Qualification

Dialogs are classified into 3 categories according to their type. Observing their distribution makes it possible to follow the success rate of the bot.

The 3 categories are as follows:

• Only direct answers: the dialog consists only of direct questions / answers. This means that the bot has been able to understand all the questions and provide the answers;

• Ending with direct answer: during the dialog, the question or an incomprehension can be reworded, but the dialog ends with an answer;

• Failed: the dialog ends with an incomplete question or a suggestion for formulations and the user has not clicked on any of them.

The first two categories are considered successful dialogs. The evolution of the dialogs distribution over time reflects the training of the bot.

When you create a knowledge, you can specify the type of contact provided in the answer. This makes it possible to know the offset of users towards a type of contact according to the qualification.

Thus, it is possible to know, among the percentage of failures, what has been proposed to users who have not, a priori, gotten their answers through the bot and which have therefore been redirected to another type of contact for information.

You then find the qualification of the dialogs according to the number of interactions.

You can also view the dialogs qualification based on the browser used.