Have Halal Will Travel builds Sofia chatbot with Microsoft Azure
By Digital News Asia May 21, 2018
- Chatbot was designed with the help of technology partner PleoData
- HHWT now reaches over nine million Muslims each month
HAVE Halal Will Travel (HHWT) is a content platform that helps Muslims travel in countries where this can be a challenge, especially without a guide. They started out with an article on how to find halal local food like dim sum in Hong Kong; and this eventually grew to hundreds of articles and guides on the Web, as well as a mobile app and social media channels.
HHWT draws its recommendations from communities of contributors around the world, from London to Bangkok.
Often, these writers have travelled to or lived in these cities for years, bringing authentic insider knowledge to travellers on where to find the best halal local cuisine, prayer spaces, and what to look out for when visiting these destinations.
HHWT now reaches over nine million Muslims from Singapore, Malaysia and Indonesia each month, providing information to help travellers plan trips to destinations such as Hong Kong, Japan, London, Melbourne and South Korea.
Combining Microsoft’s Azure cloud and its Language Understanding Intelligence Services (LUIS), HHWT’s chatbot now answers most of the questions that travellers ask through the platform every day.
Microsoft Malaysia chief marketing & operations officer Michal Golebiewski, said, “The development of artificial intelligence (AI) is accelerating, enabling profound progress in every field. Our mission has always been to ensure that the benefits of technology can be enjoyed by one and all.
“At Microsoft, we believe in the democratising of AI. With HHWT, we are excited about our technology enhancing the travel experience of people and enabling them to enjoy their most preferred food.”
Called Sofia, chosen after users voted for the name in a public poll, the chatbot is online 24/7, assisting travellers with their queries from all over the world, regardless of which time zone they are in. With Sofia, the HHWT team can now significantly increase their engagement level with users daily.
“We created Sofia simply because people have been asking us questions which we found could be answered largely through automation,” said Melvin Mikhail Goh, co-founder of HHWT. At the same time, through the responses and feedback received from users interacting with Sofia, HHWT can now analyse and contextualise all that input to help provide more personalised content for each individual user, thus serving customers’ needs better.
What was also fascinating was that Sofia was set up in a surprisingly short amount of time. Instead of creating a chatbot from scratch, the HHWT team relied on existing tools that Microsoft provides on the cloud to create Sofia, with the help of technology partner PleoData.
The Azure cloud platform comes with an application programming interface (API) for a QnA Maker; that was the first building block the team tapped on to form answers to commonly-asked questions. Microsoft’s LUIS then enables chatbot designers to draw on datasets already in existence, enabling the team to analyse what users were asking.
“I think one of the really big benefits of Microsoft Azure is the QnA Maker,” said PleoData managing director Rachel Tan. “It allows any company to be able to release a working chatbot in less than seven working days, which is quite an amazing feat.”
It helps that HHWT already had an existing set of frequently asked questions (FAQs), which were inputted into the Q&A maker. Though that was sufficient to launch a chatbot as-is, the team went one step further to customise the chatbot so that it could offer more intelligent content to users.
Currently, Sofia uses what is known as a decision tree that lets users narrow down the answers they are looking for. In future, this process will be simpler and more intuitive — the system will automatically answer questions with a deeper understanding, without having to seek clarification.
This next step for HHWT involves sinking its teeth more deeply into machine learning. With larger datasets to draw on after running the chatbot over time, HHWT would be able to develop contextual and personalised content.
Today, HHWT works with tourism boards from countries around the world and global brands to reach out to the Muslim community. As the same time, they are also working with partners to provide functionalities such as the ability to complete travel bookings and payment transactions on the website.
With the scalability of Azure cloud, as well as LUIS, powering the Sofia chatbot, HHWT is now looking towards expansion to more countries within Southeast Asia and beyond.
Whatever HHWT’s plans are, Goh reinforced that their focus over the next two years is to build on their understanding of their consumers’ needs and wants.
“One of the things we are seeking to improve for our chatbot is its search and response – to give us a better understanding of what people are searching for, and from there, better responses and better content,” said Goh.
As HHWT continues down the path of getting to know its audience better, the online platform is making an impact that goes beyond a mere search for food. HHWT is changing mindsets, one traveller at a time.
“As a Muslim myself, I feel that Muslims shouldn’t be restricted to just kebabs or nasi biryani,” said Goh, suggesting that they should seek out halal ramen in Japan, or bibimbap in South Korea instead.
“To really understand different cultures, you have to eat their food, speak their language, and really get lost in their country. Muslims shouldn’t be deprived from that opportunity,” he added.