In-transit detection using low complexity algorithm fusion and phone state heuristics

Patent metadata

Field	Value
Publication number	US-9730145-B2
Application number	US-201313839483-A
Country	US
Kind code	B2
Filing date	Mar 15, 2013
Priority date	Mar 15, 2013
Publication date	Aug 8, 2017
Grant date	Aug 8, 2017

Abstract

System and methods are disclosed to use information available on the state of mobile devices in a heuristics-based approach to improve motion state detection. In one or more embodiments, information on the WiFi connectivity of mobile devices may be used to improve the detection of the in-transit state. The WiFi connectivity information may be used with sensor signal such as accelerometer signals in a motion classifier to reduce the false positives of the in-transit state. In one or more embodiments, information that a mobile device is connected to a WiFi access point (AP) may be used as heuristics to reduce the probability of falsely classifying the mobile device in the in-transit state when mobile device is actually in the hand of a relatively stationary user. Information on the battery charging state or the wireless connectivity of the mobile devices may also be used to improve the detection of in-transit state.

First claim

What is claimed is:

1. A method for detecting a motion state associated with a device, comprising:
receiving information on WiFi connectivity of the device;
determining a WiFi connectivity state based on the information on WiFi connectivity, wherein the WiFi connectivity state indicates whether the device is connected to a mobile WiFi access point, connected to a non-mobile WiFi access point, or not connected to a WiFi access point;
processing the information on WiFi connectivity of the device to set a probability that the device is in a first motion state based on the WiFi connectivity state;
receiving one or more sensor signals from one or more sensor devices, wherein characteristics of the one or more sensor signals reflect motion of the device; and
processing by a motion classifier the one or more sensor signals aided by the probability that the device is in the first motion state to generate a final motion state for the device.

2. The method of claim 1 , wherein the processing by the motion classifier further comprises biasing the final motion state away from the first motion state based on a low probability that the device is in the first motion state as set by the processing of the information on WiFi connectivity of the device.

3. The method of claim 2 , wherein the processing by the motion classifier further comprises, responsive to determining that the probability that the device is in the first motion state is low, eliminating the first motion state from consideration for the final motion state.

4. The method of claim 1 , wherein the processing by the motion classifier further comprises biasing the final motion state toward the first motion state based on a high probability that the device is in the first motion state as set by the processing of the information on WiFi connectivity of the device.

5. The method of claim 1 , wherein the processing the information on WiFi connectivity of the device further comprises:
setting a low probability that the device is in an in-transit state if the WiFi connectivity state indicates that the device is connected to a non-mobile WiFi access point.

6. The method of claim 1 , wherein the processing the information on WiFi connectivity of the device further comprises:
setting a high probability that the device is in an in-transit state if the WiFi connectivity state indicates that the device is connected to a mobile WiFi access point.

7. The method of claim 1 , processing information on a plurality of periodic WiFi scans performed by the device if the WiFi connectivity state indicates that the device is not connected to a WiFi access point.

8. The method of claim 7 , further comprising:
determining if there is a common access point in the plurality of periodic WiFi scans; and
setting a low probability that the device is in an in-transit state if there is a common access point in the plurality of periodic WiFi scans.

9. The method of claim 7 , wherein the processing the information on WiFi connectivity of the device further comprises:
responsive to an indication that there is no common access point in the plurality of periodic WiFi scans, setting a high probability that the device is in an in-transit state.

10. A method for detecting a motion state associated with a device, comprising:
receiving one or more sensor signals from one or more sensor devices, wherein characteristics of the one or more sensor signals reflect motion of the device;
processing by one or more tuned modules the one or more sensor signals to generate one or more tuned signals, wherein each of the tuned modules is configured to detect a tuned state of the device, and wherein each of the tuned signals indicates a probability of the tuned state, at least one of the one or more tuned signals indicating whether the device is stationary or in motion; and
if the one or more tuned signals indicate that the device is in motion, determining a final motion state of the device based on one or more operating states of the device, the one or more operating states including one or more of:
a charging state of the device; and
a network connectivity of the device.

11. The method of claim 10 , wherein one of the tuned modules comprises a pedometer module configured to detect steps.

12. The method of claim 10 , wherein the determining of the final motion state of the device further comprises using the probability of the tuned state indicated by one of the tuned signals to drive the final motion state toward the tuned state.

13. The method of claim 10 , wherein the determining of the final motion state of the device further comprises bypassing processing by a motion classifier when the probability of the tuned state indicated by one of the tuned signals expresses a high probability of the tuned state.

14. The method of claim 13 , wherein when the probability of a stationary state indicated by the tuned signal from one of the tuned modules configured to detect the stationary state exceeds a threshold, the processing by the motion classifier is bypassed, and the final motion state is the stationary state.

15. The method of claim 13 , wherein when the probability of a walk state indicated by the tuned signal from one of the tuned modules configured to detect steps exceeds a threshold, the processing by the motion classifier is bypassed, and the final motion state is the walk state.

16. The method of claim 10 , wherein the processing by the motion classifier further comprises processing information of the operating state of the device to drive the most likely motion state.

17. The method of claim 16 , wherein the processing by the motion classifier further comprises using the information of the operating state of the device to change the probability of one of the one or more tuned states.

18. The method of claim 10 , wherein, responsive to a first indication that the device is in a charging state and a second indication that the device is in motion, setting a high probability that the device is in an in-transit state.

19. The method of claim 10 , wherein, responsive to a first indication that that the device is connected to a car Bluetooth device or a mobile WiFi access point and a second indication that the device is in motion, setting a high probability that the device is in an in-transit state.

20. The method of claim 10 , wherein one of the one or more sensor devices is an accelerometer.

21. An apparatus, comprising:
a sensor configured to register a motion of the apparatus in sensor signals, wherein characteristics of the sensor signals reflect motion of the apparatus;
a memory; and
one or more processors coupled to the memory and configured to:
receive information on WiFi connectivity of the apparatus;
determine a WiFi connectivity state based on the information on WiFi connectivity, wherein the WiFi connectivity state indicates whether the device is connected to a mobile WiFi access point, connected to a non-mobile WiFi access point, or not connected to a WiFi access point;
process the information on WiFi connectivity of the apparatus to set a probability that the apparatus is in a first motion state based on the WiFi connectivity state; and
process the sensor signals aided by the probability that the apparatus is in the first motion state to generate a final motion state for the apparatus.

22. The apparatus of claim 21 , wherein the one or more processors are configured to process the sensor signals by being further configured to bias the final motion s

Assignees

• Qualcomm Inc

Inventors

• Lee Jin Won
• Sadasivam Shankar
• Ahuja Disha
• Puig Carlos M

Classifications

• H04W4/21

  for social networking applications · CPC title

• H04W48/04 Primary

  based on user or terminal location or mobility data, e.g. moving direction, speed · CPC title

• H04W64/006

  with additional information processing, e.g. for direction or speed determination · CPC title

• H04W4/025

  using location based information parameters · CPC title

• G01C22/006

  Pedometers · CPC title