Method of distinguishing the presence of a single versus multiple persons

• US 20040183667A1
• Filed: 03/21/2003
• Published: 09/23/2004
• Est. Priority Date: 03/21/2003
• Status: Active Grant

• Current Assignee: HOME DATA SOURCE LLC
• Original Assignee: HOME DATA SOURCE LLC
• Inventors: McGillicuddy, Rich, Nicoletti, Ryan, Bruemmer, Tim
• Granted Patent: US 7,009,497 B2
• Time in Patent Office: Days
• US Class Current: 340/506
• CPC Class Codes: G08B 21/0469 Presence detectors to detect unsafe condition, e.g. infrared sensor, microphone G08B21/0476 takes precedence

Abstract

A plurality of sensors are positioned in a home. Sensor fire data is delivered to a remote server, and the sensor fire data is segmented into single-state blocks broken up by door opening and closing events. The door opening and closing events represent potential state changes in the home where the number of people present in the home may have changed. The raw data from the sensor fires are then processed into adjacent sensor fires and used to populate adjacency matrices and frequency distributions. That information is subjected to a statistical goodness-of-fit test, which reveals a probability indicating the likelihood a given data block should be attributed with the single or multiple person state. The single versus multiple person state is passed along with these data to the remainder of the data analyses, which can then be properly aware of which data should be treated with due suspicion.

Claims

1. A method of monitoring a residence comprising:

a. providing a plurality of sensors in the residence;

b. collecting data from the plurality of sensors; and

c. determining whether a single person is present in the residence or multiple persons are present in the residence.

2. The method of claim 1 further comprising the step of analyzing the data to determine if an alert condition exists if a single person is present in the residence.

3. The method of claim 1 wherein the data collected from the plurality of sensors includes adjacent sensor fire data.

4. The method of claim 3 wherein the adjacent sensor fire data is analyzed in determining whether a single person is present in the residence or multiple persons are present in the residence.

5. The method of claim 4 wherein the adjacent sensor fire data is analyzed by comparing the adjacent sensor fire data to a control data distribution.

6. The method of claim 4 wherein the adjacent sensor fire data is analyzed by determining if a statistically significant number of non-contiguous adjacent sensor fires exist.

7. The method of claim 4 wherein the adjacent sensor fire data is analyzed to determine if a statistically significant number of adjacent sensor fires exist over a period of time.

8. A method of monitoring a residence comprising:

a. collecting data from the residence;

b. determining whether a single person is present in the residence or multiple persons are present in the residence; and

c. if a single person is determined to be present in the residence, analyzing the data to determine if an alert condition exists.

9. The method of claim 8 wherein the data collected from the residence includes adjacent sensor fire data.

10. The method of claim 9 wherein the adjacent sensor fire data is analyzed in determining whether a single person is present in the residence or multiple persons are present in the residence.

11. The method of claim 10 wherein the adjacent sensor fire data is analyzed by comparing the adjacent sensor fire data to a control data distribution.

12. The method of claim 10 wherein the adjacent sensor fire data is analyzed by determining if a statistically significant number of non-contiguous adjacent sensor fires exist.

13. The method of claim 10 wherein the adjacent sensor fire data is analyzed to determine if a statistically significant number of adjacent sensor fires exist over a period of time.

14. The method of claim 8 wherein the step of determining whether a single person is present in the residence or multiple persons are present in the residence comprises performing a statistical calculation to determine the probability that a single person is present in the residence.

15. The method of claim 14 wherein the step of analyzing the data to determine if an alert condition exists comprises weighting the data based upon the probability that a single person is present in the residence.

16. A method of passively monitoring the activities of an individual in a residence having a plurality of areas, the method comprising:

a. providing a plurality of sensors;

b. collecting sensor fire data from the plurality of sensors and separating the sensor fire data into a plurality of data blocks;

c. determining whether one of the plurality of data blocks is associated with the presence of a single person in the residence or multiple persons in the residence; and

d. if the one of the plurality of data blocks is associated with the presence of a single person in the residence, analyzing the sensor fire data included in the one of the plurality of data blocks.

17. The method of claim 16 wherein the sensor fire data is separated into the plurality of data blocks based upon the occurrence of a door opening event.

18. The method of claim 16 wherein the step of analyzing the sensor fire data includes determining if an alert condition exists.

19. The method of claim 18 wherein the step of determining whether one of the plurality of data blocks is associated with the presence of a single person in the residence or multiple persons in the residence comprises performing a statistical calculation to determine the probability that the one of the plurality of data blocks is associated with the presence of a single person in the residence.

20. The method of claim 19 wherein the step of analyzing the sensor fire data comprises weighting the sensor fire data based upon the probability that a single person is present in the residence.

21. The method of claim 16 wherein the step of determining whether one of the plurality of data blocks is associated with the presence of a single person in the residence or multiple persons in the residence includes analyzing adjacent sensor fires included in the sensor fire data.

