Emotion classification broadcasting system and method based on knowledge distillation

The invention discloses an emotion classification broadcasting system and method based on knowledge distillation, and the system comprises a program broadcast control service subsystem which is used for carrying out the content convergence of program text contents; the AI service subsystem is used for performing knowledge distillation on the emotion classification BERT pre-training large model, and training to obtain an edge-side emotion classification small model; and the intelligent broadcast terminal subsystem is used for transmitting the emotion factors and the program texts obtained by classification to a text-to-voice conversion engine, generating audio programs with the emotion factors and broadcasting the audio programs. According to the invention, the broadcasting system has a program broadcasting effect with emotional colors, and the transmitted data volume is greatly reduced due to the fact that the transmitted program data is changed from audio to text, so that the program transmission time is sho