Further to the Shakespeare Review which used TfL’s open data activity as a case study in 2013, we asked Deloitte to carry out a more comprehensive study on the value of open data to our customers, users and London overall.
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 constantly looking for feedback to improve our products. If you haven’t it tried yet, search for ‘TfL TravelBot’ on the Facebook Messenger app or go to http://m.me/tfltravelbot on your desktop/laptop. More details on how to use the bot can be found in our previous blog.
Please keep your feedback coming in the comments section below. We know there are more things you would like us to include, and we’re really keen to hear from you.
We’re delighted to announce that the TfL Tech Forum is now live, and is ready for you to use right away. With more than 11,000 developers working with our open data to develop innovative products, the TfL Tech Forum will be a lively space where developers can connect with experts from the TfL Online team, providing a platform for discussion around all aspects of our open data and Unified API. With over 600 travel apps powered by TfL, it’s great to see new product features being developed, and a key area of focus is accessibility (see this previous blog) – we encourage you to develop new features for your product using our data.
Over the last few months we’ve received lots of useful feedback on some of the buses-specific features on our website, and we’ve noticed some recurrent themes. We’ve worked hard to act upon your feedback in as short a time as possible, and in this post I’ll address some of your key questions and concerns, as well as what we’ve done about them.
With a real focus on our Unified API and open data policy in recent months, both on this blog and through the Hackathons and events (such as the Urban Traffic Hackathon a few weeks ago) that TfL staff have been involved with, we’ve received lots of great feedback and questions from the developer community, just as we’d hoped we would.
One such question that has cropped up many times is one around customer volume and flow data, i.e. how can we help developers create apps that take into account how busy certain lines, stations, platforms, etc are likely to be when customers are planning a journey.
To provide an update on where we are with this data, TfL’s Data Services Manager Ryan Sweeney offers this summary, and asks for your feedback to help us ensure we’re providing data that is both relevant and useful:
The 7th Over the Air took place on the 25th & 26th of September, 2015 at St. John’s in Hoxton, London and Transport for London were delighted to provide two speakers at the event on Friday 25th.
Over the Air is an annual 2-day event where the mobile developer community come together for ‘Hack Days,’ aimed at driving learning, collaboration and experimentation amongst developers, with software development recognised as a creative discipline. You can read more about the history, ethos and structure of the event on the Over the Air website and follow them on Twitter.
Rikesh Shah, Lead Digital Relationship Manager and Gordon Watson, Chief Technical Architect at Transport for London, were there to provide an overview of Open Data at TfL and to outline our commitment to the provision of free, open data which enables app developers to produce a huge range of travel products.
As expected, last week saw 4 days of high demand on our website and open data during the Tube strike and in the build up to it, with traffic at 1.67 x normal levels over Wednesday 5th and Thursday 6th August.
The strike started on the evening of Wednesday 5th which was the busiest day, with 1,315,328 visits, though this was considerably lower than the busiest day of last month’s Tube strike, when we hit a record 2,058,618 visits.
The morning of Friday 7th continued to see an increase in demand, but with numbers starting to drop back to normal levels as the day went on.
Our web and data services performed well throughout the period of high demand, with no reports of issues accessing our services.