22. A system for monitoring a life form in a residence having a plurality of areas, the system comprising:

a. a plurality of sensors, each of the plurality of sensors operable to detect the life form in one of the plurality of areas;

b. a receiver in communication with the plurality of sensors, the receiver operable to collect sensor fire data from each of the plurality of sensors;

c. a processor in communication with the receiver, the processor operable to analyze the sensor fire data collected by the receiver and determine whether a single person is present in the residence or multiple persons are present in the residence.

23. The system of claim 22 wherein the sensor fire data includes adjacent sensor fire data.

24. The system of claim 22 wherein the processor analyzes the adjacent sensor fire data to determine whether a single person is present in the residence or multiple persons are present in the residence.

25. A system for monitoring a life form in a residence having a plurality of areas, the system comprising:

a. a means for collecting data from the residence; and

b. a means for determining whether a single person is present in the residence or multiple people are present in the residence.

26. The system of claim 25 wherein the means for collecting data from the residence comprises a plurality of sensors.

27. The system of claim 26 wherein the means for determining whether a single person is present in the residence or multiple people are present in the residence includes a processor operable to analyze adjacent sensor fire data from the plurality of sensors.

28. A method of determining whether a single person or multiple persons are present in a residence having a plurality of areas, the method comprising the steps of:

a. providing a plurality of sensors, each of the plurality of sensors associated with one of the plurality of areas and each of the plurality of sensors operable to detect the existence of a person in the one of the plurality of areas;

b. collecting sensor fire data from the plurality of sensors to build a sensor fire data set containing a plurality of adjacent sensor fires;

c. analyzing the adjacent sensor fires to determine whether a single or multiple persons are present in the residence.

29. The method of claim 28 wherein the plurality of areas include at least one non-contiguous area.

30. The method of claim 29 wherein the step of analyzing the adjacent sensor fires to determine whether a single or multiple persons are present in the residence includes determining whether any of the adjacent sensor fires are associated with the at least one non-contiguous area.

31. A method for determining whether multiple persons are present in a residence having a first area that is contiguous with a second area and a third area that is not contiguous with the first area, the method comprising:

a. providing a plurality of sensors, the plurality of sensors including a first sensor operable to fire when a person is detected in the first area, a second sensor operable to fire when a person is detected in the second area, and a third sensor operable to fire when a person is detected in the third area

b. collecting sensor fire data from the plurality of sensors to build a sensor fire data set containing a plurality of adjacent sensor fires;

c. determining that multiple persons are present in the residence when a statistically significant number of the plurality of adjacent sensor fires include both the first sensor and the third sensor.

32. A method of determining whether a single life form or multiple life forms are present in a residence having a plurality of areas, wherein some of the plurality of areas are contiguous and other of the plurality of areas are not contiguous, each of the plurality of areas associated with a sensor that is operable to fire when life form activity is detected in the area, the method comprising:

a. monitoring adjacent sensor fires; and

b. using adjacent sensor fires from activity occurring in non-contiguous areas as indicative of the presence of multiple life forms in the residence.

33. The method of claim 32 further comprising the step of using a statistically significant number of adjacent sensor fires over a period of time as indicative of the presence of multiple life forms in the residence.

34. A method of determining whether a single or multiple life forms are present in a residence having a plurality of areas, each of the plurality of areas associated with a sensor that is operable to fire when life form activity is detected in the area, the method comprising:

a. collecting sensor fire data from the plurality of sensors to build a sensor fire data set containing a plurality of adjacent sensor fires;

b. forming a first control data distribution set for adjacent sensor fires that is associated with a single life form being present in the residence;

c. performing a statistical test to compare the sensor fire data set with the control data distribution set, the statistical test yielding a first result; and

d. using the first result as indicative that a single life form is present in the home if the first result meets a first predetermined threshold.

35. The method of claim 34 wherein the statistical test is a goodness-of-fit test.

36. The method of claim 35 wherein the goodness-of-fit test is the chi-square test.

37. The method of claim 34 further comprising

a. forming a second control data distribution set for adjacent sensor fires that is associated with a plurality of life forms being present in the residence;

b. performing a second statistical test to compare the sensor fire data set with the second control data distribution set, the second statistical test yielding a second result; and

c. using the second test result as indicative that multiple life forms are present in the home if the first statistical test yields a result that does not meet the first predetermined threshold but the second statistical test does meet a second predetermined threshold.

38. A method of passively monitoring the activities of an individual in a residence, the method comprising:

a. providing a plurality of sensors;

b. collecting sensor fire data from the plurality of sensors, the sensor fire data including a plurality of adjacent sensor fires;

c. determining the probability that a single person is present in the residence based on the plurality of adjacent sensor fires;

d. if a single person is determined to be present in the residence, weighting the sensor fire data based on the probability that a single person is present in the residence; and

e. analyzing the weighted sensor fire data to determine if an alert condition exists.