Method and apparatus for assisting watching video content

1. A method for assisting video content viewing, the method being performed by processing circuitry of a user terminal, and the method comprising:

displaying a playback screen of first video content on a display of the user terminal, the first video content being played on the playback screen;

generating a graphic object configured to enable playback of similar content associated with a first playback time of the first video content; and

displaying the graphic object on the display together with the playback screen of the first video content, wherein

the method further includes

extracting a keyword based on information associated with the first video content,

determining at least one comparison criterion based on the keyword, and

determining the similar content based on the at least one comparison criterion,

the first playback time in the first video content has a similarity to preference information, the similarity being equal to or greater than a first threshold,

the preference information includes at least one of a preferred image feature, a preferred sound feature, or a preferred text feature, and

the method further includes determining the preference information based on a plurality of playback times in a plurality of first videos at which a respective positive feedback input is received, each of the plurality of playback times being associated with a respective first image feature, a respective first sound feature, and a respective first text feature.

2. The method according to claim 1 , wherein the information associated with the first video content includes at least one of a title of the first video content, a description of the first video content, or a hashtag corresponding to the first video content.

3. The method according to claim 1 , wherein the similar content is a second playback time in the first video content or a third playback time in a second video content.

4. The method according to claim 1 , wherein the at least one comparison criterion includes at least one of a second image feature, a second sound feature, or a second text feature.

5. The method according to claim 1 , wherein the determining the at least one comparison criterion comprises determining the at least one comparison criterion to include a second image feature and a second text feature in response to determining that the keyword is associated with a visual theme.

6. The method according to claim 1 , wherein the determining the at least one comparison criterion comprises determining the at least one comparison criterion to include a second sound feature and a second text feature in response to determining that the keyword is associated with an auditory theme.

7. The method according to claim 1 , wherein the displaying the graphic object comprises displaying the graphic object in response to receiving a positive feedback input, the first playback time in the first video content being associated with a point at which the positive feedback input is received.

8. The method according to claim 1 , further comprising:

displaying a chatbot message on the display together with the playback screen of the first video content while playing the first video content, the chatbot message being associated with a second playback time in the first video content.

9. The method according to claim 8 , further comprising:

generating the chatbot message using a chatbot model, the chatbot model being trained based on

a plurality of comments in a second plurality of videos, and

at least one of a respective third image feature, a respective third sound feature, or a respective third text feature associated with each of the plurality of comments.

10. The method according to claim 9 , wherein the chatbot model is trained by applying a weight based on a respective number of positive feedback inputs associated with each of the plurality of comments.

11. The method according to claim 9 , further comprising:

determining the chatbot message based on at least one of a fourth image feature, a fourth sound feature, or a fourth text feature of the second playback time in the first video content.

12. The method according to claim 9 , wherein

the second playback time in the first video content is associated with a point at which an utterance is input into a chat window; and

the method further comprises determining the chatbot message based on at least one of

a fourth image feature, a fourth sound feature, or a fourth text feature of the second playback time in the first video content, and

the utterance.

13. The method according to claim 1 , further comprising:

displaying a popular comment on the display together with the playback screen of the first video content while playing the first video content, the popular comment being associated with a third playback time in the first video content.

14. The method according to claim 13 , wherein the popular comment is a comment that received a highest amount of positive feedback among a plurality of comments that include a timestamp of the third playback time.

15. The method according to claim 13 , wherein the popular comment has a number of inputs indicating positive feedback equal to or greater than a second threshold.

16. A non-transitory computer-readable recording medium storing instructions that, when executed by one or more processors, cause the one or more processors to perform the method according to claim 1 .

17. A user terminal, comprising:

a display;

communication unit; and

processing circuitry configured to

display a playback screen of first video content on the display, the first video content being played on the playback screen;

generate a graphic object configured to enable playback of similar content associated with a first playback time of the first video content; and

displaying the graphic object on the display together with the playback screen of the first video content, wherein

the processing circuitry is configured to

extract a keyword based on information associated with the first video content,

determine at least one comparison criterion based on the keyword, and

determine the similar content based on the at least one comparison criterion,

the first playback time in the first video content has a similarity to preference information, the similarity being equal to or greater than a first threshold,

the preference information includes at least one of a preferred image feature, a preferred sound feature, or a preferred text feature, and

the processing circuitry is configured to determine the preference information based on a plurality of playback times in a plurality of videos at which a respective positive feedback input is received, each of the plurality of playback times being associated with a respective image feature, a respective sound feature, and a respective text feature.