CPC H04N 21/8549 (2013.01) | 14 Claims |
1. A processing method, comprising:
determining basic information of a target video, wherein the basic information comprises at least one of: salient object information, image information, first text information corresponding to text in the target video or second text information corresponding to audio in the target video;
determining attribute information of the target video based on the basic information;
in a case where the attribute information indicates that the target video is a video capable of being structured, performing chapter division on the target video based on the basic information to obtain at least two video clips; and
determining chapter description information of the at least two video clips, a key frame of the at least two video clips and video description information of the target video;
wherein determining the chapter description information of the at least two video clips comprises:
determining the chapter description information based on third text information corresponding to text in the at least two video clips, fourth text information corresponding to audio in the at least two video clips, image information corresponding to the at least two video clips and a first copy keyword corresponding to the at least two video clips, wherein the first copy keyword is determined based on the at least two video clips.
|