Managing metadata enrichment of digital asset portfolios
Contextual data may be generated from assets in asset portfolios using metadata enrichment services. A recommendation engine may generate a set of recommended assets for presentation in a content stream based on the contextual data. Brand safety may be implemented using a brand safety policy that uses the contextual data as indicators of potentially offensive content. Advertisements included in the content stream may also be targeted based on the contextual data.
1. A computer-implemented method, comprising:
identifying, by one or more computer processors, first video content streamed to a user computing device and selected by a user for playing back on the user computing device;
applying, by the one or more computer processors, one or more video computing techniques to the first video content;
extracting, by the one or more computer processors, video context metadata associated with the first video content;
selecting, by the one or more computer processors, a set of second video contents from a video content repository, based at least in part on one or more video content control parameters and the video context metadata associated with the first video content;
assigning a set of weighted composite scores to the set of second video contents using second video context metadata associated with the set of second video contents;
identifying, by the one or more computer processors, a specific second video content from among the set of second video contents based at least in part on the set of weighted composite scores assigned to the set of second video contents;
causing, by the one or more computer processors, the second video content to be played back with the user computing device.
2. The method of claim 1 , wherein the video context metadata comprises one or more keywords extracted from a transcript of the first video content.
3. The method of claim 1 , wherein the video context metadata comprises an identifier of a visually depicted image portion in the first video content.
4. The method of claim 1 , wherein the video context metadata comprises an identified logo visually depicted in the first video content.
5. The method of claim 1 , wherein the video context metadata comprises an analysis of a visually depicted event happening in the first video content.
6. The method of claim 1 , wherein the video context metadata comprises specific non-visual information, relating to the user, determined based at least in part on visually depictions in the first video content.
7. The method of claim 1 , wherein the video context metadata comprises temporal attribute information associated with one or more clusters of frames of the first video content, and wherein the second video contents comprise a targeted video content placed after the one or more clusters of frames of the first video content based on the temporal attribute information and the one or more video content control parameters.
8. A system comprising:
one or more computer processors;
one or more non-transitory computer-readable media, storing one or more sequences of instructions, wherein execution of the one or more sequences of instructions by the one or more computer processors causes the one or more computer processors to perform:
identifying, by the one or more computer processors, first video content streamed to a user computing device and selected by a user for playing back on the user computing device;
applying, by the one or more computer processors, one or more video computing techniques to the first video content;
extracting, by the one or more computer processors, video context metadata associated with the first video content;
selecting, by the one or more computer processors, a set of second video contents from a video content repository, based at least in part on one or more video content control parameters and the video context metadata associated with the first video content;
assigning a set of weighted composite scores to the set of second video contents using second video context metadata associated with the set of second video contents;
identifying, by the one or more computer processors, a specific second video content from among the set of second video contents based at least in part on the set of weighted composite scores assigned to the set of second video contents;
causing, by the one or more computer processors, the second video content to be played back with the user computing device.
9. The system of claim 8 , wherein the video context metadata comprises one or more keywords extracted from a transcript of the first video content.
10. The system of claim 8 , wherein the video context metadata comprises an identifier of a visually depicted image portion in the first video content.
11. The system of claim 8 , wherein the video context metadata comprises an identified logo visually depicted in the first video content.
12. The system of claim 8 , wherein the video context metadata comprises an analysis of a visually depicted event happening in the first video content.
13. The system of claim 8 , wherein the video context metadata comprises specific non-visual information, relating to the user, determined based at least in part on visually depictions in the first video content.
14. The system of claim 8 , wherein the video context metadata comprises temporal attribute information associated with one or more clusters of frames of the first video content, and wherein the second video contents comprise a targeted video content placed after the one or more clusters of frames of the first video content based on the temporal attribute information and the one or more video content control parameters.
15. One or more non-transitory computer-readable media, storing one or more sequences of instructions, wherein execution of the one or more sequences of instructions by one or more computer processors causes the one or more processors to perform:
identifying, by the one or more computer processors, first video content streamed to a user computing device and selected by a user for playing back on the user computing device;
applying, by the one or more computer processors, one or more video computing techniques to the first video content;
extracting, by the one or more computer processors, video context metadata associated with the first video content;
selecting, by the one or more computer processors, a set of second video contents from a video content repository, based at least in part on one or more video content control parameters and the video context metadata associated with the first video content;
assigning a set of weighted composite scores to the set of second video contents using second video context metadata associated with the set of second video contents;
identifying, by the one or more computer processors, a specific second video content from among the set of second video contents based at least in part on the set of weighted composite scores assigned to the set of second video contents;
causing, by the one or more computer processors, the second video content to be played back with the user computing device.
16. The one or more non-transitory computer-readable media of claim 15 , wherein the video context metadata comprises one or more keywords extracted from a transcript of the first video content.
17. The one or more non-transitory computer-readable media of claim 15 , wherein the video context metadata comprises an identifier of a visually depicted image portion in the first video content.
18. The one or more non-transitory computer-readable media of claim 15 , wherein the video context metadata comprises an identified logo visually depicted in the first video content.
19. The one or more non-transitory computer-readable media of claim 15 , wherein the video context metadata comprises an analysis of a visually depicted event happening in the first video content.
20. The one or more non-transitory computer-readable media of claim 15 , wherein the video context metadata comprises specific non-visual information, relating to the user, determined based at least in part on visually depictions in the first video content.
21. The one or more non-transitory computer-readable media of claim 15 , wherein the video context metadata comprises temporal attribute information associated with one or more clusters of frames of the first video content, and wherein the second video contents comprise a targeted video content placed after the one or more clusters of frames of the first video content based on the temporal attribute information and the one or more video content control parameters.