Systems and methods for detecting mobile device movement within a vehicle using accelerometer data

• US 9,654,932 B1
• Filed: 09/13/2016
• Issued: 05/16/2017
• Est. Priority Date: 09/13/2016
• Status: Active Grant

• Current Assignee: Arity International Limited (Allstate Corporation)
• Original Assignee: Allstate Insurance Company (Allstate Corporation)
• Inventors: Mukhtar, Yasir, Nagpal, Varun, Snyder, Jared S., Walsh, Connor
• Primary Examiner(s): Siddiqui, Kashif
• Application Number:
  US15/263,562
• Time in Patent Office: 245 Days
• CPC Class Codes: G01C 21/18 Stabilised platforms, e.g. by gyroscope
• CPC Class Codes: G06Q 40/08 Insurance
• CPC Class Codes: H04M 1/724098 Interfacing with an on-board device of a vehicle for hands-free speaking in vehicles H04M1/6075
• CPC Class Codes: H04M 1/724631 by limiting the access to the user interface, e.g. locking a touch-screen or a keypad
• CPC Class Codes: H04M 2250/10 including a GPS signal receiver
• CPC Class Codes: H04W 4/026 using orientation information, e.g. compass
• CPC Class Codes: H04W 4/027 using movement velocity, acceleration information

Abstract

One or more mobile device movement detection computing devices and methods are disclosed herein based on acceleration data collected from an accelerometer of a mobile device found within an interior of a vehicle. The mobile device movement detection computing devices may identify a likely mobile device movement event based on a change of angle between two three-dimensional acceleration vectors. Where the mobile device movement detection computing devices detect a likely mobile device movement event, sensor data from various sensors of a mobile device are collected and aggregated for a window of time encompassing the mobile device movement event. Data from vehicle sensors and other external systems may also be used. The mobile device movement detection computing devices calculate a risk score based on the aggregates sensor data, and provide feedback to a mobile device or vehicle based on the calculated risk score.

Claims

1. A mobile device movement detection system comprising:

at least one processor; and

memory storing computer-readable instructions, that when executed by the at least one processor, cause the system to;

collect, by a sensor data collection device of the system, acceleration data from an accelerometer associated with a mobile device within a vehicle at a first time and at a second time;

collect, by the sensor data collection device, sensor data from sensors associated with the mobile device, wherein the sensors comprise the accelerometer, a GPS receiver, and a gyroscope;

process, by a sensor data processing device, the acceleration data to remove a gravity component of the acceleration data, and generate a processed acceleration data at the first time and at the second time;

determine, by a movement event detection device, that a mobile device movement event has occurred at the second time based, at least in part, on three-dimensional vectors representing the processed acceleration data at the first time and at the second time;

aggregate, by a sensor data aggregation device, the sensor data from the sensors associated with the mobile device for a window of time starting a first predetermined duration before the second time and ending a second predetermined duration after the second time, and generate an aggregated sensor data;

determine, by a risk determination device, a risk score based, at least in part, on the aggregated sensor data for the window of time; and

generate, by a risk feedback generation device, a notification to the mobile device based, at least in part, on the risk score.

2. The system of claim 1 wherein determining that a mobile device movement event has occurred at the second time includes:

calculating, by the movement event detection device, a difference in angle between the three-dimensional vectors representing the processed acceleration data at the first time and the second time; and

determining, by the movement event detection device, that the difference in angle is greater than a predetermined threshold angle.

3. The system of claim 1 wherein processing the acceleration data to remove the gravity component of the acceleration data includes:

applying, by the sensor data processing device, a low pass filter to the acceleration data at the first time to isolate an acceleration due to gravity at the first time;

removing, by the sensor data processing device, the acceleration due to gravity at the first time from the acceleration data at the first time;

applying, by the sensor data processing device, the low pass filter to the acceleration data at the second time to isolate an acceleration due to gravity at the second time; and

removing, by the sensor data processing device, the acceleration due to gravity at the second time from the acceleration data at the second time.

4. The system of claim 1, further including instructions that, when executed by the at least one processor, cause the system to:

collect, by the sensor data collection device, supplemental sensor data from sensors associated with the vehicle during the window of time, and aggregate, by the sensor data aggregation device, to generate supplemental aggregated sensor data; and

determine, by the risk determination device, a risk score based, at least in part, on the aggregated sensor data and the supplemental aggregated sensor data.

5. The system of claim 1, wherein the risk score is based on a plurality of scores assigned to a plurality of factors, wherein the plurality of factors comprise an average speed of the vehicle during the window of time, a weather condition during the window of time, a time of day during the window of time, a phone type of the mobile device, and a magnitude of the processed acceleration data at the second time.

6. The system of claim 5, further including instructions that, when executed by the at least one processor, cause the system to:

apply, by the risk determination device, a risk calculation equation aggregating the plurality of scores assigned to the plurality of factors to calculate the risk score.

7. The system of claim 1, further including instructions that, when executed by the at least one processor, cause the system to:

prevent, by the risk feedback generation device, interaction with a user interface of the mobile device responsive to the risk score.

