Statement Tags

Statement tag classification is the task of classifying an utterance with respect to the function it serves in a dialogue, i.e. the act the speaker is performing. These tags can be configured to detect custom intents by giving example statements.

modelType Configuration

Keys	Value
modelType	statement_tag_analysis
modelConfig	Model Configuration object for statement_tag_analysis - the statement tag ids which need to be used to

Example Request

Curl

curl --location --request POST 'https://api.marsview.ai/cb/v1/conversation/compute' \
--header 'Content-Type: application/json' \
--header "Authorization: {{Insert Auth Token}}" \
--data-raw '{
        "txnId": "{{Insert txn ID}}",
        "enableModels":[
            {
            "modelType":"speech_to_text",
                "modelConfig":{
                    "automatic_punctuation" : true,
                    "custom_vocabulary":["Marsview", "Communication"],
                    "speaker_seperation":{
                        "num_speakers":2
                    },
                    "enableKeywords":true,
                    "enableTopics":false
                    }
            },
            {
            "modelType": "statement_tag_analysis",
            "modelConfig": {
                "config": {
                    "statements": [
                        "statement-1c6q62hzkxim6ect-1640242740269", 
                        "statement-1c6q62hzkxim9q8o-1640242895640"
                        ]
                    }
                }
            }
        ]
}'

Python

import requests
auth_token = "replace this with your auth token"
txn_id = "Replace this with your txn id"
request_url = "https://api.marsview.ai/cb/v1/conversation/compute"


def get_statement_tags():
  payload={
        "txnId": txn_id,
        "enableModels":[
            {
            "modelType":"speech_to_text",
                "modelConfig":{
                    "automatic_punctuation" : True,
                    "custom_vocabulary":["Marsview", "Communication"],
                    "speaker_seperation":{
                        "num_speakers":2
                    },
                    "enableKeywords":True,
                    "enableTopics":False
                }
            },
            {
            "modelType": "statement_tag_analysis",
            "modelConfig": {
                "config": {
                    "statements": [ 
                        "statement-1c6q62hzkxim6ect-1640242740269",
                        "statement-1c6q62hzkxim9q8o-1640242895640"
                        ]
                    }
                }
            }
            ]
        }
  headers = {'authorization': '{}'.format(auth_token)}
  
  response = requests.request("POST", headers=headers, json=payload)
  print(response.text)
  if response.status_code == 200 and response.json()["status"] == "true":
    return response.json()["data"]["enableModels"]["state"]["status"]
  else:
    raise Exception("Custom exception")

if __name__ == "__main__": 
    get_statement_tags()

Example Response

"data": {
    "sentiment": [
            {
                "startTime": 1390,
                "endTime": 2690,
                "speakers": [
                    "1"
                ],
      "similarityMatch": [
        {
          "statementTagId": "statement-bxllq1zsuzkvuj44go-1636609624728",
          "statementTagName": "compliance-quality-check"
          "matchedTextList": [
            {
              "score": 0.6180883955955505,
              "text": "This call is going to be recorded for quality purposes.",
              "value": "This call will be recorded"
            }
          ],
        }
      ],                
      "sentence": "This call is going to be recorded for quality purposes."
      },
    ]
}

Response Object

Field	Description
startTime	Start time of the sentence in the input Video/Audio in milliseconds.
endTime	End time of the sentence in the input Video/Audio in milliseconds.
speakers	A list of speaker id's whose voices are identified for a given time frame. Normally this list would only have a single speaker Id.
similarityMatch	The statement tag similarity identified by the models
statementTagId	The statement tag Id against which the sentences are matched
statementTagName	The name of the matching statement tag
score	The similarity matching score ranges from 0 to 1
text	The sentence which is used to predict statement tag for
value	The predicted statement tag
sentence	A sentence identified by the model in the given time frame.