Systems and methods for identifying electronic content using video graphs
Systems and methods are provided for identifying and recommending electronic content to consumers. In accordance with an implementation, one or more elements of electronic content are identified based on video graph data. In an exemplary method, information associated with a first element of video content is received, and corresponding video graph data is obtained. One or more second elements of video content that are similar to the first element of video content are identified based on the obtained video graph data. A subset the first and second elements of video content is subsequently identified for delivery to the user.
1. A system comprising:
at least one processor; and
at least one storage device storing instructions which, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
receiving, from a client device associated with a user, information identifying a first video clip of interest to the user;
retrieving, from the at least one storage device, one or more video graphs that reference the first video clip, the one or more video graphs including a plurality of association values between the first video clip and a plurality of second video clips;
determining that a subset of the association values between the first video clip and the plurality of second video clips exceeds a threshold value for presentation to the user;
adjusting one or more association values for one or more of the plurality of second video clips based on a number of the subset of association values exceeding the threshold value;
generating, based on the association values, a ranked candidate video list including a subset of the plurality of second video clips; and
transmitting at least a portion of the ranked candidate video list to the client device.
2. The system of claim 1 , wherein ranking each video clip in the candidate video list based on the one or more factors further comprises ranking each video clip in the candidate video list based on at least one of: a number video clips linked to each video clip, a popularity of each video clip, or metadata associated with each video clip.
3. The system of claim 1 , wherein ranking each video clip in the candidate video list based on the one or more factors further comprises ranking each video clip in the candidate video list based on at least one of: (i) a number of users that have consumed each video clip, (ii) a number of users that have accessed each video clip, or (iii) a number of users that have accessed or consumed video content similar to each video clip.
4. The system of claim 1 , wherein the plurality of association values indicative of the association between the first video clip and each of the plurality of second video clips are based on at least one of: a contextual similarity between the first video clip and the plurality of second video clips, an auditory similarity between one or more segments of the first video clip and one or more segments of the plurality of second video clips, or a visual similarity between the one or more segments of the first video clip and the one of more segments of the plurality of second video clips.
5. The system of claim 1 , wherein prior to transmitting the at least the portion of the ranked candidate video list, the operations further comprise filtering the ranked candidate video list to identify one or more video clips within the candidate video list that are similar or identical to one or more video clips watched by other users associated with the user.
6. The system of claim 5 , wherein subsequent to filtering the ranked candidate video list, the operations further comprise adjusting the ranking of one or more video clips of the candidate video list based on at least one of a preference of the user or a pattern of video consumption of the user.
7. The system of claim 1 , wherein the operations further comprise updating the one or more video graphs in response to the determination that the subset of the plurality of values exceeds the threshold value for presentation to the user.
8. The system of claim 1 , wherein the user is associated with a social network.
9. A computer-implemented method using at least one processor coupled to at least one storage device storing instructions which, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
receiving, from a client device associated with a user, information identifying a first video clip of interest to the user;
retrieving, from the at least one storage device, one or more video graphs that reference the first video clip, the one or more video graphs including a plurality of association values between the first video clip and a plurality of second video clips;
determining that a subset of the association values between the first video clip and the plurality of second video clips exceeds a threshold value for presentation to the user;
adjusting one or more association values for one or more of the plurality of second video clips based on a number of the subset of association values exceeding the threshold value;
generating, based on the association values, a ranked candidate video list including a subset of the plurality of second video clips; and
transmitting at least a portion of the ranked candidate video list to the client device.
10. The method of claim 9 , wherein ranking each video clip in the candidate video list based on the one or more factors further comprises ranking each video clip in the candidate video list based on at least one of: a number video clips linked to each video clip, a popularity of each video clip, or metadata associated with each video clip.
11. The method of claim 9 , wherein ranking each video clip in the candidate video list based on the one or more factors further comprises ranking each video clip in the candidate video list based on at least one of: (i) a number of users that have consumed each video clip, (ii) a number of users that have accessed each video clip, or (iii) a number of users that have accessed or consumed video content similar to each video clip.
12. The method of claim 9 , wherein the plurality of association values indicative of the association between the first video clip and each of the plurality of second video clips are based on at least one of: a contextual similarity between the first video clip and the plurality of second video clips, an auditory similarity between one or more segments of the first video clip and one or more segments of the plurality of second video clips, or a visual similarity between the one or more segments of the first video clip and the one of more segments of the plurality of second video clips.
13. The method of claim 9 , wherein prior to transmitting the at least the portion of the ranked candidate video list, the operations further comprise filtering the ranked candidate video list to identify one or more video clips within the candidate video list that are similar or identical to one or more video clips watched by other users associated with the user.
14. The method of claim 13 , wherein subsequent to filtering the ranked candidate video list, the operations further comprise adjusting the ranking of one or more video clips of the candidate video list based on at least one of a preference of the user or a pattern of video consumption of the user.
15. The method of claim 9 , wherein the operations further comprise updating the one or more video graphs in response to the determination that the subset of the plurality of values exceeds the threshold value for presentation to the user.
16. A non-transitory computer-readable medium storing computer-executable instructions which, when executed by at least one processor, cause the at least one processor to perform operations comprising:
receiving, from a client device associated with a user, information identifying a first video clip of interest to the user;
retrieving one or more video graphs that reference the first video clip, the one or more video graphs including a plurality of association values between the first video clip and a plurality of second video clips;
determining that a subset of the association values between the first video clip and the plurality of second video clips exceeds a threshold value for presentation to the user;
adjusting one or more association values for one or more of the plurality of second video clips based on a number of the subset of association values exceeding the threshold value;
generating, based on the association values, a ranked candidate video list including a subset of the plurality of second video clips; and
transmitting at least a portion of the ranked candidate video list to the client device.
17. The computer-readable medium of claim 16 , wherein ranking each video clip in the candidate video list based on the one or more factors further comprises ranking each video clip in the candidate video list based on at least one of: a number video clips linked to each video clip, a popularity of each video clip, or metadata associated with each video clip.
18. The computer-readable medium of claim 16 , wherein ranking each video clip in the candidate video list based on the one or more factors further comprises ranking each video clip in the candidate video list based on at least one of: (i) a number of users that have consumed each video clip, (ii) a number of users that have accessed each video clip, or (iii) a number of users that have accessed or consumed video content similar to each video clip.
19. The computer-readable medium of claim 16 , wherein the plurality of association values indicative of the association between the first video clip and each of the plurality of second video clips are based on at least one of: a contextual similarity between the first video clip and the plurality of second video clips, an auditory similarity between one or more segments of the first video clip and one or more segments of the plurality of second video clips, or a visual similarity between the one or more segments of the first video clip and the one of more segments of the plurality of second video clips.
20. The computer-readable medium of claim 16 , wherein prior to transmitting the at least the portion of the ranked candidate video list, the operations further comprise filtering the ranked candidate video list to identify one or more video clips within the candidate video list that are similar or identical to one or more video clips watched by other users associated with the user.