Uber Seeks Patent To Detect Drunk Passengers
Uber has an application pending with the U.S. Patent and Trademark Office for using technology that would help the ride-hailing giant to detect drunk passengers.
The patent application was initially filed by Uber in December 2016 and relates to predicting a rider's state using machine learning.
It outlines a travel coordination system that will identify "uncharacteristic user activity" and take action to "reduce undesired consequences of uncharacteristic user states."
The system will use a computer model and be able to identify if a user is displaying uncharacteristic behavior by looking at small changes in his behavior as he uses the Uber app.
To predict a rider's state, the system will compare data from that ride request to data about past rides.
"Past trip information may be parameterized to a profile of the user and identify how the user activity of the current trip request deviates from previous (or "normal") behavior for that user. The system can also compare data associated with the trip request to past trip requests submitted to the system by other users," the patent application says.
For example, the system may track how many typos occur while a user inputs a new ride request, his walking speed while making the ride request, or the angle at which the user held the phone when making the request.