Video content placement optimization based on behavior and content analysis
An ad is placed in a movie, by analyzing inherent characteristics of the movie, analyzing viewed characteristics of the movie, analyzing viewer characteristics of a viewer of the movie, obtaining advertiser preferences for placement of the ad in the movie, determining costs of placing the ad in the movie based on the inherent characteristics of the movie, the viewed characteristics of the movie, the viewer characteristics and the advertiser preferences, and placing the ad in the movie in accordance with the inherent characteristics of the movie, the viewed characteristics of the movie, the viewer characteristics, the advertiser preferences and the determined costs.
1. A method, comprising:
obtaining, by a computer from play trails that track viewing behaviors of viewers of a video, statistics regarding viewing of the video by the viewers, each play trail representing a timestamped sequence of actions that a viewer of the viewers takes with respect to the video while playing the video on a user device and that together is sufficient to reconstruct the viewing in entirety, the timestamped sequence of actions including adding a deep tag to the video and replaying and pausing portions of the video, wherein each of the play trails is recorded on a device of the viewers, and wherein, among at least some of the viewers, their timestamped sequences of actions with respect to the video as recorded in the play trails are sequentially different;
determining, by the computer based at least in part from the timestamped sequences of actions recorded in the play trails, viewer characteristics and viewed characteristics,
the viewer characteristics including at least one of:
demographic information of the viewer,
an action of the viewer, or
a material previously viewed by the viewer, and
the viewed characteristics including a number of times that the video has been requested by the viewers;
retrieving or obtaining, by the computer in view of at least one of:
the statistics of the video obtained from the play trails,
the viewer characteristics, or
the viewed characteristics,
content placement preferences that specify a content placement price setting mechanism, the content placement price setting mechanism including a content placement rule;
determining, by the computer based on the content placement price setting mechanism, a plurality of prices for placing content at a plurality of places in the video;
determining, by the computer based on the content placement rule, whether placement of the content in the video is manual or automatic;
responsive to the content placement rule specifying that the placement of the content in the video is automatic, automatically placing, by the computer, the content in the video at one of the plurality of places in the video; and
responsive to the content placement rule specifying that the placement of the content in the video is manual, notifying, by the computer, a user for manual placement of the content in the video.
2. The method according to claim 1 , wherein the play trails are retrieved from a database or received from user devices of the viewers.
3. The method according to claim 1 , wherein the play trail has a head that indicates an identifier of the video.
4. The method according to claim 1 , further comprising:
storing the play trail with at least one of a time at which the play trail is received from the user device of the viewer, an identity of the viewer, or a computer address from which the play trail was sent.
5. The method according to claim 1 , wherein the play trail is stored on the user device of the viewer in a cookie or a locally stored data file that tracks the actions that the viewer takes in playing the video on the user device.
6. The method according to claim 5 , wherein the play trail is persisted on the user device such that the actions are tracked across browser sessions of a browser running on the user device.
7. The method according to claim 1 , wherein further comprising:
updating basic statistics for the video, the basic statistics including a number of deep tags created for a portion of the video, an access frequency for portions of the video, a reply frequency for portions of the video, a pause frequency for portions of the video, or a community score for portions of the video.
8. A system, comprising:
a processor;
a non-transitory computer-readable medium; and
stored instructions translatable by the processor for:
obtaining, from play trails that track viewing behaviors of viewers of a video, statistics regarding viewing of the video by the viewers, each play trail representing a timestamped sequence of actions that a viewer of the viewers takes with respect to the video while playing the video on a user device and that together is sufficient to reconstruct the viewing in entirety, the timestamped sequence of actions including adding a deep tag to the video and replaying and pausing portions of the video, wherein each of the play trails is recorded on a device of the viewers, and wherein, among at least some of the viewers, their timestamped sequences of actions with respect to the video as recorded in the play trails are sequentially different;
determining, based at least in part from the timestamped sequences of actions recorded in the play trails, viewer characteristics and viewed characteristics,
the viewer characteristics including at least one of:
demographic information of the viewer,
an action of the viewer, or
a material previously viewed by the viewer, and
the viewed characteristics including a number of times that the video has been requested by the viewers;
retrieving or obtaining, in view of at least one of:
the statistics of the video obtained from the play trails,
the viewer characteristics, or
the viewed characteristics,
content placement preferences that specify a content placement price setting mechanism, the content placement price setting mechanism including a content placement rule;
determining, based on the content placement price setting mechanism, a plurality of prices for placing content at a plurality of places in the video;
determining, based on the content placement rule, whether placement of the content in the video is manual or automatic;
responsive to the content placement rule specifying that the placement of the content in the video is automatic, automatically placing the content in the video at one of the plurality of places in the video; and
responsive to the content placement rule specifying that the placement of the content in the video is manual, notifying a user for manual placement of the content in the video.
