GETTING STARTED
Kore.ai XO Platform
Virtual Assistants Overview
Natural Language Processing (NLP)
Concepts and Terminology
Help & Learning Resources
Quick Start Guide
Accessing the Platform
Navigating the Kore.ai XO Platform
Building a Virtual Assistant
Using Workspaces
Release Notes
Current Version
Previous Versions
Deprecations
Request a Feature
CONCEPTS
Design
Storyboard
Overview
FAQs
Conversation Designer
Overview
Dialog Tasks
Mock Scenes
Dialog Tasks
Overview
Navigate Dialog Tasks
Build Dialog Tasks
Nodes & Connections
Overview
Node Types
Intent Node
Dialog Node
Entity Node
Entity Rules
Form Node
Confirmation Node
Message Nodes
Logic Node
Bot Action Node
Service Node
Webhook Node
Script Node
Process Node
Agent Transfer
Node Connections Setup
Sub-Intent Scoping
User Prompts
Voice Call Properties
Dialog Task Management
Supported Entity Types
Supported Company Names
Supported Colors
Knowledge Graph
Introduction
Knowledge Extraction
Build Knowledge Graph
Create Node Structure
Build the Graph
Add FAQs
Add FAQs from an Existing Source
Run a Task
Traits, Synonyms, and Stop Words
Manage Variable Namespaces
Update Knowledge Graph
Introduction
Move Question and Answers Between Nodes
Edit and Delete Terms
Edit Questions and Responses
Knowledge Graph Analysis
Knowledge Graph Import and Export
Prepare Data for Import
From a CSV File
From a JSON File
Importing Knowledge Graph
Exporting Knowledge Graph
Auto-Generate Knowledge Graph
Alert Tasks
Small Talk
Digital Skills
Overview
Digital Forms
Digital Views
Introduction
Widgets
Panels
Session and Context Variables
Context Object
Train
NLP Optimization
ML Engine
Overview
Model Validation
FM Engine
KG Engine
Traits Engine
Ranking and Resolver
Training Validations
NLP Configurations
NLP Guidelines
Intelligence
Introduction
Event Handlers
Default Standard Responses
Contextual Memory
Contextual Intents
Interruption Management
Multi-intent Detection
Amending Entities
Default Conversations
Conversation Driven Dialog Builder
Sentinment Management
Tone Analysis
Test & Debug
Overview
Talk to Bot
Utterance Testing
Batch Testing
Conversation Testing
Health and Monitoring
Deploy
Channels
Publishing
Versioning
Analyze
Introduction
Overview Dashboard
Conversations Dashboard
Users Dashboard
Performance Dashboard
Custom Dashboards
Introduction
Custom Meta Tags
Create Custom Dashboard
NLP Insights
Conversations History
Conversation Flows
Analytics Dashboard Filters
Usage Metrics
Containment 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
Get Started
Supported Components & Features
Manage Languages
Manage Translation Services
Multiingual Virtual Assistant Behavior
Masking PII Details
Variables
Collections
IVR Settings
General Settings
Assistant Management
Manage Namespace
Data as Service
Data Table
Table Views
App Definitions
Sharing Data Tables or Views
HOW TOs
Build a Travel Planning Assistant
Travel Assistant Overview
Create a Travel Virtual Assistant
Design Conversation Skills
Create an ‘Update Booking’ Task
Create a Change Flight Task
Build a Knowledge Graph
Schedule a Smart Alert
Design Digital Skills
Configure Digital Forms
Configure Digital Views
Train the Assistant
Use Traits
Use Patterns
Manage Context Switching
Deploy the Assistant
Configure Agent Transfer
Use Bot Functions
Use Content Variables
Use Global Variables
Use Web SDK
Build a Banking 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
Composite Entities
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
Intent Scoping using Group Node
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
Widget SDK Tutorial
Web SDK Tutorial
ADMINISTRATION
Introduction to 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 & Control
Using Single-Sign On
Security Settings
Cloud Connector
Analytics
Billing
  1. Home
  2. Docs
  3. Virtual Assistants
  4. Bot Settings
  5. Conversation Sessions

Conversation Sessions

Conversation sessions are defined as uninterrupted interactions between the bot and the user. These sessions are used in multiple analytics dashboards in the Bot Builder as well as Bot Admin Console platforms.

