Uber will also potentially modify "pickup or drop-off locations to areas that are well lit and easy to access" when it has determined the user's state is "unusual". Its algorithms weigh a number of factors, including typos, walking speed, how precisely you press in-app buttons, and the amount of time it takes, standing on the curb, to order a ride. A driver set to pick up a particularly tipsy passenger might get a notification on their phone beforehand, or they could be told to meet the rider at the designated location a bit later to give the person more time to get to the vehicle before driving off.
"Predicting user state using machine learning", is how the company succinctly describes their latest technological endeavour. By user's state, it means Uber would be able to identify if you're drunk and how far from your normal state.
If there are no drivers with expertise in such matters available, the drunk passengers could be denied service.
'It may also make journeys safer for drunk passengers, so if they know who is a risky driver they might prevent that unsafe driver from picking up vulnerable riders'.
Take a look at these Uber incidents below.
Knowing whether a passenger is behaving unusually can help mitigate any issues before they become problems.
The patent adds that Uber drivers could be warned of a passenger's state before they're picked up, letting them prepare for the journey in advance.
Using this information, Uber may change the service offered to the user.