Integrated multi-location scheduling, routing, and task management

A system comprising one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations 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.

A non-transitory computer-readable medium having stored thereon instructions that, when executed by a computing system, cause the computing system to perform operations 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.