US 12,272,197 B2
Controlling access based on a machine-learning model
Divya Gupta, Gurugram (IN); Siddharth Gaur, Gurugram (IN); Jeevan Kaur, Dehradun (IN); Aravindan Varadan, Bengaluru (IN); Priya Jindal, Gurgaon (IN); and Bhavay Satija, New Delhi (IN)
Assigned to ASSA ABLOY AB, Stockholm (SE)
Appl. No. 18/252,582
Filed by ASSA ABLOY AB, Stockholm (SE)
PCT Filed Nov. 10, 2021, PCT No. PCT/EP2021/081194
§ 371(c)(1), (2) Date May 11, 2023,
PCT Pub. No. WO2022/101245, PCT Pub. Date May 19, 2022.
Claims priority of application No. 202011049223 (IN), filed on Nov. 11, 2020; and application No. 2150061-6 (SE), filed on Jan. 20, 2021.
Prior Publication US 2024/0005712 A1, Jan. 4, 2024
Int. Cl. G07C 9/00 (2020.01); G07C 9/33 (2020.01)
CPC G07C 9/00817 (2013.01) [G07C 9/00309 (2013.01); G07C 9/00563 (2013.01); G07C 9/33 (2020.01); G07C 2009/00849 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A method for controlling access to a physical space secured by an electronic lock, the method being performed in an access evaluator and comprising:
obtaining one or more input parameters relating to a user requesting access to the restricted physical space;
evaluating a first access condition based on a credential presented by the user;
evaluating a second access condition using a machine-learning model, based on the one or more input parameters;
unlocking the electronic lock when both the first access condition and the second access condition are evaluated to be true;
evaluating a third access condition when the first access condition is evaluated to be true and the second access condition is evaluated to be false;
unlocking the electronic lock when both the first access condition and the third access condition are evaluated to be true; and
training the machine learning model with the one or more input parameters when both the first access condition and the third access condition are evaluated to be true.