Learn how to train your chatbot to correctly identify and start a conversation from the Cognitive Flow.
Conversations are an important part of your NativeChat chatbot definition, and training your chatbot to correctly differentiate them is essential.
For each conversation, you need to define a set of user expressions that are real-world examples of how would your users engage with your chatbot.
Here is a set of examples for a booking an appointment with a doctor:
- I would like to book an appointment with doctor John Burke
- Can I check the schedule of doctor Burke for tomorrow?
- Can you book me an appointment with doctor John Burke on Tuesday?
- It will be great if I can meet with doctor Burke this week. What’s his schedule?
- Is there any available slot for today in doctor Burke’s schedule?
The amount of expression varies, but providing an initial set of 10-15 examples is a good start. Once your bot is live, you will be able to train your bot with real examples coming from your users.
Important: Start your training by defining a Conversation type first. It’s essential that your bot recognizes the type of conversation that your users would like to have. It’s a best practice to limit the number of conversations your chatbot supports to 4 or 5.
Important: The value of your Conversation type should directly match the conversation name that you define in the Cognitive Flow definition. The bot won’t know which conversation to trigger if the value doesn’t match the conversation name.
Somethings missing or not clear?
Ask a question in our community forums or submit a support ticket.