As you may already know if you’re following this blog, we recently released the TfL TravelBot on Facebook Messenger. If you haven’t read them yet, Steven and Charul’s posts will give you a bit of background. Check out TravelBot here or search for TfL TravelBot in the messenger application. In this post I will explore the reasons for introducing a conversational bot and our learnings around the design of conversation.
Diverse backgrounds, cultures and lifestyles mean that we all use different words to talk about things. This can become frustrating when you’re trying to find something on a website.
In our team, we try to label things in a way that most users will understand, but are well aware of the fact that we will never be able to cater for everyone. This means that some users have to change the way they think to match what they are looking for.
We recently launched our first ever Chatbot – the “TfL TravelBot” on Facebook, which uses artificial intelligence to help answer customer queries expressed in everyday language. The bot was launched just two weeks ago and we have already received lots of great feedback. We wanted to offer you more insight into the thinking behind the TravelBot, and shed some light on how we developed it.
Why the TfL TravelBot?
Millions of people already use our website to help them get around London, and we’re constantly seeking new channels to make the process even easier. Research indicates that more than half of the world’s population is now online, and more than 50% of those online are active social media users*. Facebook is comfortably the biggest social media platform, and hence we wanted to take the opportunity to provide them with information via their channel of choice.
Instant messaging has emerged as the primary platform for communication these days**. With the advent of digital solutions making it easier to provide conversational platform, we felt it was the right time for us to enter the world of bots. We pride ourselves on being early adopters of technology, and wanted to leverage the potential of existing solutions to come up with a product which is one of the first of its kind in the world of travel.
How was it made?
We designed the logic behind the chatbot and it is hosted in the cloud. Every customer message passes through our logic, and the bot then seeks to deliver the best response. We use artificial intelligence enabled by the machine-learning framework to process the customer messages (Natural Language Processing). It works by understanding intent rather than phrases. Once the message is processed, the bot replies with either a response from our unified API or a friendly retort. The bot is intelligent and has the potential to learn over time.
How does it help?
Apart from being the channel of choice for receiving information, our bot will help the customers in many ways. It will help our customers get the information in the quickest possible time with a 100% response rate. For instance, queries like ‘When is my next bus due?’ can be easily automated, saving customers time and meaning they don’t need to wait for a customer services agent to get a response. In the case of more complex queries, the chatbot can prompt you to speak with an agent.
As a business, this frees up the time of our customer service agents and helps them focus on more complex customer queries. We are also be able to handle many more queries in the same time, therefore improving our response rate.
We’re proud to introduce our Facebook Messenger TravelBot, which has the ability to provide updates on bus arrivals as well as Tube and bus status updates.
Through our two Facebook pages – the main TfL page and the London Underground page – we deal with a huge number of queries every day, and we wanted to make it even easier for customers to get our information on the Facebook platform in a way that’s fast and straightforward. With theopen data in our Unified API already helping to provide live information on many services like third-party apps and Twitter alerts, we hope this will be another big step towards enabling customers to quickly and easily access the information they need via social media.
**Planned industrial action by drivers on the Circle, Hammersmith & City and Piccadilly lines this week has now been suspended**
Some drivers on the Circle, Hammersmith & City and Piccadilly lines who are RMT union members are planning to strike from the evening of Tuesday 6 December. We will run as many services as possible depending on how many employees are available. However, we advise customers to plan for no Piccadilly line service and a significantly reduced service on the Circle and Hammersmith & City lines until the end of the day on Wednesday 7 December. Customers are advised to complete their journeys on these lines by 19:00 on Tuesday 6 December.
Interchange stations and lines will be much busier than usual. Services on other Tube and rail lines, the bus network and river will run as normal but are expected to be busy as passengers seek alternative routes. Roads in west, central and east London will also be busier than usual.
We have a variety of digital tools available to help you get around during the disruption.
We’re proud to introduce our Twitter status checker, as well as improved Twitter alerts and weekly travel advice. In partnership with Twitter, we’ve added the ability to instantly check the status of your line and improved the services that we introduced earlier this year. Improvements include an easier way to manage your subscriptions – all through Twitter direct messages, supported by ‘quick replies‘. And, for new users, it’s easier to subscribe because you can do it all within a direct message on our accounts.
For around five years we’ve been informing customers about travel disruption through our @TfLTravelAlerts account. It’s one of our most popular and together with our Tube and rail accounts, we manage over 30,000 interactions every month, including questions about weekend planned works and changes due to events such as marathons and festivals.