Advanced topics

Intents

The core of well functioning conversational AI is intent classification. Intent classification is the process of understanding what a user means by the text they type. For example, a user who types 'I want to fly from Amsterdam to San Francisco' probably has the intention of booking a flight. Our Natural Language Processing (NLP) takes care of intent classification, but in order to function it needs to be trained with examples.

Adding a Text Trigger lets you train an intent. When you click the Train button you can add examples for this intent. Adding more examples enables the classifier to make better predictions. When you add fewer than ten examples, only exact matching will be used. Always make sure you add a least ten examples that are diverse and have little overlap. When you have a sufficient amount of examples you can click Save. This will save your examples and initiate the training process.

TIP: Make sure you do not create semantically similar intents: if two intents are very similar, the probability of misclassification rises. In that case the best practice is to create a more general intent and then ask follow up questions.

Best practices

Here are some pointers for intent and entity design:

  • Organize your chatflows: make sure you create a flow for every new conversation topic you want to model. Not only does this keep things organized, it also helps the NLP engine.

  • Provide lots of diverse examples for each intent. The more knowledge you enter into your bot, the better it behaves. As a rule of thumb you should provide minimally 10 examples per intent, with as little overlap as possible.

  • Mark entities consistently: mark every item you want your bot to recognize consistently. Do not skip any, as this harms the classification process.

  • Do not create semantically similar intents: if two intents are very similar, the probability of misclassification rises. In that case it’s better to create a more general intent and then ask follow up questions.

  • Use entities for variables and intents for branching. This prevents flows with a wild growth of branches.

results matching ""

    No results matching ""