How to get the user Input mode of an entity?

XO Platform
1

I have bot configured for IVR Channel, it collects both voice and dtmf input. The bot is working fine and i can able to collect voice or dtmf input and flow is good.

I need to know how we can get the Shadow Variables like in VXML, i.e. how can i get which input mode caller provided the input? whether they entered dtmf input or ASR?

2

Hello Vijaya Kumar,

Welcome back to Kore.ai Community

To extract the metadata from the ASR transcription, follow these steps:

  1. In IVR Channel settings under Voice Call Properties various details like Input Mode , ASR Confidence Threshold etc. are configured.


See Voice Call Properties: Channel Settings for more information.

  1. The additional information provided by the ASR engines can be extracted using the context object . This is configured at Bot User Session → lastMessage → asrMetaData .

  2. Go to the Settings panel of the last message node for your dialog task and configure the JavaScript Message under Bot Responses , as shown below:


The ASR metadata is extracted in the response using the following syntax:
print(JSON.stringify(context.session.BotUserSession.lastMessage.asrMetaData))

In this example, based on the ASR Confidence value extracted from the user input, we define the connection rules for the dialog as shown below:

  1. Go to Analyze → NLP Insights of your Virtual Assistant on the Kore.ai XO Platform.

  1. Click on the relevant utterance to see the Chat History details.
  2. Click the ellipsis icon on top of the J avascript Message to view the details of the ASR metadata extracted from the response.

In this example, the parameters like ASR Confidence score , input mode , utterance, etc. are extracted in the syntax shown below:

“data”: {

“text”:
“{“confidence”:”0.810000″,
“Inputmode”:”voice”,
“interpretation”:”Login.”,
“utterance”:”Login.”}”

Reference Documentation:

Hope the helps.

Thank you,
Srujan Madderla
Kore.ai community Team

3

We have Kore AI On Prem Setup and running 10.1.6. We use Nuance NLU Krytpon grammars which we set in IVR channel level and at the node level, we are using directed grxml for dtmf. We are not using transcribe engine and it is not even an option 10.1.6.

I dont see any value in asrMetadata, it is printing as empty json. In the above case, how can i get the filled shadow variables i.e. input mode