User activity tracking system and device

• US 9,519,672 B2
• Filed: 07/22/2015
• Issued: 12/13/2016
• Est. Priority Date: 06/28/2013
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Pennanen, Juho, Kyrl, Aapo
• Primary Examiner(s): Eisner, Ronald
• Application Number:
  US14/806,422
• Publication Number:
  US 20150324412A1
• Time in Patent Office: 510 Days
• Field of Search: 4554141-4143, 455418-420, 455/404.1, 455/404.2, 4554561-457, 340/539.13, 340988-996
• US Class Current: 1/1
• CPC Class Codes: G06F 16/2291 User-Defined Types; Storage management thereof
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: H04W 4/02 Services making use of location information
• CPC Class Codes: H04W 4/027 using movement velocity, acceleration information
• CPC Class Codes: H04W 4/029 Location-based management or tracking services
• CPC Class Codes: H04W 64/00 Locating users or terminals or network equipment for network management purposes, e.g. mobility management

Abstract

In an embodiment, a computing device determines sensor signals detected by one or more sensors of the computing device. The sensor signals indicate motion of the computing device. The computing device selects one of a plurality of activity categories that corresponds to a portion of the sensor signals, each of the activity categories including one or more activity types. The activity types in each activity category are characterized by a common motion corresponding to the portion of the sensor signals. One of the activity types in the selected activity category is determined by analyzing the sensor signals with respect to each of the activity types in the selected activity category, and calculating a probability of each of the activity types. The determined activity type is displayed on the computing device.

Claims

1. A method comprising:

by a computing device, determining one or more sensor signals detected by one or more sensors of the computing device, the sensor signals being indicative of motion of the computing device;

by the computing device, selecting one of a plurality of activity categories that corresponds to a portion of the sensor signals, wherein each of the activity categories comprises one or more activity types and is characterized by a motion that the activity types in the selected activity category have in common;

by the computing device, determining one of the activity types in the selected activity category by;

analyzing the sensor signals with respect to each of the activity types in the selected activity category; and

calculating a probability of each of the activity types based on the analysis; and

by the computing device, displaying the determined activity type on a display of the computing device.

2. The method of claim 1, wherein the sensor signals are analyzed substantially in parallel by one or more processors of the computing device, each of the processors being specialized in identifying characteristics of the sensor signals corresponding to a predefined activity type.

3. The method of claim 1, wherein determining the activity types comprises generating a temporal log of activity types experienced by the mobile device.

4. The method of claim 1, wherein the sensor signals further comprise an estimated speed of the computing device based on location data of the computing device.

5. The method of claim 1, wherein the one or more sensors comprise a gyroscopic angular sensor, an accelerometer, a GPS position sensor, a cellular positioning sensor, a magnetometer, a microphone, a camera, or a temperature sensor.

6. The method of claim 1, wherein the analysis of the sensor signals comprises:

a supervised or semisupervised classification analysis;

or

a heuristic analysis.

7. The method of claim 6, wherein the supervised or semisupervised classification analysis comprises classification algorithms that use as input the amplitudes of the frequency components of the information included in the sensor signals, and the output of the classification algorithms are estimated probabilities of different activity types based at least in part on the sensor signals.

8. The method of claim 1, wherein displaying the determined activity type comprises displaying analyzed activity results on a graphical user interface of a software application of the computing device, wherein the displayed analyzed activity results comprise a timeline comprising a plurality of mutually different symbols representing different activity types.

9. A system comprising:

one or more processors;

a display;

one or more sensors; and

a memory coupled to the processors comprising instructions executable by the processors, the processors being operable when executing the instructions to;

determine one or more sensor signals detected by the one or more sensors, the sensor signals being indicative of motion of the system;

select one of a plurality of activity categories that corresponds to a portion of the sensor signals, wherein each of the activity categories comprises one or more activity types and is characterized by a motion that the activity types in the selected activity category have in common;

determine one of the activity types in the selected activity category by;

analyzing the sensor signals with respect to each of the activity types in the selected activity category; and

calculating a probability of each of the activity types based on the analysis; and

display the determined activity type on the display.

10. The system of claim 9, wherein the sensor signals are analyzed substantially in parallel by one or more processors of the computing device, each of the processors being specialized in identifying characteristics of the sensor signals corresponding to a predefined activity type.

11. The system of claim 9, wherein determining the activity type comprises generating a temporal log of activity types experienced by the mobile device.

12. The system of claim 9, wherein the sensor signals further comprise an estimated speed of the computing device based on location data of the computing device.

13. The system of claim 9, wherein the one or more sensors comprise a gyroscopic angular sensor, an accelerometer, a GPS position sensor, a cellular positioning sensor, a magnetometer, a microphone, a camera, or a temperature sensor.

14. The system of claim 9, wherein the analysis of the sensor signals comprises:

a supervised or semisupervised classification analysis;

or

a heuristic analysis.

15. The system of claim 14, wherein the supervised or semisupervised classification analysis comprises classification algorithms that use as input the amplitudes of the frequency components of the information included in the sensor signals, and the output of the classification algorithms are estimated probabilities of different activity types based at least in part on the sensor signals.

16. The system of claim 9, wherein displaying the activity type comprises sending analyzed activity results to the mobile device for display on a graphical user interface of a software application of the mobile device, wherein the displayed analyzed activity results comprise a timeline comprising a plurality of mutually different symbols representing different activity types.

17. One or more computer-readable non-transitory storage media embodying software that is operable when executed to:

determine one or more sensor signals detected by one or more sensors of a computing device, the sensor signals being indicative of motion of the computing device;

select one of a plurality of activity categories that corresponds to a portion of the sensor signals, wherein each of the activity categories comprises one or more activity types and is characterized by a motion that the activity types in the selected activity category have in common;

determine one of the activity types in the selected activity category by;

analyzing the sensor signals with respect to each of the activity types in the selected activity category; and

calculating a probability of each of the activity types based on the analysis; and

display the activity type on a display of the computing device.

18. The media of claim 17, wherein the sensor signals are analyzed substantially in parallel by one or more processors of the computing device, each of the processors being specialized in identifying characteristics of the sensor signals corresponding to a predefined activity type.

19. The media of claim 17, wherein the analysis of the sensor signals comprises:

a supervised or semisupervised classification analysis;

or

a heuristic analysis.

20. The media of claim 19, wherein the supervised or semisupervised classification analysis comprises classification algorithms that use as input the amplitudes of the frequency components of the information included in the sensor signals, and the output of the classification algorithms are estimated probabilities of different activity types based at least in part on the sensor signals.