US 12,236,374 B1
Enhanced dynamic last-mile modeling for delivery assistants
Rohit Malshe, Kirkland, WA (US); Liron David Yedidsion, Redmond, WA (US); Jin Ye, Kirkland, WA (US); and Dipal Patel Gupta, Issaquah, WA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Feb. 15, 2023, as Appl. No. 18/110,265.
Int. Cl. G06Q 10/047 (2023.01); G01C 21/34 (2006.01); G06Q 10/083 (2024.01)
CPC G06Q 10/047 (2013.01) [G01C 21/3438 (2013.01); G06Q 10/083 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method of optimizing a delivery route for a delivery vehicle driver and a delivery assistant, the method comprising:
identifying, by at least one processor of a first device, a delivery route for a delivery vehicle, the delivery route comprising multiple delivery locations to which packages are to be delivered from the delivery vehicle;
determining, by the at least one processor, for each of the packages, a first delivery time needed for a delivery vehicle driver of the delivery vehicle to deliver the respective package without the delivery assistant;
determining, by the at least one processor, for each of the packages, a second delivery time needed for a delivery assistant of the delivery vehicle to deliver the respective package without the delivery vehicle driver;
determining, by the at least one processor, for each of the packages, a third delivery time needed for both the delivery assistant and the delivery vehicle driver to travel together in the delivery vehicle to deliver the respective package;
determining, by the at least one processor, a meet up time for the delivery vehicle driver and the delivery assistant to meet up at the delivery vehicle after separate respective package deliveries;
determining, by the at least one processor, based on the first delivery time, the second delivery time, the third delivery time, and the meet up time, minimum times needed by the delivery vehicle driver and the delivery assistant to deliver the packages using the delivery route, wherein the minimum times needed comprise a split delivery time period during which the delivery vehicle driver delivers a first subset of the packages separately while the delivery assistant delivers a second subset of the packages;
generating, by the at least one processor, based on the minimum times needed, marginal delivery contribution times for the delivery vehicle driver and the delivery assistant to deliver the packages using the delivery route, the marginal delivery contribution times each comprising 3-tuples for which a first value of the 3-tuples is a respective value of the minimum times needed, a second value of the 3-tuples is indicative of the split delivery time, and a third value of the 3-tuples is indicative of a package of the first subset and the second subset;
generating, by the at least one processor, estimated total delivery times for the delivery vehicle driver and the delivery assistant to deliver the packages using the delivery route, based on a minimum of respective sums of respective marginal delivery contribution times of the marginal delivery contribution times and respective subsets of the packages, the respective subsets comprising the first subset and the second subset;
identifying, by the at least one processor, a minimum of the estimated total delivery times;
determining, by the at least one processor, that the minimum of the estimated total delivery times corresponds to a marginal delivery contribution time of the marginal delivery contribution times;
generating, by the at least one processor, based on determining that the minimum of the estimated total delivery times corresponds to the marginal delivery contribution time, the first subset and the second subset; and
causing presentation, by the at least one processor, at a second device, of a first indication that the delivery vehicle driver is to deliver the first subset, using the delivery route, separately from the delivery assistant while the delivery assistant delivers the second subset using the delivery route.