Intent Phrase Detection

The Intent Phrase Analysis model will help you capture semantics behind users' messages and assign it to the right label. It is designed to understand human conversation in the form or free text or spoken text.

Example Response

{
  "status": true,
  "error": {},
  "warning": {},
  "data": {
    {
    "phraseMatch": [
        {
          "matchedTextList": [
            {
              "score": 0.5230883955955505,
              "text": "Marsview is a great place to work",
              "value": "Marsview"
            }
          ],
          "intentId": "intent-bxllq2f7hpkrvtyzi3-1627981197627",
          "intentName": "Marsview"
        },
      ],
    }
  }
}

status field will be set to false if something went wrong while processing the request check for any error messages in the error field

warning field will contain any warnings raised to the user while processing the request. For example if the user sends in a request with invalid intent_ids warning field will contain the list of invalid intent_ids

Response Object

Field	Description
phraseMatch	The intent phrase match output from the models
intentId	The intent Id against which the sentences are matched
intentName	The name of the matching intent
score	The similarity matching score ranges from 0 to 1
text	The sentence which is used to predict intent for
value	The predicted intent