Contact Lens for Amazon Connect launches real-time contact center analytics to detect customer issues on live calls
Contact Lens for Amazon Connect, launched at re:Invent 2019, provides a set of machine learning (ML) capabilities integrated into Amazon Connect that analyze call recordings or customer sentiment, trends, and compliance of conversations. Now, Contact Lens supports real-time call analytics capabilities, enabling you to detect customer issues during live calls and resolve them faster.
Contact Lens for Amazon Connect, launched at re:Invent 2019, provides a set of machine learning (ML) capabilities integrated into Amazon Connect that analyze call recordings or customer sentiment, trends, and compliance of conversations. Now, Contact Lens supports real-time call analytics capabilities, enabling you to detect customer issues during live calls and resolve them faster.
With Contact Lens, contact center supervisors can create rules in Amazon Connect to be alerted about customer experience issues based on speech patterns, volume levels, and specific language. For example, supervisors can create rules to track calls where a customer says “not happy,” “poor quality product,” or “cancel my subscription", and get real-time alerts within the Connect real-time metrics dashboard. This enables them to review the customer experience issue, and decide whether to assist the agent through chat, or have the agent transfer the call. When a call is transferred, the agent can pass a real-time transcript with conversation details (like sentiment) to the next agent or supervisor to bring them up to speed so that the customer doesn’t need to repeat themselves.
For automated contact categorization, we have launched semantic matching and pattern matching capabilities. With semantic matching, supervisors can use Contact Lens to categorize/tag calls that contain words/phrases with similar meaning even if they are not mentioned explicitly during the definition of a particular contact category. This is achieved through an ML-based intent matching model that is trained to understand the context and meaning of the keywords specified in the category definition. With pattern matching, Contact Lens can categorize/tag calls based on supervisor-defined patterns related to the phrases spoken by the customer and/or the agent. In addition to this, we have also expanded our language support for Contact Lens to 18 post-call and 4 real-time language variants.
These new real-time capabilities are now available in US West (Oregon), US East (N. Virginia), and Asia Pacific (Sydney) regions. With Contact Lens for Amazon Connect, you only pay for what you use based on the number of call minutes. There are no required up-front payments, long-term commitments, or minimum monthly fees. To learn more about Contact Lens, please visit our webpage or read the blog post.