Driver log analytics system
View Patent ↗Aspects of notification of a predicted driving event include receiving driver log information associated with one or more drivers respectively corresponding to one or more vehicles, and aggregating the driver log information for a predetermined time period. Further, the aspects include extracting derivations from the aggregated driver log information in accordance with one or more derivation rules associated with an event prediction model operable to predict an adverse driving event. Also, the aspects include applying the event prediction model to the derivations to generate an adverse driver event prediction for each of the one or more drivers. Additionally, the aspects include transmitting a notification message including one or more of the adverse driver event predictions.
1. A method of notification of a predicted driving event, comprising:
generating or modifying, by a processor, an event prediction model based on driver log information, from a first predetermined time period, and associated with a corresponding historical adverse driving event;
receiving, by the processor via a transceiver, driver log information associated with one or more drivers respectively corresponding to one or more vehicles;
aggregating, by the processor, the driver log information for a second predetermined time period;
extracting, by the processor, derivations from the aggregated driver log information in accordance with one or more derivation rules associated with the event prediction model operable to predict an adverse driving event;
applying, by the processor, the event prediction model to the derivations to generate an adverse driver event prediction for each of the one or more drivers; and
transmitting, by the processor via the transceiver, a notification message including one or more of the adverse driver event predictions,
wherein the first predetermined time period and the second predetermined time period are different time periods.
2. The method of claim 1 , wherein the driver log information includes one or more log codes indicating one or more of:
whether one of the one or more drivers is driving at a sampled time point,
whether the driver is on duty but not driving at the sampled time point,
whether the driver is resting at the sampled time point, and
whether the driver is off duty at the sampled time point.
3. The method of claim 1 , wherein the derivations include:
a first number of hours that one of the one or more drivers rests in a first time period during a week,
a second number of times that the driver violates rules or regulations,
a third number of times that the driver had sufficient hours of rest during the week, and
a fourth number of times that the driver did not have at least ten hours off duty in any day in the week.
4. The method of claim 1 , wherein the adverse driver event includes one of a preventable accident, or a severe accident, or a traffic rule violation, or an hours-of-service violation.
5. The method of claim 1 , further comprising ranking, by the processor, the one or more drivers in accordance with a value of the confidence factor.
6. The method of claim 1 , further comprising triggering, by the processor, a remedial measure for at least one of the one or more drivers based on a value of the confidence factor.
7. The method of claim 1 , wherein extracting the derivations further comprises extracting a subset of at least one of the driver log information and aggregated driver log information that indicate that a respective driver is in danger of violating a government-based or fleet operator-based traffic rule.
8. The method of claim 1 , wherein extracting the derivations further comprises extracting a subset of at least one of the driver log information and aggregated driver log information that indicate that a respective driver is in danger of violating a government-based or fleet operator-based hours-of-service regulation.
9. The method of claim 1 , wherein each adverse driver event prediction includes a confidence factor that indicates a likelihood of whether each of the one or more drivers will experience the adverse driving event in a subsequent time period.
10. A non-transitory computer-readable medium storing code for notification of a predicted driving event, the code comprising instructions executable to:
generate or modify an event prediction model based on driver log information, from a first predetermined time period, and associated with a corresponding historical adverse driving event;
receive driver log information associated with one or more drivers respectively corresponding to one or more vehicles;
aggregate the driver log information for a second predetermined time period;
extract derivations from the aggregated driver log information in accordance with one or more derivation rules associated with the event prediction model operable to predict an adverse driving event;
apply the event prediction model to the derivations to generate an adverse driver event prediction for each of the one or more drivers; and
transmit a notification message including one or more of the adverse driver event predictions,
wherein the first predetermined time period and the second predetermined time period are different.
11. The non-transitory computer-readable medium of claim 10 , wherein the adverse driver event includes one of a preventable accident, or a severe accident, or a traffic rule violation, or an hours-of-service violation.
12. An apparatus for notification of a predicted driving event, comprising:
a memory configured to store instructions;
a processor communicatively coupled with the memory, the processor configured to execute the instructions to:
generate or modify an event prediction model based on driver log information, from a first predetermined time period, and associated with a corresponding historical adverse driving event;
receive driver log information associated with one or more drivers respectively corresponding to one or more vehicles;
aggregate the driver log information for a second predetermined time period;
extract derivations from the aggregated driver log information in accordance with one or more derivation rules associated with the event prediction model operable to predict an adverse driving event;
apply the event prediction model to the derivations to generate an adverse driver event prediction for each of the one or more drivers; and
transmit a notification message including one or more of the adverse driver event predictions,
wherein the first predetermined time period and the second predetermined time period are different.
13. The apparatus of claim 12 , wherein the driver log information includes one or more log codes indicating one or more of:
whether one of the one or more drivers is driving at a sampled time point,
whether the driver is on duty but not driving at the sampled time point,
whether the driver is resting at the sampled time point, and
whether the driver is off duty at the sampled time point.
14. The apparatus of claim 12 , wherein the derivations include:
a first number of hours that one of the one or more drivers rests in a first time period during a week,
a second number of times that the driver violates rules or regulations,
a third number of times that the driver had sufficient hours of rest during the week, and
a fourth number of times that the driver did not have at least ten hours off duty in any day in the week.
15. The apparatus of claim 12 , wherein the adverse driver event includes one of a preventable accident, or a severe accident, or a traffic rule violation, or an hours-of-service violation.
16. The apparatus of claim 12 , wherein the processor is further configured to execute the instructions to rank the one or more drivers in accordance with a value of the confidence factor.
17. The apparatus of claim 12 , wherein the processor is further configured to execute the instructions to trigger a remedial measure for at least one of the one or more drivers based on a value of the confidence factor.
18. The apparatus of claim 12 , wherein the extract the derivations further comprises extracting a subset of at least one of the driver log information and aggregated driver log information that indicate that a respective driver is in danger of violating a government-based or fleet operator-based traffic rule.
19. The apparatus of claim 12 , wherein the extract the derivations further comprises extracting a subset of at least one of the driver log information and aggregated driver log information that indicate that a respective driver is in danger of violating a government-based or fleet operator-based hours-of-service regulation.
20. The apparatus of claim 12 wherein each adverse driver event prediction includes a confidence factor that indicates a likelihood of whether each of the one or more drivers will experience the adverse driving event in a subsequent time period.