Text Intent Recognition
The Intent 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.

API Request

post
https://api.marsview.ai/text/intent
/get_intent
Returns the predicted intent for a given phrases / sentences

Example Curl Request

Shown below is a code snippet to generate an API token
1
curl --location --request POST 'https://api.marsview.ai/cb/v1/auth/create_access_token' \
2
--header 'Content-Type: application/json' \
3
--data-raw '{
4
"jwtToken" : "Insert JWT token Key",
5
"threshold": "Insert a desired confidence threshold",
6
"intentIds": "Insert a list of intent IDs",
7
"sentences": "Insert your sentece for intent recognition",
8
"userId" : "[email protected]"
9
}'
Copied!

Example Response

Shown below is a sample JSON response from the above request.
1
{
2
"status": true,
3
"error": {},
4
"data": {
5
{
6
"similarityMatch": [
7
{
8
"matchedTextList": [
9
{
10
"score": 0.5230883955955505,
11
"text": "Marsview is a great place to work",
12
"value": "Marsview"
13
}
14
],
15
"intentId": "intent-bxllq2f7hpkrvtyzi3-1627981197627",
16
"intentName": "Marsview"
17
},
18
],
19
}
20
}
21
}
Copied!

Response Object

Field
Description
similarityMatch
The intent similarity 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
Last modified 7d ago