MINING VIEWER RESPONSES TO MULTIMEDIA CONTENT

• US 20100070987A1
• Filed: 09/30/2008
• Published: 03/18/2010
• Est. Priority Date: 09/12/2008
• Status: Abandoned Application

• Current Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Abella, Alicia, Stead, Larry, Amento, Brian Scott
• Application Number:
  US12/242,451
• Publication Number:
  US 20100070987A1
• Time in Patent Office: Days
• US Class Current: 725/10
• CPC Class Codes: H04H 60/33 Arrangements for monitoring the users' behaviour or opinions
• CPC Class Codes: H04H 60/40 for identifying broadcast time

Abstract

Viewers of a multimedia program are monitored to detect responses. Time data is stored with the responses and compared to responses from other viewers at the same time in the multimedia program. A viewer type is determined based on the responses. Further multimedia programs may be offered to the viewer based on the viewer type. Transducers and sensors placed within a viewing area may include, without limitation, audio sensors, video sensors, motion sensors, subdermal sensors, and biometric sensors.

Claims

1. A method of mining viewer responses to a program of multimedia content, the method comprising:

monitoring a viewer for a response to a portion of the program of multimedia content;

comparing the response to stored responses;

characterizing a status of the viewer based on said comparing; and

storing the status of the viewer.

2. The method of claim 1, further comprising:

selecting further multimedia programs for offer to the viewer based on the stored status.

3. The method of claim 1, further comprising:

associating a timestamp with the stored status.

4. The method of claim 1, further comprising:

collecting a plurality of status conditions from a plurality of viewers of the program of multimedia content; and

integrating the plurality of status conditions from the plurality of viewers into a plurality of known status conditions.

5. The method of claim 4, wherein said storing the status includes storing a plurality of status conditions of the viewer at a plurality of portions of the program, wherein the method further comprises:

comparing a portion of the stored plurality of status conditions of the viewer to a portion of the plurality of known status conditions; and

assigning a type for the viewer based on said comparing.

6. The method of claim 5, further comprising:

predicting whether the viewer would enjoy a further program of multimedia content based on the assigned type.

7. The method of claim 6, wherein said monitoring includes:

monitoring the viewer for a gaze status, wherein a gaze status is indicative of a level of eye movement; and

estimating whether the viewer is paying attention to the program based on the gaze status.

8. The method of claim 1, further comprising:

generating video data from a plurality of video images of the viewer; and

wherein said characterizing is further based on comparing the video data to predetermined video parameters.

9. The method of claim 8:

wherein said comparing of the video data includes analyzing the video data to determine whether the viewer is smiling or laughing.

10. The method of claim 8, further comprising:

wherein said comparing of the video data includes analyzing the video data to determine whether the viewer is facing a display on which the program of multimedia content is presented.

11. The method of claim 8, further comprising:

analyzing the video data to track a color-coded implement that may be moved by the viewer.

12. The method of claim 11, wherein the color-coded implement is a glove.

13. The method of claim 1, wherein said monitoring includes generating audio data from a plurality of audio signals captured from a location local to the viewer, and wherein said characterizing is further based on a comparing of the audio data to predetermined audio parameters to characterize the status of the viewer.

14. The method of claim 13, wherein a portion of the plurality of audio signals are generated using bone conduction microphones.

15. The method of claim 13, further comprising:

estimating whether the viewer has a vocal outburst to a portion of the program of multimedia content by detecting magnitude changes in the audio signals.

16. The method of claim 13, the method further comprising:

generating motion data from said monitoring; and

wherein said characterizing is further based on a comparing of the motion data to predetermined motion parameters.

17. The method of claim 1, further comprising:

capturing biometric data indicative of a biometric parameter of the viewer;

comparing the biometric data to predetermined biometric norms; and

wherein said characterizing is further based on said comparing of the biometric data.

18. The method of claim 17, wherein said capturing includes capturing data indicative of a pulse rate of the viewer.

19. The method of claim 18, wherein said capturing includes capturing temperature data indicative of a temperature of the viewer.

20. The method of claim 18, wherein said capturing includes capturing data from a subdermal transducer.

21. A computer program product stored on at least one computer readable media, the computer program product for characterizing a viewer response to a multimedia content program, the computer program product comprising instructions for:

detecting a viewer response to a portion of the multimedia content program using data captured from transducers that are placed within a viewing area that is proximal to the viewer;

comparing the viewer response to stored responses;

characterizing a status of the viewer based on said comparing; and

storing the status of the viewer.

22. The computer program product of claim 21, further comprising instructions for:

collecting a plurality of status conditions from a plurality of viewers of the multimedia content program; and

integrating the plurality of status conditions from the plurality of viewers into a plurality of known status conditions.

23. The computer program product of claim 21, wherein said storing includes storing a plurality of status conditions at a plurality of portions of the program, wherein the method further comprises:

comparing a portion of the stored plurality of status conditions of the viewer to a portion of the plurality of known status conditions;

assigning a type for the viewer based on said comparing; and

predicting whether the viewer would enjoy a further program of multimedia content based on the assigned type.

24. The computer program product of claim 23, wherein said detecting includes:

monitoring the viewer for a gaze status indicative of a level of eye movement; and

estimating whether the viewer is paying attention to the program based on the gaze status.

25. The computer program product of claim 21, further comprising instructions for:

generating video data from a plurality of video images captured from the viewer;

comparing the video data to predetermined video parameters;

analyzing the video data to determine whether the viewer is smiling or laughing;

analyzing the video data to determine whether the viewer is facing a display on which the program of multimedia content is presented;

generating audio data from a plurality of audio signals captured from a location local to the viewer;

comparing the audio data to predetermined audio parameters;

estimating whether the viewer has a vocal outburst by detecting changes in an audio level measured at the location;

generating motion data from monitoring the viewer;

comparing the motion data to predetermined motion parameters; and

capturing biometric data from the viewer.

26. A device for processing data generated from monitoring a viewer of a multimedia content program to estimate a plurality of reactions from the viewer, the device comprising:

an interface for receiving data from a plurality of transducers in a data collection environment in which the multimedia content program is presented, wherein the data includes;

audio data; and

video data; and

a processor for;

comparing the data to known data and estimating the plurality of reactions;

associating the plurality of reactions with time data; and

estimating whether the viewer would enjoy a further program of multimedia content based on the plurality of reactions.

27. The device of claim 26, wherein the data further includes:

biometric data.

28. The device of claim 27, wherein the biometric data includes pulse data.

29. The device of claim 28, wherein one or more of the plurality of transducers is subdermal.

30. The device of claim 26, wherein a portion of the plurality of transducers uses one or more bone conduction microphones.

31. The device of claim 26, wherein the device comprises customer premises equipment (CPE) suitable for processing the multimedia content program for presentation to a display.

32. The device of claim 31, wherein the CPE comprises a set-top box.