Method and system for vehicle-related driver characteristic determination

Abstract

A method for characterizing a user associated with a vehicle including collecting a movement dataset sampled at least at one of a location sensor and a motion sensor associated with the vehicle, during a time period associated with movement of the vehicle; extracting a set of movement features associated with movement of at least one of the user and the vehicle during the time period; and determining one or more user characteristics describing the user based on the set of movement features, wherein the one or more user characteristics include a classification of the user as at least one of a passenger and a driver for the time period associated with movement of the vehicle.

We claim: 
     
         1 . A method for characterizing a user associated with a vehicle, the method comprising:
 during a post-trip time period occurring after a trip, wherein a mobile device associated with the user is arranged within the vehicle during the trip:
 collecting a post-trip motion dataset with a motion sensor of the mobile device, wherein the post-trip motion dataset comprises turning data associated with the mobile device; 
   determining a set of post-trip movement features from the post-trip motion dataset, wherein the set of post-trip movement features comprises a turning radius of the mobile device;   classifying the user as one of a passenger and a driver during the trip based on the post-trip movement features; and   in an event that the user is classified as the driver, updating a driving parameter associated with the user.   
     
     
         2 . The method of  claim 1 , wherein the driving parameter comprises a driving risk score associated with the user. 
     
     
         3 . The method of  claim 1 , wherein the motion sensor is an accelerometer. 
     
     
         4 . The method of  claim 1 , further comprising determining an egress direction of the user exiting the vehicle based on the set of post-trip movement features, wherein the user is classified as one of the passenger and the driver based on the egress direction. 
     
     
         5 . The method of  claim 1 , further comprising collecting an in-trip dataset sampled at a set of sensors of the mobile device, wherein the in-trip dataset is collected during the trip. 
     
     
         6 . The method of  claim 5 , wherein the set of sensors comprises the motion sensor and a location sensor. 
     
     
         7 . The method of  claim 6 , wherein classifying the user as one of a passenger and a driver is further performed based on the in-trip dataset. 
     
     
         8 . The method of  claim 1 , wherein the vehicle is parked during the post-trip time period. 
     
     
         9 . The method of  claim 8 , wherein the user egresses the vehicle during the post-trip time period, and wherein an egress direction of the user is determined based on the set of post-trip movement features. 
     
     
         10 . The method of  claim 9 , wherein determining the egress direction based on the set of post-trip movement features comprises extracting the egress direction relative to a heading of the vehicle, wherein the heading of the vehicle is determined based on a set of vehicle motion features collected at the mobile device during the trip. 
     
     
         1 . method of  claim 1 , wherein classifying the user as one of a passenger and a driver is performed with a machine learning model trained based on a corpus of post-trip motion datasets collected from a population of users. 
     
     
         12 . The method of claim  11 , further comprising updating the model based on classifying the user as one of a passenger and a driver. 
     
     
         13 . A system for characterizing a user associated with a vehicle, the system comprising:
 a client application executable on a mobile device associated with the user, wherein the mobile device is arranged within the vehicle during a trip, wherein the client application:
 during a post-trip time period occurring after a trip, collects a post-trip motion dataset with a motion sensor of the mobile device, wherein the post-trip motion dataset comprises turning data associated with the mobile device; 
   a computing system in communication with the client application, wherein the computing system:
 determines a set of post-trip movement features from the post-trip motion dataset, wherein the set of post-trip movement features comprises a set of turning parameters associated with the mobile device; and 
 classifies the user as one of a passenger and a driver during the trip based on the set of turning parameters. 
   
     
     
         14 . The system of  claim 13 , wherein the computing system comprises a remote computing system arranged remote from the mobile device. 
     
     
         15 . The system of  claim 13 , wherein the motion sensor is an accelerometer. 
     
     
         16 . The system of  claim 13 , wherein the set of turning parameters comprises a turning radius of the mobile device. 
     
     
         17 . The system of  claim 13 , further comprising, in response to classifying the user as the driver, updating a driving parameter associated with the user. 
     
     
         13 . system of  claim 13 , wherein at least a portion of the computing system is arranged remote from the mobile device. 
     
     
         19 . The system of claim  18 , wherein a portion of the computing system is arranged onboard the mobile device. 
     
     
         20 . The system of  claim 13 , further comprising a trained model, wherein the computing system classifies the user as one of a passenger and a driver based on the trained model, and wherein the trained model is updated based on the classification and the post-trip motion dataset.