US 12,112,329 B2
Image-based authorization systems
Elizabeth M. Shoup, Mechanicsville, VA (US); Caroline Harriott, Richmond, VA (US); Imani Holmes, Richmond, VA (US); Joshua Edwards, Philadelphia, PA (US); and Yingli Sieh, Cambridge, MA (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Aug. 16, 2022, as Appl. No. 17/888,970.
Prior Publication US 2024/0062210 A1, Feb. 22, 2024
Int. Cl. G06Q 40/00 (2023.01); G06Q 20/38 (2012.01); G06Q 20/40 (2012.01); G06T 7/70 (2017.01); G06V 20/50 (2022.01)
CPC G06Q 20/4015 (2020.05) [G06Q 20/382 (2013.01); G06T 7/70 (2017.01); G06V 20/50 (2022.01); G06T 2207/20081 (2013.01); G06V 2201/07 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, by a first computing device and from a second computing device, a request, associated with a user account, to approve a transaction;
receiving, from a database, a message indicating that the user account is subject to a transaction category restriction;
processing the request to identify, based on data in the request, that the transaction belongs to a first category;
transmitting, to a third computing device and based on a determination that approving a transaction of the first category violates the transaction category restriction, a declination of the request;
causing, after the request is declined and on a graphical user interface associated with a user device, output of:
a plurality of user selectable options, each associated with a respective transaction category; and
an instruction to take one or more photos that depict a physical environment where the transaction is requested;
receiving, from the user device;
the one or more photos; and
a selection, of one of the plurality of user selectable options, that indicates the transaction belonging to a second category;
providing, to a machine learning model, the one or more photos;
receiving, as output from the machine learning model, a prediction of one or more times of day when the one or more photos were taken;
processing, using one or more object recognition algorithms and based on the one or more times of day satisfying a threshold, the one or more photos to identify one or more objects in the physical environment where the transaction is requested;
determining, based on comparing the one or more objects to one or more reference objects associated with the second category, that the transaction belongs to the second category, wherein the second category is different from the first category; and
transmitting, to the third computing device and based on a determination that approving a transaction of the second category does not violate the transaction category restriction, an approval of the transaction.