System and method for determining driving patterns using telematics data
First Claim
1. A method for determining a driving pattern from raw telematics data originated from a client computing device in a vehicle, the method comprising:
- removing, by one or more processors, a gravitational data component from the telematics data in a first primary movement window of a vehicle trip leaving a vector defined by a longitudinal data component and a latitudinal data component in a longitudinal-latitudinal plane, wherein the first primary movement window is indicative of the client computing device being static with respect to movement of the vehicle, and wherein each of the longitudinal data component and the latitudinal data component has two acceleration effects;
combining, by the one or more processors, the longitudinal data component and the latitudinal data component to create an angular average of four times the directions of all vectors in the longitudinal-latitudinal plane such that all four acceleration effects of the plurality of telematics data are in one direction;
generating, by the one or more processors, one or more yaw angle estimates from the primary movement window of the vehicle trip using the angular average;
determining, by the one or more processors, a driving pattern using at least one of the yaw angle estimates.
1 Assignment
0 Petitions
Accused Products
Abstract
A computer implemented method for determining a driving pattern from raw telematics data is presented. A data server may receive, via a computer network, a plurality of telematics data corresponding to a trip of a vehicle, wherein the plurality of telematics data originates from a client computing device. The data server may also identify a first primary movement window of the vehicle trip and one or more constant speed and idling windows of the vehicle trip. The data server may further estimate gravity from the telematics data in the first primary movement window of the vehicle trip and generate a pitch and a roll angle from the first primary movement window of the vehicle trip, as well as one or more yaw angle estimates from the first primary movement window of the vehicle trip. The data server may further determine a driving pattern using at least constant speed times, idling times, acceleration, breaking, vehicle turns and relate that to estimate driving risk and insurance premium.
50 Citations
17 Claims
-
1. A method for determining a driving pattern from raw telematics data originated from a client computing device in a vehicle, the method comprising:
-
removing, by one or more processors, a gravitational data component from the telematics data in a first primary movement window of a vehicle trip leaving a vector defined by a longitudinal data component and a latitudinal data component in a longitudinal-latitudinal plane, wherein the first primary movement window is indicative of the client computing device being static with respect to movement of the vehicle, and wherein each of the longitudinal data component and the latitudinal data component has two acceleration effects; combining, by the one or more processors, the longitudinal data component and the latitudinal data component to create an angular average of four times the directions of all vectors in the longitudinal-latitudinal plane such that all four acceleration effects of the plurality of telematics data are in one direction; generating, by the one or more processors, one or more yaw angle estimates from the primary movement window of the vehicle trip using the angular average; determining, by the one or more processors, a driving pattern using at least one of the yaw angle estimates. - View Dependent Claims (2, 3, 4, 5, 6)
-
-
7. A computer device for determining a driving pattern from raw telematics data originated from a client computing device in a vehicle, the computer device comprising:
-
one or more processors; and one or more memories coupled to the one or more processors; the one or more memories including non-transitory computer executable instructions stored therein that, when executed by the one or more processors, cause the one or more processors to; remove a gravitational data component from the telematics data in a first primary movement window of a vehicle trip leaving a vector defined by a longitudinal data component and a latitudinal data component in a longitudinal-latitudinal plane, wherein the first primary movement window is indicative of the client computing device being static with respect to movement of the vehicle, and wherein each of the longitudinal data component and the latitudinal data component has two acceleration effects; combine the longitudinal data component and the latitudinal data component to create an angular average of four times the directions of all vectors in the longitudinal-latitudinal plane such that all four acceleration effects of the plurality of telematics data are in one direction; generate, using the angular average, one or more yaw angle estimates from the first primary movement window of the vehicle trip; and determine a driving pattern based on at least one of the yaw angle estimates. - View Dependent Claims (8, 9, 10, 11)
-
-
12. A non-transitory computer readable storage medium having instructions stored thereon for determining a driving pattern from raw telematics data originated from a client computing device in a vehicle, the instructions when executed on one or more processors cause the one or more processors to:
-
remove a gravitational data component from the telematics data in a first primary movement window of a vehicle trip leaving a vector defined by a longitudinal data component and a latitudinal data component in a longitudinal-latitudinal plane, wherein the first primary movement window is indicative of the client computing device being static with respect to movement of the vehicle, and wherein each of the longitudinal data component and the latitudinal data component has two acceleration effects; combine the longitudinal data component and the latitudinal data component to create an angular average of four times the directions of all vectors in the longitudinal-latitudinal plane such that all four acceleration effects of the plurality of telematics data are in one direction; generate, using the angular average, one or more yaw angle estimates from the first primary movement window of the vehicle trip using the created function without determining which data component corresponds with which acceleration effect; and determine a driving pattern based on at least one of the yaw angle estimates. - View Dependent Claims (13, 14, 15, 16, 17)
-
Specification