Granted Patent B2

US 12,413,799 · App. 18/399,367 · Granted Sep 9, 2025

Inventors: Xinyi Li (Beijing, CN); Ye Lin (Beijing, CN); Min Zhu (Beijing, CN)

Assignee: DOUYIN VISION CO., LTD.

H04N21/239H04N21/4668

Abstract

Claims (69)

1. A method for controlling video playing, comprising:

invoking a human-computer interaction portal while displaying a video playing window in which a first video is played, wherein the human-computer interaction portal is configured to acquire user feedback on the first video;

receiving feedback information associated with the first video through the human-computer interaction portal;

sending the feedback information associated with the first video to a pre-trained video recommendation model while the first video is displayed in the video playing window, wherein the pre-trained video recommendation model performs real-time video recommendation based on the feedback information associated with the first video;

receiving at least one second video determined based on an output of the pre-trained video recommendation model, wherein the at least one second video is different from the first video; and

presenting the at least one second video in the video playing window.

2. A terminal device, comprising:

a memory storing a program and a processor, wherein the program upon execution by the processor causes the processor to implement operations comprising:

invoking a human-computer interaction portal while displaying a video playing window in which a first video is displayed, wherein the human-computer interaction portal is configured to acquire user feedback on the first video;

receiving feedback information associated with the first video through the human-computer interaction portal;

sending the feedback information associated with the first video to a pre-trained video recommendation model while the first video is displayed in the video playing window, wherein the pre-trained video recommendation model performs real-time video recommendation based on the feedback information associated with the first video;

receiving at least one second video determined based on an output of the pre-trained video recommendation model, wherein the at least one second video is different from the first video; and

presenting the at least one second video in the video playing window.

3. A non-transitory computer-readable storage medium, storing a program that upon execution by a processor causes the processor to implement operations comprising:

invoking a human-computer interaction portal while displaying a video playing window in which a first video is played, wherein the human-computer interaction portal is configured to acquire user feedback on the first video;

receiving feedback information associated with the first video through the human-computer interaction portal;

sending the feedback information associated with the first video to a pre-trained video recommendation model while the first video is displayed in the video playing window, wherein the pre-trained video recommendation model performs real-time video recommendation based on the feedback information associated with the first video;

receiving at least one second video determined based on an output of the pre-trained video recommendation model, wherein the at least one second video is different from the first video; and

presenting the at least one second video in the video playing window.

4. The method of claim 1 , wherein the video playing comprises playing streamed video data.

5. The method of claim 1 , further comprising:

stopping playing the first video during a process of invoking the human-computer interaction portal; and

continuing to display the video playing window while stopping playing the first video.

6. The method of claim 1 , further comprising:

closing the human-computer interaction portal in response to receiving the feedback information through the human-computer interaction portal; and

automatically and directly playing the at least one second video in the video playing window.

7. The method of claim 1 , wherein the human-computer interaction portal comprises a human-computer interaction interface, and wherein the method further comprises displaying the human-computer interaction interface by overlaying the human-computer interaction interface on the video playing window.

8. The method of claim 1 , wherein the human-computer interaction portal comprises a human-computer interaction interface, and wherein the method further comprises:

reducing a size of the video playing window; and

displaying the human-computer interaction interface in a second area while displaying the size-reduced video playing window in a first area.

9. The method of claim 8 , further comprising:

restoring the size of the video playing window when the at least one second video is played.

10. The method of claim 1 , wherein the human-computer interaction portal comprises a human-computer interaction voice component, and wherein the human-computer interaction voice component is configured to play, acquire, and recognize voice signals.

11. The method of claim 1 , further comprising at least one of:

automatically invoking the human-computer interaction portal in response to detecting a target object in the first video during playing the first video;

automatically invoking the human-computer interaction portal in response to detecting that the first video is played to a certain time instant;

automatically invoking the human-computer interaction portal in response to detecting a completion of playing the first video; or

automatically invoking the human-computer interaction portal in response to detecting that a number of repetitions of playing the first video reaches a threshold.

12. The terminal device of claim 2 , the operations further comprising:

stopping playing the first video during a process of invoking the human-computer interaction portal; and

continuing to display the video playing window while stopping playing the first video.

13. The terminal device of claim 2 , the operations further comprising:

closing the human-computer interaction portal in response to receiving the feedback information through the human-computer interaction portal; and

automatically and directly playing the at least one second video in the video playing window.

14. The terminal device of claim 2 , wherein the human-computer interaction portal comprises a human-computer interaction interface, and wherein the method further comprises displaying the human-computer interaction interface by overlaying the human-computer interaction interface on the video playing window.

15. The terminal device of claim 2 , wherein the human-computer interaction portal comprises a human-computer interaction interface, and wherein the operations further comprise:

reducing a size of the video playing window;

displaying the human-computer interaction interface in a second area while displaying the size-reduced video playing window in a first area; and

restoring the size of the video playing window when the at least one second video is played.

16. The terminal device of claim 2 , the operations further comprising at least one of:

automatically invoking the human-computer interaction portal in response to detecting a target object in the first video during playing the first video;

automatically invoking the human-computer interaction portal in response to detecting that the first video is played to a certain time instant;

automatically invoking the human-computer interaction portal in response to detecting a completion of playing the first video; or

automatically invoking the human-computer interaction portal in response to detecting that a number of repetitions of playing the first video reaches a threshold.

17. The non-transitory computer-readable storage medium of claim 3 , the operations further comprising:

stopping playing the first video during a process of invoking the human-computer interaction portal; and

continuing to display the video playing window while stopping playing the first video.

18. The non-transitory computer-readable storage medium of claim 3 , the operations further comprising:

closing the human-computer interaction portal in response to receiving the feedback information through the human-computer interaction portal; and

automatically and directly playing the at least one second video in the video playing window.

19. The non-transitory computer-readable storage medium of claim 3 , wherein the human-computer interaction portal comprises a human-computer interaction interface, and wherein the operations further comprise:

reducing a size of the video playing window;

displaying the human-computer interaction interface in a second area while displaying the size-reduced video playing window in a first area; and

restoring the size of the video playing window when the at least one second video is played.

20. The non-transitory computer-readable storage medium of claim 3 , the operations further comprising at least one of:

automatically invoking the human-computer interaction portal in response to detecting a target object in the first video during playing the first video;

automatically invoking the human-computer interaction portal in response to detecting that the first video is played to a certain time instant;

automatically invoking the human-computer interaction portal in response to detecting a completion of playing the first video; or

automatically invoking the human-computer interaction portal in response to detecting that a number of repetitions of playing the first video reaches a threshold.

Assignments (6)

Priority Claims (1)

Continuity (3)

References Cited (41)