Consumer Affairs reports that your smartphone can often clamor for your attention like a three year-old. There are chimes for text messages, Twitter posts, email arrivals, and news alerts. Sometimes it seems like your phone never shuts up.
What if your smartphone was a little smarter, only interrupting you for things that were really important to you, and only when it was convenient to receive them? It would have to know you a little better and be a little smarter.
“Ideally, a smartphone notification management system should be like an excellent human secretary who knows when you want to be interrupted or left alone,” said Janne Lindqvist, an assistant professor in the Department of Electrical and Computer Engineering in Rutgers’ School of Engineering.
Since all of us seem to struggle with time management, Lindqvist says a smartphone could actually be a help instead of a nuisance.
Options are limited
But currently, he says, your options are pretty limited. You can turn off the ringer, but then you might not get any notifications. Lindqvist and his colleagues have been
working on a system that would turn your phone into an assistant that would recognize your patterns of use and behavior, then alert you to things you really need to know about, but otherwise minimize interruptions.
The Rutgers study looked at smartphone records from 22 participants over a four-week period. From that, researchers were able to determine how busy the participants were. They then built a model to tell the smartphone how open to being interrupted the participants were, at different times and places, and when they were engaged in a range of activities.
For example, some participants were happy to be interrupted when they were in medical facilities, probably because they were waiting to see a doctor and were bored. They were less agreeable to smartphone alerts when they were studying, working out at the gym, or driving.
A smarter smartphone system
With that data in hand, the Rutgers team is working on a system for smarter smartphone notifications.
“We could, for example, optimize our model to allow smartphone customization to match different preferences, such as always allowing someone to interrupt you,” Lindqvist said. “This would be something an excellent human secretary would know. A call from your kids or their daycare should always pass through, no matter the situation, while some people might want to ignore their relatives, for example.”
Ideally, says Lindqvist, a smartphone should learn this automatically. As of now, though, notifications depend on a user's settings, such as turning on or off certain alerts. The Rutgers system, should it come to fruition, would be more like a human secretary, he says, in that it is able to make smart predictions.
