Learning situations via pattern matching

• US 8,768,865 B2
• Filed: 10/07/2011
• Issued: 07/01/2014
• Est. Priority Date: 01/19/2011
• Status: Active Grant

• Current Assignee: Qualcomm, Inc.
• Original Assignee: Qualcomm, Inc.
• Inventors: Narayanan, Vidya, Nanda, Sanjiv, Shih, Fuming
• Primary Examiner(s): CHEN, ALAN S
• Application Number:
  US13/269,516
• Publication Number:
  US 20120265717A1
• Time in Patent Office: 998 Days
• Field of Search: None
• US Class Current: 706/12
• CPC Class Codes: G01P 15/00 Measuring acceleration; Measuring deceleration; Measuring shock, i.e. sudden change of acceleration
• CPC Class Codes: G06F 18/217 Validation; Performance evaluation; Active pattern learning techniques
• CPC Class Codes: G06F 18/2411 based on the proximity to a decision surface, e.g. support vector machines
• CPC Class Codes: G06F 18/24137 Distances to cluster centroïds
• CPC Class Codes: G06F 18/2453 non-linear, e.g. polynomial classifier
• CPC Class Codes: G06F 18/251 of input or preprocessed data
• CPC Class Codes: G06F 2218/12 Classification; Matching
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 20/10 using kernel methods, e.g. support vector machines [SVM]
• CPC Class Codes: G06N 3/126 Evolutionary algorithms, e.g. genetic algorithms or genetic programming
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition
• CPC Class Codes: G06N 5/048 Fuzzy inferencing
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06V 40/25 Recognition of walking or running movements, e.g. gait recognition

Abstract

Example methods, apparatuses, or articles of manufacture are disclosed herein that may be utilized, in whole or in part, to facilitate or support one or more operations or techniques for machine learning of situations via pattern matching or recognition.

Claims

1. A method comprising:

monitoring, at a mobile device, input signals from a plurality of information sources associated with said mobile device;

detecting at least one condition based, at least in part, on at least one of said monitored input signals;

identifying a first pattern based, at least in part, on said at least one detected condition; and

fixing a subset of varying parameters associated with said first pattern by associating at least one parameter of said subset of varying parameters with said first pattern to represent said at least one detected condition, said varying parameters derived, at least in part, from said monitored input signals.

2. The method of claim 1, wherein said fixing said subset of varying parameters comprises associating said varying parameters to represent a condition derived from said monitored input signals from at least one of the following disposed in said mobile device:

an accelerometer, a Global Positioning System (GPS)-enabled device, a Wireless Fidelity (WiFi)-enabled device, or any combination thereof.

3. The method of claim 1, and further comprising initiating a process to attempt a recognition of a second pattern in connection with said monitoring said input signals based, at least in part, on said first identified pattern.

4. The method of claim 3, wherein said second pattern is recognized in a reduced set of varying parameters derived from said monitored input signals in response, at least in part, to said fixing of said subset of varying parameters.

5. The method of claim 3, wherein said process further comprises:

capturing a snapshot of said monitored input signals in response to said detection of said at least one condition, said monitored input signals defining at least one context-related information stream; and

correlating said snapshot with said second pattern in a database.

6. The method of claim 5, wherein said second pattern is attempted to be recognized in connection with correlating said snapshot with at least one of the following:

a temporal pattern, an action-correlated pattern, a transition-correlated pattern, a relational pattern, or any combination thereof.

7. The method of claim 5, wherein said snapshot comprises at least one of the following:

a snapshot of said first identified pattern, a snapshot of said second pattern, a snapshot of said at least one context-related information stream, or any combination thereof.

8. The method of claim 5, wherein said snapshot is correlated in connection with a captured history of said at least one context-related information stream.

9. The method of claim 8, wherein said history comprises a time period captured prior to said detecting said at least one condition.

10. The method of claim 9, wherein said time period comprises a time period existing for a threshold duration.

11. The method of claim 10, wherein said threshold duration comprises a duration relevant to said at least one detected condition.

