US 11,893,617 B2
Systems and methods of application of machine learning to traffic data for vehicle recommendation
Chih-Hsiang Chow, Plano, TX (US); Elizabeth Furlan, Plano, TX (US); and Steven Dang, Plano, TX (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Sep. 20, 2021, as Appl. No. 17/448,098.
Application 17/448,098 is a continuation of application No. 16/903,750, filed on Jun. 17, 2020, granted, now 11,151,633.
Prior Publication US 2022/0005100 A1, Jan. 6, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 30/00 (2023.01); G06Q 30/0601 (2023.01); G08G 1/017 (2006.01); G06Q 30/018 (2023.01); G06Q 10/087 (2023.01); G01C 21/34 (2006.01); G06N 20/00 (2019.01); G06N 5/04 (2023.01); G01C 21/28 (2006.01); G06Q 30/08 (2012.01)
CPC G06Q 30/0631 (2013.01) [G01C 21/28 (2013.01); G01C 21/3492 (2013.01); G06N 5/04 (2013.01); G06N 20/00 (2019.01); G06Q 10/087 (2013.01); G06Q 30/018 (2013.01); G06Q 30/08 (2013.01); G08G 1/0175 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for providing product recommendations based on traffic camera data, the method comprising:
acquiring, by one or more processors, traffic data from a plurality of traffic cameras;
determining, by the one or more processors using one or more machine learning models, vehicle information based on the traffic data from the plurality of traffic cameras, wherein the one or more machine learning models analyze the traffic data to identify the vehicle information;
selecting, by the one or more processors, at least one available product for purchase, wherein the at least one available product matches one or more predetermined requirements based on the determined vehicle information; and
transmitting, by the one or more processors, a recommendation to a user based on the selected at least one available product for purchase.