Methods and apparatus to determine locations of audience members

• US 9,258,607 B2
• Filed: 09/29/2014
• Issued: 02/09/2016
• Est. Priority Date: 12/14/2010
• Status: Active Grant

• Current Assignee: The Nielsen Company LLC (MOOD Media Corporation)
• Original Assignee: The Nielsen Company LLC (MOOD Media Corporation)
• Inventors: Chen, Jie
• Primary Examiner(s): Paul, Disler
• Application Number:
  US14/500,443
• Publication Number:
  US 20150052541A1
• Time in Patent Office: 498 Days
• Field of Search: 381/56, 381 58- 59, 381/306, 725 9- 10, 725/18
• US Class Current: 1/1
• CPC Class Codes: G01S 3/801 Details G01S3/82, G01S3/84, G01S3/86 take precedence
• CPC Class Codes: H04N 21/44218 Detecting physical presence or behaviour of the user, e.g. using sensors to detect if the user is leaving the room or changes his face expression during a TV program methods or arrangements for recognising human body or animal bodies or body parts G06V40/10; methods or arrangements for acquiring or recognising human faces, facial parts, facial sketches, facial expressions G06V40/16; methods or arrangements for recognising movements or behaviour G06V40/20; arrangements for identifying users in broadcast systems H04H60/45
• CPC Class Codes: H04R 2430/21 Direction finding using differential microphone array [DMA]
• CPC Class Codes: H04R 3/005 for combining the signals of two or more microphones specially adapted for hearing aids H04R25/407

Abstract

A disclosed example method involves determining, using a neural network at a stationary unit, a first distance of a first portable audio detector from the stationary unit, the first portable audio detector associated with a first panelist, the stationary unit located in proximity to the media presentation device. The example method also involves determining, using the neural network, a second distance of a second portable audio detector from the stationary unit, the second portable audio detector associated with a second panelist. In response to the first distance being less than a threshold distance, the media is credited as exposed to the first panelist. In response to the second distance being more than the threshold distance, the media is not credited as exposed to the second panelist.

Claims

1. A method to credit media presented by a media presentation device, the method comprising:

determining, via a neural network, a first distance of a first portable audio detector from a stationary unit, the first portable audio detector associated with a first panelist, the stationary unit located in proximity to the media presentation device;

determining, via the neural network, a second distance of a second portable audio detector from the stationary unit, the second portable audio detector associated with a second panelist;

in response to the first distance being less than a threshold distance, crediting the media with an exposure credit, the exposure credit indicative of the media being exposed to the first panelist; and

in response to the second distance being more than the threshold distance, not crediting the media as exposed to the second panelist.

2. A method as defined in claim 1, wherein the neural network is trainable to detect different distances of portable audio detectors by analyzing audio samples corresponding to different training distances in a monitoring environment.

3. A method as defined in claim 1, wherein the stationary unit is separate from the media presentation device.

4. A method as defined in claim 1, wherein the determining of the first distance occurs in real-time when first audio samples are collected by the stationary unit from the first portable audio detector.

5. A method as defined in claim 1, wherein the determining of the first distance includes using a post-process after first audio samples are received.

6. A method to credit media presented by a media presentation device, the method comprising:

determining, using a neural network, a first distance of a first portable audio detector from a stationary unit, the first portable audio detector associated with a first panelist, the stationary unit located in proximity to the media presentation device, wherein the neural network determines the first distance by performing a correlation analysis on first audio samples of the media collected by the stationary unit and on second audio samples collected by the first portable audio detector;

determining, using the neural network, a second distance of a second portable audio detector from the stationary unit, the second portable audio detector associated with a second panelist;

in response to the first distance being less than a threshold distance, crediting the media as exposed to the first panelist; and

in response to the second distance being more than the threshold distance, not crediting the media as exposed to the second panelist.

