Inferring a context from crowd-sourced activity data

• US 8,948,789 B2
• Filed: 09/26/2012
• Issued: 02/03/2015
• Est. Priority Date: 05/08/2012
• Status: Expired due to Fees

• Current Assignee: Qualcomm, Inc.
• Original Assignee: Qualcomm, Inc.
• Inventors: Sadasivam, Shankar, Grokop, Leonard Henry, Narayanan, Vidya
• Primary Examiner(s): MAPA, MICHAEL Y
• Application Number:
  US13/627,702
• Publication Number:
  US 20130303198A1
• Time in Patent Office: 860 Days
• Field of Search: 455/404.2, 455/414.2, 4554561-457
• US Class Current: 455/456.3
• CPC Class Codes: G01S 19/39 the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
• CPC Class Codes: G01S 19/48 by combining or switching between position solutions derived from the satellite radio beacon positioning system and position solutions derived from a further system
• CPC Class Codes: G01S 5/017 Detecting state or type of motion
• CPC Class Codes: G01S 5/0278 involving statistical or probabilistic considerations G01S5/0252, G01S5/0294 take precedence
• CPC Class Codes: H04M 1/72454 according to context-related or environment-related conditions
• CPC Class Codes: H04W 4/023 using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds

Abstract

Techniques are provided to infer a context associated with a mobile device based on aggregated data from a set of other mobile devices. The set of mobile devices can include mobile devices currently or previously near a location of the mobile device. Each mobile device in the set of other mobile devices can collect sensor data and infer a low-level context (e.g., “sitting” or “standing”). The low-level contexts can be aggregated. Based on the aggregated low-level contexts, a high-level context (e.g., “at a party” or “watching television”) associated with the mobile device can be inferred or a low-level context associated with the mobile device can be refined.

Claims

1. A method for inferring a high-level context associated with a mobile device, the method comprising:

accessing low-level context information for each of a plurality of other devices, wherein location information associated with each of the other devices indicates a proximity to a location of the mobile device, and wherein the low-level context information for each of the other devices is based on data collected by a sensor of the respective other device;

aggregating the low-level context information across the plurality of other devices;

comparing the aggregated low-level context information to a plurality of templates, each template being associated with a high-level context and including one or more histograms of context data;

determining match scores between the aggregated low-level context information and each of the one or more histograms of context data; and

transmitting, to the mobile device, a multi-device statistical summary comprising the aggregated low-level context information and the match scores; and

the mobile device inferring a context based on the multi-device statistical summary and additional data not included in the multi-device statistical summary.

2. The method of claim 1, wherein the plurality of other devices comprise at least one non-mobile device in a security system.

3. The method of claim 1, wherein the location information associated with each of the other devices indicates a current proximity to the location of the mobile device, the location of the mobile device being a current location.

4. The method of claim 1, wherein each of the other devices and the mobile device are estimated to be at a same type of location.

5. The method of claim 1, further comprising:

estimating a time context of the mobile device, wherein the mobile device is estimated to be in the time context and at the location simultaneously, and wherein each of the plurality of other devices is estimated to be at the respective proximity during another time context, the time context and the another time context being the same.

6. The method of claim 1, wherein the low-level context information comprises information indicative of a motion state, a device position or both.

7. The method of claim 1, wherein the high-level context comprises a situation.

8. The method of claim 1, wherein the low-level context information comprises motion sensor information from which a low-level context can be inferred.

9. The method of claim 1, wherein at least one of the other devices comprises another mobile device.

10. The method of claim 1, wherein each high-level context of a plurality of high-level contexts is associated with a set of templates, each template in the set of templates being associated with a different type of low-level context.

11. A system for inferring a high-level context associated with a mobile device, the system comprising:

memory;

a processor coupled to the memory;

a context aggregator configured to;

access, via the processor, low-level context information for each of a plurality of other devices, wherein location information associated with each of the other devices indicates a proximity to a location of the mobile device, and wherein the low-level context information for each of the other devices is based on data collected by a sensor of the respective other device;

aggregate the low-level context information across the plurality of other devices;

a high-level template comparison engine configured to;

compare, via the processor, the aggregated low-level context information to a plurality of templates, each template being associated with a high-level context and including one or more histograms of context data;

determine match scores between the aggregated low-level context information and each of the one or more histograms of context data; and

a transceiver configured to transmit, to the mobile device, a multi-device statistical summary comprising the aggregated low-level context information and the match scores; and

the mobile device inferring a context based on the multi-device statistical summary and additional data not included in the multi-device statistical summary.