12. The method of claim 5, wherein said database comprises at least one of the following:

a condition database, a correlation database, or any combination thereof.

13. The method of claim 12, wherein said condition database comprises said at least one context-related information stream.

14. The method of claim 12, wherein said correlation database comprises at least one of the following:

a condition correlation database, a transition correlation database, or any combination thereof.

15. The method of claim 1, wherein at least one of said plurality of information sources comprises signals generated in response to at least one of the following:

a user executing an instruction on said mobile device, a host application executing an instruction on said mobile device, or any combination thereof.

16. The method of claim 15, wherein said host application executes said instruction in response to at least one signal received from at least one sensor associated with said mobile device.

17. The method of claim 1, wherein said fixed subset of said varying parameters comprises said first pattern.

18. The method of claim 1, and further comprising identifying at least one pattern irrelevant to said at least one condition in connection with said monitoring input signals.

19. The method of claim 18, wherein said irrelevant pattern is identified via an application of at least one of the following:

a context labeling-type process, a situation labeling-type process, or any combination thereof.

20. The method of claim 18, wherein said irrelevant pattern is identified in connection with a user identifying at least one of the following:

a relevant information source among said plurality of information sources, a relevant information stream among a plurality of context-related information streams, or any combination thereof.

21. An apparatus comprising:

a mobile device comprising at least one processor configured to;

monitor input signals from a plurality of information sources associated with said mobile device;

detect at least one condition based, at least in part, on at least one of said monitored input signals;

identify a first pattern based, at least in part, on said at least one detected condition; and

fix a subset of varying parameters associated with said first pattern by associating at least one parameter of said subset of varying parameters with said first pattern to represent said at least one detected condition, said varying parameters derived, at least in part, from said monitored input signals.

22. The apparatus of claim 21, wherein said at least one processor is further configured to initiate a process to attempt a recognition of a second pattern in connection with said processor to monitor said input signals based, at least in part, on said first identified pattern.

23. The apparatus of claim 22, wherein said second pattern is associated with a reduced set of varying parameters derived from said monitored input signals due, at least in part, to fixing said subset of varying parameters.

24. The apparatus of claim 22, wherein said processor is further configured to:

capture a snapshot of said monitored input signals in response to said detection of said at least one condition, said monitored input signals defining at least one context-related information stream; and

correlate said snapshot with said second pattern in a database.

25. The apparatus of claim 24, wherein said snapshot comprises at least one of the following:

a snapshot of said first identified pattern, a snapshot of said second pattern, a snapshot of said at least one context-related information stream, or any combination thereof.

26. The apparatus of claim 24, wherein said second pattern is attempted to be recognized in connection with said correlation of said snapshot with at least one of the following:

a temporal pattern, an action-correlated pattern, a transition-correlated pattern, a relational pattern, or any combination thereof.

27. The apparatus of claim 24, wherein said snapshot is correlated in connection with a captured history of said at least one context-related information stream.

28. The apparatus of claim 21, wherein at least one of said plurality of information sources comprises signals generated in response to at least one of the following:

a user executing an instruction on said mobile device, a host application executing an instruction on said mobile device, or any combination thereof.

29. The apparatus of claim 21, wherein said fixed subset of said varying parameters comprises said first pattern.

30. The apparatus of claim 21, wherein said at least one processor is further configured to identify at least one pattern irrelevant to said at least one condition in connection with said processor to monitor said input signals.

31. An apparatus comprising:

means for monitoring, at a mobile device, input signals from a plurality of information sources associated with said mobile device;

means for detecting at least one condition based, at least in part, on at least one of said monitored input signals;

means for identifying a first pattern based, at least in part, on said at least one detected condition; and

means for fixing a subset of varying parameters associated with said first pattern by associating at least one parameter of said subset of varying parameters with said first pattern to represent said at least one detected condition, said varying parameters derived, at least in part, from said monitored input signals.

