US 11,836,662 B2
Systems and methods for identifying processes for robotic automation and building models therefor
Jiyong Ma, San Diego, CA (US); Stephen Michael Thompson, Oceanside, CA (US); and Jan W. Amtrup, Silver Spring, MD (US)
Assigned to KOFAX, INC., Irvine, CA (US)
Filed by Kofax, Inc., Irvine, CA (US)
Filed on Feb. 17, 2022, as Appl. No. 17/674,714.
Application 17/674,714 is a continuation of application No. 16/387,269, filed on Apr. 17, 2019, granted, now 11,281,936.
Claims priority of provisional application 62/787,136, filed on Dec. 31, 2018.
Prior Publication US 2022/0171988 A1, Jun. 2, 2022
Int. Cl. G06F 3/01 (2006.01); G06Q 10/0633 (2023.01); G06F 18/23213 (2023.01)
CPC G06Q 10/0633 (2013.01) [G06F 18/23213 (2023.01)] 18 Claims
OG exemplary drawing
 
1. A computer-implemented method of identifying one or more processes for robotic automation (RPA), the method comprising:
recording a plurality of event streams, each event stream corresponding to a human user interacting with a computing device to perform one or more tasks;
concatenating the event streams;
segmenting some or all of the concatenated event streams to generate one or more individual traces performed by the user interacting with the computing device, each trace corresponding to a particular task;
clustering the traces according to a task type;
identifying, from among some or all of the clustered traces, one or more candidate processes for robotic automation;
prioritizing the candidate processes; and
generating a software robot configured to automate the at least one of the prioritized candidate processes, wherein generating the software robot comprises:
generating a directed, acyclic graph (DAG) representing traces of the at least one prioritized, candidate process; and
identifying a minimum-weight, maximum-frequency path from an initial node of the DAG to a final node of the DAG.