Cognitive dialog system for driving safety

• US 9,878,663 B1
• Filed: 12/07/2016
• Issued: 01/30/2018
• Est. Priority Date: 12/07/2016
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Kochura, Nadiya, Lu, Fang
• Primary Examiner(s): Nguyen, Tai T
• Application Number:
  US15/372,137
• Time in Patent Office: 419 Days
• Field of Search: 340439, 340436, 340901, 340988, 340995, 901213, 901301, 901469
• CPC Class Codes: B60W 2040/0818 Inactivity or incapacity of driver
• CPC Class Codes: B60W 2050/0075 Automatic parameter input, automatic initialising or calibrating means
• CPC Class Codes: B60W 2556/10 Historical data
• CPC Class Codes: B60W 2556/45 External transmission of data to or from the vehicle
• CPC Class Codes: B60W 40/08 related to drivers or passengers
• CPC Class Codes: B60W 50/0098 Details of control systems ensuring comfort, safety or stability not otherwise provided for

Abstract

The system gathers a current set of biometric data for a driver of a vehicle from an Internet of Things (IoT) device during a driving phase. The system gathers a set of external factor data from a cloud resource during the driving phase. The system adjusts a threshold value for a first threshold between a normal biometric condition and a first abnormal biometric condition for the driver for a first biometric parameter according to the set of external factor data. The system determines whether the gathered biometric data of the driver is consistent with the normal biometric condition or the first abnormal biometric condition according to the adjusted first threshold value. If the gathered biometric data is consistent with the first abnormal biometric condition, the system performs a selected one of a set of actions to alleviate the first abnormal biometric condition.

Claims

1. A computer implemented method for driving safety comprising:

gathering a current set of biometric data of a vehicle driver from an Internet of Things (IoT) device during a driving phase, wherein the current set of biometric data comprises current values for dynamic biometric data indicating a biometric condition;

gathering a set of external factor data from a cloud resource during the driving phase, wherein the set of external factor data comprises values for external factors that may impact vehicle driver performance;

adjusting a threshold value for a first threshold between a normal biometric condition and a first abnormal biometric condition for the vehicle driver for a first biometric parameter according to the set of external factor data;

determining whether the gathered biometric data of the vehicle driver is consistent with the normal biometric condition or the first abnormal biometric condition according to the adjusted first threshold value; and

responsive to a determination that the gathered biometric data is consistent with the first abnormal biometric condition, performing a selected one of a set of actions, the selected action designed to alleviate the first abnormal biometric condition.

2. The method as recited in claim 1, further comprising;

gathering a current driving pattern from a vehicle sensor during the driving phase;

adjusting a threshold value for a second threshold between a normal driving pattern and a first abnormal driving pattern for the vehicle driver for according to the set of external factor data;

determining whether the current driving pattern of the vehicle driver is consistent with the normal driving pattern or the first abnormal driving pattern according to the adjusted second threshold value; and

responsive to a determination that the current driving pattern is consistent with the first abnormal driving condition, performing a selected one of the set of actions.

3. The method as recited in claim 1, wherein the selected action is to perform a dialog with the vehicle driver designed to bring the vehicle driver into the normal biometric condition.

4. The method as recited in claim 3, wherein the first abnormal biometric condition is a member of a plurality of inattentive conditions and the method further comprises selecting the dialog with the vehicle driver for the first abnormal biometric condition from a set of dialogs, each dialog of the set of dialogs designed to bring the vehicle driver to the normal biometric condition from a respective one of the plurality of inattentive conditions.

5. The method as recited in claim 2, wherein the external factor data is selected from the group consisting of traffic factor data, weather factor data and road condition data.

6. The method as recited in claim 1, wherein the external factor data indicates a presence of a negative external factor and wherein the adjusting the threshold value for the first threshold between the normal biometric condition and the first abnormal biometric condition for the vehicle driver adjusts the value for the first biometric parameter to a higher value.

7. The method as recited in claim 2, wherein the external factor data indicates a presence of a negative external factor and wherein the adjusting the threshold value for the second threshold between the normal driving pattern and the first abnormal driving pattern for the vehicle driver results in a greater range of current driving patterns determined to be a normal driving pattern.

8. The method as recited in claim 1, wherein the external factor data is traffic factor data indicating an accident along a planned route and the method further comprises:

predicting that the vehicle driver biometric condition will increase above the adjusted first threshold value; and

performing a selected one of a set of actions to alleviate the first abnormal biometric condition.

