GETTING STARTED
Kore.ai XO Platform
Virtual Assistants Overview
Natural Language Processing (NLP)
Concepts and Terminology
Quick Start Guide
Accessing the Platform
Navigating the Kore.ai XO Platform
Building a Virtual Assistant
Help & Learning Resources
Release Notes
Current Version
Recent Updates
Previous Versions
CONCEPTS
Design
Storyboard
Overview
FAQs
Conversation Designer
Overview
Dialog Tasks
Mock Scenes
Dialog Tasks
Overview
Navigate Dialog Tasks
Build Dialog Tasks
Node Types
Overview
Intent Node
Dialog Node
Dynamic Intent Node
GenAI Node
GenAI Prompt
Entity Node
Form Node
Confirmation Node
Message Nodes
Logic Node
Bot Action Node
Service Node
Webhook Node
Script Node
Process Node
Agent Transfer
Node Connections
Node Connections Setup
Sub-Intent Scoping
Entity Types
Entity Rules
User Prompts or Messages
Voice Call Properties
Knowledge AI
Introduction
Knowledge Graph
Introduction
Terminology
Build a Knowledge Graph
Manage FAQs
Knowledge Extraction
Import or Export Knowledge Graph
Prepare Data for Import
Importing Knowledge Graph
Exporting Knowledge Graph
Auto-Generate Knowledge Graph
Knowledge Graph Analysis
Answer from Documents
Alert Tasks
Small Talk
Digital Skills
Overview
Digital Forms
Digital Views
Introduction
Widgets
Panels
Session and Context Variables
Context Object
Intent Discovery
Train
NLP Optimization
ML Engine
Overview
Model Validation
FM Engine
KG Engine
Traits Engine
Ranking and Resolver
Training Validations
NLP Configurations
NLP Guidelines
LLM and Generative AI
Introduction
LLM Integration
Kore.ai XO GPT Module
Prompts & Requests Library
Co-Pilot Features
Dynamic Conversations Features
Intelligence
Introduction
Event Handlers
Contextual Memory
Contextual Intents
Interruption Management
Multi-intent Detection
Amending Entities
Default Conversations
Conversation Driven Dialog Builder
Sentinment Management
Tone Analysis
Default Standard Responses
Ignore Words & Field Memory
Test & Debug
Overview
Talk to Bot
Utterance Testing
Batch Testing
Conversation Testing
Conversation Testing Overview
Create a Test Suite
Test Editor
Test Case Assertion
Test Case Execution Summary
Glossary
Health and Monitoring
NLP Health
Flow Health
Integrations
Actions
Actions Overview
Asana
Configure
Templates
Azure OpenAI
Configure
Templates
BambooHR
Configure
Templates
Bitly
Configure
Templates
Confluence
Configure
Templates
DHL
Configure
Templates
Freshdesk
Configure
Templates
Freshservice
Configure
Templates
Google Maps
Configure
Templates
Here
Configure
Templates
HubSpot
Configure
Templates
JIRA
Configure
Templates
Microsoft Graph
Configure
Templates
Open AI
Configure
Templates
Salesforce
Configure
Templates
ServiceNow
Configure
Templates
Stripe
Configure
Templates
Shopify
Configure
Templates
Twilio
Configure
Templates
Zendesk
Configure
Templates
Agents
Agent Transfer Overview
Custom (BotKit)
Drift
Genesys
Intercom
NiceInContact
NiceInContact(User Hub)
Salesforce
ServiceNow
Configure Tokyo and Lower versions
Configure Utah and Higher versions
Unblu
External NLU Adapters
Overview
Dialogflow Engine
Test and Debug
Deploy
Channels
Publishing
Versioning
Analyze
Introduction
Dashboard Filters
Overview Dashboard
Conversations Dashboard
Users Dashboard
Performance Dashboard
Custom Dashboards
Introduction
Custom Meta Tags
Create Custom Dashboard
Create Custom Dashboard Filters
LLM and Generative AI Logs
NLP Insights
Task Execution Logs
Conversations History
Conversation Flows
Conversation Insights
Feedback Analytics
Usage Metrics
Containment Metrics
Universal Bots
Introduction
Universal Bot Definition
Universal Bot Creation
Training a Universal Bot
Universal Bot Customizations
Enabling Languages
Store
Manage Assistant
Team Collaboration
Plan & Usage
Overview
Usage Plans
Templates
Support Plans
Invoices
Authorization
Conversation Sessions
Multilingual Virtual Assistants
Get Started
Supported Components & Features
Manage Languages
Manage Translation Services
Multiingual Virtual Assistant Behavior
Feedback Survey
Masking PII Details
Variables
Collections
IVR Settings
General Settings
Assistant Management
Manage Namespace
Data
Overview
Data Table
Table Views
App Definitions
Data as Service
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
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
Migrate External Bots
Google Dialogflow Bot
APIs & SDKs
API Reference
API Introduction
Rate Limits
API List
koreUtil Libraries
SDK Reference
SDK Introduction
Web SDK
How the Web SDK Works
SDK Security
SDK Registration
Web Socket Connect and RTM
Tutorials
Widget SDK Tutorial
Web SDK Tutorial
BotKit SDK
BotKit SDK Deployment Guide
Installing the BotKit SDK
Using the BotKit SDK
SDK Events
SDK Functions
Tutorials
BotKit - Blue Prism
BotKit - Flight Search Sample VA
BotKit - Agent Transfer
  1. Home
  2. Docs
  3. Virtual Assistants
  4. Builder
  5. Knowledge Graph
  6. Build a Knowledge Graph

