SELECTIVE CARRYING OUT OF SCHEDULED CONTROL OPERATIONS BY AN INTELLIGENT CONTROLLER

• US 20140317029A1
• Filed: 04/17/2013
• Published: 10/23/2014
• Est. Priority Date: 04/17/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Nest Labs Incorporated (Alphabet Inc.)
• Inventors: Matsuoka, Yoky, Fisher, Evan J., Malhotra, Mark, Stefanski, Mark D.
• Granted Patent: US 10,775,814 B2
• Time in Patent Office: Days
• US Class Current: 706/12
• CPC Class Codes: G05B 15/02 electric
• CPC Class Codes: G05B 2219/2642 Domotique, domestic, home control, automation, smart house
• CPC Class Codes: G05D 23/1919 characterised by the type of controller
• CPC Class Codes: G06F 18/214 Generating training patterns; Bootstrap methods, e.g. bagging or boosting
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/025 Extracting rules from data
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: Y02B 20/40 Control techniques providing energy savings, e.g. smart controller or presence detection

Abstract

The current application is directed to intelligent controllers that use sensor output and electronically stored information 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/or modify control schedules with respect to the presence and absence of the one or more entities. The intelligent controllers selectively carry out scheduled control operations during periods of time when one or more types of entities are determined not to be in a controlled environment.

Claims

1. An intelligent controller comprising:

a processor;

one or more sensors;

a memory that stores a control schedule and cumulative probability-of-presence data; and

instructions stored within the memory that, when executed by the processor, controls the intelligent controller to

determine, from output of one or more of the one or more sensors, whether or not a human being is present in the controlled environment, and

while no human being is determined to be present in the controlled environment, modify the control schedule to maintain one or more environmental parameters at energy-efficient levels while selectively carrying out control operations corresponding to scheduled setpoints.

2. The intelligent controller of claim 1 wherein the intelligent controller selectively carries out control operations corresponding to scheduled setpoints while no human being is determined to be present in the controlled environment by:

for each control operation corresponding to a scheduled setpoint,

evaluating the corresponding setpoint with respect to the cumulative probability-of-presence data to determine whether or not to carry out the control operation.

3. The intelligent controller of claim 2 wherein evaluating the corresponding setpoint with respect to the cumulative probability-of-presence data further comprises determining whether or not the cumulative probability-of-presence data indicates an increase in the probability of presence at the time of day of the setpoint corresponding to the control operation.

4. The intelligent controller of claim 3 wherein determining whether or not the cumulative probability-of-presence data indicates an increase in the probability of presence at the time of day of the setpoint corresponding to the control operation further comprises:

selecting a first time of day t1 prior to the time of day of the setpoint corresponding to the control operation, t;

selecting a second time of day t2 following the time of day of the setpoint corresponding to the control operation, t; and

when either the cumulative probability of presence at time of day t2 is greater than the cumulative probability of presence at time of day t or the cumulative probability of presence at time of day t is greater than the cumulative probability of presence at time of day t1, determining that the probability of presence at the time of day of the setpoint corresponding to the control operation is increasing and, otherwise, determining that the probability of presence at the time of day of the setpoint corresponding to the control operation is not increasing.

5. The intelligent controller of claim 1 wherein the intelligent determines, from output of one or more of the one or more sensors, whether or not a human being is present in the controlled environment at times within a range of times of day within which a determination of whether or not a human being is present can be reliably made.

6. The intelligent controller of claim 5 wherein the range of times of day within which a determination of whether or not a human being is present can be reliably made is determined from cumulative sensor data.

7. The intelligent controller of claim 5 wherein the range of times of day within which a determination of whether or not a human being is present can be reliably made is 8:

00 AM until 8;

00 PM.

8. The intelligent controller of claim 1 wherein the intelligent controller selectively carries out control operations corresponding to scheduled setpoints while no human being is determined to be present in the controlled environment by:

for each control operation corresponding to a scheduled setpoint,

evaluating the corresponding setpoint with respect to the cumulative probability-of-presence data to determine whether or not to carry out the control operation; and

when the evaluation of the corresponding setpoint indicates that the control operation is to be carried out, returning to maintenance of the one or more environmental parameters at energy-efficient levels.

9. The intelligent controller of claim 8 wherein the variable threshold amount of time varies from a maximum variable threshold amount of time, immediately following a determination that no human being is present in the controlled environment, to 0, after an amount of time has elapsed that indicates a long-term absence of human beings in the controlled environment.

10. The intelligent controller of claim 9 wherein maximum variable threshold amount of time is 2 hours and the amount of elapsed time that indicates a long-term absence of human beings in the controlled environment is 2 days, with the variable threshold amount of time decreasing linearly over the period of 2 days.

11. The intelligent controller of claim 1 wherein control operations corresponding to scheduled setpoints include:

changing one or more environmental parameter settings at a time corresponding to a scheduled setpoint; and

changing one or more environmental parameter settings at a time prior to a time corresponding to a scheduled setpoint in order to carry out preconditioning.

12. The intelligent controller of claim 1 wherein the intelligent controller is a thermostat.

13. The intelligent controller of claim 12 wherein the one or more environmental parameters is temperature.

14. The intelligent controller of claim 13 wherein the thermostat is in a heating mode and wherein the thermostat modifies the control schedule to maintain one or more environmental parameters at energy-efficient levels by setting a temperature setting to a specified away temperature below 70 degrees Fahrenheit and above 32 degrees Fahrenheit.

15. The intelligent controller of claim 13 wherein the thermostat is in a cooling mode and wherein the thermostat modifies the control schedule to maintain one or more environmental parameters at energy-efficient levels by setting a temperature setting to a specified away temperature above 65 degrees Fahrenheit and below 90 degrees Fahrenheit.

16. A method for controlling an environment by an intelligent controller that includes a processor, one or more sensors, a memory that stores a control schedule and cumulative probability-of-presence data, and instructions stored within the memory that, when executed by the processor, control the intelligent controller, the method comprising:

determining, from output of one or more of the one or more sensors, whether or not a human being is present in the controlled environment, and

while no human being is determined to be present in the controlled environment, modifying the control schedule to maintain one or more environmental parameters at energy-efficient levels while selectively carrying out control operations corresponding to scheduled setpoints.

17. The method of claim 16 wherein selectively carrying out control operations corresponding to scheduled setpoints while no human being is determined to be present in the controlled environment further comprises:

for each control operation corresponding to a scheduled setpoint,

evaluating the corresponding setpoint with respect to the cumulative probability-of-presence data to determine whether or not to carry out the control operation.

18. The method of claim 17 wherein evaluating the corresponding setpoint with respect to the cumulative probability-of-presence data further comprises determining whether or not the cumulative probability-of-presence data indicates an increase in the probability of presence at the time of day of the setpoint corresponding to the control operation.

19. The method of claim 18 wherein determining whether or not the cumulative probability-of-presence data indicates an increase in the probability of presence at the time of day of the setpoint corresponding to the control operation further comprises:

selecting a first time of day t1 prior to the time of day of the setpoint corresponding to the control operation, t;

selecting a second time of day t2 following the time of day of the setpoint corresponding to the control operation, t; and

when either the cumulative probability of presence at time of day t2 is greater than the cumulative probability of presence at time of day t or the cumulative probability of presence at time of day t is greater than the cumulative probability of presence at time of day t1, determining that the probability of presence at the time of day of the setpoint corresponding to the control operation is increasing and, otherwise, determining that the probability of presence at the time of day of the setpoint corresponding to the control operation is not increasing.