Conversational AI Cloud Metrics
When optimizing your Conversational AI Cloud project your environment provides you with a number of metrics to drive your optimization efforts. CM.com always recommends to optimize based on your customers’ behavior, which you can see in our analytics dashboards.
Recognition Rate
Recognition rate shows you how many incoming user questions are being answered by your Conversational AI Cloud project. It’ll show you where you’re currently lacking in recognition, resulting in fallback events being triggered. You can optimize recognition rate by:
Evaluating what use cases your customers are asking about through the recognition analysis dashboard, and adding new intents/entities to your recognition based on those insights.
Be careful when optimizing for recognition rate, as it is fine to lack recognition for questions that don’t relate to your company, the products, or the services you provide. In a lot of scenario’s it could be more desirable to have no recognition, with a proper fallback answer than to optimize for questions/use cases that don’t serve your companies goals.
Recognition Quality
Recognition quality shows you how well a question was recognized by our entity driven rule-based recognition engine. It’ll only show for recognition that wasn’t caught by your trained intent model and was matched purely through entities, and keywords. The recognition quality is a calculation of the number of condition sets (entities, keywords) present in the end-users question compared to the question on the article that it matched to. Recognition quality can be used to determine where you might want to expand an entity, add additional keyword triggers to a Q&A to improve the performance of your rule-based recognition engine.
