US 12,306,736 B2
Inserting probabilistic models in deterministic workflows for robotic process automation and supervisor system
Prabhdeep Singh, Bellevue, WA (US); and Anton McGonnell, Seattle, WA (US)
Assigned to UiPath, Inc., New York, NY (US)
Filed by UiPath, Inc., New York, NY (US)
Filed on Oct. 30, 2023, as Appl. No. 18/497,496.
Application 18/497,496 is a continuation of application No. 17/828,682, filed on May 31, 2022, granted, now 11,803,458.
Application 17/828,682 is a continuation of application No. 16/708,083, filed on Dec. 9, 2019, granted, now 11,347,613, issued on May 31, 2022.
Claims priority of provisional application 62/915,434, filed on Oct. 15, 2019.
Prior Publication US 2024/0061760 A1, Feb. 22, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 11/32 (2006.01); G06F 11/30 (2006.01); G06F 17/18 (2006.01); G06N 20/00 (2019.01)
CPC G06F 11/327 (2013.01) [G06F 11/302 (2013.01); G06F 17/18 (2013.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for implementing probabilistic models in a deterministic workflow for robotic process automation (RPA), comprising:
automatically replacing a deterministic activity in a robotic process automation (RPA) workflow with a probabilistic activity, by an RPA designer application or another application stored in memory of a computing system and executed by at least one processor, responsive to a machine learning (ML) model called by the probabilistic activity reaching a confidence threshold; and
deploying an RPA robot stored in the memory of the computer system, the RPA robot configured to execute the RPA workflow at runtime, wherein RPA robot executes the RPA workflow at least in part using one or more drivers.