Occupancy pattern detection, estimation and prediction

• US 8,510,255 B2
• Filed: 09/14/2010
• Issued: 08/13/2013
• Est. Priority Date: 09/14/2010
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Nest Labs Incorporated (Alphabet Inc.)
• Inventors: Fadell, Anthony Michael, Rogers, Matthew Lee, Ben-Menahem, Shahar, Sharan, Rangoli, Rogers, Kipp Avery, Ishihara, Abraham K.
• Primary Examiner(s): CHANG, LI WU
• Application Number:
  US12/881,430
• Publication Number:
  US 20120066168A1
• Time in Patent Office: 1,064 Days
• Field of Search: None
• US Class Current: 706/52
• CPC Class Codes: G05B 15/02 electric
• CPC Class Codes: G05B 2219/2642 Domotique, domestic, home control, automation, smart house
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 5/048 Fuzzy inferencing
• CPC Class Codes: H04L 12/282 based on user interaction within the home receiver circuitry for displaying additional information being controlled by a remote control apparatus H04N21/42204
• CPC Class Codes: H04L 12/2823 Reporting information sensed by appliance or service execution status of appliance services in a home automation network device-related reporting H04L43/065; arrangements in telecontrol or telemetry systems for selectively calling a substation from a main station, in which substation desired apparatus is selected for applying a control signal thereto or for obtaining measured values therefrom H04Q9/00
• CPC Class Codes: H04Q 2209/40 using a wireless architecture
• CPC Class Codes: H04Q 2209/60 for transmitting utility meters data, i.e. transmission of data from the reader of the utility meter
• CPC Class Codes: H04Q 9/00 Arrangements in telecontrol or telemetry systems for selectively calling a substation from a main station, in which substation desired apparatus is selected for applying a control signal thereto or for obtaining measured values therefrom
• CPC Class Codes: H05B 47/115 by determining the presence or movement of objects or living beings
• CPC Class Codes: H05B 47/13 by using passive infrared detectors
• CPC Class Codes: Y02B 20/40 Control techniques providing energy savings, e.g. smart controller or presence detection
• CPC Class Codes: Y02B 70/30 Systems integrating technologies related to power network operation and communication or information technologies for improving the carbon footprint of the management of residential or tertiary loads, i.e. smart grids as climate change mitigation technology in the buildings sector, including also the last stages of power distribution and the control, monitoring or operating management systems at local level
• CPC Class Codes: Y04S 20/20 End-user application control systems

Abstract

Systems and methods are described for predicting and/or detecting occupancy of an enclosure, such as a dwelling or other building, which can be used for a number of applications. An a priori stochastic model of occupancy patterns based on information of the enclosure and/or the expected occupants of the enclosure is used to pre-seed an occupancy prediction engine. Along with data from an occupancy sensor, the occupancy prediction engine predicts future occupancy of the enclosure. Various systems and methods for detecting occupancy of an enclosure, such as a dwelling, are also described.

Claims

1. A method for detecting occupancy of an enclosure comprising:

determining a probability that occupants of the enclosure will depart from or arrive at the enclosure at a certain time of the day based on a pre-existing model of occupancy patterns, the pre-existing model being available to a thermostat at the time of installation of the thermostat in the enclosure, the model being indicative of a probability that occupants of the enclosure will depart from and arrive at the enclosure at certain times over the course of a day;

monitoring, by the thermostat after installation of the thermostat in the enclosure, communication signals which indicate a likelihood of occupancy of the enclosure ranging from not occupied to occupied;

revising the model of occupancy patterns based at least in part on the monitored communication signals; and

determining a probability that occupants of the enclosure will depart from or arrive at the enclosure at a certain time of the day based on the revised model of occupancy patterns,

wherein the pre-existing model is generated based on a type of information other than the monitored communication signals.

2. A method according to claim 1 wherein in the communication signals is one or more network connections and the monitoring includes monitoring for changes in network communications which indicate a likelihood of occupancy.

3. A method according to claim 2 wherein the one or more network connections include a network connection of a type selected from a group consisting of:

wi-fi and email.

4. A method according to claim 2 wherein the changes in network communication includes monitoring changes in network traffic which indicate a likelihood of internet usage.

