US 12,387,572 B2
Monitoring and predicting physical force attacks on transaction terminals
Jodessiah Sumpter, Alpharetta, GA (US); Christopher John Costello, Suwanee, GA (US); Matthew Robert Burris, Lawrenceville, GA (US); Gregory Joseph Hartl, Atlanta, GA (US); and Caleb Wayne Martinez, Fayetteville, GA (US)
Assigned to NCR Atleos Corporation, Atlanta, GA (US)
Filed by NCR Atleos Corporation, Atlanta, GA (US)
Filed on Dec. 19, 2023, as Appl. No. 18/545,727.
Application 18/545,727 is a continuation of application No. 17/732,889, filed on Apr. 29, 2022, granted, now 11,881,089.
Application 17/732,889 is a continuation in part of application No. 17/665,021, filed on Feb. 4, 2022, granted, now 11,676,460.
Prior Publication US 2024/0119810 A1, Apr. 11, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G07F 19/00 (2006.01); G06Q 20/10 (2012.01); G06V 10/75 (2022.01); G06V 20/40 (2022.01); G06V 20/62 (2022.01)
CPC G07F 19/207 (2013.01) [G06Q 20/1085 (2013.01); G06V 10/75 (2022.01); G06V 20/44 (2022.01); G06V 20/625 (2022.01)] 12 Claims
OG exemplary drawing
 
1. A method, comprising:
obtaining real-time video depicting an area having a terminal;
analyzing the real-time video for depictions of a vehicle and objects associated with the use of brute force;
providing factors associated with the analyzing to a machine learning model (MLM) and receiving a confidence value as output from the MLM, wherein the factors include features derived from the real-time video associated with the vehicle, the objects, and an individual associated with the vehicle and the objects, and wherein the factors further include a total number of past brute force attacks in the area and a severity level associated with each past brute force attack; and
sending an alert when the confidence value exceeds a threshold.