US 12,066,297 B2
Systems and methods for personalized route prediction
Fling Finn Tseng, Ann Arbor, MI (US); Shiqi Qiu, Canton, MI (US); Dimitar Filev, Novi, MI (US); Johannes Geir Kristinsson, Ann Arbor, MI (US); Nikhil Jamdade, Dearborn, MI (US); Swati Rawat, Mississauga (CA); Kalyani Sonawane, Plymouth, MI (US); Himanshu Verma, Farmington Hills, MI (US); and Bhagyashri Katti, Novi, MI (US)
Assigned to Ford Global Technologies, LLC, Dearborn, MI (US)
Filed by Ford Global Technologies, LLC, Dearborn, MI (US)
Filed on Jan. 14, 2022, as Appl. No. 17/648,051.
Prior Publication US 2023/0228582 A1, Jul. 20, 2023
Int. Cl. G01C 21/34 (2006.01); G06N 20/00 (2019.01)
CPC G01C 21/3484 (2013.01) [G06N 20/00 (2019.01); G01C 21/3492 (2013.01)] 14 Claims
OG exemplary drawing
 
1. A system comprising:
a processor; and
a memory storing computer-executable instructions, that when executed by the processor, cause the processor to:
receive, at a first time, first input data associated with a first route traversed by a vehicle;
populate a first database with the input data;
receive, at a third time, second input data associated with a second route traversed by the vehicle;
compare the second input data to the first input data included within the first database;
determine, based on the comparison, a first cluster including the first data and the second input data or a second cluster including the second input data;
populate a second database based on the first cluster or the second cluster;
determine, using the first database and at a second time, at least one of: predicted departure data, predicted destination data, and/or predicted route data; and
cause, based on the predicted departure data, predicted destination data, and/or predicted route data, to perform an action in association with the vehicle,
wherein determining the predicted departure data, predicted destination data, and/or predicted route data is based on a first type of prediction and a second type of prediction, the first type of prediction being based on a relative frequency and the second type of prediction being based on a Poisson parameter, and
wherein determining the predicted departure data, predicted destination data, and/or predicted route data further comprises:
determining a first probability based on the first type of prediction and a second probability based on the second type of prediction;
determining a first weighted sum of the first probability and a second weighted sum of the second probability; and
determining a third probability based on a combination of the first probability and the second probability.