Automatic determination of indoor or outdoor environmental conditions of a device
View Patent ↗Systems and methods are provided for deterministically estimating whether the location of a computing device that is fixed or mobile is inside a fully enclosed building or not (e.g., fully or partially indoors/outdoors). Various environments are supported by the substance of the disclosure, including fully or partially indoor and outdoor environments.
1. A computer-implemented method, comprising:
receiving sensor data regarding a computing device from sensors associated with the computing device;
storing the received sensor data as time series data at the computing device;
determine based on the time series data, a likelihood that the computing device and sensors are at a predicted location that is either fully indoors, partially indoors, fully outdoors, or partially outdoors;
generate and store one or more sensor rules based on the time series data for adjusting a confidence value regarding the predicted location of the computing device and the sensors;
providing a determination that the computing device and the sensors are at the predicated location in accordance with an adjusted confidence value, and triggering an action based on the predicted location of the computing device and the sensors.
2. The computer-implemented method of claim 1 , wherein the computing device and the sensors associated with the computing device are co-located.
3. The computer-implemented method of claim 1 , wherein the sensor data is received with time stamp, the sensor data in combination with the time stamp comprising the time series data.
4. The computer-implemented method of claim 1 , wherein the determined likelihood comprises a probability value.
5. The computer-implemented method of claim 1 , wherein determining the likelihood that the computing device and sensors are at the predicted location comprises performing, on the sensor data, at least one of comparison-based sensor data analytics, pattern recognition, linear programming, or a machine learning model.
6. The computer-implemented method of claim 5 , wherein the machine learning model assigns weights to each type of sensor data that are one of correlated or convolved with one another.
7. The computer-implemented method of claim 1 , wherein the determination of the likelihood that the computing device and sensors are at a predicted location is performed within a specified timeframe.
8. The computer-implemented method of claim 7 , wherein the machine learning model identifies a deterministic relationship between a particular sensor of the sensors associated with the computing device and the determined predicted location.
9. The computer-implemented method of claim 1 , wherein the sensor data reflects one of an absence of expected data, observation of data crossing single or multiple staged thresholds, observation of changes in the data over time, observation of aggregated state patterns over recurring time intervals, observation of changes in data suggesting movement of the computer device and the sensors.
10. The computer-implemented method of claim 1 , wherein the one or more sensor rules for adjusting the confidence value adjust the confidence value based on an external system's characterization of indoor and outdoor environments.
11. A computing device, comprising:
a memory; and
one or more processors that are configured to execute machine readable instructions stored in the memory to:
receive sensor data regarding the computing device from sensors co-located with the computing device;
estimate a location of the computing device as being one of fully indoors, partially indoors, fully outdoors, or partially outdoors based on a probability calculated from the sensor data with an associated confidence value;
based on a location estimate with a sufficiently dispositive confidence value, providing a determination that the computing device is at the estimated location, and triggering an action based on the estimated location of the computing device.
12. The computing device of claim 11 , wherein estimating the location of the computing device comprises performing, on the sensor data, at least one of comparison-based sensor data analytics, pattern recognition, linear programming, or a machine learning model.
13. The computing device of claim 11 , wherein the one or more processors executing the estimating of the location of the computing device executes further machine readable instructions stored in the memory to determine whether to recalculate the estimated location and the confidence value in response to movement of the computing device or an adjustment of an environment of the computing device in real-time.
14. The computing device of claim 13 , wherein the machine learning model assigns weights to each type of sensor data that are one of correlated or convolved with one another.
15. The computing device of claim 11 , wherein the sufficiently dispositive confidence value comprises a confidence value exceeding or falling below a defined threshold.
16. The computing device of claim 15 , wherein the machine learning model identifies a deterministic relationship between a particular sensor of the sensors co-located with the computing device and the estimated location.
17. The computing device of claim 11 , wherein the sensor data reflects one of an absence of expected data, observation of data crossing single or multiple staged thresholds, observation of changes in the data over time, observation of aggregated state patterns over recurring time intervals, observation of changes in data suggesting movement of the computer device and the sensors.
18. The computing device of claim 11 , wherein the one or more processors execute further machine readable instructions stored in the memory to generate and store one or more sensor rules based on the sensor data for adjusting the confidence value.
19. The computing device of claim 18 , wherein the one or more sensor rules for adjusting the confidence value adjust the confidence value based on an external system's characterization of indoor and outdoor environments.
20. The computing device of claim 11 , wherein the one or more processors execute further machine readable instructions stored in the memory to convert the sensor data into recognizable data signatures.