	US 12,073,346 B2
	Systems and methods for optimizing automated modelling of resource allocation
Nicholas Arcolano, Watertown, MA (US); Glenn Stephen Barnett, Needham, MA (US); Philip Joseph Braden, Washington, DC (US); David James Gourley, Boston, MA (US); Matthew Paul Klein, Hingham, MA (US); Andrew Man-Hon Lau, Cambridge, MA (US); and Alexander Stephen Metzger, Boston, MA (US)
Assigned to Orthogonal Networks, Inc., Boston, MA (US)
Filed by Orthogonal Networks, Inc., Boston, MA (US)
Filed on Sep. 22, 2022, as Appl. No. 17/950,230.
Application 17/950,230 is a continuation of application No. 16/556,507, filed on Aug. 30, 2019, granted, now 11,488,081.
Claims priority of provisional application 62/777,506, filed on Dec. 10, 2018.
Claims priority of provisional application 62/725,741, filed on Aug. 31, 2018.
Prior Publication US 2023/0077908 A1, Mar. 16, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 10/0631 (2023.01); G06F 8/71 (2018.01); G06N 20/00 (2019.01)

CPC G06Q 10/06313 (2013.01) [G06F 8/71 (2013.01); G06N 20/00 (2019.01)]

18 Claims

1. A system for optimizing automated modelling of resource allocation, the system comprising:

at least one processor operatively connected to a memory;

a capture component, executed by the at least one processor, configured to:

automatically retrieve a plurality of work interaction events associated with a first user;

generate probabilistic values indicative of respective probabilities that the first user worked on a first task during a first time interval based on the plurality of work interaction events; and

generate a probabilistic work allocation based on the probabilistic values, wherein the probabilistic work allocation defines a probability distribution over a plurality of tasks for a series of candidate time intervals associated with the first user, wherein the plurality of tasks includes the first task and the series of candidate time intervals includes the first time interval;

a correlation component, executed by the at least one processor, configured to:

associate a plurality of users identities across a plurality of data sources to respective users and respective task based information;

dynamically adjust weights associated with the plurality of work interaction events responsive to corroboration of a first data source of the plurality of data sources, and dynamically adjust the weights responsive to corroboration of a second data source of the plurality of data sources;

allocate a second time interval of the series of candidate time intervals to a second task of the plurality of tasks based on the probabilistic work allocation; and

responsive to dynamically adjusting the weights, re-determine the second time interval for at least the first task;

an adjustment component, executed by the at least one processor, configured to:

responsive to automatically retrieving additional work interaction events associated with the first user, reduce, modify, or eliminate one or more time interval from the series of candidate time intervals and/or one or more tasks from the plurality of tasks.