Context aware Hidden Markov Model for Intention process mining

Abstract

Nowadays, the omnipresence of digital devices and solutions in daily life made the digital footprints of individuals and the traces of their activities widely available. Smart devices generate a tremendous amount of data that and enables tracking their users’ activity. Extensive research has been conducted to produce generic process models based on the analysis of user’s activity recorded during the enactment of operational processes. Unfortunately, these approaches considered only the relation between the observed activities and their sequences to infer the underlying process. Thus, ignoring the goal conditioning the user’s behavior when triggering the actual process. Nevertheless, the same activity traces could serve to unhide the intention behind each process. This article will focus on presenting our approach to Contextual intention mining using Hidden Markov Model (HMM). This approach explores the close relationships between intention and context to construct the process model while ensuring consistency between observed context and actual intentions.