US 12,131,613 B2
Surveillance system for data centers and other secure areas
Chandrakantha Reddy, Bangalore (IN); Deepthi Sethuraman, Bengaluru (IN); Lalitha M. Eswara, Bengaluru (IN); Srikanth Nagaraj, Bangalore (IN); and Umesh Hosamani, Bangalore (IN)
Assigned to HONEYWELL INTERNATIONAL INC., Charlotte, NC (US)
Filed by Honeywell International Inc., Charlotte, NC (US)
Filed on Dec. 3, 2021, as Appl. No. 17/542,102.
Prior Publication US 2023/0177934 A1, Jun. 8, 2023
Int. Cl. G08B 13/196 (2006.01); G06N 20/00 (2019.01); G06V 10/70 (2022.01); G06V 20/52 (2022.01); G06V 40/16 (2022.01); G06V 40/20 (2022.01)
CPC G08B 13/19613 (2013.01) [G06N 20/00 (2019.01); G06V 10/70 (2022.01); G06V 20/52 (2022.01); G06V 40/172 (2022.01); G06V 40/20 (2022.01); G08B 13/19608 (2013.01)] 13 Claims
OG exemplary drawing
 
1. A method of monitoring worker behavior within a secure area of a data center that includes a plurality of server racks, the method including a deployment phase and an operational phase, the method comprising:
during the deployment phase:
identifying an identity of each worker that enters the secure area of the data center;
monitoring the behavior of each worker while the worker is in the secure area;
developing an Artificial Intelligence (AI) model for each worker, wherein the AI model is specific to each worker and is representative of at least part of the behavior of the corresponding worker in the secure area, wherein developing the AI model for each worker includes receiving one or more of:
tasks assigned to and carried out by the corresponding worker in the secure area;
skills possessed by the corresponding worker; and
a worker category from a plurality of worker categories for the corresponding worker;
during the operational phase:
identifying the identity of each worker that enters the secure area of the data center;
monitoring a current behavior of each worker in the secure area;
comparing the current behavior of each worker in the secure area with the behavior represented by the AI model that corresponds to the worker; and
raising an alarm when the current behavior of one or more workers diverges from the behavior represented by the AI model that corresponds to the worker.