9. The system of claim 8 , wherein the play trails are retrieved from a database or received from user devices of the viewers.
10. The system of claim 8 , wherein the play trail has a head that indicates an identifier of the video.
11. The system of claim 8 , wherein the stored instructions are further translatable by the processor for:
storing the play trail with at least one of a time at which the play trail is received from the user device of the viewer, an identity of the viewer, or a computer address from which the play trail was sent.
12. The system of claim 8 , wherein the play trail is stored on the user device of the viewer in a cookie or a locally stored data file that tracks the actions that the viewer takes in playing the video on the user device.
13. The system of claim 12 , wherein the play trail is persisted on the user device such that the actions are tracked across browser sessions of a browser running on the user device.
14. The system of claim 8 , wherein the stored instructions are further translatable by the processor for:
updating basic statistics for the video, the basic statistics including a number of deep tags created for a portion of the video, an access frequency for portions of the video, a reply frequency for portions of the video, a pause frequency for portions of the video, or a community score for portions of the video.
15. A computer program product comprising a non-transitory computer-readable medium storing instructions translatable by a processor for:
obtaining, from play trails that track viewing behaviors of viewers of a video, statistics regarding viewing of the video by the viewers, each play trail representing a timestamped sequence of actions that a viewer of the viewers takes with respect to the video while playing the video on a user device and that together is sufficient to reconstruct the viewing in entirety, the timestamped sequence of actions including adding a deep tag to the video and replaying and pausing portions of the video, wherein each of the play trails is recorded on a device of the viewers, and wherein, among at least some of the viewers, their timestamped sequences of actions with respect to the video as recorded in the play trails are sequentially different;
determining, based at least in part from the timestamped sequences of actions recorded in the play trails, viewer characteristics and viewed characteristics,
the viewer characteristics including at least one of:
demographic information of the viewer,
an action of the viewer, or
a material previously viewed by the viewer, and
the viewed characteristics including a number of times that the video has been requested by the viewers;
retrieving or obtaining, in view of at least one of:
the statistics of the video obtained from the play trails,
the viewer characteristics, or
the viewed characteristics,
content placement preferences that specify a content placement price setting mechanism, the content placement price setting mechanism including a content placement rule;
determining, based on the content placement price setting mechanism, a plurality of prices for placing content at a plurality of places in the video;
determining, based on the content placement rule, whether placement of the content in the video is manual or automatic;
responsive to the content placement rule specifying that the placement of the content in the video is automatic, automatically placing the content in the video at one of the plurality of places in the video; and
responsive to the content placement rule specifying that the placement of the content in the video is manual, notifying a user for manual placement of the content in the video.
16. The computer program product of claim 15 , wherein the play trails are retrieved from a database or received from user devices of the viewers.
17. The computer program product of claim 15 , wherein the instructions are further translatable by the processor for:
storing the play trail with at least one of a time at which the play trail is received from the user device of the viewer, an identity of the viewer, or a computer address from which the play trail was sent.
18. The computer program product of claim 15 , wherein the play trail is stored on the user device of the viewer in a cookie or a locally stored data file that tracks the actions that the viewer takes in playing the video on the user device.
19. The computer program product of claim 15 , wherein the play trail is persisted on the user device such that the actions are tracked across browser sessions of a browser running on the user device.
20. The computer program product of claim 15 , wherein the instructions are further translatable by the processor for:
updating basic statistics for the video, the basic statistics including a number of deep tags created for a portion of the video, an access frequency for portions of the video, a reply frequency for portions of the video, a pause frequency for portions of the video, or a community score for portions of the video.