GETTING STARTED
Kore.ai XO Platform
Virtual Assistants Overview
Natural Language Processing (NLP)
Concepts and Terminology
Quick Start Guide
Accessing the Platform
Working with the Builder
Building a Virtual Assistant
Using Workspaces
Release Notes
Current Version
Previous Versions
Deprecations

CONCEPTS
Design
Storyboard
Dialog Tasks
Overview
Dialog Builder
Node Types
Intent Node
Dialog Node
Entity Node
Form Node
Confirmation Node
Message Nodes
Logic Node
Bot Action Node
Service Node
Webhook Node
Script Node
Group Node
Agent Transfer
User Prompts
Voice Call Properties
Dialog Task Management
Connections & Transitions
Component Transition
Context Object
Event Handlers
Knowledge Graph
Introduction
Knowledge Extraction
Build Knowledge Graph
Add Knowledge Graph to Bot
Create the Graph
Build Knowledge Graph
Add FAQs
Run a Task
Build FAQs from an Existing Source
Traits, Synonyms, and Stop Words
Manage Variable Namespaces
Update
Move Question and Answers Between Nodes
Edit and Delete Terms
Edit Questions and Responses
Knowledge Graph Training
Knowledge Graph Analysis
Knowledge Graph Import and Export
Importing Knowledge Graph
Exporting Knowledge Graph
Creating a Knowledge Graph
From a CSV File
From a JSON file
Auto-Generate Knowledge Graph
Alert Tasks
Small Talk
Digital Skills
Digital Forms
Views
Introduction
Panels
Widgets
Feedback Survey
Train
Introduction
ML Engine
Introduction
Model Validation
FM Engine
KG Engine
Traits Engine
Ranking and Resolver
NLP Configurations
NLP Guidelines
Intelligence
Introduction
Contextual Memory
Contextual Intents
Interruption Management
Multi-intent Detection
Amending Entities
Default Conversations
Sentinment Management
Tone Analysis
Test & Debug
Talk to Bot
Utterence Testing
Batch Testing
Conversation Testing
Deploy
Channels
Publish
Analyze
Introduction
Conversations Dashboard
Performance Dashboard
Custom Dashboards
Introduction
Meta Tags
Dashboards and Widgets
Conversations History
Conversation Flows
Feedback Analytics
NLP Metrics
Containment Metrics
Usage Metrics
Smart Bots
Universal Bots
Introduction
Universal Bot Definition
Universal Bot Creation
Training a Universal Bot
Universal Bot Customizations
Enabling Languages
Store
Manage Assistant
Plan & Usage
Overview
Usage Plans
Support Plans
Invoices
Authorization
Multilingual Virtual Assistants
Masking PII Details
Variables
IVR Settings
General Settings
Assistant Management
Data Table
Table Views
App Definitions
Sharing Data Tables or Views

HOW TOs
Build a Flight Status Assistant
Design Conversation Skills
Create a Sample Banking Assistant
Create a Transfer Funds Task
Create a Update Balance Task
Create a Knowledge Graph
Set Up a Smart Alert
Design Digital Skills
Configure Digital Forms
Configure Digital Views
Add Data to Data Tables
Update Data in Data Tables
Add Data from Digital Forms
Train the Assistant
Use Traits
Use Patterns for Intents & Entities
Manage Context Switching
Deploy the Assistant
Configure an Agent Transfer
Use Assistant Functions
Use Content Variables
Use Global Variables
Web SDK Tutorial
Widget SDK Tutorial
Analyze the Assistant
Create a Custom Dashboard
Use Custom Meta Tags in Filters

APIs & SDKs
API Reference
API Introduction
API List
API Collection
koreUtil Libraries
SDK Reference
SDK Introduction
SDK Security
SDK Registration
Web Socket Connect and RTM
Using the BotKit SDK
BotKit SDK Tutorial - Blue Prism

ADMINISTRATION
Introduction
Assistant Admin Console
Administration Dashboard
User Management
Add Users
Manage Groups
Manage Roles
Assistant Management
Enrollment
Invite Users
Send Bulk Invites
Import User Data
Synchronize Users from AD
Security & Compliance
Using Single-Sign On
Security Settings
Cloud Connector
Analytics
Billing
  1. Home
  2. Docs
  3. Virtual Assistants
  4. How Tos
  5. Using nlMeta4 min read

Using nlMeta4 min read

At times one wants to control the flow of the virtual assistant by taking an alternate path to improve the user’s experience.