5. A method according to claim 1 wherein the communication signals are radio frequency communication signals.

6. A method according to claim 5 wherein the communication signals are mobile phone signals.

7. A method according to claim 1 wherein the enclosure is a single family dwelling.

8. A method according to claim 1 further comprising controlling an HVAC system for the enclosure based at least in part on the probability that occupants of the enclosure will depart from or arrive at the enclosure at a certain time of the day based on the pre-existing model of occupancy patterns.

9. A method according to claim 1 further comprising controlling an HVAC system for the enclosure based at least in part on the probability that occupants of the enclosure will depart from or arrive at the enclosure at a certain time of the day based on the revised model of occupancy patterns.

10. A method according to claim 1 wherein the communication signals are monitored for patterns which indicate a likelihood of occupancy.

11. A method for detecting occupancy of an enclosure comprising:

determining a probability that occupants of the enclosure will depart from or arrive at the enclosure at a certain time of the day based on a pre-existing model of occupancy patterns, the pre-existing model being available to a thermostat at the time of installation of the thermostat in the enclosure, the model being indicative of a probability that occupants of the enclosure will depart from and arrive at the enclosure at certain times over the course of a day;

monitoring, by the thermostat after installation of the thermostat in the enclosure, sound pressure information which indicates a likelihood of occupancy of the enclosure ranging from not occupied to occupied;

revising the model of occupancy patterns based at least in part on the monitored pressure information; and

determining a probability that occupants of the enclosure will depart from or arrive at the enclosure at a certain time of the day based on the revised model of occupancy patterns,

wherein the pre-existing model is generated based on a type of information other than the monitored pressure information.

12. A method according to claim 11 wherein the sound pressure monitored is in the audible range.

13. A method according to claim 12 wherein the types of sounds monitored include one or more types selected from a group consisting of:

footsteps, voices, and doors closing.

14. A method according to claim 11 wherein the sound pressure monitored is in the ultrasonic range.

15. A method according to claim 14 wherein the types of sounds monitored include one or more types selected from a group consisting of footsteps, and air movement due to human movement.

16. A method for detecting occupancy of an enclosure comprising:

determining a probability that occupants of the enclosure will depart from or arrive at the enclosure at a certain time of the day based on a pre-existing model of occupancy patterns, the pre-existing model being available to a thermostat at the time of installation of the thermostat in the enclosure, the model being indicative of a probability that occupants of the enclosure will depart from and arrive at the enclosure at certain times over the course of a day;

monitoring, by the thermostat after installation of the thermostat in the enclosure, utility information for the enclosure which indicates a likelihood of occupancy of the enclosure ranging from not occupied to occupied;

revising the model of occupancy patterns based at least in part on the monitored utility information; and

determining a probability that occupants of the enclosure will depart from or arrive at the enclosure at a certain time of the day based on the revised model of occupancy patterns,

wherein the pre-existing model is generated based on a type of information other than the monitored utility information.

17. A method according to claim 16 wherein the utility information is powerline information, and the powerline information is filtered to detect the use of electronic devices which indicate a likelihood of occupancy in the enclosure.

18. A method according to claim 16 wherein the utility information is obtained from a Smart Meter that tends to indicate a likelihood of occupancy in the enclosure.

19. A method according to claim 18 wherein pattern recognition is used to monitor changes in the utility information from a baseline to detect likelihoods of occupancy of the enclosure.

20. A method according to claim 16 wherein the enclosure is a dwelling.

21. A system for detecting occupancy of an enclosure comprising:

a processing system adapted to determine a probability that occupants of the enclosure will depart from or arrive at the enclosure at a certain time of the day based on a pre-existing model of occupancy patterns, the pre-existing model being available to the processing system at the time of installation of the processing system in the enclosure, the model being indicative of a probability that occupants of the enclosure will depart from and arrive at the enclosure at certain times over the course of a day; and

a sensing system adapted to monitor, after installation of the sensing system in the enclosure, utility information for the enclosure which indicates a likelihood of occupancy of the enclosure ranging from not occupied to occupied;

the processing system being further adapted to revise the model of occupancy patterns based at least in part on the monitored utility information by the sensing system, and to determine a probability that occupants of the enclosure will depart from or arrive at the enclosure at a certain time of the day based on the revised model of occupancy patterns,

wherein the pre-existing model is generated based on a type of information other than the monitored utility information.

