The public transit sector is enough to make a data nerd feel like a kid in a candy factory. With use cases for big data galore, the payoff is especially fascinating in cities such as London and Paris filled with millions of travelers who have come to expect up-to-the-minute information on thousands of buses, trams and trains delivered seamlessly to their smartphones. diginomica explains how these innovations came to be and continue to unfold with the growth of AI.
British rail booking service Trainline, for example, launched last month and sends personalized travel alerts to users powered by AI. Their AI analyzes the Twitter feeds of various train companies throughout the UK, favoring the speed of this channel as compared to official data from the national rail service.
Natural language processing helps the AI determine how much weight to assign each tweet and figure out where the delay is occurring. Trainline’s voice app then relays this information to users, who can simply ask about their journey and learn whether disruptions are ahead.
This is just one example of the complexity of juggling multiple data sources and delivering quick, efficient information to travelers. The use of Twitter for Trainline’s app was novel, considering how operator-managed data feeds have been the norm in London and in other major cities for quite some time.
Meanwhile, Paris’ national rail operator SNCF has been running a chatbot pilot available to the 3.2 million passengers on the Transilien network between the suburbs and the city center who want custom information for their itineraries. The chatbot is currently on Facebook Messenger for this test, but SNCF plans a full service rollout next year.
“A big part of the work for us at SNCF is to reorganize our IT system because, since it’s a very old company, the IT is also very old and it was built by layers to bring more information,” says Olivia Fischer, Digital Media Director. “We are really working hard at this time to reorganize and transform all this data and put it in an API.” The chatbot caps off a recent merge that combined real-time data from multiple APIs with schedules, enabling the train status updates it now can deliver.
“The chatbot reverses completely the relation because we go where the customers are and we don’t ask them to go to our media and to learn how to use our media.”
Currently, their team is training the bot to better field questions from people, but plans to teach the bot how to provide full, multilingual door-to-door journey information and alerts, with special attention to tourists and visitors who might be more inclined to use an app they are already familiar with instead of downloading something else.
Fischer sees this as an advantage of this technology versus alternatives. “The chatbot reverses completely the relation because we go where the customers are and we don’t ask them to go to our media and to learn how to use our media. We go to them...It’s the best way to have both a tailor made service and [provide it] on an industrial basis. Only the chatbot can do that.”
With AI, the public transit sector can help travelers go the distance more confidently than ever.
