Probabilistic methods and apparatus to determine the state of a media device

• US 8,793,717 B2
• Filed: 10/31/2008
• Issued: 07/29/2014
• Est. Priority Date: 10/31/2008
• Status: Active Grant

• Current Assignee: The Nielsen Company LLC (MOOD Media Corporation)
• Original Assignee: The Nielsen Company LLC (MOOD Media Corporation)
• Inventors: Lee, Morris
• Primary Examiner(s): Chokshi, Pinkal R
• Application Number:
  US12/263,150
• Publication Number:
  US 20100114527A1
• Time in Patent Office: 2,097 Days
• Field of Search: 725/9, 725/14, 725/18, 725/114, 725/131, 725/139, 725/151
• US Class Current: 725/18
• CPC Class Codes: H04H 60/32 Arrangements for monitoring conditions of receiving stations, e.g. malfunction or breakdown of receiving stations
• CPC Class Codes: H04N 21/23418 involving operations for analysing video streams, e.g. detecting features or characteristics television picture signal circuitry for scene change detection H04N5/147; filtering for image enhancement G06T5/00; methods or arrangements for recognising scenes G06V20/00; arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59
• CPC Class Codes: H04N 21/42202 environmental sensors, e.g. for detecting temperature, luminosity, pressure, earthquakes
• CPC Class Codes: H04N 21/42203 sound input device, e.g. microphone
• CPC Class Codes: H04N 21/442 Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk arrangements for monitoring broadcast services or broadcast-related services H04H60/29; arrangements for identifying or recognising characteristics with a direct linkage to broadcast information H04H60/35; monitoring of user activities for profile generation for accessing a video database G06F16/739; monitoring in wireless networks H04W24/00
• CPC Class Codes: H04N 21/44227 Monitoring of local network, e.g. connection or bandwidth variations; Detecting new devices in the local network configuring of peripheral devices in general G06F9/4411; monitoring connectivity in data switched networks H04L43/0811
• CPC Class Codes: H04N 21/4424 Monitoring of the internal components or processes of the client device, e.g. CPU or memory load, processing speed, timer, counter or percentage of the hard disk space used error monitoring in general G06F11/30; arrangements for monitoring conditions of receiving stations in broadcast systems H04H60/32; diagnosis, testing or measuring for television receivers H04N17/04
• CPC Class Codes: H04N 21/4663 involving probabilistic networks, e.g. Bayesian networks
• CPC Class Codes: H04N 7/163 by receiver means only

Abstract

Probabilistic methods and apparatus to determine the state of a media device are described. An example method to determine the state of a media device includes processing a first output signal from a first sensor measuring a first property of the media device to generate a first parameter value and processing a second output signal from a second sensor measuring a second property of the media device to generate a second parameter value. Next, the example method includes combining first conditional probabilities of the first parameter value and the second parameter value to determine a first state probability for the first state of the media device and combining second conditional probabilities of the first parameter value and the second parameter value to determine a second state probability for the second state of the media device. Then, determining the state of the media device by selecting the greater of the first state probability or the second state probability.

Claims

1. A method to determine a state of a media device, the method comprising:

processing a first output signal from a first sensor measuring a first property of the media device to generate a first parameter value;

processing a second output signal from a second sensor measuring a second property of the media device to generate a second parameter value;

generating a first state probability by combining a first conditional probability that the first parameter value corresponds to the media device being in a first state and a second conditional probability that the second parameter value corresponds to the media device being in the first state;

generating a second state probability by combining a third conditional probability that the first parameter value corresponds to the media device being in a second state and a fourth conditional probability that the second parameter value corresponds to the media device being in the second state; and

determining a detected state of the media device by selecting a greater of the first state probability or the second state probability.

2. A method as defined in claim 1, wherein the second sensor and the first sensor are the same sensor.

3. A method as defined in claim 1, wherein the second parameter and the first parameter are the same parameter.

4. A method as defined in claim 1, further comprising:

determining the first conditional probability associated with the first parameter value and the second probability associated with the second parameter value by placing a training media device into the first state, recording a first set of first parameter values, recording a second set of second parameter values, calculating a first probability distribution of the first parameter values in the first set, and calculating a second probability distribution of the second parameter values in the second set; and

determining the third conditional probability associated with the first parameter value and the fourth probability associated with the second parameter value by placing the training media device into the second state, recording a third set of first parameter values, recording a fourth set of second parameter values, calculating a third probability distribution of the first parameter values in the third set, and calculating a fourth probability distribution of the second parameter values in the fourth set.

5. A method as defined in claim 4, wherein the first conditional probability corresponds to a first range of the set of the first parameter values and the second conditional probability corresponds to a second range of the set of the second parameter values.

6. A method as defined in claim 1, further comprising transmitting the detected state of the media device to a meter by transmitting a confidence probability associated with the detected state of the media device.

7. A method as defined in claim 6, wherein the confidence probability is the greater of the first state probability or the second state probability.

8. A method as defined in claim 1, wherein processing the first output signal and processing the second output signal includes at least one of conditioning, normalizing, summing, averaging, filtering, normally distributing, parsing, amplifying, or converting.

9. A method as defined in claim 1, further comprising:

inputting at least one of the first parameter value or the second parameter value into a preliminary classifier that generates a preliminary output by processing the first parameter value or the second parameter value using a probabilistic algorithm;

combining the first conditional probability associated with the first parameter value, the second conditional probability associated with the second parameter value, and the preliminary output for the first state of the media device prior to determining the first state probability for the first state of the media device; and

combining the third conditional probability associated with the first parameter value, the fourth conditional probability associated with second parameter value, and the preliminary output for the second state of the media device prior to determining the second state probability for the second state of the media device.