9. Apparatus, comprising:

a processor;

an Internet of Things (IoT) device;

a communications control unit;

computer memory holding computer program instructions executed by the processor for driving safety, the computer program instructions comprising;

program code, operative to gather a current set of biometric data of a vehicle driver from the Internet of Things (IoT) device during a driving phase, wherein the current set of biometric data comprises current values for dynamic biometric data indicating a biometric condition;

program code, operative to gather a set of external factor data from a cloud resource via the communications control unit during the driving phase, wherein the set of external factor data comprises values for external factors that may impact vehicle driver performance;

program code, operative to adjust a threshold value for a first threshold between a normal biometric condition and a first abnormal biometric condition for the vehicle driver for a first biometric parameter according to the set of external factor data;

program code, operative to determine whether the gathered biometric data of the vehicle driver is consistent with the normal biometric condition or the first abnormal biometric condition according to the adjusted first threshold value; and

program code responsive to a determination that the gathered biometric data is consistent with the first abnormal biometric condition, operative to perform at least a selected one of a set of actions, the selected action designed to alleviate the first abnormal biometric condition.

10. The apparatus as recited in claim 9, further comprising:

program code, operative to gather a current driving pattern from a vehicle sensor during the driving phase;

program code, operative to adjust a threshold value for a second threshold between a normal driving pattern and a first abnormal driving pattern for the vehicle driver for according to the set of external factor data;

program code, operative to determine whether the current driving pattern of the vehicle driver is consistent with the normal driving pattern or the first abnormal driving pattern according to the adjusted second threshold value; and

program code responsive to a determination that the current driving pattern is consistent with the first abnormal driving condition, operative to perform a selected one of the set of actions.

11. The apparatus as recited in claim 9, wherein the selected action is to perform a dialog with the vehicle driver designed to bring the vehicle driver into the normal biometric condition.

12. The apparatus as recited in claim 10, wherein the first abnormal biometric condition is a member of a plurality of inattentive conditions and the method further comprises selecting the dialog with the vehicle driver for the first abnormal biometric condition from a set of dialogs, each dialog of the set of dialogs designed to bring the vehicle driver to the normal biometric condition from a respective one of the plurality of inattentive conditions.

13. The apparatus as recited in claim 9, wherein the external factor data indicates a presence of a negative external factor and wherein the adjusting the threshold value for the first threshold between the normal biometric condition and the first abnormal biometric condition for the vehicle driver adjusts the value for the first biometric parameter to a higher value.

14. The apparatus as recited in claim 10, wherein the external factor data indicates a presence of a negative external factor and wherein the adjusting the threshold value for the second threshold between the normal driving pattern and the first abnormal driving pattern for the vehicle driver results in a greater range of current driving patterns determined to be a normal driving pattern.

15. A computer program product in a non-transitory computer readable storage medium for use in a data processing system, the computer program product holding computer program instructions executed by the data processing system for driving safety, the computer program instructions comprising:

program code, operative to gather a current set of biometric data of a vehicle driver from an Internet of Things (IoT) device during a driving phase, wherein the current set of biometric data comprises current values for dynamic biometric data indicating a biometric condition;

program code, operative to gather a set of external factor data from a cloud resource during the driving phase, wherein the set of external factor data comprises values for external factors that may impact vehicle driver performance;

program code, operative to adjust a threshold value for a first threshold between a normal biometric condition and a first abnormal biometric condition for the vehicle driver for a first biometric parameter according to the set of external factor data;

program code, operative to determine whether the gathered biometric data of the vehicle driver is consistent with the normal biometric condition or the first abnormal biometric condition according to the adjusted first threshold value; and

program code responsive to a determination that the gathered biometric data is consistent with the first abnormal biometric condition, operative to perform at least a selected one of a set of actions, the selected action designed to alleviate the first abnormal biometric condition.

16. The computer program product as recited in claim 15, further comprising:

program code, operative to gather a current driving pattern from a vehicle sensor during the driving phase;

program code, operative to adjust a threshold value for a second threshold between a normal driving pattern and a first abnormal driving pattern for the vehicle driver for according to the set of external factor data;

program code, operative to determine whether the current driving pattern of the vehicle driver is consistent with the normal driving pattern or the first abnormal driving pattern according to the adjusted second threshold value; and

program code responsive to a determination that the current driving pattern is consistent with the first abnormal driving condition, operative to perform a selected one of the set of actions.

17. The computer program product as recited in claim 15, wherein the selected action is to perform a dialog with the vehicle driver designed to bring the vehicle driver into the normal biometric condition.

18. The computer program product as recited in claim 15, wherein the first abnormal biometric condition is a member of a plurality of inattentive conditions and the method further comprises selecting the dialog with the vehicle driver for the first abnormal biometric condition from a set of dialogs, each dialog of the set of dialogs designed to bring the vehicle driver to the normal biometric condition from a respective one of the plurality of inattentive conditions.

19. The computer program product as recited in claim 15, wherein the external factor data indicates presence of a negative external factor and wherein the adjusting the threshold value for the first threshold between the normal biometric condition and the first abnormal biometric condition for the vehicle driver adjusts the value for the first biometric parameter to a higher value.

20. The computer program product as recited in claim 16, wherein the external factor data indicates a presence of a negative external factor and wherein the adjusting the threshold value for the second threshold between the normal driving pattern and the first abnormal driving pattern for the vehicle driver results in a greater range of current driving patterns determined to be a normal driving pattern.