Computing system with driver behavior detection mechanism and method of operation thereof

• US 10,685,248 B1
• Filed: 05/30/2019
• Issued: 06/16/2020
• Est. Priority Date: 05/30/2019
• Status: Active Grant

• Current Assignee: Mojio Inc.
• Original Assignee: Mojio Inc.
• Inventors: Sanandaji, Borhan Molazem, Liu, Xi
• Primary Examiner(s): Odom, Curtis B
• Application Number:
  US16/427,090
• Time in Patent Office: 383 Days
• CPC Class Codes: B60W 2050/146 Display means
• CPC Class Codes: B60W 2520/10 Longitudinal speed
• CPC Class Codes: B60W 2520/105 Longitudinal acceleration
• CPC Class Codes: B60W 2540/30 Driving style
• CPC Class Codes: B60W 2555/60 Traffic rules, e.g. speed limits or right of way
• CPC Class Codes: B60W 40/09 Driving style or behaviour
• CPC Class Codes: B60W 50/10 Interpretation of driver requests or demands
• CPC Class Codes: B60W 50/14 Means for informing the driver, warning the driver or prompting a driver intervention
• CPC Class Codes: G06F 18/2148 characterised by the process organisation or structure, e.g. boosting cascade
• CPC Class Codes: G06F 18/23213 with fixed number of clusters, e.g. K-means clustering
• CPC Class Codes: G06F 2218/00 Aspects of pattern recognition specially adapted for signal processing
• CPC Class Codes: G06V 20/597 Recognising the driver's state or behaviour, e.g. attention or drowsiness

Abstract

A computing system and method for operating the computing system including: a control unit configured to: generate a filtered data set based on a data set; group the filtered data set based on a previous origin indicator to obtain a device group data; generate a label based on the device group data; generate a training moving average based on the label and the device group data; generate an operating pattern based on the training moving average; identify a change in a driving behavior based on comparing the operating pattern and a detection moving average; generate a notification based on the change; and a communication unit, coupled to the control unit, configured to: send the notification for display on a display interface.

Claims

1. A method of operating a computing system comprising:

generating a filtered data set based on a data set;

grouping the filtered data set based on a previous origin indicator to obtain a device group data;

generating a label based on the device group data;

generating a training moving average based on the label and the device group data;

generating an operating pattern based on the training moving average;

identifying a change in a driving behavior based on comparing the operating pattern and a detection moving average;

generating a notification based on the change; and

sending the notification for display on a display interface.

2. The method as claimed in claim 1 wherein generating the operating pattern includes grouping the training moving average based on K-Means Clustering.

3. The method as claimed in claim 1 wherein generating the label includes:

generating a deviation speed profile for the device group data based on a previous average speed and a known speed limit for one or more segments of one or more paths traversed during consecutive trips;

calculating a proximity score based on the deviation speed profile;

determining whether the proximity score is greater than a proximity threshold value; and

generating the label based on the proximity score being greater than the proximity threshold value.

4. The method as claimed in claim 1 wherein generating the label includes:

generating an acceleration speed profile for the device group data based on a previous sum of acceleration force values during consecutive trips;

calculating a proximity score based on the acceleration speed profile;

determining whether the proximity score is greater than a proximity threshold value; and

generating the label based on the proximity score being greater than the proximity threshold value.

5. The method as claimed in claim 1 further comprising normalizing the device group data based on a previous trip length to compare the device group data based on the previous trip length.

6. The method as claimed in claim 1 further comprising rescaling the training moving average based on a scale from [0, 1] to compare the training moving average based on the scale.

7. The method as claimed in claim 1 wherein sending the notification for display on the display interface includes sending the notification based on a decision window.

8. A computing system comprising:

a control unit configured to;

generate a filtered data set based on a data set;

group the filtered data set based on a previous origin indicator to obtain a device group data;

generate a label based on the device group data;

generate a training moving average based on the label and the device group data;

generate an operating pattern based on the training moving average;

identify a change in a driving behavior based on comparing the operating pattern and a detection moving average;

generate a notification based on the change; and

a communication unit, coupled to the control unit, configured to;

send the notification for display on a display interface.

9. The computing system as claimed in claim 8 wherein the control unit is further configured to group the training moving average based on K-Means Clustering.

10. The computing system as claimed in claim 8 wherein the control unit is further configured to:

generate a deviation speed profile for the device group data based on a previous average speed and a known speed limit for one or more segments of one or more paths traversed during consecutive trips;

calculate a proximity score based on the deviation speed profile;

determine whether the proximity score is greater than a proximity threshold value; and

generate the label based on the proximity score being greater than the proximity threshold value.

11. The computing system as claimed in claim 8 wherein the control unit is further configured to:

generate an acceleration speed profile for the device group data based on a previous sum of acceleration force values during consecutive trips;

calculate a proximity score based on the acceleration speed profile;

determine whether the proximity score is greater than a proximity threshold value; and

generate the label based on the proximity score being greater than the proximity threshold value.

12. The computing system as claimed in claim 8 wherein the control unit is further configured to normalize the device group data based on a previous trip length to compare the device group data based on the previous trip length.

13. The computing system as claimed in claim 8 wherein the control unit is further configured to rescale the training moving average based on a scale from [0, 1] to compare the training moving average based on the scale.

14. A non-transitory computer readable medium including instructions for operating a computing system comprising:

generating a filtered data set based on a data set;

grouping the filtered data set based on a previous origin indicator to obtain a device group data;

generating a label based on the device group data;

generating a training moving average based on the label and the device group data;

generating an operating pattern based on the training moving average;

identifying a change in a driving behavior based on comparing the operating pattern and a detection moving average;

generating a notification based on the change; and

sending the notification for display on a display interface.

15. The non-transitory computer readable medium as claimed in claim 14 with instructions wherein generating the operating pattern includes grouping the training moving average based on K-Means Clustering.

16. The non-transitory computer readable medium as claimed in claim 14 with instructions wherein generating the label includes:

generating a deviation speed profile for the device group data based on a previous average speed and a known speed limit for one or more segments of one or more paths traversed during consecutive trips;

calculating a proximity score based on the deviation speed profile;

determining whether the proximity score is greater than a proximity threshold value; and

generating the label based on the proximity score being greater than the proximity threshold value.

17. The non-transitory computer readable medium as claimed in claim 14 with instructions wherein generating the label includes:

generating an acceleration speed profile for the device group data based on a previous sum of acceleration force values during consecutive trips;

calculating a proximity score based on the acceleration speed profile;

determining whether the proximity score is greater than a proximity threshold value; and

generating the label based on the proximity score being greater than the proximity threshold value.

18. The non-transitory computer readable medium as claimed in claim 14 with instructions further comprising normalizing the device group data based on a previous trip length to compare the device group data based on the previous trip length.

19. The non-transitory computer readable medium as claimed in claim 14 with instructions further rescaling the training moving average based on a scale from [0, 1] to compare the training moving average based on the scale.

20. The non-transitory computer readable medium as claimed in claim 14 with instructions wherein sending the notification for display on the display interface includes sending the notification based on a decision window.