Turner Taps Audio Fingerprints to Drive Multiscreen Ad Revenue

Turner Broadcasting outlines how it could deliver interactive and personalized advertising to TV viewers by reading audio fingerprints on mobile devices and connected TVs.

“Having the ability to identify context and program timing may enable a network to increase audience engagement, extend viewing times, and provide program sponsors additional ways to engage with the audience, such as offering viewers personalized advertising offers or creating a second-screen experience during an advertisement break,” Turner states in a patent published on Tuesday .

Loheide
Loheide

Turner Senior Director of Emerging Video Platforms Nishith Sinha, VP of Advanced Video Don Loheide and Senior Director of Emerging Technologies Matthe Giles are named as inventors on the patent, titled, “Method and system for logo identification based on automatic content recognition.”

Patent

Abstract: A method and system for logo identification based on automatic content recognition (ACR) are described in which a connected television (TV) or other end-user device may be provided with instructions to fingerprint certain regions in a video frame to identify the source of the content being displayed. Such instructions may be provided when, for example, fingerprint matching is able to identify content that is provided by multiple sources but is unable to identify the particular source of the content. In those instances, one or more additional locations may be determined for taking fingerprints in the video frame.

Giles
Giles

These locations correspond to region of the video frame in which a graphical item that represents the network television station is typically displayed. A profile with these locations is generated and sent to the connected TV to take additional fingerprints to enable the identification of the network television station providing content.

Claims: 

1. A method, comprising: in a device that is operable to handle operations for automatic content recognition, the device being operable to: receive multiple sequences of video fingerprints that are generated from identical segments of a video feed utilizing a plurality of different fingerprint technologies; and time assignment of event identifiers to the multiple sequences of video fingerprints that are generated from the identical segments of the video feed such that same event identifiers are assigned to each of the multiple sequences of video fingerprints that are generated from the identical segments of the video feed by the different video fingerprint technologies utilizing a common reference clock: generating one or more signals that provide instructions to: determine one or more locations in a video frame to take fingerprints, wherein the one or more locations correspond to a determined portion of the video frame in which a graphical item that represents a network television station is displayed; generate a profile comprising the determined one or more locations; and send the generated profile for communication to an end-user device, wherein the end-user device is operable to utilize the profile to take fingerprints of content provided by the network television station.

2. The method of claim 1, wherein the graphical item comprises one or more of a logo, a symbol, a sign, a watermark, and text that represent the network television station.

3. The method of claim 1, wherein the generated one or more signals provide instructions to: generate an indication that the determined one or more locations are to be automatically utilized by the end-user device to take fingerprints when one or more fingerprints previously taken by the end-user device match fingerprints that correspond to content provided by the network television station; and send the generated indication for communication to the end-user device.

4. The method of claim 1, comprising: receiving an indication that one or more fingerprints previously taken by the end-user device match fingerprints that correspond to content provided by the network television station; and in response to the received indication, the generated one or more signals provide instructions to generate the profile.

5. The method of claim 1, comprising: generating one or more additional signals that provide instructions to: generate additional profiles at a determined rate, wherein: each additional profile comprises one or more locations in a video frame to take fingerprints; and the one or more locations of each additional profile corresponds to a determined portion of the video frame in which a graphical item that represents the network television station is displayed; and send the generated additional profiles for communication to the end-user device.

6. The method of claim 5, wherein the determined rate is approximately one profile every five seconds.

7. The method of claim 1, comprising: receiving an indication that the content provided by the network television station is provided concurrently by other network television stations; and in response to the received indication, the generated one or more signals provide instructions to generate the profile.

8. The method of claim 1, comprising: receiving an indication that one or more fingerprints previously taken by the end-user device match fingerprints that correspond to content provided by the network television station and also match content provided by one or more additional network television stations; and in response to the received indication, the generated one or more signals provide instructions to generate the profile.

9. The method of claim 1, wherein the profile comprises a plurality of locations in the video frame to take fingerprints that correspond to a portion of the video frame that is different from the determined portion of the video frame in which the graphical item is displayed.

10. The method of claim 9, wherein the plurality of locations comprise from about 16 locations to about 36 locations.

11. The method according to claim 1, wherein the video feed comprises a live feed.

12. The method according to claim 1, wherein the video feed comprises previously ingested content.

13. A system, comprising: a device that is operable to handle operations for automatic content recognition, the device being operable to: receive multiple sequences of video fingerprints that are generated from identical segments of a video feed utilizing a plurality of different fingerprint technologies; and time assignment of event identifiers to the multiple sequences of video fingerprints that are generated from the identical segments of the video feed same video content but with different fingerprint technologies such that same event identifiers are assigned to different sets each of the multiple sequences of video fingerprints that are generated from the identical segments of the video feed by the different video fingerprint technologies utilizing a common reference clock; and generate one or more signals that provide instructions to: determine one or more locations in a video frame to take fingerprints, wherein the one or more locations correspond to a determined portion of the video frame in which a graphical item that represents a network television station is displayed; generate a profile comprising the determined one or more locations; and send the generated profile for communication to an end-user device, wherein the end-user device is operable to utilize the profile to take fingerprints of content provided by the network television station.

