Video generation method and apparatus, and device, medium and product
The present disclosure provides a video generation method and apparatus, a device, and a medium and a product, and relates to the technical field of computers. The method includes: acquiring description information of a target video to be generated; according to the description information of the target video, acquiring, from a video material library, a target clip corresponding to the description information; splicing the target clip with each candidate clip of a plurality of candidate clips in the video material library respectively to obtain a plurality of candidate videos; evaluating a score of each candidate video of the plurality of candidate videos; and generating the target video according to the score of each candidate video of the plurality of candidate videos.
1. A video generation method, comprising:
acquiring description information of a target video to be generated;
acquiring, from a plurality of video clips in a video material library, a target clip corresponding to the description information according to the description information of the target video, wherein the plurality of video clips have corresponding description information;
determining a plurality of candidate clips based on the target clip and the plurality of video clips;
splicing the target clip with each candidate clip of the plurality of candidate clips respectively to obtain a plurality of candidate videos;
evaluating a score of each candidate video of the plurality of candidate videos; and
generating the target video according to the score of each candidate video of the plurality of candidate videos.
2. The method according to claim 1 , wherein evaluating the score of each candidate video of the plurality of candidate videos comprises:
evaluating the score of each candidate video of the plurality of candidate videos based on semantic continuity of adjacent clips of each candidate video and/or a click-through rate of each clip.
3. The method according to claim 1 , wherein acquiring the description information of the target video to be generated comprises:
acquiring description information inputted by a target user for the target video to be generated.
4. The method according to claim 1 , wherein the description information is generated randomly or generated based on historical description information.
5. The method according to claim 1 , wherein the method further comprises:
acquiring a target user video of a target user; and
splicing the target user video with the plurality of candidate videos respectively to obtain spliced candidate videos;
evaluating the score of each candidate video of the plurality of candidate videos comprises:
evaluating scores of the spliced candidate videos; and
generating the target video according to the score of each candidate video of the plurality of candidate videos comprises:
generating the target video according to the scores of the spliced candidate videos.
6. The method according to claim 1 , wherein the method further comprises:
delivering the target video within a first user range and acquiring behavior information of a user within the first user range with respect to the target video;
when the behavior information meets a preset condition, delivering the target video within a second user range;
wherein a number of the user within the first user range is less than a number of users within the second user range.
7. The method according to claim 6 , wherein the behavior information comprises a completion rate and/or a play duration, and the preset condition comprises that the completion rate is greater than a first preset threshold and/or the play duration is greater than a second preset threshold.
8. The method according to claim 1 , wherein the method further comprises:
receiving adjustment information of a target user with respect to the target video; and
adjusting the target video according to the adjustment information.
9. The method according to claim 2 , wherein acquiring the description information of the target video to be generated comprises:
acquiring description information inputted by a target user for the target video to be generated.
10. The method according to claim 2 , wherein the description information is generated randomly or generated based on historical description information.
11. The method according to claim 2 , wherein the method further comprises:
acquiring a target user video of a target user; and
splicing the target user video with the plurality of candidate videos respectively to obtain spliced candidate videos;
evaluating the score of each candidate video of the plurality of candidate videos comprises:
evaluating scores of the spliced candidate videos; and
generating the target video according to the score of each candidate video of the plurality of candidate videos comprises:
generating the target video according to the scores of the spliced candidate videos.
12. The method according to claim 5 , wherein the method further comprises:
delivering the target video within a first user range and acquiring behavior information of a user within the first user range with respect to the target video;
when the behavior information meets a preset condition, delivering the target video within a second user range;
wherein a number of the user within the first user range is less than a number of users within the second user range.
13. The method according to claim 5 , wherein the method further comprises:
receiving adjustment information of a target user with respect to the target video; and
adjusting the target video according to the adjustment information.
14. The method according to claim 6 , wherein the method further comprises:
receiving adjustment information of a target user with respect to the target video; and
adjusting the target video according to the adjustment information.
15. An electronic device, comprising:
a storage apparatus storing a computer program; and
a processing apparatus, configured to execute the computer program on the storage apparatus to implement the method according to claim 1 .
16. The electronic device according to claim 15 , wherein evaluating the score of each candidate video of the plurality of candidate videos in the method comprises:
evaluating the score of each candidate video of the plurality of candidate videos based on semantic continuity of adjacent clips of each candidate video and/or a click-through rate of each clip.
17. The electronic device according to claim 15 , wherein the method further comprises:
acquiring a target user video of a target user; and
splicing the target user video with the plurality of candidate videos respectively to obtain spliced candidate videos;
evaluating the score of each candidate video of the plurality of candidate videos comprises:
evaluating scores of the spliced candidate videos; and
generating the target video according to the score of each candidate video of the plurality of candidate videos comprises:
generating the target video according to the scores of the spliced candidate videos.
18. The electronic device according to claim 15 , wherein the method further comprises:
delivering the target video within a first user range and acquiring behavior information of a user within the first user range with respect to the target video;
when the behavior information meets a preset condition, delivering the target video within a second user range;
wherein a number of the user within the first user range is less than a number of users within the second user range.
19. The electronic device according to claim 18 , wherein the behavior information comprises a completion rate and/or a play duration, and the preset condition comprises that the completion rate is greater than a first preset threshold and/or the play duration is greater than a second preset threshold.
20. A non-transitory computer-readable storage medium, wherein a computer program is stored on the non-transitory computer-readable medium, and when the computer program is executed by a processing apparatus, the method according to claim 1 is implemented.