US 11,727,345 B1
Integrated multi-location scheduling, routing, and task management
Patrick Miller Coughran, Tucson, AZ (US); Douglas David Coughran, IV, Tucson, AZ (US); Evan Fields, Cambridge, MA (US); Rany Polany, Foster City, CA (US); Raimundo Onetto, Walnut Creek, CA (US); Nathalie Saade, Berkeley, CA (US); Nasser Mohamed, Oakland, CA (US); and Aurelio de Padua Gandra, Sao Paulo (BR)
Assigned to Descartes Systems (USA) LLC, Atlanta, GA (US)
Filed by Descartes Systems (USA) LLC, Atlanta, GA (US)
Filed on Mar. 22, 2021, as Appl. No. 17/208,708.
Application 17/208,708 is a continuation of application No. 15/238,708, filed on Aug. 16, 2016, granted, now 10,956,855.
Claims priority of provisional application 62/259,295, filed on Nov. 24, 2015.
Claims priority of provisional application 62/219,608, filed on Sep. 16, 2015.
Claims priority of provisional application 62/205,727, filed on Aug. 16, 2015.
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 5/04 (2023.01); G06N 7/00 (2023.01); G06Q 10/08 (2023.01); G06N 20/00 (2019.01); G06N 20/10 (2019.01); G06N 20/20 (2019.01); G06Q 10/04 (2023.01); G06Q 10/0835 (2023.01); G06Q 10/047 (2023.01); G06N 7/01 (2023.01)
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
OG exemplary drawing
 
1. A computer-implemented method comprising:
obtaining route data representing a current route of a vehicle, wherein the route data specifies (i) an ordering of a set of waypoints and (ii) for each waypoint in the set of waypoints, a respective task to be completed at the waypoint at a respective time according to the ordering of the set of waypoints;
obtaining real-time trip data representing a completed portion of the current route, the completed portion comprising a proper subset of the set of waypoints to which the vehicle has already travelled, the real-time trip data comprising driver data representing a behavior of a driver of the vehicle during the completed portion of the current route;
determining, from the real-time trip data, to update the current route of the vehicle;
determining a plurality of candidate updated routes, wherein each candidate updated route specifies: (i) a respective reordering of the waypoints in the set of waypoints that are not in the proper subset, wherein each respective reordering is different from the ordering corresponding to the current route, and (ii) for each waypoint in the set of waypoints that is not in the proper subset, a respective time at which the respective task of the waypoint is to be completed according to the respective reordering specified by the candidate updated route;
generating, for each respective candidate updated route of the plurality of candidate updated routes, independent feature values for the candidate updated route based on the respective reordering of the waypoints specified by the candidate updated route;
computing, for each candidate updated route and using a machine learning model, a respective score for the candidate updated route based on the independent feature values for the candidate updated route, wherein the machine learning model has been trained using a plurality of training examples 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 updated routes based on the respective score computed for each candidate updated route; and
providing a representation of at least one candidate updated route based on ranking the plurality of candidate updated routes.