ADAPTATION OF CONTEXT MODELS

• US 20130238535A1
• Filed: 07/01/2010
• Published: 09/12/2013
• Est. Priority Date: 07/01/2010
• Status: Active Grant

• Current Assignee: Piece Future Pte., Ltd.
• Original Assignee: Nokia Corporation
• Inventors: Leppanen, Jussi, Eronen, Antti, Andippan, Rajasekaran
• Granted Patent: US 9,443,202 B2
• Time in Patent Office: Days
• US Class Current: 706/12
• CPC Class Codes: G06F 18/253 of extracted features
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: H04L 67/12 specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
• CPC Class Codes: H04W 4/025 using location based information parameters
• CPC Class Codes: H04W 4/38 for collecting sensor information

Abstract

There is disclosed a method including receiving sensor data extracted from one or more physical sensors, using the extracted sensor data and a context model to perform a first level context determination, and examining the at least one condition. If the examining indicated that the at least one condition was fulfilled, the context model is adapted on the basis of the sensor data, otherwise adaptation data formed on the basis of the sensor data is provided to a second level context determination. A corresponding apparatus and computer program product are also provided.

Claims

1. A method comprising:

receiving sensor data extracted from one or more physical sensors;

using the extracted sensor data and a context model to perform a first level context determination;

examining, with a processor, at least one condition; and

if the examining indicated that the at least one condition was fulfilled, adapting the context model on the basis of the sensor data, otherwise providing adaptation data formed on the basis of the sensor data to a second level context determination.

2. The method according to claim 1, wherein said at least one condition comprises at least one of

reliability of the context determination;

availability of further sensor data from another level to help context determination;

or

an available power budget defining limitations to proceeding to said second level context determination or to a higher level context determination.

3. The method according to claim 1, wherein said first level context determination comprises:

receiving virtual sensor data from one or more virtual sensors at said first level; and

combining the virtual sensor data with the extracted sensor data to be used in said first level context determination.

4. The method according to claim 1, wherein said second level context determination comprises:

receiving virtual sensor data from one or more virtual sensors; and

combining the virtual sensor data with the extracted sensor data to be used in said second level context determination.

6. The method according to claim 1, wherein said second level context determination comprises:

examining at least one condition of the second level context determination; and

if the examining indicated that the at least one condition of the second level context determination was fulfilled, adapting the context model, otherwise providing adaptation data formed on the basis of the sensor data and virtual sensor data to a third level context determination.

7. The method according to claim 6, wherein said at least one condition of the second level context determination comprises at least one of

reliability of the context determination;

availability of further sensor data from another level to help context determination;

or

an available power budget defining limitations to proceeding to said third level context determination or to a higher level context determination.

8. The method according to claim 6, wherein said third level context determination comprises:

examining at least one condition of the third level context determination; and

if the examining indicated that the at least one condition of the third level context determination was fulfilled, adapting the context model, otherwise providing adaptation data formed on the basis of the sensor data and the virtual sensor data to a fourth level context determination.

9. The method according to claim 8, wherein said at least one condition of the third level context determination comprises at least one of

reliability of the context determination;

availability of further sensor data from another level to help context determination;

or

an available power budget defining limitations to proceeding to said fourth level context determination or to a higher level context determination.

5. (canceled)

10-32. -32. (canceled)

33. An apparatus comprising:

at least one processor,

and at least one memory including computer program code,

the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus at least to

receive sensor data extracted from one or more physical sensors;

use the extracted sensor data and a context model to perform a first level context determination; and

examine at least one condition;

wherein the at least one memory and the computer program code is are further configured to adapt the context model on the basis of the sensor data if the examining indicated that the at least one condition was fulfilled, otherwise to provide adaptation data formed on the basis of the sensor data to a second level context determination.

34. The apparatus according to claim 33, wherein said at least one condition comprises at least one of

reliability of the context determination;

availability of further sensor data from another level to help context determination;

or

an available power budget defining limitations to proceeding to said second level context determination or to a higher level context determination.

35. The apparatus according to claim 33, wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the apparatus at least to:

receive virtual sensor data from one or more virtual sensors at said first level; and

combine the virtual sensor data with the extracted sensor data to be used in said first level context determination.

36. The apparatus according to claim 33, wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the apparatus at least to:

receive virtual sensor data from one or more virtual sensors; and

combine the virtual sensor data with the extracted sensor data to be used in said second level context determination.

38. The apparatus according to claim 33, wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the apparatus at least to:

examine at least one condition of the second level context determination, and

adapt the context model if the examining indicated that the at least one condition of the second level context determination was fulfilled, otherwise to provide adaptation data formed on the basis of the sensor data and virtual sensor data to a third level context determination.

39. The apparatus according to claim 38, wherein said at least one condition of the second level context determination comprises at least one of

reliability of the context determination;

availability of further sensor data from another level to help context determination;

or

an available power budget defining limitations to proceeding to said third level context determination or to a higher level context determination.

40. The apparatus according to claim 38, wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the apparatus at least to:

examine at least one condition of the third level context determination; and

adapt the context model if the examining indicated that the at least one condition of the third level context determination was fulfilled, otherwise to provide adaptation data formed on the basis of the sensor data and the virtual sensor data to a fourth level context determination.

41. The apparatus according to claim 40, wherein said at least one condition of the third level context determination comprises at least one of

reliability of the context determination;

availability of further sensor data from another level to help context determination;

or

an available power budget defining limitations to proceeding to said fourth level context determination or to a higher level context determination.

37. (canceled)

42-48. -48. (canceled)

49. A computer program product comprising at least one non-transitory computer-readable storage medium having computer-executable program code portions stored therein, the computer-executable program code portions comprising program code instructions for:

receiving sensor data extracted from one or more physical sensors;

using the extracted sensor data and a context model to perform a first level context determination;

examining at least one condition; and

if the examining indicated that the at least one condition was fulfilled, adapting the context model on the basis of the sensor data, otherwise providing adaptation data formed on the basis of the sensor data to a second level context determination.

51. The computer program product according to claim 49, wherein said first level context determination comprises:

receiving virtual sensor data from one or more virtual sensors at said first level; and

combining the virtual sensor data with the extracted sensor data to be used in said first level context determination.

52. The computer program product according to claim 49, wherein said second level context determination comprises:

receiving virtual sensor data from one or more virtual sensors; and

combining the virtual sensor data with the extracted sensor data to be used in said second level context determination.

53. The computer program product according to claim 49, wherein said second level context determination comprises:

examining at least one condition of the second level context determination; and

if the examining indicated that the at least one condition of the second level context determination was fulfilled, adapting the context model, otherwise providing adaptation data formed on the basis of the sensor data and virtual sensor data to a third level context determination.

50. (canceled)