to the face image control information.

Description

Technical field [0001] The present application relates to speech recognition technology, in particular, to a virtual role image output method, apparatus, device, and storage medium. Background technique [0002] With today, with the development of Internet technology and multimedia technology, people's dependence of electronic products is getting stronger and stronger. At present, there are many applications of virtual characters interaction, and some speech or action can be achieved by interacting with virtual characters. Since most of the current virtual technologies are obtained by post-processing after three-dimensional modeling, the expression of the virtual character is not natural when interacting, the user is interactive, and the current interaction The way is mostly interacting through the preset human-computer interaction, reducing the fun of interaction. Inventive content [0003] The primary object of the present application example is to provide a virtual role image...

AI Technical Summary

Problems solved by technology

[0002] Nowadays, with the development of Internet technology and multimedia technology, people are becoming more and more dependent on electronic products. At present, there are many applications for virtual character interaction. By interacting with virtual characters, some voices or actions can be obtained. However, since the current virtual technology is mostly obtained through post-processing after 3D modeling, the expressions of the virtual characters are unnatural when interacting, and the user experience is not good when interacting. At the same time, the current interaction Most of the way is to interact through the preset human-computer interaction interface, which reduces the fun of the interaction experience

Images