Video processing method, electronic device, and non-transitory computer-readable storage medium

An electronic device, comprising:

• at least one processing apparatuses;
• and
• a storage apparatus configured to store at least one program;
• wherein the at least one program, when executed by the at least one processing apparatus, causes the at least one processing apparatus to implement:
• determining a candidate slice information set of an original video based on video information of the original video;
• segmenting the original video into a plurality of video segments based on each piece of candidate slice information of pieces of candidate slice information in the candidate slice information set;
• inputting the plurality of video segments into an evaluation model to determine a piece of probability information of each piece of candidate slice information;
• and
• determining target slice information of the original video based on the piece of probability information corresponding to each piece of candidate slice information, wherein the piece of probability information is a probability value for each piece of candidate slice information to serve as a piece of target slice information;
• wherein the at least one program, when executed by the at least one processing apparatus, causes the at least one processing apparatus to further implement:
• in response to determining that a duration between adjacent pieces of candidate slice information is greater than a set duration threshold, newly adding one piece of slice information every other set duration threshold between the adjacent pieces of candidate slice information;
• and
• using all pieces of newly-added slice information between the adjacent pieces of candidate slice information as pieces of candidate slice information and adding all the pieces of newly-added slice information to the candidate slice information set.

A non-transitory computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processing apparatus, implements:

• determining a candidate slice information set of an original video based on video information of the original video;
• segmenting the original video into a plurality of video segments based on each piece of candidate slice information of pieces of candidate slice information in the candidate slice information set;
• inputting the plurality of video segments into an evaluation model to determine a piece of probability information of each piece of candidate slice information;
• and
• determining target slice information of the original video based on the piece of probability information corresponding to each piece of candidate slice information, wherein the piece of probability information is a probability value for each piece of candidate slice information to serve as a piece of target slice information;
• wherein the computer program, when executed by a processing apparatus, further implements:
• in response to determining that a duration between adjacent pieces of candidate slice information is greater than a set duration threshold, newly adding one piece of slice information every other set duration threshold between the adjacent pieces of candidate slice information;
• and
• using all pieces of newly-added slice information between the adjacent pieces of candidate slice information as pieces of candidate slice information and adding all the pieces of newly-added slice information to the candidate slice information set.