A natural language search tool for managing Germany’s high-speed railway network
The Challenge
How to provide every employee at Deutsche Bahn access to booking and prognosis data about all future long distance train operations.
The Result
A digital assistant helps formulate the right question to query complex data sets with no expertise required.
Our Expertise
- Ideation
- Data Visualization
- UX & UI Design
The Brief
Since 2017 we design, develop and nurture the dashboard app Peakspotting for Deutsche Bahn AG. It is a browser based tool, that allows its users to explore and work with booking and prognosis data for all long distance train operations in Germany. But is is also a complex tool. Specific design decisions aim to support its power users, the yield managers of Deutsche Bahn.
Spotti sits happily on the other site of the spectrum! Using Peakspotting as a foundation, it aims to be a search tool for everbody at Deutsche Bahn whilst providing access to the same vast data set.
An expert tool: The map view of our Peak Spotting application
However, Spotti is not merly a tool for the yield management department at Deutsche Bahn. Throughout its runtime in the last years, it actively invited and gained a following and among other users in the organization as well.
They all profit from up-to-date booking and prognosis data in their daily operation:
- Train station operators know when more passengers arrive at specific platforms in advance.
- Service personnel knows which carriage might require additional staff for cleaning and maintenance.
- Traffic control can plan future construction works based on the expected network load.
Spotti's overall goal is to provide them with a public interface that picks up their tongue and overcomes any required domain expertise.
Our Approach
Spotti allows train service operators to quickly get up-to-date information on train capacities, bookings, and predictions using simple natural language. Millions of data points are instantly available to yield and traffic managers through a familiar search interface. These features make Spotti the primary tool for quick and direct tasks done by the teams working with Peak Spotting every day.
Investigating load balances of train operations with Spotti (obfuscated data).
Example of a natural language query
Spotti recognizes place names, train numbers, times and dates as well as several operational criteria such as estimated bookings. The pattern recognition allows to express queries to the database in flexible ways in order to support different search behaviors. The results themselves are fully working Peak Spotting interface elements, e.g. train lists, which provide familiar ways to further work with the selected trains.
Credits
In collaboration with