Kore.ai virtual assistant platform allows you to customize how these Conversation Sessions are to be created and closed.

Conversation Sessions are different from Billing Sessions, refer here for more on Billing Sessions.

Overview

A Conversation Session is defined as an uninterrupted volley between the end-user and the bot.

  • Before the release of v7.2 of the platform – a new session was created after the inactivity duration (set as 15 mins) has elapsed since the end-users’ last interaction.
  • Post v7.2 release – after the inactivity duration (set as 15 mins) has elapsed
    • if the end-user comes back and continues with the same intent, then the current session continues;
    • if the end-user comes back with a new intent or with an invalid input for the existing intent, a new session is created.
  • Post v8.0 release, platform gives you an option to:
    • Proactively close the sessions after inactivity – see Manage Sessions to know more.
    • Not proactively close the sessions after inactivity – retain the v7.2 behavior described above;

Conversation Sessions are created for all interactions with the virtual assistant. These include:

  • All conversations that include one or more messages from the user marked as interactive sessions. These include all end-user interactions across all channels and events including providing authorization details.
  • All Virtual assistant initiated conversion sessions like onConnect event messages are recorded as non-interactive sessions. These sessions will be updated as Interactive sessions as soon as a user message is received. Non-interactive sessions are not considered for calculating the billing sessions.
  • Developer interactions are also included as conversation sessions. A flag differentiates the user sessions from developer sessions and billing sessions are not created for these developer sessions.

Note: Inclusion of non-interactive and developer interactions in conversation sessions was implemented starting from ver8.0.

Manage Sessions

This feature is only available post v8.0 of the platform release.

You can define the Conversation Session behavior sing the Manage Sessions option under Configurations from Build tab.

The following details explain the options available on the page, to define the conversation sessions.

  • Do not proactively close the sessions after inactivity – Select this option to close the session only when the user returns after 15 minutes of inactivity and provides a new intent. This was the default behavior before the release of ver8.0 of the platform. This option will be deprecated in future releases.
  • Proactively close the sessions after inactivity – Select this option to close the session after a defined duration of inactivity. You can set the following parameters:
    • Inactivity Duration – this is set to 15 minutes by default. The session closes after the time duration set here.

      Note: The minimum value that can be set here is 5 min and the maximum value is 20160 min (14 days). These values can be configured at the application level through Koreconfig.

    • Pre-closure Behavior – You can choose to close the session without informing the user or inform the user about the session closure by sending out a message. This message can be customized using the Manage response link. You can click Add Response, if you want to add a new response.

Implementation

When does a Conversation Session start?

Conversation Sessions are created for all interactions:

  • All end-user interactions across all channels and events – Conversation sessions are created for On_connect – Run a script, Run a Message, Trigger a Dialog scenario. There are two categories of these conversation sessions:
    • Interactive sessions are conversations that include one or more messages from the user.
    • Non-interactive sessions are conversations with no messages from the user. All bot initiated conversion sessions start as ‘Non-interactive’. These sessions are updated as Interactive sessions as soon as a user message is received. The non-interactive sessions are not considered for calculating the billing sessions.
  • Developer interactions will also be considered for creating conversation sessions but these are marked as different from the user sessions and are not considered for Billing Sessions.

When does a Conversation Session close?

  • The platform proactively closes inactive sessions after the specified time of inactivity set in the Manage Sessions option.
  • When the following utterances are detected – “Discard”
  • When the chat window is refreshed ie “refresh: true” is detected.

What happens when a Conversation Session closes?

  • Post-session closure, the following information or variables will be cleared:
    • Conversation session;
    • Bot User Session (developer-defined variables without custom TTL)
    • Dialog Context (Topic File and Conversation Details)
    • If configured, before closing the conversation session, the platform will proactively send a session closure message to the users on supported channels.
  • For “refresh: true”:
    • Complete session information is cleared;
    • A new conversation session is created.
  • For “discard all
    • The Dialog context, Current and Historic Tags are cleared;
    • The Sentiment Tones are reset;
    • The same Conversation Session will be continued
  • For “discard
    • The current Dialog context will be cleared;
    • The Current Tags will be replaced with the last updated ‘tags’ in the Historic Tags, and the Historic Tags would be cleared;
Menu