US 11,954,990 B2
Artificial intelligence (AI)-based security systems for monitoring and securing physical locations
George Anthony Albero, Charlotte, NC (US); Nathalie Elizabeth Conley, Jacksonville, FL (US); Elizabeth Jordan Knight, Clover, SC (US); Lauren Thanh Nguyen-Lo, Houston, TX (US); and Robert Jon Armstrong, Charlotte, NC (US)
Assigned to Bank of America Corporation, Charlotte, NC (US)
Filed by Bank of America Corporation, Charlotte, NC (US)
Filed on Jun. 23, 2021, as Appl. No. 17/356,151.
Prior Publication US 2022/0415149 A1, Dec. 29, 2022
Int. Cl. G08B 13/22 (2006.01); G06N 3/08 (2023.01); G06V 20/52 (2022.01); G07C 9/00 (2020.01)
CPC G08B 13/22 (2013.01) [G06N 3/08 (2013.01); G06V 20/52 (2022.01); G07C 9/00309 (2013.01); G07C 2009/00476 (2013.01)] 18 Claims
OG exemplary drawing
 
1. An artificial intelligence (AI)-based system for monitoring and securing a retail banking physical location, the system comprising:
one or more video cameras at the physical location;
one or more actuators associated with security systems at the physical location;
an electronic monitoring platform communicatively coupled to the one or more video cameras and the one or more actuators, the electronic monitoring platform comprising:
at least one processor;
a communication interface communicatively coupled to the at least one processor; and
memory storing computer-readable instructions that, when executed by the at least one processor, cause the electronic monitoring platform to:
receive, from the one or more video cameras and via the communication interface, videos associated with the physical location;
identify, based on the videos, speech and movement patterns associated with a plurality of individuals at the physical location;
train, based on the speech and the movement patterns associated with the plurality of individuals, an AI model to recognize:
normal movement patterns and normal speech, wherein the training the AI model to recognize normal movement patterns and normal speech comprises performing a cluster analysis to group normal movement patterns and normal speech, and
anomalous movement patterns and anomalous speech outside the grouped normal movement patterns and normal speech;
identify, based on the videos, speech and a movement pattern associated with an individual;
determine, based on the AI model, that the speech and the movement pattern associated with the individual is anomalous, wherein the determining that the speech and movement pattern associated with the individual is anomalous is based on determining that the movement pattern and the speech associated with the individual is outside the grouped normal movement patterns and normal speech; and
based on the determining:
send, via the communication interface, one or more notifications to the one or more actuators, wherein at least one actuator of the one or more actuators is associated with a vault in the physical location, and wherein the actuator causes the vault to lock based on receiving a notification, and
send, via the communication interface, an alert notification to a computing device.