System and method for determining periods of interest in home of persons living independently

• US 7,091,865 B2
• Filed: 02/04/2004
• Issued: 08/15/2006
• Est. Priority Date: 02/04/2004
• Status: Active Grant

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Weisenberg, Jenny Marie, Ganesh, Meena, Cuddihy, Paul Edward, Graichen, Catherine Mary
• Primary Examiner(s): MULLEN, THOMAS J
• Application Number:
  US10/772,761
• Publication Number:
  US 20050181771A1
• Time in Patent Office: 923 Days
• Field of Search: 340/573.1, 340/573.4, 340/545.1, 340/545.6, 340/539.1, 34053911-53914, 34053916-53917, 340/539.22, 340/309.16, 379/38
• US Class Current: 340/573.1
• CPC Class Codes: G08B 21/0423 detecting deviation from an expected pattern of behaviour or schedule
• CPC Class Codes: G08B 21/0492 Sensor dual technology, i.e. two or more technologies collaborate to extract unsafe condition, e.g. video tracking and RFID tracking
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 40/63 for local operation
• CPC Class Codes: G16H 40/67 for remote operation

Abstract

A system and method for monitoring the activities of a resident living independently to distinguish normal activity from unusual activity. A variety of sensors distributed around the home collect data on activity in the home. The data is communicated to a remote monitoring center and collated in a database according to applicable time slots. The time slots for a twenty-four hour cycle are at least three and can be as many as forty-eight or more. Historical activity time lines are created and a buffer time is added to and offset from the maximum historical activity time line. If a new data point comes in that exceeds both the maximum historical activity time line and the buffer time, an alert is issued indicating the activity is unusual.

Claims

1. A system for monitoring activity of a resident, comprising:

a plurality of sensors positioned throughout a home of the resident for collecting data points on activity of the resident;

a communication platform in communication with sensors; and

a monitoring center located remote from the resident and in communication with the communication platform, said monitoring center comprising;

a database for collecting the data points on activity of the resident, wherein the collected data points are collated into at least three time slots per every twenty-four hour time cycle for determining activity of the resident.

2. The system of claim 1, wherein the collected data points are collated into at least ten time slots per every twenty-four hour time cycle.

3. The system of claim 2, wherein the collected data points are collated into at least forty-eight time slots per every twenty-four hour time cycle.

4. The system of claim 1 , wherein the plurality of sensors comprise one or more from the group consisting of motion sensors, exterior door sensors, inside door sensors, cabinet sensors, kitchen sensors, appliance sensors, hazard sensors, and security sensors.

5. The system of claim 1, wherein the plurality of sensors comprise at least one motion sensor and at least one exterior door sensor.

6. The system of claim 5, wherein said monitoring center is adapted to determine whether the resident is away from the home.

7. The system of claim 1, wherein said communication platform comprises a near real-time communication platform.

8. The System of claim 1, wherein at least one of the sensors is worn by the resident.

9. A system for monitoring activity within a home, comprising:

a plurality of sensors positioned throughout the home for collecting data points on activity in the home, wherein the plurality of sensors comprises one or more from the group consisting of motion sensors, exterior door sensors, inside door sensors, cabinet sensors, kitchen sensors, appliance sensors, hazard sensors, and security sensors;

a communication platform in communication with the plurality of sensors; and

a monitoring center located remote from the home and in communication with the communication platform, said monitoring center comprising;

a database for collecting the data points on activity in the home, wherein the collected data points are collated into at feast ten time slots per every twenty-four hour time cycle for determining activity Within the home.

10. The system of claim 9, wherein the collected data points are collated into at least forty-eight time slots per every twenty-four hour time cycle.

11. The system of claim 9, wherein the plurality of sensors comprise at least one motion sensor and at least one exterior door sensor.

12. The system of claim 11, wherein said monitoring center is adapted to determine whether a resident of the home is away from the home.

13. The system of claim 9, wherein said communication platform comprises a near real-time communication platform.

14. A method for distinguishing between normal and unusual activity in a home, comprising:

obtaining historical activity data within the home for a twenty-four hour cycle;

collating the historical activity data into at least three time slots within the twenty-four hour cycle; and

evaluating a new data point against the collated historical activity data to determine whether the new data point indicates normal or unusual activity in the home, wherein the activity to be distinguished is inactivity; and

,

producing a maximum historical inactivity time line based upon the collated historical activity data.

