PHYSICAL ACTIVITY INFERENCE FROM ENVIRONMENTAL METRICS

• US 20140167973A1
• Filed: 12/14/2012
• Published: 06/19/2014
• Est. Priority Date: 12/14/2012
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Letchner, Julia Maureen, Brush, Alice Jane, Kansal, Aman, Morris, Daniel, Saponas, Scott
• Granted Patent: US 9,700,240 B2
• Time in Patent Office: Days
• US Class Current: 340/870.02
• CPC Class Codes: A61B 2503/12 Healthy persons not otherwise provided for, e.g. subjects of a marketing survey
• CPC Class Codes: A61B 2503/22 Motor vehicles operators, e.g. drivers, pilots, captains
• CPC Class Codes: A61B 2560/0247 for compensation or correction of the measured physiological value
• CPC Class Codes: A61B 2562/0204 Acoustic sensors
• CPC Class Codes: A61B 2562/0219 Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• CPC Class Codes: A61B 2562/0223 Magnetic field sensors
• CPC Class Codes: A61B 5/1118 Determining activity level
• CPC Class Codes: A61B 5/18 for vehicle drivers or machine operators
• CPC Class Codes: A61B 5/6801 specially adapted to be attached to or worn on the body surface
• CPC Class Codes: A61B 5/7475 User input or interface means, e.g. keyboard, pointing device, joystick
• CPC Class Codes: G06F 16/95 Retrieval from the web
• CPC Class Codes: G06Q 30/0242 Determining effectiveness of advertisements
• CPC Class Codes: G06Q 30/0243 Comparative campaigns
• CPC Class Codes: G06Q 30/0244 Optimization
• CPC Class Codes: G06Q 30/0245 Surveys
• CPC Class Codes: G06Q 30/0254 based on statistics
• CPC Class Codes: G06Q 30/0277 Online advertisement
• CPC Class Codes: G06Q 30/0613 Third-party assisted
• 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

Portable devices include environmental sensors that generate metrics about the environment (e.g., accelerometers detecting impulses and vibration, and GPS receivers detecting position and velocity). Such devices often use environmental metrics to extract user input directed at the device by the user, and status information about the device and the environment. Presented herein are techniques for using environmental metrics to infer physical activities performed by the user while attached to the device. For example, jogging may be inferred from regular, strong impulses and typical jogging speed; walking may be inferred from regular, weak impulses and typical walking speed; and riding in a vehicle may be inferred from low-level vibrations and high speed (optionally identifying the type of vehicle ridden by the user). Based on these inferences, the device may automatically present applications and/or or adjust user interfaces suitable for the user'"'"'s physical activity, rather than responsive to user input.

Claims

1. A method of identifying a physical activity of a user of a device having a processor and at least one environmental sensor, the method comprising:

executing on the processor instructions configured to;

retrieve from at least one environmental sensor at least one environmental metric associated with the device while attached to the user and not comprising user input received from the user; and

identify a physical activity that, when performed by the user while attached to the device, results in the at least one environmental metric.

2. The method of claim 1, the environmental metric selected from an environmental metric set comprising:

a geolocation metric;

a linear velocity metric;

an angular velocity metric;

an acceleration metric;

a device orientation metric;

a light level metric;

a sound level metric;

a magnetic field metric;

a wireless communication signal metric; and

a touch metric that does not comprise user input.

3. The method of claim 1, the at least one physical activity selected from a physical activity set comprising:

a walking physical activity;

a standing physical activity;

a sitting physical activity;

a jogging physical activity;

a swimming physical activity; and

a bicycling physical activity.

4. The method of claim 1:

the at least one physical activity selected from a physical activity set comprising a vehicle riding physical activity; and

the instructions further configured to, upon identifying the vehicle riding physical activity, identify at least one vehicle type that, when the vehicle riding physical activity is performed by the user while attached to the device and while the user is riding in a vehicle of the vehicle type, results in the environmental metric.

5. The method of claim 1, identifying the physical activity comprising:

sending the at least one environmental metric to a physical activity identification service; and

receive from the physical activity identification service an identification of the physical activity performed by the user according to the environmental metrics.

6. The method of claim 1:

the device comprising at least one physical activity profile associated with a physical activity and specifying at least one environmental metric detected by the at least one sensor of the device while the physical activity is performed by the user while attached to the device, results in the environmental metric; and

the identifying comprising;

comparing the at least one environmental metric to the environmental metrics associated with respective physical activity profiles to identify a selected physical activity profile; and

identifying the physical activity associated with the selected physical activity profile.

