AT&T Ties Advanced Ads to Emotions

AT&T won a U.S. patent for an invention that could allow it to deliver advertising to viewers based emotions that scene in a TV show or movie may evoke.

The system may insert a commercial for automobile insurance after a scene featuring a car crash, AT&T notes in the patent, titled,  “Method and apparatus for presenting advertising in content having an emotional context.”

“A sponsor of the first advertisement would likely find it desirable to present the first advertisement after the car crash since viewing such a dramatic crash may lead the viewer to think of the dangers of driving, injuries that can be caused to multiple parties in an accident, and loss of value in significant car accidents. Viewing a car insurance commercial after a car crash can therefore correlate to a viewer’s emotional state and perhaps desire to mitigate dangerous events such as the dramatic footage depicted in the program scene,” AT&T states in the patent.

Simon Byers
AT&T inventor Simon Byers

AT&T Labs Research Principal Inventive Scientist Simon Byers is named as inventor on the patent published on Tuesday.

Abstract: Aspects of the subject disclosure may include, for example, receiving a media program on a first media channel, detecting a first segment in the media program, where the first segment comprises media content combined with an embedded advertisement, determining a first emotional context from a first analysis of the media content, determining a second emotional context from a second analysis of the embedded advertisement, and detecting an inconsistency between the first emotional context and the second emotional context. Other embodiments are disclosed.

Claims: 

1. A device, comprising: at least one processor; and at least one memory that stores executable instructions that, when executed by the at least one processor, facilitate performance of operations, comprising: receiving a media program having advertisement slots for presenting advertisements with the media program; determining a first emotional context from a first analysis of a first segment of the media program to predict an emotional bias associated with viewing the first segment, the first analysis comprising image processing of programming content in the first segment; obtaining an advertisement having a correlation to the first emotional context of the first segment determined from the first analysis; and presenting the advertisement in one of the advertisement slots of the media program occurring after the first segment, wherein responsive to the first emotional context comprising a negative event, the correlation of the advertisement is in accordance with the advertisement mitigating the negative event.

2. The device of claim 1, wherein the operations further comprise determining whether the first emotional context of the first segment comprises a desirable event.

3. The device of claim 2, wherein obtaining the advertisement comprises obtaining the advertisement from a database of advertisements based on the advertisement correlating to the desirable event.

4. The device of claim 3, wherein the correlation is determined from a presentation of the advertisement being complimentary to an event associated with a presentation of the desirable event.

5. The device of claim 1, wherein receiving the media program further comprises receiving descriptive metadata for the first segment.

6. The device of claim 5, wherein the correlation is determined by correlating the metadata to a description of the advertisement.

7. The device of claim 1, wherein obtaining the advertisement further comprises obtaining the advertisement from a database of advertisements based on the correlation of the advertisement.

8. The device of claim 1, wherein the media program is received in a first media channel, and wherein the operations further comprise: detecting a second segment in the media program, wherein the second segment comprises media content combined with an embedded advertisement; determining a second emotional context from a second analysis of the media content; determining a third emotional context from a third analysis of the embedded advertisement; and detecting a disparity between the second emotional context and the third emotional context.

9. The device of claim 8, wherein the operations further comprise: detecting a request to tune to a different media channel while the embedded advertisement is being presented; and detecting a correlation between the request to tune to the different media channel and the disparity between the second emotional context and the third emotional context.

10. The device of claim 9, wherein the operations further comprise submitting a request to replace the embedded advertisement with another advertisement that is correlated with the second emotional context of the media content of the second segment.

11. A non-transitory machine-readable storage device, comprising executable instructions that, when executed by a processor, facilitate performance of operations, comprising: receiving a media program on a first media channel; detecting a first segment in the media program, wherein the first segment comprises media content combined with an embedded advertisement; determining a first emotional context from a first analysis of the media content to predict a first emotional bias associated with viewing the media content, the first analysis comprising image processing of the media content; determining a second emotional context from a second analysis of the embedded advertisement to predict a second emotional bias associated with viewing the embedded advertisement; and detecting an inconsistency between the first emotional context and the second emotional context.

12. The non-transitory machine-readable storage device of claim 11, wherein the operations further comprise: detecting a request to tune to a different media channel while the embedded advertisement is being presented; and detecting a correlation between the request to tune to the different media channel and the inconsistency between the first emotional context and the second emotional context.

13. The non-transitory machine-readable storage device of claim 12, wherein the operations further comprise submitting a request to replace the embedded advertisement responsive to detecting the correlation between the request to tune to the different media channel and the inconsistency between the first emotional context and the second emotional context.

14. The non-transitory machine-readable storage device of claim 13, wherein the operations further comprise obtaining a replacement advertisement that is correlated to the first emotional context.

15. The non-transitory machine-readable storage device of claim 14, wherein the operations further comprise replacing the embedded advertisement with the replacement advertisement.

16. The non-transitory machine-readable storage device of claim 11, wherein the operations further comprise: detecting a second segment in the media program; determining a third emotional context from a third analysis of the second segment; obtaining an advertisement that correlates to the third emotional context of the second segment; and presenting the advertisement in an advertisement slot in the media program occurring after the second segment.

17. The non-transitory machine-readable storage device of claim 16, wherein the operations further comprise determining whether the third emotional context of the second segment comprises a desirable event or undesirable event, wherein obtaining the advertisement comprises obtaining the advertisement from a database of advertisements based on the advertisement correlating to the desirable event or the undesirable event.

18. A method, comprising: receiving, by a system comprising a processor, a media program; identifying, by the system, a segment in the media program; performing, by the system, emotional context analysis on the segment to determine an event state of subject matter presented in the segment and to predict an emotional bias associated with viewing the segment, the emotional context analysis comprising image processing of programming content in the segment; and obtaining, by the system, an advertisement having a correlation to the event state, wherein responsive to the event state comprising a negative event, the correlation of the advertisement is in accordance with the advertisement mitigating the negative event.

19. The method of claim 18, further comprising presenting, by the system, the advertisement in an advertisement slot in the media program occurring after the segment.

20. The method of claim 18, wherein obtaining the advertisement comprises obtaining the advertisement from a database of advertisements based on the correlation of the advertisement to the event state.