US 11,893,371 B2
Using artificial intelligence to select and chain models for robotic process automation
Prabhdeep Singh, Bellevue, WA (US)
Assigned to UiPath, Inc., New York, NY (US)
Filed by UiPath, Inc., New York, NY (US)
Filed on Mar. 12, 2021, as Appl. No. 17/200,315.
Application 17/200,315 is a continuation of application No. 16/707,933, filed on Dec. 9, 2019, granted, now 10,963,231.
Claims priority of provisional application 62/915,399, filed on Oct. 15, 2019.
Prior Publication US 2021/0200523 A1, Jul. 1, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 8/60 (2018.01); G06F 11/34 (2006.01); G06N 20/00 (2019.01)
CPC G06F 8/60 (2013.01) [G06F 11/3466 (2013.01); G06N 20/00 (2019.01)] 19 Claims
OG exemplary drawing
 
1. A computer-implemented method for using artificial intelligence (AI) to select and/or chain machine learning (ML) models for robotic process automation (RPA), comprising:
executing, by a computing system, a model of models that analyzes performance of individual ML models and chains of ML models in an ML model pool to be called in a workflow of an RPA robot; and
responsive to a superior performance outcome to an existing ML model or an existing chain of ML models being discovered by the model of models:
deploying the discovered ML model or the discovered chain of ML models, by the computing system, and replacing the existing ML model or the existing chain of ML models, wherein
the analysis of the performance of the individual ML models and the chains of ML models comprises performing AI-based experimentation on permutations of chained ML models in series, in parallel, or a combination thereof, and analyzing results output by the individual ML models and the chains of ML models.