Driver identification among a limited pool of potential drivers
First Claim
1. A method of identifying a driver in the presence of vehicle telematics data from multiple data collection devices, the method comprising:
- retrieving, by a server and from a vehicle telematics database, historical vehicle telematics data including (i) first historical vehicle telematics data known to correspond to one or more trips driven by a first person, and (ii) second historical vehicle telematics data known to correspond to one or more trips driven by a second person, wherein the first historical vehicle telematics data and the second historical vehicle telematics data are indicative of a plurality of driving behaviors for the first person and the second person, respectively;
generating, by the server and based upon both the first historical vehicle telematics data and the second historical vehicle telematics data, a custom statistical model specific to the first person and the second person, wherein the custom statistical model (i) gives greater weight to those driving behaviors, of the plurality of driving behaviors, having greater predictive power with respect to distinguishing driving by the first person from driving by the second person, and (ii) gives less or no weight to those driving behaviors, of the plurality of driving behaviors, having less or no predictive power with respect to distinguishing driving by the first person from driving by the second person;
receiving, at the server, first vehicle telematics data collected by a first data collection device during a first trip;
receiving, at the server, second vehicle telematics data collected by a second data collection device during the first trip;
determining, by the server, one or both of (i) a first measure indicating likelihood that the first trip was driven by the first person, and (ii) a second measure indicating likelihood that the first trip was driven by the second person, at least in part by processing one or both of the first vehicle telematics data and the second vehicle telematics data according to the custom statistical model; and
based upon one or both of the first measure and the second measure, assigning, by the server, the first trip to either the first person or the second person.
1 Assignment
0 Petitions
Accused Products
Abstract
Historical vehicle telematics data, corresponding to trips known to have been driven by specific persons within a limited pool of potential drivers, may be processed to generate a statistical model that is customized for those persons. Once generated, the custom statistical model may be used to process vehicle telematics data from trips where it is known that the driver was one of the drivers in the pool of drivers, but the specific identify of the driver is not known. Because the statistical model is specifically optimized or designed to distinguish among the drivers in the pool, the model may be more accurate than universal driver identification models.
22 Citations
20 Claims
-
1. A method of identifying a driver in the presence of vehicle telematics data from multiple data collection devices, the method comprising:
-
retrieving, by a server and from a vehicle telematics database, historical vehicle telematics data including (i) first historical vehicle telematics data known to correspond to one or more trips driven by a first person, and (ii) second historical vehicle telematics data known to correspond to one or more trips driven by a second person, wherein the first historical vehicle telematics data and the second historical vehicle telematics data are indicative of a plurality of driving behaviors for the first person and the second person, respectively; generating, by the server and based upon both the first historical vehicle telematics data and the second historical vehicle telematics data, a custom statistical model specific to the first person and the second person, wherein the custom statistical model (i) gives greater weight to those driving behaviors, of the plurality of driving behaviors, having greater predictive power with respect to distinguishing driving by the first person from driving by the second person, and (ii) gives less or no weight to those driving behaviors, of the plurality of driving behaviors, having less or no predictive power with respect to distinguishing driving by the first person from driving by the second person; receiving, at the server, first vehicle telematics data collected by a first data collection device during a first trip; receiving, at the server, second vehicle telematics data collected by a second data collection device during the first trip; determining, by the server, one or both of (i) a first measure indicating likelihood that the first trip was driven by the first person, and (ii) a second measure indicating likelihood that the first trip was driven by the second person, at least in part by processing one or both of the first vehicle telematics data and the second vehicle telematics data according to the custom statistical model; and based upon one or both of the first measure and the second measure, assigning, by the server, the first trip to either the first person or the second person. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A server comprising:
-
one or more processors; and a memory storing instructions that, when executed by the server, cause the server to retrieve, from a vehicle telematics database, historical vehicle telematics data including (i) first historical vehicle telematics data known to correspond to one or more trips driven by a first person, and (ii) second historical vehicle telematics data known to correspond to one or more trips driven by a second person, wherein the first historical vehicle telematics data and the second historical vehicle telematics data are indicative of a plurality of driving behaviors for the first person and the second person, respectively, generate, based upon both the first historical vehicle telematics data and the second historical vehicle telematics data, a custom statistical model specific to the first person and the second person, wherein the custom statistical model (i) gives greater weight to those driving behaviors, of the plurality of driving behaviors, having greater predictive power with respect to distinguishing driving by the first person from driving by the second person, and (ii) gives less or no weight to those driving behaviors, of the plurality of driving behaviors, having less or no predictive power with respect to distinguishing driving by the first person from driving by the second person, receive first vehicle telematics data collected by a first data collection device during a first trip, receive second vehicle telematics data collected by a second data collection device during the first trip, determine one or both of (i) a first measure indicating likelihood that the first trip was driven by the first person, and (ii) a second measure indicating likelihood that the first trip was driven by the second person, at least in part by processing one or both of the first vehicle telematics data and the second vehicle telematics data according to the custom statistical model, and based upon one or both of the first measure and the second measure, assign the first trip to either the first person or the second person. - View Dependent Claims (10, 11, 12)
-
-
13. A method of identifying a driver given a limited pool of potential drivers, the method comprising:
-
identifying, by a server, a plurality of persons that may potentially be driving while a particular data collection device collects vehicle telematics data; retrieving, by the server and from a vehicle telematics database, a plurality of sets of historical vehicle telematics data each known to correspond to one or more trips driven by a respective one of the plurality of persons, wherein each set of the plurality of sets of historical vehicle telematics data is indicative of a plurality of driving behaviors for the respective one of the plurality of persons; generating, by the server and based upon the plurality of sets of historical vehicle telematics data, a custom statistical model specific to the plurality of persons, wherein the custom statistical model (i) gives greater weight to those driving behaviors, of the plurality of driving behaviors, having greater predictive power with respect to distinguishing driving by different persons among the plurality of persons, and (ii) gives less or no weight to those driving behaviors, of the plurality of driving behaviors, having less or no predictive power with respect to distinguishing driving by different persons among the plurality of persons; receiving, at the server, a first set of vehicle telematics data collected by the particular data collection device during a first trip; determining, by the server, at least a first measure indicating likelihood that the first trip was driven by a first person of the plurality of persons, at least in part by processing the first set of vehicle telematics data according to the custom statistical model; and based upon at least the first measure, assigning, by the server, the first trip to either (i) the first person, or (ii) a different one of the plurality of persons or a category of persons that does not include the first person. - View Dependent Claims (14, 15, 16, 17, 18, 19, 20)
-
Specification