Man-machine interaction method and device, storage medium and electronic device

Abstract

The invention relates to a man-machine interaction method, a man-machine interaction device, a storage medium and an electronic device. The method comprises the following steps: acquiring video data during the process that a user inputs first voice information; inputting the video data into an answer generating model network, thus obtaining answer information corresponding to the first voice information and output by the answer generating model network, wherein the answer generating model network comprises a separation model, a human face information extracting model, a voice recognizing model, a human face information sequence generating model and an answer generating model, the input of the human face information extracting model is coupled with the image output of the separation model,the input of voice recognizing model is coupled with the voice output of the separation model, the input of the human face information sequence generating model is coupled with the output of the humanface information extracting model, and the input of the answer generating model is coupled with the output of the human face information sequence generating model and the output of the voice recognizing model; and outputting the answer information. With the technical scheme, the accuracy of voice information analysis and the answer information can be improved.

Description

technical field [0001] The present disclosure relates to the field of human-computer interaction, and in particular, to a method, device, storage medium and electronic equipment for human-computer interaction. Background technique [0002] With the rapid development of computer technology and the improvement of artificial intelligence, human-computer interaction is becoming more and more important in people's lives, such as augmented reality applications, mixed reality applications, and educational applications. In the prior art, human-computer interaction usually processes speech information containing semantic features, and determines dialogues or problems in human-computer interaction through context-based semantic analysis. However, in actual use scenarios, the same voice information in the same scene may still correspond to multiple semantics, and the corresponding dialogue or question cannot be accurately determined through the above method, which reduces the experienc...

AI Technical Summary

Problems solved by technology

However, in actual usage scenarios, the same voice information in the same scenario may still correspond to multiple semantics. The above method still cannot accurately determine the corresponding dialogue or question, which reduces the experience of human-computer interaction.

Images