Uber’s new AI system will help the company determine drunk passengers.
A patent application published on Thursday revealed that Uber is working on a new AI system that could help identify drunk passengers. This latest innovation could allegedly allow the ride-sharing company to customize the ride options for its customers.
“A travel coordination system (also referred to herein as “a system” for simplicity) identifies uncharacteristic user activity and may take an action to reduce undesired consequences of uncharacteristic user states,” a part of the patent application read.
“The system uses a computer model to identify user and trip characteristics indicative of the unusual user state. A system receives information about transport services (e.g., trips) requested by users and/or provided by providers. The information includes information about trip requests submitted by users, data obtained by monitoring trips as they occur, and feedback regarding trips received from users and providers.”
Apparently, the system will learn how a particular person uses the Uber application, identifying unusual behavior. The system will do this using an algorithm that would weigh in a variety of factors like typos, clicking on links and buttons, walking speed, and how long a person takes time to request a ride. The system will also take into consideration the time of the day and the location of where the ride is requested.
“The system receives the trip request from a user and generates a prediction about the current state of the user using the computer model. To predict user state, the system compares data associated with the trip request to data about past trip requests submitted by the user. 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 patent stated.
If approved, this new AI system could help Uber solve the problem drivers are facing when dealing with abusive drunk riders.
Comments (0)
Least Recent