Customer service is one of the prime targets for automation in the business world. Virtual customer agents are a prime example. These intelligent systems are able to understand what users ask via chat and to provide them with adequate answers. Venture Beat brought this news to us in their article, “The reality of automating customer service chat with AI today.”
Virtual customer agents are able to understand natural language and text and do not just operate in a rules-based multiple-choice environment. They can compete directly with humans to resolve customer service issues.
With all the advances in machine and deep learning, most algorithms rely on largely pattern-based approaches to extract intent from a large repository of previous chat history. The questions asked to banks differ from questions asked to telecom companies. There is currently no off-the-shelf algorithm to fit both cases.
One solution being used to accommodate this situation is to use a host of different algorithms to match user questions to specific intents. This approach increases the accuracy of the answers.
Melody K. Smith
Sponsored by Data Harmony, a unit of Access Innovations, the world leader in indexing and making content findable.
