US 12,260,356 B2
Machine learning techniques for optimized equipment allocation
Jon Kevin Muse, Thompsons Station, TN (US); Gregory J. Boss, Saginaw, MI (US); Rama S. Ravindranathan, Edison, NJ (US); and Marilyn L. Gordon, Cherry Hill, NJ (US)
Assigned to UnitedHealth Group Incorporated, Minnetonka, MN (US)
Filed by UnitedHealth Group Incorporated, Minnetonka, MN (US)
Filed on Sep. 9, 2021, as Appl. No. 17/470,551.
Prior Publication US 2023/0073776 A1, Mar. 9, 2023
Int. Cl. G06Q 10/0631 (2023.01); G06Q 10/0635 (2023.01); G16H 40/20 (2018.01); G16H 40/40 (2018.01); G16H 50/30 (2018.01); G16H 50/80 (2018.01)
CPC G06Q 10/0631 (2013.01) [G06Q 10/0635 (2013.01); G16H 40/20 (2018.01); G16H 40/40 (2018.01); G16H 50/30 (2018.01); G16H 50/80 (2018.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving, by one or more processors, one or more equipment history events for an equipment item for a demand point within a physical environment;
inputting, by the one or more processors, the one or more equipment history events to a first neural network, causing the first neural network to determine and apply weights to the one or more equipment history events to generate a predicted evaluation score set, wherein:
(i) the predicted evaluation score set includes a per-category predicted evaluation score for the equipment item and a risk category that relates to a particular health condition of a monitored entity that is different than the equipment item, and
(ii) the per-category predicted evaluation score provides a predicted likelihood that an equipment associated with the equipment item is capable of transmitting a pathogen associated with the particular health condition to another equipment or another entity;
inputting, by the one or more processors, the predicted evaluation score set to a second neural network, causing the second neural network to generate an optimized allocation scheme for the equipment item and the demand point;
determining, by the one or more processors and based at least in part on a sensor device associated with the equipment, an equipment location for the equipment within the physical environment;
determining, by the one or more processors, an optimal pathway between the equipment location and the demand point within the physical environment based at least in part on the optimized allocation scheme; and
initiating, by the one or more processors and via the optimal pathway, a transportation of the equipment between the equipment location and the demand point within the physical environment.