Plus   Neg

Uber Seeks Patent To Detect Drunk Passengers

uber drunk 061318 lt

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.

Based on how the rider's behavior is interpreted by the system, it may adjust how it arranges a match with a driver, the application said. It may also alter parameters association with trip coordination for the requested trip.

Some examples of trip variations include matching the user with only certain drivers, alerting a driver about the user's possible unusual state, and modifying pickup or drop-off locations to areas that are well lit and easy to access.

When the likelihood of the user acting uncharacteristically is comparatively very high, he may not be matched with any driver at all, or limited to drivers with experience or training with users having an unusual state. When the likelihood is comparatively low, the system may match the rider normally.

It is not clear if the patent would be approved, or whether Uber has immediate plans to implement the technology after approval.

"We are always exploring ways that our technology can help improve the Uber experience for riders and drivers. We file patent applications on many ideas, but not all of them actually become products or features," an Uber spokesperson said.

For comments and feedback contact: editorial@rttnews.com

Technology News

Follow RTT