Music is the product of consciousness and emotion, and is closely related to human life. The background music of film and television under big data has received extensive attention. Emotion is one of the main semantic information contained in music. Classification based on emotion can deeply explore music categories from multiple perspectives and improve the efficiency of music recognition. In recent years, it has gradually become a research hotspot in background music recognition. The research purpose of this paper is to identify the background music of film and television based on convolutional neural network. In the experiment, using the convolution operation, the selected eleven musical instruments basically cover a variety of music types, so as to identify the background music of film and television.