Utterances are sample phrases that a user would use to describe what they want to do. For example, “I want to book a room for tomorrow,” or “I want to reserve a room for tomorrow.” Both of these utterances convey the same intent: to book a room for tomorrow.
An utterance can include one or more slots, or no slots. Consider this utterance, “Book a suite for three nights starting tomorrow.” The bot identifies slots mentioned in the utterance: two rooms, three nights, and tomorrow and maps them accordingly to the corresponding slot types. While number of rooms required, number of nights, and date can map to built-in slot types, the type of room requested (executive) can map to a custom slot type.
While this article pertains to Genesys Dialog Engine Bot flows and Genesys Digital Bot Flows, this video demonstrates how utterances work using Genesys Dialog Engine Bot Flows:
When creating sample utterances, try to create variations and a wide range of semantics for each intent. Best practice recommends that you create multiple variations of the same phrase.
Intent health helps guide you as you build out your intents and gives you the tools to improve more easily and accurately the performance of your intents and training utterances. Use the view to see your intent health score based on your training data and analyze recommendations that help improve utterances that affect the health score. The intent health view gives you key performance data, including these analysis points:
- Intent score for each intent
- Recommendations to improve each utterance, such as potentially confused utterances, duplicate utterances, outliers, and utterances that are too long
- Recommendations to improve each utterance
- The list of utterances in descending order of severity count