	US 12,105,795 B2
	Computer-based systems configured for utilization of a trained detection machine learning model for activity determination and methods of use thereof
Joshua Edwards, Philadelphia, PA (US); Asher Smith-Rose, Midlothian, VA (US); Tyler Maiman, Melville, NY (US); and Shabnam Kousha, Washington, DC (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Aug. 24, 2022, as Appl. No. 17/894,922.
Prior Publication US 2024/0073258 A1, Feb. 29, 2024
Int. Cl. G06F 21/55 (2013.01); G06N 20/00 (2019.01); H04L 9/40 (2022.01); H04L 65/1076 (2022.01); H04L 65/1104 (2022.01)

CPC G06F 21/55 (2013.01) [G06N 20/00 (2019.01); H04L 63/1483 (2013.01); H04L 65/1076 (2013.01); H04L 65/1104 (2022.05)]

20 Claims

1. A computer-implemented method comprising:

instructing, by at least one processor of a first computing device, a second computing device associated with a user, to obtain, via at least one graphical user interface (GUI) having at least one programmable GUI element, a permission from the user to monitor a plurality of activities executed within the second computing device;

instructing, by the at least one processor of the first computing device, in response to obtaining the permission from the user, the second computing device to monitor the plurality of activities executed within the second computing device for a predetermined period of time;

receiving, by the at least one processor of the first computing device, from the second computing device, an indication of an incoming interaction session being initiated with the user within the predetermined period of time;

automatically verifying, by the at least one processor of the first computing device, from the second computing device, at least one session interaction parameter associated with the incoming interaction session to identify the incoming interaction session as a suspect interaction session;

determining, by the at least one processor of the first computing device, when a duration of time associated with the suspect interaction session meets or exceeds a predetermined duration threshold;

utilizing, by the at least one processor of the first computing device, a trained detection machine learning model, when the duration of time associated with the suspect interaction session meets or exceeds the predetermined duration threshold, to identify at least one future activity subsequent to the suspect interaction session based on at least one first pre-determined type activity that is associated with the user and identified within the duration of time of the suspect interaction session; and

automatically instructing, by the at least one processor of the first computing device, the first computing device to halt the at least one future activity, based on the at least one session interaction parameter of the suspect interaction session and at least one pre-determined trigger parameter.