10. A method as defined in claim 9, wherein the probabilistic algorithm is at least one of a fuzzy logic algorithm, a decision tree algorithm, a neural network algorithm, an instance-based learning algorithm, or a rule induction algorithm.

11. An apparatus to determine the state of a media device, the apparatus comprising:

a parameter generator to process a first signal from a first sensor measuring a first property of the media device to generate a first parameter value and to process a second signal from a second sensor measuring a second property of the media device to generate a second parameter value; and

a classifier to;

generate a first state probability by combining a first conditional probability that the first parameter value corresponds to the media device being in a first state and a second conditional probability that the second parameter value corresponds to the media device being in the first state;

generate a second state probability by combining a third conditional probability that the first parameter value corresponds to the media device being in a second state and a second conditional probability that the second parameter value corresponds to the media device being in the second state; and

determine a detected state of the media device by selecting a greater of the first state probability or the second state probability.

12. An apparatus defined in claim 11, further comprising:

a training data memory to store the first conditional probability; and

an input collector to receive the first signal from the first sensor and the second signal from the second sensor.

13. An apparatus as defined in claim 11, wherein the classifier is trained by:

determining the first conditional probability associated with the first parameter value and the second conditional probability associated with the second parameter value prior to receiving the first signal from the first sensor by placing a training media device into the first state, recording a first set of first parameter values, recording a second set of second parameter values, calculating a first probability distribution of the first parameter values in the first set, and calculating a second probability distribution of the second parameter values in the second set; and

determining the third conditional probability associated with the first parameter value and the fourth conditional probability associated with the second parameter value prior to receiving the second signal from the second sensor by placing the training media device into the second state, recording a third set of first parameter values, recording a fourth set of second parameter values, calculating a third probability distribution of the first parameter values in the third set, and calculating a fourth probability distribution of the second parameter values in the fourth set.

14. An apparatus as defined in claim 11, wherein the first sensor and the second sensor include at least one of an audio sensor, a visual sensor, a light sensor, a radio frequency sensor, an infrared sensor, a motion sensor, a vibration sensor, an angular rate sensor, an acceleration sensor, a pressure sensor, a voltage meter, a current meter, a power meter, a thermometer, a magnetic sensor, or a chemical sensor.

15. An apparatus as defined in claim 11, wherein the second sensor and the first sensor are the same sensor.

16. An apparatus as defined in claim 11, further comprising an input collector to receive a plurality of output signals from two or more sensors measuring a corresponding plurality of parameters of the media device.

17. An apparatus as defined in claim 11, wherein the media device includes at least one of a television, a computer, a digital video recorder, a digital video disc player, a digital audio player, a cellular telephone, a laptop, a personal digital assistant, a portable video player, a gaming machine, a pocket personal computer, a satellite radio player, or an in-vehicle entertainment system.

18. An apparatus as defined in claim 11, further comprising a preliminary classifier to receive at least one of the first parameter value or the second parameter value, generate a preliminary output by processing the first parameter value or the second parameter value using a probabilistic algorithm, and transmit the preliminary output to the classifier.

19. An apparatus as defined in claim 18, wherein the probabilistic algorithm is at least one of a fuzzy logic algorithm, a decision tree algorithm, a neural network algorithm, an instance-based learning algorithm, or a rule induction algorithm.

20. A tangible machine accessible storage device or disc comprising instructions that, when executed, cause a machine to at least:

process a first output signal from a first sensor measuring a first property of the media device to generate a first parameter value;

process a second output signal from a second sensor measuring a second property of the media device to generate a second parameter value;

generate a first state probability by combining a first conditional probability that the first parameter value corresponds to the media device being in a first state and a second conditional probability that the second parameter value corresponds to the media device being in the first state;

generate a second state probability by combining a third conditional probability that the first parameter value corresponds to the media device being in a second state and a fourth conditional probability that the second parameter value corresponds to the media device being in the second state; and

determine a detected state of the media device by selecting a greater of the first state probability or the second state probability.

21. A machine accessible storage device or disc as defined in claim 20, wherein the instructions, when executed, cause the machine to:

determine the first conditional probability associated with the first parameter value and second conditional probability associated with the second parameter value by placing a training media device into the first state, recording a first set of first parameter values, recording a second set of second parameter values, calculating a first probability distribution of the first parameter values in the first set, and calculating a second probability distribution of the second parameter values in the second set; and

determine the third conditional probabilities of the first parameter value and the second parameter value by placing the training media device into the second state, recording a third set of first parameter values, recording a fourth set of second parameter values, calculating a third probability distribution of the first parameter values in the third set, and calculating a fourth probability distribution of the second parameter values in the fourth set.

22. A machine accessible storage device or disc as defined in claim 20, wherein the instructions, when executed, cause the machine to:

process at least one of the first parameter value or the second parameter value into a preliminary output by processing the first parameter value or the second parameter value by a probabilistic algorithm;

combine the first conditional probability associated with the first parameter value, the second conditional probability associated with the second parameter value, and the preliminary output for the first state of the media device prior to determining the first state probability for the first state of the media device; and

combine the third conditional probability associated with the first parameter value, the fourth conditional probability associated with the second parameter value, and the preliminary output for the second state of the media device prior to determining the second state probability for the second state of the media device.