German rail operator use AI to fast-track responses to customer queries

Share this post:

German rail operator AIA typical visit to the train station can come with some uncertainty. Is your ticket valid for the next train to Berlin? Or do peak time restrictions apply? Are there catering facilities on board, or will you need to buy something to eat beforehand?

To take the stress out of traveling, DB Dialog and DB Systel – parts of Deutsche Bahn AG, Germany’s largest rail operator – launched a smart travel assistant service that uses artificial intelligence (AI) to quickly answer customer queries by text message.

Keeping customer services on the right track

DB Dialog is the business unit within Deutsche Bahn responsible for customer communications. It receives 12 million inquiries per year, typically by phone, email or in writing.

Expectations around customer service are changing. Digital communications, such as social media, are becoming more and more popular, especially with younger generations who would rather send a text message than pick up the phone.

Eager to offer customers a more convenient way of getting in touch, DB Dialog introduced a mobile communication channel to complement its existing call center and email services. We teamed up with DB Systel, the group’s IT services provider to develop an AI customer service solution. Together, we came up with the idea for DB Reisebuddy (German for “travel buddy”): a virtual assistant that helps customer service agents answer questions sent by text message.

Deploying an AI-based chatbot

DB Dialog and DB Systel selected IBM Watson Assistant, a platform for developing AI solutions, to underpin the service. After integrating Watson Assistant with DB Dialog’s customer relationship management (CRM) system, the repository for customer messages, we took six weeks to build the DB Reisebuddy virtual assistant and train it to recognize and respond to common customer queries.

To learn more about how we developed the solution, read the IBM case study.

The DB Reisebuddy virtual assistant is now on hand to help passengers before, during and after their train journeys. Customers send their queries – When is the next train to Munich? How do I get to Hamburg-Altona from the central station? I misplaced my wallet on the 12:05 to Stuttgart, is it in lost property? –  through SMS and web chat, and get personalized answers back a few minutes later.

There are still real people behind the DB Reisebuddy service. The virtual assistant suggests answers based on its understanding of the given questions, and human customer service agents check the proposed responses, edit them if necessary, then send them out as SMS or web chat.

Putting a travel assistant in passengers’ pockets

Today, the DB Reisebuddy virtual assistant handles common queries regarding ticketing and timetables, leaving the customer service agents free to deal with more complex inquiries. This saves the agents a lot of time and effort, taking the pressure off during busy travel times and enabling them to respond to customers much faster.

During a recent marketing campaign, which coincided with the launch of the service, the DB Reisebuddy virtual assistant provided correct responses to 40 percent of queries. We were really impressed with the percentage of correct, automated answers at such an early stage in its lifecycle.

Looking to the future, DB Dialog and DB Systel are eager to further fine tune the DB Reisebuddy virtual assistant to offer customers an even more responsive and convenient service. With many common queries now handled by the DB Reisebuddy virtual assistant, customer service agents are free to focus on more complex queries.

Learn more about IBM Watson Assistant.

More Cognitive stories

Bringing AI and esports together with Watson on cloud

Whether players are physically on the field or controlling virtual avatars in digital settings, IBM Watson is helping sports fans catch the most breathtaking moments. At the 2019 Game Developers Conference this week, IBM showcased how it’s using artificial intelligence (AI) on the IBM Cloud to make esports fan experiences better and improve player performance. […]

Continue reading

Providing around-the-clock call center support using a cognitive virtual assistant

According to Investopedia, financial technology has grown explosively since the mobile internet and smartphone revolution. Originally referring to computer technology applied to the back office of banks or trading firms, “fintech” now describes a variety of financial activities, from depositing a check with a smartphone to managing investments, generally without the assistance of a person. […]

Continue reading

How to remove the top 3 barriers to AI adoption in business automation

Many businesses are looking to automation to increase productivity, save costs and improve customer and employee experiences. For example, imagine a large insurance company that processes millions of claims a year. Around 60 percent of its claims are automatically processed, but it’d like to automate 85 percent of claims and reduce error rates, reduce costs […]

Continue reading