Intent health considerations and examples

Feature coming soon

With intent health, you can refine the health status of your intents for supported individual languages. 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. For more information, see Bot intent health overview and Work with intent health. This article demonstrates how to evaluate a bot’s intents and utterances, and then implement improvements.

The examples that follow describe different intent health summaries for a bot flow. However, you can access intent health in both Genesys Dialog Engine Bot Flows and Genesys Digital Bot Flows.

Intent health considerations

  • Check every intent, even intents in very good and good condition, to see specific suggestions.
  • You do not need to address every recommended issue in order for the bot to work properly.
  • If you have close utterances in two intents that are legitimate, but marked as in conflict because of vocabulary overlap, just make sure that you handle your most frequent examples correctly. 

Intent health examples

Some intents in the following image are in very good or good health, while others are in OK or poor health.

Click the image to enlarge.

Intent Health example

Example: Very good intent 

The next image shows details about the Account lookup intent. In this image, notice that the intent health displays a green bar and indicates that the health is very good. The intent contains no conflicts, although the number of utterances is low. Consider adding more utterances to build the confidence of this intent.

Next to the green bar, you can see that the intent has 5 utterances, which is the minimum recommendation. If you add 20 or more utterances, the green counter bar no longer appears, but the number of utterances remains.

Click the image to enlarge.

Very good intent health

Example: OK intent

Next, look at the Cancel Application intent. In this image, the intent health is OK. The intent contains enough utterances, but five utterances are in conflict.

Click the image to enlarge.

Utterances in conflict

Example: Utterance in conflict

In the first utterance, “cancel new loan,” when you hover over the Utterance in Conflict label, details about the conflict appear. Notice that the utterance is similar to one found in the “cancel loan” intent.

Click the image to enlarge.

Utterance conflict details

The utterance, “cancel new loan” in the Cancel_Application intent is in conflict with the “cancel a loan” utterance in the Cancel_Loan intent. This image shows the Cancel_Loan intent and the conflicting utterance:

Click the image to enlarge.

Conflicting utterance

The two utterances mean the same thing in both intents. Consider deleting or rephrasing utterances that are too similar in different intents to avoid confusion.

Example: Improve intent health

In this example, the intent has a status of OK because it only contains four utterances. A new utterance appears in the list, but the flow has not been saved. The utterance summary indicates that you made changes, and that you have one utterance in conflict.

Click the image to enlarge.

Utterance health status

Notice what happens after you add the fifth utterance, resolve the conflict, and save the flow. The status changes from OK to Very Good. Your intent now has at least five unique utterances that are not in conflict with another intent’s utterances.

Click the image to enlarge.

Intent in very good health