7. The method of claim 1:

the device comprising at least two environmental sensors;

respective physical activity profiles identifying, for respective environmental sensors, an environmental metric significance indicating a significance of environmental metrics of the sensor to identifying the physical activity of the physical activity profile; and

the device comprising a classifier configured to identify physical activities according to the environmental metrics and the environmental metric significance indicators of the physical activity profile.

8. A computer-readable storage device comprising instructions configured to, when executed on a processor of a device executing at least one application and having at least one environmental sensor and attached to a user, identify physical activities performed by the user by:

while the user is performing a physical activity, receive from respective environmental sensors at least one environmental metric not comprising user input received from the user;

using the environmental metrics, identify the physical activity performed by the user; and

report the physical activity of the user to the application.

9. The computer-readable storage device of claim 8, the instructions further configured to:

receive from at least one application a request to receive reports of physical activity, store the request; and

upon identifying a physical activity that is associated with a request, report the physical activity to the application associated with the request.

10. The computer-readable storage device of claim 8:

the device comprising at least one user interface presented to the user having at least two user interface modes respectively associated with a physical activity; and

the instructions further configured to, upon identifying a physical activity while presenting the user interface to the user, select the user interface mode for the user interface that is associated with the physical activity.

11. The computer-readable storage device of claim 8, the instructions further configured to:

upon receiving from the application a request to identify the physical activity of the user, enable the at least one environmental sensor to detect the environmental metric; and

after reporting the physical activity of the user, disable the at least one environmental sensor.

12. The computer-readable storage device of claim 8:

the device comprising a classifier logic that is configured to, for at least one environmental metric, select a physical activity associated with the environmental metric; and

identifying the at least one physical activity comprising;

invoking the classifier logic to identify the physical activity associated with the at least one environmental metric.

13. The computer-readable storage device of claim 12:

the device comprising at least one training data set identifying, for respective environmental metrics, a physical activity identifiable by at least one environmental metric;

the instructions further configured to train the classifier logic to identify, for respective training data sets, the physical activity identified by the training data set for the environmental metric.

14. The computer-readable storage device of claim 12:

respective environmental metrics identifying the physical activity when performed by a particular user while attached to the device; and

the instructions further configured to, upon identifying from the environmental metric the physical activity performed by the particular user, update the classifier logic to identify the physical activities of the particular user for the environmental metric.

15. The computer-readable storage device of claim 12:

the classifier logic further configured to, in addition to the selection of the physical activity, identify a selection confidence of the selection of the physical activity associated with the environmental metric; and

identifying the at least one physical activity comprising;

invoking the classifier logic to identify the physical activity associated with the at least one environmental metric and having a selection confidence above a selection confidence threshold.

16. The computer-readable storage device of claim 15, the instructions further configured to, upon the classifier logic failing to identify a physical activity having a selection confidence above the selection confidence threshold:

receive at least one additional environmental metric from the at least one environmental sensor metric; and

invoke the classifier logic to identify the physical activity associated with the at least one environmental metric and the at least one additional environmental metric.

17. The computer-readable storage device of claim 12, the instructions further configured to, upon receiving from the user a user identification of a physical activity performed by the user when the environmental sensor received the environmental metric, update the classifier logic to identify the physical activity of the user for the environmental metric.

18. The computer-readable storage device of claim 17, the instructions further configured to:

receive the classifier logic from a physical activity identifying service; and

upon receiving the user identification of the physical activity, send the user identification and the at least one environmental metric to the physical activity identifying service.

19. A method of facilitating devices comprising at least one environmental sensor in identifying physical activities performed by a user while attached to the device, the method involving a computer having a processor and a classifier logic and comprising:

executing on the processor instructions configured to, upon receiving from a device at least one environmental metric not comprising user input received from the user and detected by at least one environmental sensor of the device while attached to the user;

identify, according to the classifier logic, a physical activity that, when performed by the user while attached to the device, results in the at least one environmental metric; and

send the physical activity to the device.

20. The method of claim 19, the instructions further configured to, upon receiving from a device an identification of a physical activity performed by a user while attached to the device when the environmental sensor detected the at least one environmental metric, update the classifier logic according to the physical activity and the at least one environmental metric.