7. A method as defined in claim 6, wherein the correlation analysis is performed in the frequency domain.

8. A tangible machine accessible medium comprising instructions that, when executed, cause a machine in communication with a stationary unit located adjacent to a media presentation device that is to present media to at least:

determine, via a neural network, a first distance of a first portable audio detector from the stationary unit, the first portable audio detector exposed to the media and associated with a first panelist;

determine, via the neural network, a second distance of a second portable audio detector from the stationary unit, the second portable audio detector exposed to the media and associated with a second panelist;

in response to the first distance being less than a threshold distance, credit the media with an exposure credit, the exposure credit indicative of the media being exposed to the first panelist; and

in response to the second distance being more than the threshold distance, not credit the media as exposed to the second panelist.

9. The tangible machine accessible medium of claim 8, wherein the instructions further cause the machine to train the neural network to detect different distances of portable audio detectors by analyzing audio samples corresponding to different training distances in a monitoring environment.

10. The tangible machine accessible medium of claim 8, wherein the stationary unit is separate from the media presentation device.

11. The tangible machine accessible medium of claim 8, wherein the instructions are further to cause the machine to determine, via the neural network, the first distance of the first portable audio detector from the stationary unit in real-time when first audio samples are collected from the first portable audio detector.

12. The tangible machine accessible medium of claim 8, wherein the instructions are further to cause the machine to determine, via the neural network, the first distance of the first portable audio detector from the stationary unit at a time after first audio samples are collected by the stationary unit from the first portable audio detector.

13. A tangible machine accessible medium comprising instructions that, when executed, cause a machine in communication with a stationary unit located adjacent a media presentation device that is to present media to at least:

determine, via a neural network, a first distance of a first portable audio detector from the stationary unit by performing a correlation analysis on first audio samples of the media collected by the stationary unit and on second audio samples collected by the first portable audio detector, the first portable audio detector exposed to the media and associated with a first panelist;

determine, via the neural network, a second distance of a second portable audio detector from the stationary unit, the second portable audio detector exposed to the media and associated with a second panelist;

in response to the first distance being less than a threshold distance, credit the media as exposed to the first panelist; and

in response to the second distance being more than the threshold distance, not credit the media as exposed to the second panelist.

14. The tangible machine accessible medium of claim 13, wherein the neural network is to perform the correlation analysis in the frequency domain.

15. A processing unit in communication with a stationary unit located in proximity to a media presentation device that is to present media, the processing unit comprising:

a neural network to;

determine a first distance of a first portable audio detector from the stationary unit, the first portable audio detector associated with a first panelist; and

determine a second distance of a second portable audio detector from the stationary unit, the second portable audio detector associated with a second panelist; and

a processor to;

in response to the first distance being less than a threshold distance, store an exposure credit to indicate the media was exposed to the second panelist; and

in response to the second distance being more than the threshold distance, not store the exposure credit to indicate the media was exposed to the second panelist.

16. A processing unit as defined in claim 15, wherein the neural network is trainable to detect different distances of portable audio detectors by analyzing audio samples corresponding to different training distances in a monitoring environment.

17. A processing unit as defined in claim 15, wherein the stationary unit is separate from the media presentation device.

18. A processing unit as defined in claim 15, wherein the neural network is to determine the first distance of the first portable audio detector from the stationary unit in real-time when first audio samples are collected by the stationary unit from the first portable audio detector.

19. A processing unit as defined in claim 15, wherein the neural network is to determine the first distance of the first portable audio detector from the stationary unit by executing a post-process after first audio samples are received.

20. An apparatus comprising:

a processor; and

a memory to store machine readable instructions that, when executed by the processor, cause the processor to perform operations including;

determining, using a neural network, a first distance of a first portable audio detector from a stationary unit, the first portable audio detector associated with a first panelist, the stationary unit located in proximity to a media presentation device that is to present media, wherein the neural network determines the first distance by performing a correlation analysis on first audio samples of the media collected by the stationary unit and on second audio samples collected by the first portable audio detector;

determining, using the neural network, a second distance of a second portable audio detector from the stationary unit, the second portable audio detector associated with a second panelist;

in response to the first distance being less than a threshold distance, crediting the media as exposed to the first panelist; and

in response to the second distance being more than the threshold distance, not crediting the media as exposed to the second panelist.

21. An apparatus as defined in claim 20, wherein the processor is to perform the correlation analysis in the frequency domain.