DEVICE METHOD AND READABLE MEDIA FOR MULTIMODAL RECOGNIZING EMOTION BASED ON ARTIFICIAL INTELLIGENCE

摘要

The multi-modal emotional recognition device using artificial intelligence of the present disclosure is a multi-modal emotional recognition device using artificial intelligence, comprising: a data input unit that receives a user's image data and audio data, and generates voice feature data from the audio data. A pre-processing unit, a data pre-processing unit including an image pre-processing unit generating one or more facial feature data from the image data, and preliminary reasoning generating context determination data regarding whether a user's context changes according to a temporal order based on the image data And a main reasoning unit generating at least one sub-feature map based on the voice feature data or the face feature data, and inferring a user's emotional state based on the sub-feature map and the situation determination data.