Unfolding-Based Process Discovery
Abstract
This paper presents a novel technique for process discovery. In contrast to the current trend, which only considers an event log for discovering a process model, we assume two additional inputs: an independence relation on the set of logged activities, and a collection of negative traces. After deriving an intermediate net unfolding from them, we perform a controlled folding giving rise to a Petri net which contains both the input log and all independence-equivalent traces arising from it. Remarkably, the derived Petri net cannot execute any trace from the negative collection. The entire chain of transformations is fully automated. A tool has been developed and experimental results are provided that witness the significance of the contribution of this paper.
Keywords
Cite
@article{arxiv.1507.02744,
title = {Unfolding-Based Process Discovery},
author = {Hernán Ponce-de-León and César Rodríguez and Josep Carmona and Keijo Heljanko and Stefan Haar},
journal= {arXiv preprint arXiv:1507.02744},
year = {2015}
}
Comments
This is the unabridged version of a paper with the same title appearead at the proceedings of ATVA 2015