Augmenting transport services using driver profiling
View Patent ↗Trip is analyzed from a population of drivers in order to determine one or more indicators of one or more driving styles. The trip data may include sensor information obtained from one or more sensor devices which are present in a vehicle of each driver of the population. A driving style is determined for the driver during a monitored trip by analyzing sensor information obtained from one or more sensor devices of the driver during the trip for at least one of the indicators of the one or more driving styles.
1. A method for programmatically analyzing sensor data associated with a trip provided by a driver of a transport service to evaluate the driver, the method being implemented by one or more computer systems and comprising:
determining one or more indicators for each of one or more driving styles based on accumulated sensor data generated by and received from a plurality of driver computing devices for past trips of the transport service;
receiving, from a driver computing device of the driver, a set of on-trip sensor data generated by one or more sensors of the driver computing device during the trip provided by the driver for a passenger, wherein the set of on-trip sensor data includes data generated by one or more of an accelerometer, altimeter, global positioning system (GPS) resource, or gyroscope;
determining, for the driver, a driving style from the one or more driving styles based on the set of on-trip sensor data and the one or more indicators; and
in response to the determined driving style for the driver being a particular one of the one or more driving styles, implementing one or more remedial actions including suspending the driver from providing additional trips for the transport service for at least a period of time.
2. The method of claim 1 , wherein determining the one or more indicators includes determining one or more patterns of actions for an aggressive driving style, and wherein making the determination of the driving style for the driver during the trip includes analyzing the accumulated sensor data for a pattern of actions that correlate to the aggressive driving style.
3. The method of claim 2 , further comprising developing a model of the aggressive driving style based on the one or more patterns, and wherein making the determination of the driving style for the driver during the trip is based on the model.
4. The method of claim 1 , further comprising receiving a set of passenger data from a passenger computing device of the passenger to confirm the determination of the driving style for the driver during the trip.
5. The method of claim 3 , wherein developing the model is specific to a subset of drivers who drive within a city or geographic region of the driver.
6. The method of claim 1 , wherein determining the one or more indicators includes:
obtaining ground truth data by processing a subset of the accumulated sensor data that is generated by a subset of driver computing devices of the plurality of driver computing devices just before drivers associated with the subset of driver computing devices are involved in respective accidents; and
analyzing the ground truth data to identify the one or more indicators.
7. The method of claim 1 , wherein developing the one or more indicators includes identifying a subset of drivers each having one or more relevant driving incidents that are indicative of aggressive driving, and using a subset of the accumulated sensor data associated with the subset of drivers to determine the one or more indicators for an aggressive driving style.
8. The method of claim 1 , wherein developing the one or more indicators includes analyzing the accumulated sensor data corresponding to one or more of an accelerometer, altimeter, global positioning system (GPS) resource, or gyroscope of one or more of the plurality of driver computing devices.
9. The method of claim 1 , wherein determining, for the driver, a driving style from the one or more driving styles is based further on sensor data received from the passenger computing device.
10. The method of claim 1 , wherein determining, for the driver, a driving style from the one or more driving styles is based further on data generated by an On Board Diagnostic (“OBD”) device coupled to the driver's vehicle.
11. The method of claim 1 , further comprising interpreting the set of on-trip sensor data based on a route of the driver to determine one or more of (i) a lane change, (ii) a braking event, (iii) a traffic light event, (iv) a speeding event, or (v) a near collision.
12. A computer system for programmatically analyzing sensor data associated with a trip provided by a driver of a transport service to evaluate the driver during the trip, the computer system comprising:
a memory resource which store a set of instructions;
one or more processors which execute the set of instructions to:
determine, one or more indicators for each of one or more driving styles based on accumulated sensor data generated by and received from a plurality of driver computing devices for past trips of the transport service;
receive, from a driver computing device of the driver, a set of on-trip sensor data generated by one or more sensors of the driver computing device during the trip provided by the driver for a passenger, wherein the set of on-trip sensor data includes data generated by one or more of an accelerometer, altimeter, global positioning system (GPS) resource, or gyroscope;
determine, for the driver, a driving style from the one or more driving styles based on the set of on-trip sensor data and the one or more indicators; and
in response to the determined driving style for the driver being a particular one of the one or more driving styles, implement one or more remedial actions including suspending the driver from providing additional trips for the transport service for at least a period of time.
13. The computer system of claim 12 , wherein determining the one or more indicators includes determining one or more patterns of actions for an aggressive driving style, and wherein making the determination of the driving style for the driver during the trip includes analyzing the accumulated sensor data for a pattern of actions that correlate to the aggressive driving style.
14. The computer system of claim 12 , wherein developing the one or more indicators includes analyzing the accumulated sensor data corresponding to one or more of an accelerometer, altimeter, global positioning system (GPS) resource, or gyroscope of one or more of the plurality of driver computing devices.
15. The computer system of claim 12 , wherein determining, for the driver, a driving style from the one or more driving styles is based further on sensor data received from the passenger computing device.
16. A non-transitory computer-readable medium storing instructions that, when executed by one or more hardware processors of a computer system, cause the computer system to programmatically analyze sensor data associated with a trip provided by a driver of a transport service to evaluate the driver during the trip by:
determining one or more indicators for each of one or more driving styles based on accumulated sensor data generated by and received from a plurality of driver computing devices for past trips of the transport service;
receiving, from a driver computing device of the driver, a set of on-trip sensor data generated by one or more sensors of the driver computing device during the trip provided by the driver for a passenger, wherein the set of on-trip sensor data includes data generated by one or more of an accelerometer, altimeter, global positioning system (GPS) resource, or gyroscope;
determining, for the driver, a driving style from the one or more driving styles based on the set of on-trip sensor data and the one or more indicators; and
in response to the determined driving style for the driver being a particular one of the one or more driving styles, implementing one or more remedial actions including suspending the driver from providing additional trips for the transport service for at least a period of time.