13 September 2018 at 09:42 (GMT) Download PDF
Trainline’s voice app now pulls contextual data from train operators’ Twitter feeds, overlaying onto industry data, to provide most advanced real-time disruption alerts available to train travellers.
London, UK 13 SEPTEMBER 2018: Trainline, Europe’s leading train and coach app, has launched the world’s first personalised disruption voice alerts for rail, integrated into Trainline’s voice app, built for the Google Assistant.
Launching in beta in Trainline’s voice app, personalised voice alerts provide customers with enhanced real-time updates on disruption to their journey. Using natural language processing and machine-learning, Trainline’s team of data scientists and voice technology experts have created a rail disruption model, utilising data from train operators’ Twitter accounts, more advanced than anything currently available to UK train travellers. Users simply give the app basic voice commands, such as ‘how is my commute doing?’ or ‘is this train running on time?’ to receive the alerts.
The new feature is another milestone in Trainline’s mission to create smarter rail and coach journeys globally with cutting-edge tech, using AI and data science capabilities to optimise the travel experience.
How it works
Using natural language processing, the AI analyses vast amounts of data collected from train operator Twitter feeds on rail disruptions. The notification system works firstly by automatically classifying the importance of the message. It then uses a second layer of contextual scoring, which calculates which stations the disruption is affecting, as well as how this will impact each individual train. This information is used to build a picture of which lines, tracks and rail services are being disrupted.
Once the content and importance of the message has been determined, the AI can automatically match this to individual journeys. When a customer asks the Trainline voice app about their journey, they will be alerted about disruption, often before this data is available through the national rail data feeds. The customer is even shown the history of the disruption, so they can see its scale, when it started, how it has unfolded and what is being done to fix it.
We’re proud to be launching another industry first. Through our voice app – designed to be used on the go - we can now offer customers faster and smarter updates on their journeys, helping them limit the impact of rail disruption. By creating an AI that can read information being shared on train operators’ Twitter feeds, we were able to overcome a key challenge in collecting data quickly from a variety of different sources. It’s another example of how Trainline is harnessing the power of AI, big data and voice tech to make travel a smoother experience for everyone.
Senior Director of Product at Trainline
Trainline’s voice disruption notifications are the latest feature built by Trainline’s world-class team of travel tech specialists and data scientists. The team has recently released new innovations including Price Prediction, which uses advanced data models and machine learning to identify when advance fares are likely to rise; and previously ‘BusyBot,’ an AI that helps passengers find a seat on busy trains using crowdsourced data.
Trainline’s disruption notifications are available now in the Trainline voice app, built for the Google Assistant, and can be activated initially by opening the Google Assistant and asking it to ‘Talk to Trainline’.
Notes to Editors
Trainline is Europe’s leading train and coach app. We work with 183 rail and coach companies to offer our customers travel to thousands of destinations in and across 37 countries. Our aim is to bring together all rail, coach and other travel services into one simple experience, so customers can get the best prices and smart, real time travel information on the go.