22. A system according to claim 21 wherein the utility information is powerline information, and the powerline information is filtered to detect the use of electronic devices which indicate a likelihood of occupancy in the enclosure.

23. A system according to claim 21 wherein the utility information is obtained from a Smart Meter that tends to indicate a likelihood of occupancy in the enclosure.

24. A system according to claim 23 wherein pattern recognition is used by the processing system to monitor changes in the utility information from a baseline to detect likelihoods of occupancy of the enclosure.

25. A system according to claim 21 wherein the enclosure is a dwelling.

26. A method for detecting occupancy of an enclosure comprising:

determining a probability that occupants of the enclosure will depart from or arrive at the enclosure at a certain time of the day based on a pre-existing model of occupancy patterns, the pre-existing model being available to a thermostat at the time of installation of the thermostat in the enclosure, the model being indicative of a probability that occupants of the enclosure will depart from and arrive at the enclosure at certain times over the course of a day;

monitoring, by the thermostat after installation of the thermostat in the enclosure, motion information from a sensor;

revising the model of occupancy patterns based at least in part on the monitored motion information; and

determining a probability that occupants of the enclosure will depart from or arrive at the enclosure at a certain time of the day based on the revised model of occupancy patterns,

wherein the pre-existing model is generated based on a type of information other than the monitored motion information.

27. A method according to claim 26 wherein the sensor is an accelerometer and the motion information is acceleration information monitored within one meter of the sensor.

28. A method according to claim 26, further comprising preparing a device for interaction with a user based on the monitored motion information.

29. A method according to claim 26 wherein the enclosure is a small dwelling.

30. A method for detecting occupancy of an enclosure comprising:

determining a probability that occupants of the enclosure will depart from or arrive at the enclosure at a certain time of the day based on a pre-existing model of occupancy patterns, the pre-existing model being available to a thermostat at the time of installation of the thermostat in the enclosure, the model being indicative of a probability that occupants of the enclosure will depart from and arrive at the enclosure at certain times over the course of a day;

monitoring, by the thermostat after installation of the thermostat in the enclosure, infrared signals within the enclosure which indicate operation of one or more infrared controllable devices;

revising the model of occupancy patterns of the enclosure based at least in part on the monitored infrared signals; and

determining a probability that occupants of the enclosure will depart from or arrive at the enclosure at a certain time of the day based on the revised model of occupancy patterns,

wherein the pre-existing model is generated based on a type of information other than the monitored infrared signals.

31. A method according to claim 30 wherein the infrared signals indicate remote control of one or more electronic devices by an occupant.

32. A method according to claim 30 wherein the enclosure is a dwelling.

33. A system for detecting occupancy of an enclosure comprising:

a processing system adapted to determine a probability that occupants of the enclosure will depart from or arrive at the enclosure at a certain time of the day based on a pre-existing model of occupancy patterns, the pre-existing model being available to the processing system at the time of installation of the processing system in the enclosure, the model being indicative of a probability that occupants of the enclosure will depart from and arrive at the enclosure at certain times over the course of a day; and

an infrared sensor adapted to monitor, after installation of the infrared sensor in the enclosure, infrared signals within the enclosure which indicate operation of one or more infrared controllable devices;

the processing system being further adapted to revise the model of occupancy patterns based at least in part on the monitored infrared signals by the infrared sensor, and to determine a probability that occupants of the enclosure will depart from or arrive at the enclosure at a certain time of the day based on the revised model of occupancy patterns,

wherein the pre-existing model is generated based on a type of information other than the monitored infrared signals.

34. A system according to claim 33 wherein the infrared signals indicate remote control of one or more electronic devices by an occupant.