12. The system of claim 11, further comprising a low-level context inferring engine configured to infer a low-level context for the mobile device based on data collected by a sensor of the mobile device.

13. The system of claim 11, wherein the context aggregator is configured to aggregate the low-level context information for each of the plurality of other devices and low-level context information for the mobile device.

14. The system of claim 11, wherein the aggregated low-level context information comprises a distribution.

15. The system of claim 11, wherein comparing the aggregated low-level context information to a plurality of templates comprises generating a score associated with each template of the plurality of templates.

16. A system for inferring a high-level context associated with a mobile device, the system comprising:

means for accessing low-level context information for each of a plurality of other devices, wherein location information associated with each of the other devices indicates a proximity to a location of the mobile device, and wherein the low-level context information for each of the other devices is based on data collected by a sensor of the respective other device;

means for aggregating the low-level context information across the plurality of other devices;

means for comparing the aggregated low-level context information to a plurality of templates, each template being associated with a high-level context and including one or more histograms of context data;

means for determining match scores between the aggregated low-level context information and each of the one or more histograms of context data; and

means for transmitting, to the mobile device, a multi-device statistical summary comprising the aggregated low-level context information and the match scores;

scores and the mobile device comprising means for inferring a context based on the multi-device statistical summary and additional data not included in the multi-device statistical summary.

17. The system of claim 16, wherein the location information associated with each of the other devices indicates a current proximity to the current location of the mobile device.

18. The system of claim 16, further comprising:

means for estimating a time context of the mobile device, wherein the mobile device is estimated to be in the time context and at the location simultaneously, and wherein each of the plurality of other devices is estimated to be at the respective proximity during another time context, the time context and the another time context being the same.

19. The system of claim 16, wherein the low-level context information comprises information indicative of a motion state, a device position or both.

20. A computer-readable storage medium containing program instructions, that, when executed by a processor, cause the processor to execute a method comprising:

accessing low-level context information for each of a plurality of other devices, wherein location information associated with each of the other devices indicates a proximity to a location of a mobile device, and wherein the low-level context information for each of the other devices is based on data collected by a sensor of the respective other device;

aggregating the low-level context information across the plurality of other devices;

comparing the aggregated low-level context information to a plurality of templates, each template being associated with a high-level context and including one or more histograms of context data;

determining match scores between the aggregated low-level context information and each of the one or more histograms of context data; and

transmitting, to the mobile device, a multi-device statistical summary comprising the aggregated low-level context information and the match scores; and

the mobile device inferring a context based on the multi-device statistical summary and additional data not included in the multi-device statistical summary.

21. The computer-readable storage medium of claim 20, wherein the method further comprises estimating the location of the mobile device based on data collected by the sensor of the mobile device.

22. The computer-readable storage medium of claim 20, wherein the method further comprises identifying an application from a set of available software applications based on the high-level context.

23. The computer-readable storage medium of claim 20, wherein the sensor of the mobile device and the sensor of at least one of the other devices include different types of sensors.

24. A method for inferring a context associated with a mobile device, the method comprising:

accessing low-level context information for each of a plurality of other devices, wherein location information associated with each of the other devices indicates a proximity between a location of the other device at a first time and a location of the mobile device at a second time, the first time and the second time being different, and wherein the low-level context information for each of the other devices is based on data collected by a sensor of the respective other device;

aggregating the low-level context information across the plurality of other devices;

comparing the aggregated low-level context information to a plurality of templates, each template being associated with a high-level context and including one or more histograms of context data;

determining match scores between the aggregated low-level context information and each of the one or more histograms of context data; and

transmitting, to the mobile device, a multi-device statistical summary comprising the aggregated low-level context information and the match scores; and

the mobile device inferring a context based on the multi-device statistical summary and additional data not included in the multi-device statistical summary.

