No Frank, chatbots are not going to take over your hotel!

See Velma in action! Get to know Velma

AI seems to be the universal answer to all our problems. For the very first time, innovation might destroy jobs without creating new ones. That may well be the case, but as far as hospitality is concerned, chatbots will not take over hotels. Rather, they are here to extend your reach. 

There are so many places where you are losing business because you aren’t able to properly engage your customers. Like, on your website, your Facebook account, WhatsApp, WeChat etc. Hotel Chatbots enable you to scale your presence on the platforms that you currently can’t cover because you’re chronically short-staffed. They filter and manage recurring requests and call you when the human touch is needed.

Sarah Connor?

Chatbots talk and may be equipped with artificial intelligence. But, they are no Terminators sent from the future to destroy humanity. So it’s likely your chatbots will not take over your hotels. Their AI component simply allows them to recognize patterns in human language. They then match the need expressed by the client to a database of possible answers. We speak of NLU (Natural Language Understanding).

Sometimes, your customers ask a question with spelling mistakes or in a form that your bot has never encountered before. In such cases, its ability to answer depends on the quality of the content you have fed it.

  • Generic – available for free on the Internet and will help the bot understand basic expressions like “Hello”, “Thank you” and “How are you?”
  • Specific -what makes your bot capable of being relevant to your business context and challenges. For example, in the hotel industry, it has to understand what a check-in is. The best way to do this is from conversations in verbatim (transcripts of real conversations). These allow the chatbot to understand more and more precisely, concrete requests with the actual formulations of customers. Proper training will make your bot capable of differentiating “I’d like to place a booking” from “I booked through booking”.
  • API content lets your bot access other systems of your IT environment such as your booking engine. Thus it can search and show customer relevant information in real time. For example, room availability and pricing etc. The more APIs you’re able to connect to your bot, the smarter it will be.

Zoe, tell me a joke

Training and conversation design can make chatbots experts at responding to customers on specific topics. However, they don’t think like humans. So they remain unable to respond as soon as the topic of conversation falls out of their area of expertise.

On one hand, a Hotel chatbot can answer very complex but frequently asked questions. On the other, it will not be able to crack a simple joke or tell you how it feels. Which is OK, as chatbots are virtual assistants for specific applications, not your new life companion. On a human chat, you wouldn’t ask these things either. So why the heck would you ask a bot what it is wearing? Zoe answers to over 4000 hotel conversations daily. Not once has it received questions out of the hospitality scope.

Do you expect a quick result from your chatbot ? Then I encourage you to work with an expert company specialized in your industry. One that has already accumulated enough experience and verbatim. (More info on the learning curves of chatbots here.)

Conversation design is as important as intelligence

Conversation design is the ability to frame a conversation. This is to ensure that that the customer immediately feels comfortable and understands what your bot can be helpful with. Some elements of design are essential.

  • Welcome message: Your bot must be extremely clear about its nature and abilities. Most conversation failures happen right at the beginning. So, a well crafted welcome message can dramatically increase the success rate of your bot conversations.
  • Funnels: Some questions such as check-in time can be tackled with simple answers. Others such as booking a room, require a more complex dialogue. This kind of interaction needs to be handled with a series of Q&As called funnels. Funnels gather all the information your chatbot needs to give a precise answer. Once the bot enters a funnel, any question outside of this funnel won’t be understood until the funnel is completed. So if a customer enters a ‘book a room’ funnel and in the middle decides that he wants to ask about the menu of the restaurant, the chatbot won’t understand. It is critical to properly identify what the customer wants before starting a funnel. Also, make the dialog as short as possible.
  • Fallbacks: These define what happens in case of conversation failure. Usually, the chatbot will try to put the conversation back on track. If it doesn’t work, it will transfer to a human being. Thanks to fallbacks, trapping people in an infinite loop no longer happens with decent chatbots. (More info on the different offers of chatbots available on the market here.)

Artificial intelligence is not comparable to human thinking. (Which is why we know chatbots will not take over hotels!) However, while chatbots are not able to improvise, they are very useful to scale repetitive customer interactions and to trigger sales.

If you’d like to discuss more why chatbots will not take over hotels or have questions about artificial intelligence for the hospitality industry, please visit our website or contact Benjamin Devisme at bde@quicktext.im.

Checklist: The Best Direct Booking Strategy
QUICKTEXT
Free Download
10 Best Practices to Boost Direct Bookings
Recent Post
Are you ready to increase your operational efficiency and direct revenue?
Subscribe to our Newsletter
Read more
Optimize your hotel's efficiency and direct bookings
Book a demo