Method and system for editing video on basis of context obtained using artificial intelligence

A computer apparatus comprising:

• at least one processor configured to execute a computer-readable instruction,
• wherein the at least one processor is configured to:
• analyze an input video through an artificial intelligence model, set a plurality of contexts for the video, and extract, from the video, a plurality of clips corresponding to the set plurality of contexts, respectively,
• generate a user interface for selecting a specific context from among the plurality of contexts,
• provide a plurality of clips extracted from the video for a context selected from among the plurality of contexts through the generated user interface, through the user interface,
• provide an editing function of a frame unit for a clip selected from among the plurality of clips provided through the user interface, wherein the editing function comprises providing a plurality of individual frames from the selected clip through the user interface, whereby the user interface is configured and arranged to allow a user to delete one or more of the individual frames and to change the order of the individual frames and to insert an additional frame between two of the individual frames;
• and
• generate a highlight image of the selected context for the video by merging clips selected from among the plurality of clips provided through the user interface,
• wherein:
• each of the plurality of contexts has a hierarchical structure of a single main context and a plurality of sub-contexts for the single main context, and
• the at least one processor is configured to classify a plurality of clips extracted for the single main context into the plurality of sub-contexts,
• the single main context comprises a person that appears in the input video, whereby each of the plurality of clips extracted from the video includes the person in each frame thereof;
• and
• the plurality of sub-contexts comprises at least three of the following sub-contexts:
• single, in which the person is shown alone;
• multiple, in which the person is shown with others;
• food, in which the person is shown with food;
• animal, in which the person is shown with an animal;
• and
• a particular season, in which the person is shown in the particular season.