US 11,790,293 B2
Pattern analysis for schedule optimization
Su Liu, Austin, TX (US); Debbie Anglin, Leander, TX (US); Rui Yang, Austin, TX (US); Paul Bernell Finley, Jr., Austin, TX (US); and Amir Sanjar, Austin, TX (US)
Assigned to INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Dec. 14, 2020, as Appl. No. 17/120,773.
Prior Publication US 2022/0188739 A1, Jun. 16, 2022
Int. Cl. G06Q 10/0631 (2023.01); G06Q 10/1093 (2023.01); G06N 5/04 (2023.01); G06Q 50/26 (2012.01); G01B 21/16 (2006.01); H04L 9/40 (2022.01); G06F 16/2458 (2019.01); G06N 20/00 (2019.01); G06Q 30/04 (2012.01)
CPC G06Q 10/063116 (2013.01) [G01B 21/16 (2013.01); G06F 16/2477 (2019.01); G06N 5/04 (2013.01); G06N 20/00 (2019.01); G06Q 10/06316 (2013.01); G06Q 10/1097 (2013.01); G06Q 30/04 (2013.01); G06Q 50/26 (2013.01); H04L 63/101 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method in an authentication-based access control system (ACS) comprising:
configuring an authentication-based access control system (ACS) with a sensor interface, a machine learning model (ML model), a schedule generation module, and a data structure;
causing the sensor interface to communicate with a set of location sensing sensors over a data network;
detecting using the set of sensors, a location and physical movements of a first worker and a location and physical movements of a second worker in a workspace plan;
generating, by executing the schedule generation module, a first preliminary schedule for a first task assigned to the first worker and a second preliminary schedule for a second task assigned to the second worker;
predicting, by executing the ML model, physical movements of a plurality of workers in the workspace plan, the predicting preventing a generation of worker schedules that are likely to result in workers being located within a distance of less than a threshold value in the workspace plan;
storing in a computer memory location associated with the data structure, a first block of time that is part of the first preliminary schedule and the second preliminary schedule;
generating from the ML model a first location prediction for the first worker during the first block of time;
generating from the ML model a second location prediction for the second worker during the first block of time;
outputting from the ML model a predicted distance between the first worker and the second worker based on the first location prediction and the second location prediction;
revising, responsive to determining that the distance is less than the threshold value, the second preliminary schedule to replace the first block of time with a second block of time that is not part of the first preliminary schedule;
generating an access control list that includes the first preliminary schedule as a first access schedule for the first worker; and
responding to an access query regarding the first worker by referring to the first access control list and determining whether the first access schedule includes a time associated with the access query, the access query being received by the ACS from an access control device configured in the ACS.