15. The method of claim 14, further comprising providing a butter time to the maximum historical inactivity time line to create an alert line.

16. The method of claim 15, further comprising offsetting the buffer time, wherein the new data point is evaluated against both the historical activity data and the alert line.

17. The method of claim 15, wherein the evaluating step comprises:

collating the new data point into one of the at least three time slots; and

evaluating the new data point against the historical activity data of said one of the at least three time slots as well as against surrounding time slats.

18. The method of claim 17, wherein the evaluating step further comprises determining whether sufficient historical activity data exists for said one of the at least three time slots and for said surrounding time slots.

19. The method of claim 18, wherein the evaluating step further comprises determining whether the new data point exceeds the maximum historical inactivity time line and the alert line.

20. The method of claim 17, further comprising determining whether a resident of the home is at home or away and ignoring any new data points received during a period when the resident is away from the home.

21. The method of claim 15, further comprising creating a sleep window from the historical activity data based upon the lowest activity detected in the at least three time slots during the twenty-four hour cycle.

22. The method of claim 21, further comprising altering the alert fine within the sleep window.

23. The method of claim 14, wherein the collating step comprises collating the historical activity data into at least ten time slots within the twenty-four hour cycle.

24. The method of claim 23, wherein the collating step comprises collating the historical activity data into at least forty-eight time slots within the twenty-four hour cycle.

25. The method of claim 14, wherein the activity to be distinguished further comprises movement of an exterior door to the home.

26. The method of claim 14, wherein the activity to be distinguished further comprises activity within a kitchen in the home.

27. The method of claim 14, wherein the evaluating step includes plotting the new data point against the collated historical activity data to determine whether the new data point indicates normal or unusual activity in the home.

28. A method for distinguishing between unusual periods of inactivity and normal periods of inactivity in a home, comprising:

obtaining historical activity data within the home for a twenty-four hour cycle;

collating the historical activity data into at least ten time slots within the twenty-four hour cycle;

producing a maximum historical inactivity time line based upon the collated historical activity data; and

evaluating a new data point against the collated historical activity data to determine whether the new data point indicates an unusual period of inactivity or a normal period of inactivity in the home.

29. The method of claim 28, further comprising providing a buffer time to the maximum historical inactivity time line to create an alert line.

30. The method of claim 29, further comprising offsetting the buffer time, wherein the new data point is evaluated against both the historical activity data and the alert line.

31. The method of claim 29, wherein the evaluating step comprises:

collating the new data point into one of the at least three time slots; and

evaluating the new data point against the historical activity data of said one of the at least three time slots as well as against surrounding time slots.

32. The method of claim 31, wherein the evaluating step further comprises determining whether sufficient historical activity data exists for said one of the at least three time slots and for said surrounding time slots.

33. The method of claim 32, wherein the evaluating step further comprises determining whether the new data point exceeds the maximum historical inactivity time line and the area line.

34. The method of claim 33, further comprising issuing an alert when the new data point exceeds the maximum historical inactivity time line and the alert line.

35. The method of claim 29, further comprising creating a sleep window from the historical activity data based upon the lowest activity detected in the at least three time slots during the twenty-four hour cycle.

36. The method of claim 35, further comprising altering the alert line within the sleep window.

37. The method of claim 36, wherein the evaluating step further comprises determining whether the new data point exceeds the maximum historical inactivity time line and the alert line.

38. The method of claim 37, further comprising triggering an alert and delaying issuance of the alert until after the sleep window has elapsed.

39. The method of claim 37, further comprising triggering an alert and e-mailing the alert to a caregiver.

40. The method of claim 29, further comprising determining whether a resident of the home is at home or away and ignoring any new data points received during a period when the resident is away from the home.

41. The method of claim 29, wherein the collating step comprises collating the historical activity data into at least ten time slots within the twenty-four hour cycle.

42. The method of claim 41, wherein the collating step comprises collating the historical activity data into at least forty-eight time slots within the twenty-four hour cycle.