Increasing conversational intelligence with machine learning

Project Pathfinder reads existing chat logs and transcripts of conversations between agents and customers within contact centers, and automatically builds highly effective dialog models used to create and support two-way conversations between virtual assistants and consumers.

Many businesses, government agencies and healthcare organizations are working to implement VAs that are experts in answering questions and responding to requests in areas specific to their organization. Until now, training a virtual assistant to specialize in financial services, telecommunications, healthcare, insurance and other industries was a highly manual, time-consuming and often lengthy process prone to human error. Project Pathfinder demonstrates how machine learning and AI can automate the creation of dialog models by learning from logs of human conversations. This significantly reduces the time and cost to create an intelligent VA that resolves issues quickly and is capable of a contextual, two-way conversation.

“While today’s virtual assistants can reliably facilitate basic gateway questions and answers—such as ‘What’s my account balance?’—most are not able to have a real conversation or address more complex questions,” said Robert Weideman, EVP and GM of Nuance Communications Enterprise Division. “Unlike other conversational AI tools—which are predominantly programmed by humans—Project Pathfinder automates the build for human-to-machine interactions thanks to our advancements in natural language understanding (NLU) and intent discovery. Through Project Pathfinder, Nuance is raising the bar for the value that VAs can deliver.”

Nuance has made Project Pathfinder available to a number of strategic customers. The technology is expected to be generally available within Nuance solutions by the summer of 2019.

Source: Nuance Communications

05.02.2019

• AI (804)
• automation (205)
• machine learning (172)
• medical technology (1541)
• speech processing (36)