Build a Knowledge Graph

The XO Platform’s Knowledge Graph (KG) helps you turn your static FAQ text into an intelligent, personalized conversational experience. It goes beyond the usual practice of capturing FAQs as flat question-answer pairs. Instead, the Knowledge Graph enables you to create a hierarchical structure of key domain terms and associate them with context-specific questions and their alternatives, synonyms, traits, and more. Additionally, you can opt for the LLM-based Few-Shot Knowledge Graph, which requires no ontology and reduces maintenance and training requirements.

See here for more on KG Terminology.

To generate a Knowledge Graph, you need to add FAQs to an existing or new VA. If you have not created a VA, refer to Building a Virtual Assistant..

To open the Knowledge Graph builder, follow the below steps:

  1. Log in to the XO Platform and open the VA to which you want to add the Knowledge Graph.
  2. Select the Build tab from the top menu.
  3. On the left menu, select Conversation Skills and click Knowledge Graph.
  4. You will notice that there is already a Knowledge Graph with the name of your assistant.

Notes on the Few-Shot Knowledge Graph

All features explained here are supported by the Few-Shot Knowledge Graph, except for the following:

  1. Few-Shot Knowledge Graphs do not require an ontology structure, but you can create one to  improve intent detection. 
  2. Default terms are not available in Few-Shot Knowledge Graphs. The only exception is when you switch from an Ontology Graph, in which case existing Default terms are stored as such until updated. Afterward, Default terms become Organizer terms and can be set as Mandatory.
  3. Lemmatization using Parts of Speech, Search in Answer, and Contextual Paths Qualification are not supported by Few-Shot Graphs. Please see the Knowledge Graph Types Comparison Table for a detailed list of supported features.
  4. Path Level and Knowledge Graph Synonyms are only supported for Mandatory Terms and for Tags.

Create the Knowledge Graph Node Structure

By default, the name of the VA becomes the root node of the hierarchy and you can edit this. Create the rest of the nodes below the root node.

To create nodes, follow the below steps:

  1. Open the Knowledge Graph.
  2. On the top left of the Knowledge Graph window, hover over the root node.
  3. Click the + icon. A text box appears below to Add Node. For better performance, there is a restriction of 50k FAQs spread across 20k maximum allowed number of nodes.
  4. Type the name of the node in the text box and press Enter. A warning would be displayed in case you enter a duplicate node name, i.e. if a child node with the same name already exists under the parent node.

    Note: This node becomes a child for the root node and can be referred to as a First-level node.
  5. Repeat steps 1 to 3 to create other First-level nodes.
  6. After you create First-level nodes, create child nodes as follows:
    1. Hover over any First-level node, and click the plus icon to create its child node.
    2. You can create a child node for any level node by hovering over it and clicking the + icon.

Follow the same process to create multiple node levels. 

The demo below shows you how to create nodes.

You can delete nodes by clicking the bin icon on the right.


Build the Knowledge Graph

The next step is to add Knowledge Graph Intents which can be either:

  • FAQ – to answer user queries
  • Task – to execute a dialog task.

Add FAQs

Using this option, you can add relevant question-answer sets to the nodes in the hierarchy. Note that there is a limit  of 50k FAQs over 20k nodes to avoid performance issues. Learn more about FAQs.

Run a Task

You can link a dialog task to a Knowledge Graph Intent. It helps you to leverage the capabilities of the Knowledge Graph and dialog tasks to handle FAQs that involve complex conversations.

  1. On the Intent window, under the Intent section, select Task.
  2. Optionally, enter a Display Name. This name will be used for presenting the FAQ to the end-users in case of ambiguity.
  3. Select a task from the drop-down list. You can Add Utterance that triggers this task.
  4. If multiple utterances mean the same, Add Alternate Utterance.
  5. You can also add a Reference Id. This field can be used to add a reference to any external content used as a source for this FAQ.
  6. Click Save.


Manage Traits, Synonyms, and Stop Words

You can improve the performance of your Knowledge Graph by adding tags, synonyms, traits, and more. Refer here to know more.

Manage Variable Namespaces

Manage Variable Namespaces section (introduced in v8.0) allows you to associate the Variable Namespaces to use with this Knowledge Graph. This option is visible only when the Variable Namespace is enabled for the VA. For more information, refer to Managing Namespace.


Update a Knowledge Graph

Once created, there will be times when you want to make changes to the Knowledge Graph for better organization and presentation.

Note: Once you make any changes to the Knowledge Graph, make sure to click Train on the top-right to send the updates to the Knowledge Graph engine. If you do not train the VA, the changes are not reflected in its responses.

