CPC G06Q 10/08355 (2013.01) [G06N 5/04 (2013.01); G06N 7/01 (2023.01); G06N 20/00 (2019.01); G06N 20/10 (2019.01); G06N 20/20 (2019.01); G06Q 10/04 (2013.01); G06Q 10/047 (2013.01)] | 20 Claims |
1. A computer-implemented method comprising:
determining a plurality of candidate routes for a vehicle, wherein each respective candidate route (i) includes each waypoint of a same predetermined plurality of waypoints and (ii) specifies a corresponding ordering of the same predetermined plurality of waypoints;
generating, for each respective candidate route of the plurality of candidate routes, independent feature values for the respective candidate route based on the corresponding ordering of the same predetermined plurality of waypoints;
computing, for each respective candidate route and using a machine learning model, a corresponding score for the respective candidate route based on the independent feature values for the respective candidate route, wherein the machine learning model has been trained using a plurality of training samples each comprising (i) training independent feature values from a particular trip and (ii) a corresponding dependent score that represents an outcome of at least a portion of the particular trip;
ranking the plurality of candidate routes based on the respective score computed for each respective candidate route; and
providing a representation of at least one candidate route based on the ranking of the plurality of candidate routes.
|