Dynamic distributed-sensor thermostat network for forecasting external events

• US 8,620,841 B1
• Filed: 08/31/2012
• Issued: 12/31/2013
• Est. Priority Date: 08/31/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Nest Labs Incorporated (Alphabet Inc.)
• Inventors: Filson, John B., Daniels, Eric B., Matsuoka, Yoky, Mittleman, Adam, Nelmes, Sierra L.
• Primary Examiner(s): VINCENT, DAVID ROBERT
• Application Number:
  US13/601,890
• Time in Patent Office: 487 Days
• Field of Search: 706/12, 706/45
• US Class Current: 706/12
• CPC Class Codes: G05D 23/1902 characterised by the use of a variable reference value
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G08B 17/10 Actuation by presence of smoke or gases , e.g. automatic alarm devices for analysing flowing fluid materials by the use of optical means
• CPC Class Codes: G08B 21/10 responsive to calamitous events, e.g. tornados or earthquakes
• CPC Class Codes: G08B 21/18 Status alarms G08B21/02 takes precedence
• CPC Class Codes: G08B 27/005 with transmission via computer network
• CPC Class Codes: G08B 27/006 with transmission via telephone network
• CPC Class Codes: G08B 29/188 Data fusion; cooperative systems, e.g. voting among different detectors
• CPC Class Codes: G08B 31/00 Predictive alarm systems characterised by extrapolation or other computation using updated historic data
• CPC Class Codes: H04L 12/1895 for short real-time information, e.g. alarms, notifications, alerts, updates
• 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

Systems and methods for forecasting events can be provided. A measurement database can store sensor measurements, each having been provided by a non-portable electronic device with a primary purpose unrelated to collecting measurements from a type of sensor that collected the measurement. A measurement set identifier can select a set of measurements. The electronic devices associated with the set of measurements can be in close geographical proximity relative to their geographical proximity to other devices. An inter-device correlator can access the set and collectively analyze the measurements. An event detector can determine whether an event occurred. An event forecaster can forecast a future event property. An alert engine can identify one or more entities to be alerted of the future event property, generate at least one alert identifying the future event property, and transmit the at least one alert to the identified one or more entities.

Claims

1. A event-forecasting system comprising:

a measurement database that stores a plurality of sensor measurements, each sensor measurement having been provided by a thermostat device, wherein a primary purpose of each thermostat device is to control a temperature condition within a structure in addition to collecting measurements from a non-temperature related sensor that collected the sensor measurement, wherein said non-temperature related sensor is selected from the group consisting of;

seismic activity sensors hazard related environmental sensors, microphones optical sensors and radiation sensors;

a measurement set identifier that selects a set of sensor measurements from the plurality of sensor measurements provided by the thermostat devices in the measurement database, wherein the thermostat devices associated with the set of sensor measurements are in close geographical proximity relative to their geographical proximity to other devices;

an inter-device correlator that accesses the selected set of sensor measurements provided by the thermostat devices and that collectively analyzes the sensor measurements;

an event detector that determines whether an event has occurred based on the results of the collective analysis, wherein the determination that an event has occurred requires that a criterion involving at least two of the sensor measurements provided by the thermostat devices be satisfied;

an event forecaster that forecasts a future event property, wherein the future event property is forecasted based on a same or different collective analysis of the sensor measurements provided by the thermostat devices; and

an alert engine that identifies one or more entities to be alerted of the future event property, that generates at least one alert identifying the future event property, and that transmits the at least one alert to the identified one or more entities.

2. The event-forecasting system of claim 1, further comprising a device-location database that stores, for each thermostat device of a plurality of thermostat devices, a location associated with the thermostat device,

wherein the measurement set identifier accesses the device-location database when selecting the set of sensor measurements provided by the thermostat devices.

3. The event-forecasting system of claim 1, wherein the event forecaster forecasts the future event property upon a determination that the event has occurred.

4. The event-forecasting system of claim 1, wherein the sensor measurements provided by the thermostat devices in the measurement set are associated with a similar measurement time.