8. A method comprising:

collecting, by a sensor data collection device of a mobile device movement detection system, acceleration data from an accelerometer associated with a mobile device within a vehicle at a first time and at a second time;

collecting, by the sensor data collection device, sensor data from sensors associated with the mobile device, wherein the sensors comprise the accelerometer, a GPS receiver, and a gyroscope;

processing, by a sensor data processing device, the acceleration data to remove a gravity component of the acceleration data, and generating a processed acceleration data at the first time and at the second time;

determining, by a movement event detection device, that a mobile device movement event has occurred at the second time based, at least in part, on three-dimensional vectors representing the processed acceleration data at the first time and at the second time;

aggregating, by a sensor data aggregation device, the sensor data from the sensors associated with the mobile device for a window of time starting at a first predetermined duration before the second time and ending a second predetermined duration after the second time, and generating an aggregated sensor data;

determining, by a risk determination device, a risk score based, at least in part, on the aggregated sensor data for the window of time; and

generating, by a risk feedback generation device, a notification to the mobile device based, at least in part, on the risk score.

9. The method of claim 8 wherein determining that a mobile device movement event has occurred at the second time includes:

calculating, by the movement event detection device, a difference in angle between the three-dimensional vectors representing the processed acceleration data at the first time and the second time; and

determining, by the movement event detection device, that the difference in angle is greater than a predetermined threshold angle.

10. The method of claim 8 wherein processing the acceleration data to remove the gravity component of the acceleration data includes:

applying, by the sensor data processing device, a low pass filter to the acceleration data at the first time to isolate an acceleration due to gravity at the first time;

removing, by the sensor data processing device, the acceleration due to gravity at the first time from the acceleration data at the first time;

applying, by the sensor data processing device, the low pass filter to the acceleration data at the second time to isolate an acceleration due to gravity at the second time; and

removing, by the sensor data processing device, the acceleration due to gravity at the second time from the acceleration data at the second time.

11. The method of claim 8, further comprising:

collecting, by the sensor data collection device, supplemental sensor data from sensors associated with the vehicle during the window of time, and aggregate, by the sensor data aggregation device, to generate an supplemental aggregated sensor data; and

determining, by the risk determination device, a risk score based, at least in part, on the aggregated sensor data and the supplemental aggregated sensor data.

12. The method of claim 8, wherein the risk score is based on a plurality of scores assigned to a plurality of factors, wherein the plurality of factors comprise an average speed of the vehicle during the window of time, a weather condition during the window of time, a time of day during the window of time, a phone type of the mobile device, and a magnitude of the processed acceleration data at the second time.

13. The method of claim 12, further comprising:

applying, by the risk determination device, a risk calculation equation aggregating the plurality of scores assigned to the plurality of factors to calculate the risk score.

14. The method of claim 8, further comprising:

preventing, by the risk feedback generation device, interaction with a user interface of the mobile device responsive to the risk score.

15. A computer-assisted method of detecting mobile device movement events comprising:

collecting, by a sensor data collection device of a mobile device movement detection system, acceleration data from an accelerometer associated with a mobile device within a vehicle at a first time and at a second time;

collecting, by the sensor data collection device, sensor data from sensors associated with the mobile device, wherein the sensors comprise the accelerometer, a GPS receiver, and a gyroscope;

processing, by a sensor data processing device, the acceleration data to remove a gravity component of the acceleration data, and generating a processed acceleration data at the first time and at the second time;

determining, by a movement event detection device, that a mobile device movement event has occurred at the second time based, at least in part, on three-dimensional vectors representing the processed acceleration data at the first time and at the second time;

aggregating, by a sensor data aggregation device, the sensor data from the sensors associated with the mobile device for a window of time starting at a first predetermined duration before the second time and ending a second predetermined duration after the second time, and generating an aggregated sensor data;

determining, by a risk determination device, a risk score based, at least in part, on the aggregated sensor data for the window of time; and

generating, by a risk feedback generation device, a notification to the mobile device based, at least in part, on the risk score.

16. The computer-assisted method of claim 15 wherein determining that a mobile device movement event has occurred at the second time includes:

calculating, by the movement event detection device, a difference in angle between the three-dimensional vectors representing the processed acceleration data at the first time and the second time; and

determining, by the movement event detection device, that the difference in angle in greater than a predetermined threshold angle.

17. The computer-assisted method of claim 15 wherein processing the acceleration data to remove the gravity component of the acceleration data includes:

applying, by the sensor data processing device, a low pass filter to the acceleration data at the first time to isolate an acceleration due to gravity at the first time;

removing, by the sensor data processing device, the acceleration due to gravity at the first time from the acceleration data at the first time;

applying, by the sensor data processing device, the low pass filter to the acceleration data at the second time to isolate an acceleration due to gravity at the second time; and

removing, by the sensor data processing device, the acceleration due to gravity at the second time from the acceleration data at the second time.

18. The computer-assisted method of claim 15, wherein the risk score is based on a plurality of scores assigned to a plurality of factors, wherein the plurality of factors comprise an average speed of the vehicle during the window of time, a weather condition during the window of time, a time of day during the window of time, a phone type of the mobile device, and a magnitude of the processed acceleration data at the second time.

19. The computer-assisted method of claim 18 further comprising:

applying, by the risk determination device, a risk calculation equation aggregating the plurality of scores assigned to the plurality of factors to calculate the risk score.

20. The computer-assisted method of claim 15 further comprising:

preventing, by the risk feedback generation device, interaction with a user interface of the mobile device responsive to the risk score.