MULTIPLE METER DETECTION AND PROCESSING USING MOTION DATA

• US 20130138388A1
• Filed: 11/30/2012
• Published: 05/30/2013
• Est. Priority Date: 11/30/2011
• Status: Active Grant

• Current Assignee: The Nielsen Company LLC (MOOD Media Corporation)
• Original Assignee: Arbitron Inc. (MOOD Media Corporation)
• Inventors: Jain, Anand, Stavropoulos, John, Neuhauser, Alan, Lynch, Wendell, Kuznetsov, Vladimir, Crystal, Jack
• Granted Patent: US 9,696,336 B2
• Time in Patent Office: Days
• US Class Current: 702/141
• CPC Class Codes: G01P 15/00 Measuring acceleration; Measuring deceleration; Measuring shock, i.e. sudden change of acceleration
• CPC Class Codes: G01P 15/18 in two or more dimensions
• CPC Class Codes: G06F 17/00 Digital computing or data processing equipment or methods, specially adapted for specific functions information retrieval, database structures or file system structures therefor G06F16/00
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data

Abstract

Systems and methods are disclosed for identifying users of portable user devices according to one or more accelerometer profiles created for a respective user. During a media session, the portable computing device collects media exposure data, while at the same time, collects data from the accelerometer and compares it to the user profile. The comparison authenticates the user and determines the physical activity the user is engaged in. Additional data may be collected from the portable computing device to determine one or more operational conditions of the device itself, including the detection of multiple devices being physically carried by one user. Gross motion strings may also be generated by devices and compared to see if strings match, thus suggesting multiple devices are being carried by one user.

Claims

1. A computer-implemented method for determining multiple portable computing devices being physically carried by one person, comprising the steps of:

receiving media exposure data over a data network from at least one of a plurality of portable computing devices;

receiving motion strings over the data network respectively from each of the plurality of portable computing devices, each of said strings comprising a successive binary representation of motion over a first period of time;

comparing the motion strings in a processor to determine if at least two motion strings match within a predetermined threshold; and

identifying the devices that produced matching motion strings.

2. The computer-implemented method of claim 1, wherein the first period of time comprises a plurality of shorter periods of time, and wherein the successive binary representation comprises a series of values representing motion for each of the shorter periods of time.

3. The computer-implemented method of claim 2, wherein each of the series of values are formed by determining if the gross motion within the shorter period of time exceeded a motion threshold.

4. The computer-implemented method of claim 3, wherein a binary “

1”

is generated if the gross motion within the shorter time period meets or exceeds the motion threshold, and a binary “

0”

is generated if the gross motion within the shorter time period does not meet or exceed the motion threshold.

5. The computer implemented method of claim 2, further comprising the step of comparing a sub-string of each motion strings in a processor to determine if at least two motion sub-strings match within a predetermined threshold.

6. The computer implemented method of claim 5, further comprising the step of determining if identified devices provided media exposure data.

7. A system for detecting multiple portable computing devices being physically carried by one person, comprising:

a first input for receiving media exposure data over a data network from at least one of a plurality of portable computing devices;

a second input for receiving motion strings over the data network respectively from each of the plurality of portable computing devices, each of said strings comprising a successive binary representation of motion over a first period of time; and

a processor, operatively coupled to the first and second input, said processor being configured to compare the motion strings to determine if at least two motion strings match within a predetermined threshold, and identify the devices that produced matching motion strings.

8. The system of claim 7, wherein the first period of time comprises a plurality of shorter periods of time, and wherein the successive binary representation comprises a series of values representing motion for each of the shorter periods of time.

9. The system of claim 8, wherein each of the series of values are formed by determining if the gross motion within the shorter period of time exceeded a motion threshold.

10. The system of claim 9, wherein a binary “

1”

is generated if the gross motion within the shorter time period meets or exceeds the motion threshold, and a binary “

0”

is generated if the gross motion within the shorter time period does not meet or exceed the motion threshold.

11. The system of claim 8, further comprising the step of comparing a sub-string of each motion strings in a processor to determine if at least two motion sub-strings match within a predetermined threshold.

12. The system of claim 7, further comprising the step of determining if identified devices provided media exposure data.

13. A computer-implemented method, comprising the steps of:

receiving media exposure data from at least one of a plurality of portable computing devices;

receiving segmented accelerometer data from the plurality of portable computing devices;

extracting features from each of the segmented accelerometer data and forming accelerometer classification data for each portable computing device;

comparing each of the accelerometer classification data to at least one of (i) accelerometer classification data for another portable computing device and (ii) a stored profile for another portable computing device to determine if accelerometer classification data for one portable computing device is sufficiently similar to another portable computing device;

identifying the one portable computing device as having a duplicate user if the comparison step determines that the accelerometer classification data for the one portable computing device is sufficiently similar to another computing device.

14. The computer-implemented method of claim 13, wherein the media exposure data comprises at least one of (i) ancillary codes detected from audio, and (ii) one or more signatures extracted from audio.

15. The computer-implemented method of claim 13, wherein the media exposure data comprises at least one of (i) a web page, (ii) application data, and (iii) metadata.

16. The computer-implemented method of claim 13, wherein the stored profile comprises previously-acquired accelerometer classification data for each of the plurality of portable computing devices.

17. The computer-implemented method of claim 16, wherein the accelerometer classification data and previously-acquired accelerometer classification data each comprise raw accelerometer data processed in one of a time domain and a frequency domain.

18. The computer-implemented method of claim 17, wherein the comparing steps comprise a comparison of the accelerometer classification data to the previously-acquired accelerometer classification data to determine the similarity is based on one of (1) cross-correlation, (2) absolute Manhattan distance, (3) Euclidean distance, and (4) dynamic time warping.

19. The computer-implemented method of claim 16, wherein the accelerometer classification data for the one portable computing device is sufficiently similar when the similarity is above a predetermined threshold.

20. The computer-implemented method of claim 13, wherein each of the plurality of portable computing devices are associated with a group.