Nuance's AI uses real interactions to make chat bots smarter

Project Pathfinder draws on human conversation, not service scripts.

Many high profile brands and companies have a customer service chat bot function on their website. Indeed, some research suggests that by 2020 conversational AI will be the main go-to for customer support in large organizations. But as the current technology stands, it's only as effective as the manual programming that's gone into its creation, and relies on the customer asking the right questions or including the right keywords to send the bot down the right branch of script. Today, though, Nuance Communication has announced a new technology that aims to make the conversational intelligence of chat bots a whole lot smarter.

Instead of using specially trained "conversation designers" to create dialog patterns, Project Pathfinder leverages machine learning and AI to read existing transcripts of conversations between human service agents and customers, and creates a new workflow based on that data. Using what Nuance calls "intent discovery," the system is able to build a comprehensive conversation map to build a visual representation of all the different avenues its customer service conversations take -- from first question to each follow-up-- to reveal the best paths to resolution, as well as unknown problem areas. So while current chat bots might be able to address basic questions such as "What's my account balance?" Project Pathfinder enables the system to address more complex queries, rather than farming customers off to human agents.

The technology will have particularly useful applications within industries such as finance and healthcare, where queries are often niche and demand privacy compliance, although this kind of system will undoubtedly make its way to a wider range of services in future, as customer service increasingly moves online. Nuance is currently working with a number of unnamed strategic partners, but expects to roll out Project Pathfinder more generally this summer.