This paper introduces computational narrative analysis and visual recognition algorithms to combine quantitative and qualitative research on film and television adaptations of Chinese and foreign classic literature. The film and television works of literary adaptation of Pride and Prejudice and Dream of the Red Chamber are selected as examples, and through TF-IDF, LDA thematic model and deep learning methods, the plot structure, emotional arc and thematic model of the script and the original are compared to each other, to reveal the law of narrative structure replacement in the adaptation; at the same time, the combination of image features combining the spatial pyramid model and contextually relevant histogram are utilized to construct the work At the same time, the combination of spatial pyramid model and context-dependent histogram image features is used to construct a work style analysis model, and the key frames of the film are identified with typological visual elements. From the results of the study, it can be seen that there are seven themes in Chinese and foreign literary works, the warm tone of film and television works accounted for more than 20%, the cold tone occupies a small portion, the film and television content is dominated by the warm tone, in the emotional fragments of panic and excitement, the sound effects and the background music production are mostly using percussion musical instruments, in the mood of relaxation and sadness, the film and television works of the orchestral musical instruments are more used, the tempo of the camera transition are relatively smooth.