35. A method for detecting occupancy of an enclosure comprising:

determining a probability that occupants of the enclosure will depart from or arrive at the enclosure at a certain time of the day based on a pre-existing model of occupancy patterns, the pre-existing model being available to a thermostat at the time of installation of the thermostat in the enclosure, the model being indicative of a probability that occupants of the enclosure will depart from and arrive at the enclosure at certain times over the course of a day;

monitoring, by the thermostat after installation of the thermostat in the enclosure, pressure information within the enclosure which indicates occupancy of the enclosure;

revising the model of occupancy patterns based at least in part on the monitored pressure information; and

determining a probability that occupants of the enclosure will depart from or arrive at the enclosure at a certain time of the day based on the revised model of occupancy patterns,

wherein the pre-existing model is generated based on a type of information other than the monitored pressure information.

36. A method according to claim 35 wherein the pressure information includes change in atmospheric pressure in the enclosure that indicate opening of doors and/or windows.

37. A method according to claim 35 wherein the enclosure is a dwelling.

38. A system for detecting occupancy of an enclosure comprising:

a processing system adapted to determine a probability that occupants of the enclosure will depart from or arrive at the enclosure at a certain time of the day based on a pre-existing model of occupancy patterns, the pre-existing model being available to the processing system at the time of installation of the processing system in the enclosure, the model being indicative of a probability that occupants of the enclosure will depart from and arrive at the enclosure at certain times over the course of a day; and

a pressure sensor adapted to monitor, after installation of the pressure sensor in the enclosure, pressure information within the enclosure which indicates occupancy of the enclosure;

the processing system being further adapted to revise the model of occupancy patterns based at least in part on the monitored pressure information by the pressure sensor, and to determine a probability that occupants of the enclosure will depart from or arrive at the enclosure at a certain time of the day based on the revised model of occupancy patterns,

wherein the pre-existing model is generated based on a type of information other than the monitored pressure information.

39. A system according to claim 38 wherein the pressure information includes change in atmospheric pressure in the enclosure that indicate opening of doors and/or windows.

40. A method for detecting occupancy of an enclosure comprising:

determining a probability that occupants of the enclosure will depart from or arrive at the enclosure at a certain time of the day based on a pre-existing model of occupancy patterns, the pre-existing model being available to a thermostat at the time of installation of the thermostat in the enclosure, the model being indicative of a probability that occupants of the enclosure will depart from and arrive at the enclosure at certain times over the course of a day;

monitoring, by the thermostat after installation of the thermostat in the enclosure, ambient light information within the enclosure which indicates occupancy of the enclosure;

revising the model of occupancy patterns based at least in part on the monitored ambient light information; and

determining a probability that occupants of the enclosure will depart from or arrive at the enclosure at a certain time of the day based on the revised model of occupancy patterns,

wherein the pre-existing model is generated based on a type of information other than the monitored ambient light information.

41. A method according to claim 40 wherein the ambient light information includes rapid changes in ambient light in the enclosure that tends to indicate switching on and off of lights or sudden opening or closing of blinds and/or curtains.

42. A method according to claim 40 wherein the ambient light information includes wavelength composition of incident light that tends to indicate whether the light source is artificial or natural.

43. A method according to claim 40 wherein the enclosure is a dwelling.

44. A system for detecting occupancy of an enclosure comprising:

a processing system adapted to determine a probability that occupants of the enclosure will depart from or arrive at the enclosure at a certain time of the day based on a pre-existing model of occupancy patterns, the pre-existing model being available to the processing system at the time of installation of the processing system in the enclosure, the model being indicative of a probability that occupants of the enclosure will depart from and arrive at the enclosure at certain times over the course of a day; and

an ambient light sensor adapted to monitor, after installation of the ambient light sensor in the enclosure, ambient light information within the enclosure which indicates occupancy of the enclosure;

the processing system being further adapted to revise the model of occupancy patterns based at least in part on the monitored ambient light information by the ambient light sensor, and to determine a probability that occupants of the enclosure will depart from or arrive at the enclosure at a certain time of the day based on the revised model of occupancy patterns,

wherein the pre-existing model is generated based on a type of information other than the monitored ambient light information.

45. A system according to claim 44 wherein the ambient light information includes rapid changes in ambient light in the enclosure that tends to indicate turning on and off of lights or opening and closing of blinds and/or curtains.

46. A system according to claim 44 wherein the ambient light information includes whether ambient light is from artificial source that tends to indicate presence of occupants in certain structure types.