Automated presence detection and presence-related control within an intelligent controller

• US 9,189,751 B2
• Filed: 12/06/2013
• Issued: 11/17/2015
• Est. Priority Date: 09/30/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Matsuoka, Yoky, Fisher, Evan J., Malhotra, Mark, Stefanski, Mark D., Sharan, Rangoli, Astier, Frank E.
• Primary Examiner(s): Bahta, Kidest
• Application Number:
  US14/099,760
• Publication Number:
  US 20140101082A1
• Time in Patent Office: 711 Days
• Field of Search: 700/12, 700/276, 700/278, 700/277, 700/299, 706/52, 706/32, 709/223, 709/250, 707/809
• US Class Current: 1/1
• CPC Class Codes: F24F 11/30 for purposes related to the operation of the system, e.g. for safety or monitoring
• CPC Class Codes: F24F 11/46 Improving electric energy efficiency or saving
• CPC Class Codes: F24F 11/58 using Internet communication
• CPC Class Codes: F24F 11/61 using timers
• CPC Class Codes: F24F 11/62 characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
• CPC Class Codes: F24F 11/64 using pre-stored data
• CPC Class Codes: F24F 11/66 Sleep mode
• CPC Class Codes: F24F 11/88 Electrical aspects, e.g. circuits
• CPC Class Codes: F24F 2120/00 Control inputs relating to users or occupants
• CPC Class Codes: G05B 15/02 electric
• CPC Class Codes: G05B 2219/2642 Domotique, domestic, home control, automation, smart house
• CPC Class Codes: G05D 23/1902 characterised by the use of a variable reference value
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: H04L 12/2829 involving user profiles according to which the execution of a home appliance functionality is automatically triggered
• CPC Class Codes: H04Q 2209/10 using a centralized architecture
• 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

Abstract

The current application is directed to intelligent controllers that use sensor output and electronically stored information, including one or more of electronically stored rules, parameters, and instructions, to determine whether or not one or more types of entities are present within an area, volume, or environment monitored by the intelligent controllers. The intelligent controllers select operational modes and modify control schedules with respect to the presence and absence of the one or more entities. The intelligent controllers employ feedback information to continuously adjust the electronically stored parameters and rules in order to minimize the number of incorrect inferences with respect to the presence or absence of the one or more entities and in order to maximize the efficiency by which various types of systems controlled by the intelligent controllers carry out selected operational modes.

Claims

1. An intelligent controller comprising:

one or more processors for controlling an environmental condition within an enclosure, wherein the intelligent controller is configured to operate in a plurality of modes comprising;

a normal mode wherein the environmental condition is controlled according to a stored control schedule; and

an auto-away mode;

one or more sensors for detecting indications of occupancy in the enclosure;

one or more memories that stores a historical pattern of occupancy based on historical readings from the one or more sensors;

instructions stored in the one or more memories that, when executed by the one or more processors, cause the one or more processors to perform operations comprising;

determining, at a first time, a probability of occupancy at the first time based on the historical pattern of occupancy;

selecting between a first time window length and a second time window length based on the probability of occupancy at the first time, wherein the first time window length is longer than the second time widow length;

determining whether the one or more sensors have detected indications of occupancy during a time widow, wherein the time widow begins at the first time and extends backwards in time the selected time window length; and

determining whether the intelligent controller should operate in the auto-away mode based on the determination of whether the one or more sensors detected indications of occupancy during the time widow.

2. The intelligent controller of claim 1, wherein the second time window length is selected if the probability of occupancy at the first time is above a threshold, and wherein the first time window length is selected if the probability of occupancy at the first time is below the threshold.

3. The intelligent controller of claim 1, wherein the first time window length is between approximately 120 minutes and 150 minutes.

4. The intelligent controller of claim 1, wherein, when operating in the auto-away mode, the intelligent controller controls the environmental condition in a manner that is more energy-efficient than when the intelligent controller operates in the normal mode.

5. The intelligent controller of claim 1, wherein the historical pattern of occupancy comprises a plurality of time buckets, wherein each of the plurality of time buckets corresponds to a time interval recurring each week, wherein each of the plurality of time buckets stores indications of occupancy occurring during the time interval.

6. The intelligent controller of claim 1, wherein the intelligent controller comprises a thermostat, and wherein the environmental condition comprises an ambient temperature within the enclosure.

7. The intelligent controller of claim 1, wherein:

the plurality of modes further comprises a vacation-away mode; and

the instructions stored in the one or more memories cause the one or more processors to further perform operations comprising;

determining times when the enclosure is likely unoccupied for an extended period of time based at least in part on;

(i) the measurements received from the one or more sensors not indicating occupancy for at least a second time interval; and

(ii) a portion of the historical pattern of occupancy that corresponds to the second time interval; and

during the times when it is determined that the enclosure is likely unoccupied for an extended period of time, causing the intelligent controller to transition to the vacation-away mode.

8. The intelligent controller of claim 1, wherein the one or more sensors comprises a passive infrared (PIR) sensor.

9. The intelligent controller of claim 1, wherein selecting between the first time window length and the second time window length is further based on information received over a wireless network.

10. A method for controlling an environmental condition, the method comprising:

controlling the environmental condition within an enclosure using an intelligent controller that is configured to operate in a plurality of modes comprising;

a normal mode wherein the environmental condition is controlled according to a stored control schedule; and

an auto-away mode;

receiving, by one or more processors of the intelligent controller, measurements from one or more sensors that detect indications of occupancy within the enclosure;

storing, in one or more memories of the intelligent controller, a historical pattern of occupancy based on historical readings from the one or more sensors;

determining, at a first time, a probability of occupancy at the first time based on the historical pattern of occupancy;

selecting between a first time window length and a second time window length based on the probability of occupancy at the first time, wherein the first time window length is longer than the second time widow length;

determining whether the one or more sensors have detected indications of occupancy during a time widow, wherein the time widow begins at the first time and extends backwards in time the selected time window length; and

determining whether the intelligent controller should operate in the auto-away mode based on the determination of whether the one or more sensors detected indications of occupancy during the time widow.

11. The method of claim 10, wherein the second time window length is selected if the probability of occupancy at the first time is above a threshold, and wherein the first time window length is selected if the probability of occupancy at the first time is below the threshold.

12. The method of claim 10, wherein the first time window length is between approximately 120 minutes and 150 minutes.

13. The method of claim 10, wherein, when operating in the auto-away mode, the intelligent controller controls the environmental condition in a manner that is more energy-efficient than when the intelligent controller operates in the normal mode.

14. The method of claim 10, wherein the historical pattern of occupancy comprises a plurality of time buckets, wherein each of the plurality of time buckets corresponds to a time interval recurring each week, and wherein each of the plurality of time buckets stores indications of occupancy occurring during the time interval.

15. The method of claim 10, wherein the intelligent controller comprises a thermostat, and wherein the environmental condition comprises an ambient temperature within the enclosure.

16. The method of claim 10, wherein:

the plurality of modes further comprises a vacation-away mode; and

the the method further comprises;

determining times when the enclosure is likely unoccupied for an extended period of time based at least in part on;

(i) the measurements received from the one or more sensors not indicating occupancy for at least a second time interval; and

(ii) a portion of the historical pattern of occupancy that corresponds to the second time interval; and

during the times when it is determined that the enclosure is likely unoccupied for an extended period of time, causing the intelligent controller to transition to the vacation-away mode.

17. The method of claim 10, wherein the one or more sensors comprises a passive infrared (PIR) sensor.

18. The method of claim 10, wherein selecting between the first time window length and the second time window length is further based on information received over a wireless network.