US 11,852,495 B1
Computational model for creating personalized routes based at least in part upon predicted total cost of claim frequency or severity
Kenneth Jason Sanchez, San Francisco, CA (US)
Assigned to BlueOwl, LLC, San Francisco, CA (US)
Filed by BlueOwl, LLC, San Francisco, CA (US)
Filed on May 26, 2020, as Appl. No. 16/883,436.
Int. Cl. G01C 21/34 (2006.01); G06Q 50/26 (2012.01); G06Q 40/08 (2012.01); G01C 21/36 (2006.01); G06N 3/08 (2023.01); G06N 3/044 (2023.01)
CPC G01C 21/3484 (2013.01) [G01C 21/3461 (2013.01); G01C 21/3691 (2013.01); G06N 3/044 (2023.01); G06N 3/08 (2013.01); G06Q 40/08 (2013.01); G06Q 50/265 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for determining personalized risk associated with a driving route, the computer-implemented method comprising:
receiving, by one or more processors, a trained machine learning model to determine base risk values associated with road segments, wherein the trained machine learning model is trained using labeled training data indicative of risk associated with operation of vehicles, wherein the trained machine learning model includes one or more weights for at least one input selected from a group consisting of a road type and a road condition, and a road driving behavior;
obtaining, by the one or more processors, a personalized driver profile corresponding to a driver, the personalized driver profile being based at least in part upon vehicle telematics data indicative of operation of one or more vehicles by the driver;
receiving, by the one or more processors, via an electronic computing device corresponding to the driver, an indication of one or more driving routes corresponding to the driver, each of the one or more driving routes comprising a respective plurality of road segments;
determining, by the one or more processors, for each of the one or more routes, a respective personalized risk value associated with the respective route, at least by processing the plurality of road segments using the trained machine learning model and the personalized driver profile; and
causing, via the one or more processors, for at least one of the one or more routes, an indication of the respective personalized risk value of the route to be displayed at a graphical user interface of the electronic computing device.