Mindful interruptions

Abstract

We present the design, development, and evaluation of a personalised, privacy-aware and multi-modal wearable-only system to model interruptibility. Our system runs as a background service of a wearable OS and operates on two key techniques: i) online learning to recognise interruptible situation at a personal scale and ii) runtime inference of opportune moments for an interruption. .e former is realised by a set of fast and ecient algorithms to automatically discover and learn interruptible situations as a function of meaningful places, and physical and conversational activities with active user engagement. .e la.er is substantiated with a multiphased context sensing mechanics to identify moments which are then utilised to delivery noti€cations and interactive contents at the right moment. Early experimental evaluation of our system shows a sharp 46% increase in the response rate of noti€cations in wearable se.ings at the expense of negligible 6.3% resource cost.