METHOD AND SYSTEM FOR IDENTIFYING EXCEPTIONS OF PEOPLE BEHAVIOR

• US 20160007165A1
• Filed: 02/18/2014
• Published: 01/07/2016
• Est. Priority Date: 02/19/2013
• Status: Active Grant

• Current Assignee: Angel Sense Ltd
• Original Assignee: Angel Sense Ltd
• Inventors: SOMER, Doron, BEN-AZAR, Nery
• Granted Patent: US 10,104,509 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: H04M 1/72454 according to context-related or environment-related conditions
• CPC Class Codes: H04W 4/029 Location-based management or tracking services
• CPC Class Codes: H04W 4/90 Services for handling of emergency or hazardous situations, e.g. earthquake and tsunami warning systems [ETWS]
• CPC Class Codes: H04W 84/18 Self-organising networks, e.g. ad-hoc networks or sensor networks

Abstract

The present invention discloses a method and system for identifying exceptions, of a person/child behavior through scheduled behavior, using a personal communication device having at least one sensor attached to person/child body which provide location data and motion data, The method comprising the steps of: sampling measurements data for each sensor of the personal communication device, identifying atomic pattern of sampled measurements, said atomic pattern representing basic behavior of the person/child, identify location in which person has spent time using a clustering algorithm, create activity segmentation characterized by location, schedule, caregiver, or content derived from sensors measurements and atomic patterns and analyzing characteristics changes or combination thereof of activities in sequenced/complex activities in comparison to baseline, to identify exception which indicate of at least one of the following: changes at activity level, changes at emotional arousal level, unknown locations or unexpected locations based on schedule.

Claims

1. A method for identifying exceptions, of a person behavior and/or location through scheduled behavior, using a personal communication device associated with least one sensor, which provide at least location data and/or motion data, attached to a person body or garments, said method comprising the steps of:

sampling measurements data for each sensor associated with the person'"'"'s communication device;

identifying atomic pattern of sampled measurements, said atomic pattern representing basic behavior of the person;

identify locations in which the person has spent time using a clustering algorithm;

create activity segmentation characterized by location, schedule, activity type, or content derived from sensors measurements and atomic patterns;

analyzing characteristics changes or combination thereof of activities in sequenced/complex activities in comparison to given baseline, to identify exception which indicate of at least one of the following;

changes at activity level, changes at emotional arousal level, unknown locations or unexpected locations based on schedule.

2. The method of claim 1 further comprising the step of creating visualization presentation of the scheduled location based on activity segmentation.

3. The method of claim 1 further comprising the steps of receiving sensor measurements received from communication device associated with a caregiver or person currently located in vicinity of the person and identifying correlations/association between different sensors measurements.

4. The method of claim 1 further comprising the steps of receiving data from environmental sensors

5. The method of claim 1 further comprising the steps of receiving location based data from web based or external services.

6. The method of claim 1 further comprising the step of creating a hierarchical representation of activity sequences of time period with the same context.

8. The method of claim 1 further comprising the step of receiving information from guardian associating a specific pattern or a specific time interval with a specific emotion and applying algorithms to learn the typical behavior of the person representing each emotion using the information provided by the guardian.

9. The method of claim 1 further comprising the step of using predefined domain specific rules for determining a reporting mechanism for sending an alert of behavior exceptions based on at least one of the following:

severity of exceptions, classifications determined in the supervised learning stage and user preferences.

11. The method of claim 1 wherein the activities segmentation includes classifying transits state between locations.

7. (canceled)

10. (canceled)

12. (canceled)

13. A system for identifying exceptions, of a person behavior and/or location through scheduled behavior, said system comprised of

a personal communication device associated with least one sensor attached to a person body or garments which provides at least location data and/or motion data said communication device is associated with a sensor processing module for sampling measurements data for each sensor of the personal communication device and identifying atomic pattern of sampled measurements, said atomic pattern represents basic behavior of the person;

a server including segmentation modules for identifying location in which the person has spent time using a clustering algorithm, creating activity segmentation characterized by location, schedule, caregiver, or content derived from sensors measurements and atomic patterns and Exception Identification module for analyzing characteristics changes or combination thereof of activities in sequenced/complex activities in comparison to given baseline, to identify exception which indicate of at least one of the following;

changes at activity level, changes at emotional arousal level, unknown locations or unexpected locations based on schedule.

14. The system of claim 13 further comprising visualization presentation of the scheduled location based on activity segmentation.

15. The system of claim 13 wherein segmentation module further receives sensor measurements received from communication device associated with a caregiver or person currently located in vicinity of the person and identifies correlations/association between different sensors measurements.

16. The system of claim 13 wherein the segmentation modules further receives data from environmental sensors

17. The system of claim 13 wherein segmentation module further receives location based data from web based services.

18. The system of claim 13 wherein segmentation module further creates a hierarchical representation of activity sequences of time period with the same context.

19. The system of claim 13 wherein segmentation module further uses schedule information provided by the guardian or other external sources to refine segmentation.

20. The system of claim 13 wherein Exception Identification module further receives information from guardian associating a specific pattern or a specific time interval with a specific emotion and applying algorithms to learn the typical behavior of the person representing each emotion using the information provided by the guardian.

21. The system of claim 13 further wherein Exception Identification module further uses predefined domain specific rules for determining a reporting mechanism for sending an alert of behavior exceptions based on at least one of the following:

severity of exceptions, classifications determined in the supervised learning stage and user preferences.

22. The system of claim 13 further comprising communication interface for the guardian to perform inquiries based on exceptions.

23. The system of claim 13 wherein segmentation module includes classifying transits state between locations.

24. (canceled)