5. The event-forecasting system of claim 1, wherein thermostat devices associated with the sensor measurements in the measurement set are further associated with a plurality of users.

6. The event-forecasting system of claim 1, wherein the event includes a weather-related or natural-disaster event.

7. A method for forecasting events, the method comprising:

storing a plurality of sensor measurements in a measurement database, each sensor measurement having been provided by a thermostat device, wherein a primary purpose of at least one respective thermostat device is to control a temperature condition within a structure in addition to collecting measurements from a non-temperature related sensor that collected the sensor measurement, wherein said non-temperature related sensor is selected from the group consisting of;

seismic activity sensors, hazard related environmental sensors microphones, optical sensors, and radiation sensors;

selecting a set of sensor measurements from the plurality of sensor measurements provided by the thermostat devices in the measurement database, wherein the thermostat devices associated with the set of sensor measurements are in close geographical proximity relative to their geographical proximity to other devices;

collectively analyzing the sensor measurements provided by the thermostat devices to determine whether a large-scale event was occurring, wherein the determination that a large-scale event was occurring requires consistency between at least two of the sensor measurements provided by the thermostat devices;

forecasting a future event property, wherein the future event property is forecasted based on a same or different collective analysis of the sensor measurements provided by the thermostat devices;

identifying one or more entities to be alerted of the future event property;

generating at least one alert identifying the future event property; and

transmitting the at least one alert to the identified one or more entities.

8. The method for forecasting events as recited in claim 7, wherein the one or more entities include a thermostat device not associated with the set of thermostat devices and associated with geographic location extending beyond a geographic area associated with the thermostat devices associated with the set of sensor measurements.

9. The method for forecasting events as recited in claim 7, wherein transmitting the at least one alert comprises sending a signal to a phone of a user associated with a thermostat device likely to be affected by the event in the future.

10. The method for forecasting events as recited in claim 7, wherein the event comprises an earthquake.

11. The method for forecasting events as recited in claim 7, wherein collectively analyzing the sensor measurements provided by the thermostat devices comprises generating or refining a time-sensitive model.

12. The method for forecasting events as recited in claim 7, wherein collectively analyzing the sensor measurements provided by the thermostat devices comprises counting a number of sensor measurements in the set of sensor measurements.

13. The method for forecasting events as recited in claim 7, wherein the same or different collective analysis of the sensor measurements provided by the thermostat devices comprises predicting a trajectory of the event.

14. A crowdsourced event detection network, comprising:

a population of thermostat devices, each said thermostat device comprising a housing and at least one non-temperature related sensor coupled to the housing, the at least one non-temperature related sensor being configured to sense at least one environmental characteristic or condition that is generally unrelated to controlling a temperature condition within a structure, each said thermostat device further comprising a data transmission component configured to transmit first information representative of said least one sensed environmental characteristic or condition for reception by an aggregating processor, wherein said non-temperature related sensor is selected from the group consisting of;

seismic activity sensors, hazard related environmental sensors, microphones, optical sensors, and radiation sensors;

wherein the aggregating processor is configured and programmed to receive the first information from each of a plurality of the thermostat devices, to forecast a future event based on a collective analysis thereof, to identify one or more entities to be alerted of the forecasted future event, and to transmit second information representative of the forecasted future event to the identified one or more entities.

15. The crowdsourced event detection network of claim 14, wherein another thermostat device comprises the aggregating processor.

16. The crowdsourced event detection network of claim 14, further comprising a central server that comprises the aggregating processor.

17. The crowdsourced event detection network of claim 14, wherein the at least one non-temperature related sensor in each of said population of thermostat devices includes an accelerometer, and wherein the central server is configured to forecast earthquake events based on a collective analysis of the received first information derived from motion sensed by said accelerometers.

18. The crowdsourced event detection network of claim 14, wherein each said thermostat device further comprises:

a data receiving and processing component configured to receive data communications from said aggregating processor and to identify therefrom said second information representative of the forecasted future event; and

an alerting mechanism configured to alert a nearby home occupant of the forecasted future event.