25. The method of claim 24, wherein the plurality of other devices comprise at least one non-mobile device in a security system.

26. The method of claim 24, wherein the inferred context includes a high-level context.

27. The method of claim 24, wherein inferring the context includes refining a previously inferred a low-level context.

28. A system for inferring a context associated with a mobile device, the system comprising:

memory;

a processor coupled to the memory;

a context aggregator configured to;

access, via the processor, low-level context information for each of a plurality of other devices, wherein location information associated with each of the other devices indicates a proximity between a location of the other device at a first time and a location of the mobile device at a second time, the first time and the second time being different, and—

wherein the low-level context information for each of the other devices is based on data collected by a sensor of the respective other device; and

aggregate the low-level context information across the plurality of other devices; and

a context inferring engine configured to;

compare the aggregated low-level context information to a plurality of templates, each template being associated with a high-level context and including one or more histograms of context data;

determine, via the processor, a match score between the aggregated low-level context information and one or more histograms of context data; and

a transceiver configured to transmit, to the mobile device, a multi-device statistical summary comprising the aggregated low-level context information and the match scores; and

the mobile device inferring a context based on the multi-device statistical summary and additional data not included in the multi-device statistical summary.

29. The system of claim 28, wherein aggregating the low-level context information comprises generating one or more histograms with respect to a low-level context inference associated with each device of the plurality of other devices.

30. The system of claim 28, wherein aggregating the low-level context information comprises assessing a location-based criterion or a temporal-based criterion with respect to a preliminary set of devices to identify the other devices.

31. The system of claim 28, further comprising a template comparison engine configured to compare the aggregated low-level context information to a plurality of templates, each template being associated with a context.

32. A system for inferring a context associated with a mobile device, the system comprising:

means for accessing low-level context information for each of a plurality of other devices, wherein location information associated with each of the other devices indicates a proximity between a location of the other device at a first time and a location of the mobile device at a second time, the first time and the second time being different, and wherein the low-level context information for each of the other devices is based on data collected by a sensor of the respective other device;

means for aggregating the low-level context information across the plurality of other devices;

means for comparing the aggregated low-level context information to a plurality of templates, each template being associated with a high-level context and including one or more histograms of context data;

means for determining match scores between the aggregated low-level context information and the one or more histograms of context data; and

means for transmitting, to the mobile device, a multi-device statistical summary comprising the aggregated low-level context information and the match scores; and

the mobile device comprising means for inferring a context based on the multi-device statistical summary and additional data not included in the multi-device statistical summary.

33. The system of claim 32, wherein the means for accessing low-level context information for each of the plurality of other devices comprises a Bluetooth receiver.

34. The system of claim 32, further comprising means for identifying the plurality of other devices by detecting all devices at a location less than a threshold distance away from the location of the mobile device.

35. The system of claim 32, wherein the low-level context information characterizes a motion state, a device position or both.

36. The system of claim 32, wherein the inferred context characterizes a situation.

37. A computer-readable storage medium containing program instructions, that, when executed by a processor, cause the processor to execute a method comprising:

accessing low-level context information for each of a plurality of other devices, wherein location information associated with each of the other devices indicates a proximity between a location of the other device at a first time and a location of a mobile device at a second time, the first time and the second time being different, and wherein the low-level context information for each of the other devices is based on data collected by a sensor of the respective other device;

aggregating the low-level context information across the plurality of other devices;

determining match scores between the aggregated low-level context information and each of the one or more histograms of context data; and

transmitting, to the mobile device, a multi-device statistical summary comprising the aggregated low-level context information and the match scores; and

the mobile device inferring a context based on the multi-device statistical summary and additional data not included in the multi-device statistical summary.

38. The computer-readable storage medium of claim 37, wherein the method further comprises estimating the location of the mobile device based on data collected by the sensor of the mobile device.

39. The computer-readable storage medium of claim 37, wherein the method further comprises identifying a software application from a set of available software applications based on the inferred context.

40. The computer-readable storage medium of claim 37, wherein the sensor of the mobile device and the sensor of at least one of the other devices include different types of sensors.