A method of processing audio or video data is provided, which relates to a field of a natural language processing technology, and in particular to a semantic understanding of a natural language. The method includes: extracting a text information from the audio or video data; generating a text outline and a plurality of time periods according to the text information, the text outline includes multi-level outline entries, and the plurality of time periods are associated with the multi-level outline entries; generating a display field for the audio or video data according to the text outline and the plurality of time periods; adding the display field to the audio or video data, so as to obtain updated audio or video data. A device, and a storage medium are further provided.