Intention-Oriented Process Model Discovery from Incident Management Event Logs
This work addresses the problem of uncovering unobservable user behaviors in ITIL incident management processes, representing an incremental application of a new field.
The paper applied intention-oriented process mining to discover hidden user strategies and intentions from a large real-world incident management event-log dataset, using Hidden Markov Models to generate a coarse-grained Map Process Model.
Intention-oriented process mining is based on the belief that the fundamental nature of processes is mostly intentional (unlike activity-oriented process) and aims at discovering strategy and intentional process models from event-logs recorded during the process enactment. In this paper, we present an application of intention-oriented process mining for the domain of incident management of an Information Technology Infrastructure Library (ITIL) process. We apply the Map Miner Method (MMM) on a large real-world dataset for discovering hidden and unobservable user behavior, strategies and intentions. We first discover user strategies from the given activity sequence data by applying Hidden Markov Model (HMM) based unsupervised learning technique. We then process the emission and transition matrices of the discovered HMM to generate a coarse-grained Map Process Model. We present the first application or study of the new and emerging field of Intention-oriented process mining on an incident management event-log dataset and discuss its applicability, effectiveness and challenges.