Using the Intent detection node, it is possible to use an NLP service to match user input to intents.
Each Intent Detection node will provide you with a few output ports:
The second port is being deprecated and will be removed by November 2020
Create a Classic flow bot from blueprint. Our getting started bot should be good enough.
This tutorial will cover using Dialogflow, but other vendors are compatible.
intent detection node
.msg.payload.result.fulfilment
.Other properties will also be available for use in your flow.
msg :{
payload :{
result: {
intent: 'intent_name',
slots: {},
action: {},
fulfilment: 'message from NLP', //for a single response
fulfillmentResponses: ['array', 'of', 'nlp', 'responses'],
intentDetectionConfidence: 1
}
}
}
}
When using an intent detection node with DialogFlow, there are a few things to note:
smalltalk.greetings.how_are_you
.{
"intent": "smalltalk.greetings.how_are_you",
"slots": {},
"intentContext": [],
"fulfilment": "I'm doing very well. Thanks!",
"fulfillmentResponses": "I'm doing very well. Thanks!",
"action": "smalltalk.greetings.how_are_you",
"intentDetectionConfidence": 1
}
input.unknown
.{
"intent": "Default Fallback Intent",
"slots": {},
"intentContext": "system_counters",
"fulfilment": "I missed what you said. What was that?",
"fulfillmentResponses": "I missed what you said. What was that?",
"action": "input.unknown",
"intentDetectionConfidence": 1
}