Method, apparatus, device, and storage medium for determining implantation location of recommendation information

1. A method for determining an implantation location of recommendation information performed at a computer device, the method comprising:

acquiring a target video, the target video being a video to be implanted with recommendation information;

acquiring a target video frame in the target video according to a scene change status of the target video, the target video frame being a video frame used for determining an implantation location of the recommendation information, and the scene change status being determined according to a similarity between at least one group of video frames in the target video;

performing image recognition on the target video frame to obtain masking information of the target video frame, the masking information comprising regions corresponding to at least two types of objects in the target video frame, the regions comprising a first region corresponding to an object of a target type in the target video frame; and

determining an implantation location of the recommendation information in the target video frame based on the first region.

2. The method according to claim 1 , wherein the determining an implantation location of the recommendation information in the target video frame based on the first region comprises:

determining a target sub-region connected to the first region from the masking information; and

determining a location of the target sub-region as the implantation location of the recommendation information in the target video frame.

3. The method according to claim 2 , wherein the determining a target sub-region connected to the first region from the masking information comprises:

determining n candidate regions connected to the first region from the masking information, n being a positive integer;

determining a second region corresponding to a central role from the masking information;

determining a distance between each of the n candidate regions and the second region; and

using a region in the n candidate regions that has the largest distance to the second region as the target sub-region.

4. The method according to claim 3 , wherein the determining a second region corresponding to a central role from the masking information comprises:

determining m role regions corresponding to a role type from the masking information, m being a positive integer; and

using a role region with the largest region area in the m role regions as the second region corresponding to the central role.

5. The method according to claim 2 , wherein the determining a location of the target sub-region as the implantation location of the recommendation information in the target video frame comprises:

multiplying a region area of the target sub-region by a preset multiple as a target area of the recommendation information displayed in the target video frame;

determining a target region corresponding to the recommendation information in the target video frame according to the target area and a display shape of the recommendation information; and

using a location at which the target region covers the target sub-region as the implantation location of the recommendation information in the target video frame.

6. The method according to claim 2 , wherein the target video frame comprises at least two objects of the target type, and the first region comprises at least two candidate sub-regions corresponding to the objects of the target type; and

before the determining a target sub-region connected to the first region from the masking information, the method further comprises:

reserving a candidate sub-region with the largest area in the at least two candidate sub-regions as the filtered first region, and deleting other candidate sub-regions.

7. The method according to claim 1 , wherein the acquiring a target video frame in the target video according to a scene change status of the target video comprises:

performing video segmentation on the target video according to the scene change status of the target video, to obtain a video segment corresponding to the scene change status; and

acquiring the first key frame in the video segment as the target video frame, the target video frame being a video frame used for determining an implantation location of the recommendation information in the video segment.

8. The method according to claim 1 , wherein the performing image recognition on the target video frame to obtain masking information of the target video frame comprises:

performing image recognition on the target video frame to obtain a masking result set in the target video frame, the masking result set comprising an object category, an object region, and a confidence level that are of a recognized object; and

obtaining the filtered masking result set as the masking information of the target video frame by removing a result with a confidence level less than a required confidence level in the masking result set from the masking result set.

9. The method according to claim 1 , wherein the target type comprises at least one of a desktop type, a ground type, a sill type, and a counter type.

10. A computer device, comprising a processor and a memory, the memory storing at least one instruction, the at least one instruction, when executed by the processor, causing the computer device to perform a plurality of operations including:

acquiring a target video, the target video being a video to be implanted with recommendation information;

acquiring a target video frame in the target video according to a scene change status of the target video, the target video frame being a video frame used for determining an implantation location of the recommendation information, and the scene change status being determined according to a similarity between at least one group of video frames in the target video;

performing image recognition on the target video frame to obtain masking information of the target video frame, the masking information comprising regions corresponding to at least two types of objects in the target video frame, the regions comprising a first region corresponding to an object of a target type in the target video frame; and

determining an implantation location of the recommendation information in the target video frame based on the first region.

11. The computer device according to claim 10 , wherein the determining an implantation location of the recommendation information in the target video frame based on the first region comprises:

determining a target sub-region connected to the first region from the masking information; and

determining a location of the target sub-region as the implantation location of the recommendation information in the target video frame.

12. The computer device according to claim 11 , wherein the determining a target sub-region connected to the first region from the masking information comprises:

determining n candidate regions connected to the first region from the masking information, n being a positive integer;

determining a second region corresponding to a central role from the masking information;

determining a distance between each of the n candidate regions and the second region; and

using a region in the n candidate regions that has the largest distance to the second region as the target sub-region.

13. The computer device according to claim 12 , wherein the determining a second region corresponding to a central role from the masking information comprises:

determining m role regions corresponding to a role type from the masking information, m being a positive integer; and

using a role region with the largest region area in the m role regions as the second region corresponding to the central role.

14. The computer device according to claim 11 , wherein the determining a location of the target sub-region as the implantation location of the recommendation information in the target video frame comprises:

multiplying a region area of the target sub-region by a preset multiple as a target area of the recommendation information displayed in the target video frame;

determining a target region corresponding to the recommendation information in the target video frame according to the target area and a display shape of the recommendation information; and

using a location at which the target region covers the target sub-region as the implantation location of the recommendation information in the target video frame.

15. The computer device according to claim 11 , wherein the target video frame comprises at least two objects of the target type, and the first region comprises at least two candidate sub-regions corresponding to the objects of the target type; and

before the determining a target sub-region connected to the first region from the masking information, the method further comprises:

reserving a candidate sub-region with the largest area in the at least two candidate sub-regions as the filtered first region, and deleting other candidate sub-regions.

16. The computer device according to claim 10 , wherein the acquiring a target video frame in the target video according to a scene change status of the target video comprises:

performing video segmentation on the target video according to the scene change status of the target video, to obtain a video segment corresponding to the scene change status; and

acquiring the first key frame in the video segment as the target video frame, the target video frame being a video frame used for determining an implantation location of the recommendation information in the video segment.

17. The computer device according to claim 10 , wherein the performing image recognition on the target video frame to obtain masking information of the target video frame comprises:

performing image recognition on the target video frame to obtain a masking result set in the target video frame, the masking result set comprising an object category, an object region, and a confidence level that are of a recognized object; and

obtaining the filtered masking result set as the masking information of the target video frame by removing a result with a confidence level less than a required confidence level in the masking result set from the masking result set.

18. The computer device according to claim 10 , wherein the target type comprises at least one of a desktop type, a ground type, a sill type, and a counter type.

19. A non-transitory computer-readable storage medium, storing at least one instruction, the at least one instruction, when executed by a processor of a computer device, causing the computer device to perform a plurality of operations including:

acquiring a target video, the target video being a video to be implanted with recommendation information;

acquiring a target video frame in the target video according to a scene change status of the target video, the target video frame being a video frame used for determining an implantation location of the recommendation information, and the scene change status being determined according to a similarity between at least one group of video frames in the target video;

performing image recognition on the target video frame to obtain masking information of the target video frame, the masking information comprising regions corresponding to at least two types of objects in the target video frame, the regions comprising a first region corresponding to an object of a target type in the target video frame; and

determining an implantation location of the recommendation information in the target video frame based on the first region.

20. The non-transitory computer-readable storage medium according to claim 19 , wherein the determining an implantation location of the recommendation information in the target video frame based on the first region comprises:

determining a target sub-region connected to the first region from the masking information; and

determining a location of the target sub-region as the implantation location of the recommendation information in the target video frame.