Booking.com is currently training the bot to refine the current number of questions it can manage into more than 90 specific sub-topics.
Leveraging natural language processing technology, the tool identifies the most frequently asked post-booking questions from customers – including on payment, transportation, arrival and departure times, date changes, cancellation requests, parking information, extra bed requests, pet policies, Wi-Fi and Internet availability, as well as a wide variety of greetings and thank-you messages.
If the Booking Assistant, which is built entirely in-house, has identified a question it can’t solve on its own, depending on the nature of the query, it pulls in support from either the Booking.com customer service team or the property, adding their response directly into the conversation and making the source of that information known to customers.
“For us, AI is not about replacing human interaction, but is instead a vehicle to facilitate an even more personalised, instantaneously gratifying and frictionless travel experience for consumers,” said James Waters, global director of customer service at Booking.com. “As we operate in an industry that is incredibly personal, emotional and complex, maintaining the right balance between genuine human interaction and efficient automation is something we’re always trying to fine-tune and optimise throughout every stage of the consumer journey, including with the Booking Assistant.”
Get the full story at TTG Asia
Read also "Booking.com’s chatbot can handle 30% of customers’ hotel-related questions"