Electronic apparatus and method for controlling the electronic apparatus

An electronic apparatus comprising:

• a processor, the processor configured to control the electronic apparatus to:
• obtain multimedia content including a plurality of image frames and multimedia content-related information related to the multimedia content, the multimedia content-related information including a plurality of keywords,
• select a first image frame and a second image frame each including an object related to the obtained multimedia content-related information from among objects included in the plurality of image frames,
• obtain first description information for the first image frame, based on the first image frame and the obtained multimedia content-related information, the first description information including first text items associated with objects included in the first image frame and information on a relationship between the first text items,
• obtaining second description information for the second image frame based on the second image frame and the obtained multimedia content-related information, the second description information including second text items associated with objects included in the second image frame and information on a relationship between the second text items:
• obtain third description information for the multimedia content by associating text items commonly included in the first text items and the second text items;
• receive a command comprising a scene content request;
• obtain scene content from the multimedia content by comparing the scene content request to the second description information;
• and
• output the obtained scene content.

A non-transitory computer-readable recording medium storing a program which, when executed by a processor of an electronic apparatus, causes the electronic apparatus to perform operations comprising:

• obtaining multimedia content including a plurality of image frames;
• obtaining multimedia content-related information related to the multimedia content, the multimedia content-related information including a plurality of keywords;
• selecting a first image frame and a second image frame each including an object related to the obtained multimedia content-related information from among objects included in the plurality of image frames;
• obtaining first description information for the first image frame, based on the first image frame and the obtained multimedia content-related information, the first description information including first text items associated with objects included in the first image frame and information on a relationship between the first text items;
• obtaining a second description information for the second image frame, based on the second image frame and the obtained multimedia content-related information, the second description information including second text items associated with objects included in the second image frame and information on a relationship between the second text items;
• obtaining third description information for the multimedia content by associating text items commonly included in the first text items and the second text items;
• receiving a command comprising a scene content request;
• obtaining scene content from the multimedia content by comparing the scene content request to the second description information;
• and
• outputting the obtained scene content.