As the voice and sometimes face of a company, Contact Centre Agents must deal with customer inquiries efficiently and professionally. Pressures on agents include throughput-based service level goals as well as the need to ensure a top-quality service and sales experiences to customers at every point.
Maintaining this quality and efficiency requires the provision of key customer history data to agents during calls without requiring agents to engage in time consuming searches across interfaces.
SmartContact is an analytics-driven solution that automatically provides Customer Contact Centre Agents with a concise review of customer history and other relevant information points to provide an optimal service experience.
Innovative semi-supervised learning components are included that allow IT and Contact Centre management define the relevance of different information points to different customer types. The key issue handled by SmartConact is to distill, from the massive amount of data relevant to an incoming call, just the key information relevant to a customer contact.
Figure 1: The Assistance Engine learning cycle.
Figure 2: The Call Centre App informing the agent of relevant KPIs
When a call comes in the SmartContact engines predicts the key data points that an agent will need to handle the call and presents these to the agent. This prediction is made using information about:
- the customer
- the customer’s interaction history
- the current state of the customer contact centre
- a customer’s service contract
The SmartContact engine is trained to make useful predictions about the data points needed by agents using a semi-automatic active learning system that can be used by IT and Contact Centre management.
Figure 3: The Training the SmartContact system.
- Dr. Ingo R. Keck, Dublin Institute of Technology
- Dr. Robert Ross, Dublin Institute of Technology