| CPC G06F 11/2273 (2013.01) [G06F 11/263 (2013.01); G06N 20/00 (2019.01)] | 33 Claims |
|
1. One or more non-transitory computer-readable media having computer-executable instructions embodied thereon that, when executed by a processor, perform a method for prioritizing and testing user interface workflows based on machine learning models, the method comprising:
receiving a primary workflow having a plurality of steps organized in a sequence;
generating a set of test workflows having randomized the sequence of at least one step in the plurality of steps of the primary workflow, wherein generating the set of test workflows includes:
identifying at least one step having a locked position in the sequence of the primary workflow and at least one step having an unlocked position in the sequence of the primary workflow;
identifying the locked position relative to the unlocked position in the sequence of the primary workflow;
identifying each position in the sequence where the at least one step having the unlocked position can be placed while maintaining the position of the at least one step having the locked position in the sequence of the primary workflow; and
generating a separate workflow for each position in the sequence where the at least one step having the unlocked position can be placed while maintaining the position of the at least one step having the locked position in the sequence of the primary workflow;
identifying a subset of test workflows, within the set of test workflows, that meets or exceeds a matching threshold to historical data; and
communicating the subset of test workflows for display in a graphical user interface.
|