32. The apparatus of claim 31, and further comprising means for initiating a process to attempt a recognition of a second pattern in connection with said monitoring said input signals based, at least in part, on said first identified pattern.

33. The apparatus of claim 32, wherein said second pattern is associated with a reduced set of varying parameters derived from said monitored input signals due, at least in part, to said fixing of said subset of varying parameters.

34. The apparatus of claim 32, wherein said means for initiating said process further comprises:

means for capturing a snapshot of said monitored input signals in response to said detection of said at least one condition, said monitored input signals defining at least one context-related information stream; and

means for correlating said snapshot with said second pattern in a database.

35. The apparatus of claim 34, wherein said second pattern is attempted to be recognized in connection with correlating said snapshot with at least one of the following:

a temporal patter, an action-correlated pattern, a transition-correlated pattern;

a relational pattern, or any combination thereof.

36. The apparatus of claim 34, wherein said snapshot comprises at least one of the following:

a snapshot of said first identified pattern, a snapshot of said second pattern, a snapshot of said at least one context-related information stream, or any combination thereof.

37. The apparatus of claim 34, wherein said snapshot is correlated in connection with a captured history of said at least one context-related information stream.

38. The apparatus of claim 37, wherein said history comprises a time period captured prior to said detecting said at least one condition.

39. The apparatus of claim 38, wherein said time period comprises a time period existing for a threshold duration.

40. The apparatus of claim 39, wherein said threshold duration comprises a duration relevant to said at least one detected condition.

41. The apparatus of claim 34, wherein said database comprises at least one of the following:

a condition database, a correlation database, or any combination thereof.

42. The apparatus of claim 31, wherein at least one of said plurality of information sources comprises signals generated in response to at least one of the following:

a user executing an instruction on said mobile device, a host application executing an instruction on said mobile device, or any combination thereof.

43. The apparatus of claim 31, wherein said fixed subset of said varying parameters comprises said first pattern.

44. The apparatus of claim 31, and further comprising means for identifying at least one pattern irrelevant to said at least one condition in connection with said monitoring said input signals.

45. The apparatus of claim 44, wherein said irrelevant pattern is identified via an application of at least one of the following:

a context labeling-type process, a situation labeling-type process, or any combination thereof.

46. An article comprising:

a non-transitory storage medium having instructions stored thereon executable by a special purpose computing platform at a mobile device to;

monitor input signals from a plurality of information sources associated with said mobile device;

detect at least one condition based, at least in part, on at least one of said monitored input signals;

identify a first pattern based, at least in part, on said at least one detected condition; and

fix a subset of varying parameters associated with said first pattern by associating at least one parameter of said subset of varying parameters with said first pattern to represent said at least one detected condition, said varying parameters derived, at least in part, from said monitored input signals.

47. The article of claim 46, wherein said storage medium further includes instructions to initiate a process to attempt a recognition of a second pattern in connection with said monitoring said input signals based, at least in part, on said first identified pattern.

48. The article of claim 47, wherein said instructions to initiate said process further comprise instructions to:

capture a snapshot of said monitored input signals in response to said detection of said at least one condition, said monitored input signals defining at least one context-related information stream; and

correlate said snapshot with said second pattern in a database.

49. The article of claim 47, wherein said second pattern is attempted to be recognized in connection with at least one of the following:

a temporal pattern, an action-correlated pattern, a transition-correlated pattern, a relational pattern, or any combination thereof.

50. The article of claim 48, wherein said snapshot comprises at least one of the following:

a snapshot of said first identified pattern, a snapshot of said second pattern, a snapshot of said at least one context-related information stream, or any combination thereof.

51. The article of claim 48, wherein said snapshot is correlated in connection with a captured history of said at least one context-related information stream.

52. The article of claim 46, wherein said storage medium further includes instructions to identify at least one pattern irrelevant to said at least one condition in connection with said monitoring said input signals.

53. The article of claim 52, wherein said irrelevant pattern is identified via an application of at least one of the following:

a context labeling-type process, a situation labeling-type process, or any combination thereof.