14. The system of claim 13, wherein the graphical item comprises one or more of a logo, a symbol, a sign, a watermark, and text that represent the network television station.

15. The system of claim 13, wherein the generated one or more signals provide instructions to: generate an indication that the determined one or more locations are to be automatically utilized by the end-user device to take fingerprints when one or more fingerprints previously taken by the end-user device match fingerprints that correspond to content provided by the network television station; and send the generated indication for communication to the end-user device.

16. The system of claim 13, wherein device is operable to: receive an indication that one or more fingerprints previously taken by the end-user device match fingerprints that correspond to content provided by the network television station; and in response to the received indication, the generated one or more signals provide instructions to generate the profile.

17. The system of claim 13, wherein the device is operable to: generate one or more additional signals that provide instructions to: generate additional profiles at a determined rate, wherein: each additional profile comprises one or more locations in a video frame to take fingerprints; and the one or more locations of each additional profile corresponds to a determined portion of the video frame in which a graphical item that represents the network television station is displayed; and send the generated additional profiles for communication to the end-user device.

18. The system of claim 17, wherein the determined rate is approximately one profile every five seconds.

19. The system of claim 13, wherein the device is operable to: receive an indication that the content provided by the network television station is provided concurrently by other network television stations; and in response to the received indication, the generated one or more signals provide instructions to generate the profile.

20. The system of claim 13, wherein the device is operable to: receive an indication that one or more fingerprints previously taken by the end-user device match fingerprints that correspond to content provided by the network television station and also match content provided by one or more additional network television stations; and in response to the received indication, the generated one or more signals provide instructions to generate the profile.

21. The system of claim 13, wherein the profile comprises a plurality of locations in the video frame to take fingerprints that correspond to a portion of the video frame that is different from the determined portion of the video frame in which the graphical item is displayed.

22. The system according to claim 13, wherein the video feed comprises a live feed.

23. The system according to claim 13, wherein the video feed comprises previously ingested content.

24. A system, comprising: a broadcast automatic content recognition (ACR) system that is operable to time assignment of event identifiers to multiple sequences of video fingerprints that are generated from the same video content but with different fingerprint technologies such that same event identifiers are assigned to different sets of video fingerprints that are generated by the different video fingerprint technologies, the broadcast ACR system being operable to: receive an indication that one or more fingerprints previously taken by an end-user device match fingerprints that correspond to content provided by a network television station; and in response to the received indication, generate one or more instructions to: generate a profile comprising one or more locations in a video frame that correspond to a determined portion of the video frame in which a graphical item that represents the network television station is displayed; and send the generated profile for communication to the end-user device, wherein the end-user device is operable to utilize the profile to take fingerprints of content provided by the network television station; receive a query from a vendor ACR system for an updated fingerprint profile; and send the updated fingerprint profile from the broadcast ACR system to the vendor ACR system, wherein the vendor ACR system sends the updated fingerprint profile to the end-user device.

25. A non-transitory computer-readable medium for a device that handles operations for automatic content recognition, the device being operable to: receive multiple sequences of video fingerprints that are generated from identical segments of a video feed utilizing a plurality of different fingerprint technologies; and time assignment of event identifiers to the multiple sequences of video fingerprints that are generated from the identical segments of the video feed such that same event identifiers are assigned to each of the multiple sequences of video fingerprints that are generated from the identical segments of the video feed by the different video fingerprint technologies utilizing a common reference clock; and the device comprising code for: generating one or more signals that provide instructions to: determine one or more locations in a video frame to take fingerprints, wherein the one or more locations correspond to a determined portion of the video frame in which a graphical item that represents a network television station is displayed; generate a profile comprising the determined one or more locations; and send the generated profile for communication to an end-user device, wherein the end-user device is operable to utilize the profile to take fingerprints of content provided by the network television station.

26. A system, comprising: a broadcast automatic content recognition (ACR) system that is operable to: receive multiple sequences of video fingerprints that are generated from identical segments of a video feed utilizing a plurality of different fingerprint technologies; and time assignment of event identifiers to the multiple sequences of video fingerprints that are generated from the identical segments of the video feed such that same event identifiers are assigned to each of the multiple sequences of video fingerprints that are generated from the identical segments of the video feed by the different video fingerprint technologies utilizing a common reference clock, the broadcast ACR system being operable to: receive an indication that one or more fingerprints previously taken by an end-user device match fingerprints that correspond to content provided by a network television station; and in response to the received indication, generate one or more instructions to: generate a profile comprising one or more locations in a video frame that correspond to a determined portion of the video frame in which a graphical item that represents the network television station is displayed; and send the generated profile for communication to the end-user device, wherein the end-user device is operable to utilize the profile to take fingerprints of content provided by the network television station; receive a query from a vendor ACR system for an updated fingerprint profile; and send the updated fingerprint profile from the broadcast ACR system to the vendor ACR system, wherein the vendor ACR system sends the updated fingerprint profile to the end-user device.