US 12,112,092 B2
System and method for meeting volume optimizer
Michael Anthony Young, Jr., Henrico, VA (US); Christopher Mcdaniel, Glen Allen, VA (US); and Matthew Louis Nowak, Midlothian, VA (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Jan. 31, 2022, as Appl. No. 17/588,595.
Prior Publication US 2023/0244438 A1, Aug. 3, 2023
Int. Cl. G06F 3/16 (2006.01); G06F 40/20 (2020.01); G06Q 10/1093 (2023.01); G06N 20/00 (2019.01)
CPC G06F 3/165 (2013.01) [G06F 40/20 (2020.01); G06Q 10/1095 (2013.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
a machine learning system configured to:
receive first training data as an input to the machine learning system, wherein the first training data includes multiple scheduling instances, and wherein the scheduling instances specify a plurality of scheduling parameters upon which to make a prediction of a future schedule;
receive second training data as an input to the machine learning system, wherein the second training data includes multiple productivity measurement instances, and wherein the productivity measurement instances specify a plurality of productivity parameters upon which to make a prediction of a future productivity, wherein the plurality of productivity parameters are based on work product measurements;
train, by the machine learning system, a productivity predictive model with the first training data and the second training data, wherein the productivity predictive model includes one or more algorithms to predict a current productivity change based on either accepting a new scheduling request or alternatively, rescheduling the new scheduling request;
receive a current schedule and current productivity measurements of a user;
receive a scheduling request for the user, wherein the scheduling request includes one or more proposed scheduling parameters;
predict a future productivity change based on using the productivity predictive model with the current schedule, the current productivity measurements of the user, the one or more proposed scheduling parameters and accepting the scheduling request; and
a graphical user interface configured to:
display a graphic revealing the future productivity change of the user based on accepting the scheduling request.