Consider the following scenarios:

  1. The NLP engine might have identified an intent based on the user utterance. But a  different task might be more suitable based on additional information gathered from the backend systems or from the webpage where the SDK is hosted or any other external information.
  2. Consider a flight booking virtual assistant that greets the user with the best ongoing deals as part of the Welcome message. Based on the user selection, the ‘book flight’ task can be programmatically invoked by prepopulating the travel details like source city, destination city, travel, etc. from the deal information presented to the user.

Kore.ai provides a way to pass information to the virtual assistant programmatically using nlMeta data. This can be used in the BotKit SDK, Widget SDK, and Web SDK to pass information like intent to be triggered along with the entity values, and other task settings as per your need.

nlMeta

nlMeta is an object which can be used to pass information to the bot. The bot would use this information to execute the intent specified therein before attempting at decoding any other information.

Sample

The following is a sample of how the nlMeta object needs to be populated:

      'nlMeta': {
            'intent': '<intent_name>',  
            'childBotName': '<child_bot_name>',
            'isRefresh': <true/false>, 
            'entities': {      
			'<entity1_value>': value1,
                        '<entity2_value>': value2,
			},
      	    'interruptionOptions': {
               'hr': {
                 'h': 1;
                 'r': 1;
                 'nn': true
                }
              }
      }

Parameters

The following are the parameters that can be used in this object:

Parameters Description
nlMeta An object for natural language information for the bot
intent Intent identified via 3rd party which needs to be triggered by the bot
childBotName Only used in case of a universal bot to identify the child bot intent to trigger
entities Object with entity-value pairs as needed by the intent to be triggered
isRefresh
  • Set to true to end the current task and start executing incoming task
  • If not set or if set to false the incoming task would be executed as per hold and resume settings
interruptionOptions

To indicate the interruption behavior, in case any task is in progress when the bot receives this nlMeta information. Values can be:

  • discardAll – to discard current and previous tasks, if any
  • hr – for hold and resume options
    h

    for hold option, following are the options:

    • 1 – “Hold the current task and resume back once the new task is completed”
    • 2- “Discard the current task and switch to new”
    • 3- “Switch to new task without any notification to user and discard current task”
    • 4- “Continue the current task and add new task to the follow-up task list”
    • 5- “Allow the end user to select the behavior”
    r

    for resume option, following are the options:

    • 1 – “Get confirmation with the user before resuming an on-hold task”
    • 2- “Notify the user with a message that the on hold task is being resumed”
    • 3- “Resume the on hold task without any specific message to the user”
    nn

    neverNotify – notification to the user

    • True – Always resume the on hold task without any specific message to the user if the task ended in a single response
    • False – inform the user

In case, the requested task is not found the bot would respond with a standard response “Dialog task required for conversation not available”.

Usage

As mentioned, nlMeta can be populated and sent to the virtual assistant via BotKit SDK, and web/widget SDK. The following illustrates how it can be accomplished:

  • BotKit SDK – as part of metaInfo object:
    data.metaInfo = {
          'nlMeta': {
                'intent': 'Authenticate User', 
                'isRefresh': true, 
        	     'entities': {
    		"Name": "John"
    		},
     	    'interruptionOptions': 'discardAll'
          }
    }
  • Web SDK – the nlMeta information can be sent as a parameter using the sendMessage function. You can find this function in the chatWindow.js file. Add a condition when the nlMeta data needs to consumed as follows:
    if(_this.text() == “Existing”){
    me.sendMessage(_this, attachmentinfo, {'nlMeta': {
                'intent': 'Authenticate User'}}); 
    }
        	else{
    		me.sendMessage(_this, attachmentinfo);
    		}

    In the above example, the Authenticate User intent would be triggered if the text field contains the value “Existing”.

  • Widget SDK – the nlMeta information can be sent as part of the payload for various templates like button, menu, list, etc., see here for details
Menu