 

By default, intents added to a child node are visible for all its parent nodes in the path, up to the root node. If you do not want the intents from child nodes to be seen beyond a certain parent node, click the following icon on the Questions pane of the selected parent.

The intents from all its child nodes are visible to the selected parent node and not to all its parent nodes.

Move Intents Between Nodes

You can move one or more Intent and Response sets between nodes in your Knowledge Graph, as follows.

  1. On the Knowledge Graph, click the name of the node from which you want to move the intent. The intents associated to the node display on the right pane.
  2. Identify the intent that you want to move, and select the checkbox next to it. You can select multiple items.
  3. Drag the intent and drop it on the relevant node. The node is highlighted and the intent displays on the right pane of the node.

The demo below shows you how this works.


Edit and Delete Terms

  1. On the nodes hierarchy from the left pane, hover over the term/node you want to edit.
  2. Click the Settings (gear) icon. The settings window opens.
  3. You can change the name of the term, set the term types, set the term status, add traits, add or remove synonyms, and manage context from here (see here for more).
  4. To delete a term:
    1. On the nodes hierarchy, hover over the term you want to delete.
    2. Click the bin icon.
    3. On the confirmation dialog box, you can find the following options:
      1. Delete the FAQs along with the term – Choosing this option deletes the term and FAQs under it.
      2. Delete the term and move FAQs to root term –
        Choosing this option deletes the term and moves the FAQs under it to the root term.
Notes on deleting KG nodes:

    1. If the term has child nodes, all those nodes will be deleted.

  • If your VA is already published, you must train it  for the deletions to be effective.
  • If you have deleted the first level term you can selectively train to remove the d bio eleted terms from the published copy.
  • If you have deleted, say, the nth level child term, then you need to select the entire parent term for training.

Edit Intents and Responses

  1. From the nodes hierarchy, select the relevant term.
  2. Intents associated with the term appear on the right pane.
  3. Hover over the intent or response to edit it and click the edit icon.
  4. Make changes to the intent or response and click Save.
  5. You can delete the intent using the bin icon.
  6. Selecting multiple intents lets you delete them in bulk.

Improve Performance

The Knowledge Graph engine works well with the default settings, but you can fine-tune the KG engine performance. Here are a few guidelines:

  1. Configure the Knowledge Graph by defining terms, synonyms, primary and alternative questions, or user utterances. Though hierarchy does not affect the KG engine performance, it does help organize and guide your knowledge implementation.
  2. Set the following parameters:
    1. Path Coverage – For Ontology-based graphs, you can define the minimum percentage of terms in the user’s utterance to be present in a path to qualify it for further scoring.
    2. Definite Score for KG – Define the minimum score for a KG intent match to consider as a definite match and discard any other intent matches found.
    3. Minimum and Definitive Level for Knowledge Tasks – Define minimum and definitive threshold to identify and respond in case of a knowledge task.
    4. KG Suggestions Count – Define the maximum number of KG/FAQ suggestions to present when a definite KG intent match is unavailable.
    5. The proximity of Suggested Matches – Define the maximum difference to allow between top-scoring and immediate next suggested questions to consider as equally important.
    6. Qualify Contextual Paths – This ensures that the bot context is populated and retained with the terms/nodes of the matched intent. This further enhances the user experience.

      Note: You can customize these settings in Natural Language > Thresholds & Configurations. See Knowledge Graph Training for details.
  3. Traits – Traits qualify nodes/terms even if the user utterance does not contain the term/node. Traits are also helpful in filtering the suggested intent list.

Build a Knowledge Graph

The XO Platform’s Knowledge Graph (KG) helps you turn your static FAQ text into an intelligent, personalized conversational experience. It goes beyond the usual practice of capturing FAQs as flat question-answer pairs. Instead, the Knowledge Graph enables you to create a hierarchical structure of key domain terms and associate them with context-specific questions and their alternatives, synonyms, traits, and more. Additionally, you can opt for the LLM-based Few-Shot Knowledge Graph, which requires no ontology and reduces maintenance and training requirements.

See here for more on KG Terminology.

To generate a Knowledge Graph, you need to add FAQs to an existing or new VA. If you have not created a VA, refer to Building a Virtual Assistant..

To open the Knowledge Graph builder, follow the below steps:

  1. Log in to the XO Platform and open the VA to which you want to add the Knowledge Graph.
  2. Select the Build tab from the top menu.
  3. On the left menu, select Conversation Skills and click Knowledge Graph.
  4. You will notice that there is already a Knowledge Graph with the name of your assistant.

Notes on the Few-Shot Knowledge Graph

All features explained here are supported by the Few-Shot Knowledge Graph, except for the following:

  1. Few-Shot Knowledge Graphs do not require an ontology structure, but you can create one to  improve intent detection. 
  2. Default terms are not available in Few-Shot Knowledge Graphs. The only exception is when you switch from an Ontology Graph, in which case existing Default terms are stored as such until updated. Afterward, Default terms become Organizer terms and can be set as Mandatory.
  3. Lemmatization using Parts of Speech, Search in Answer, and Contextual Paths Qualification are not supported by Few-Shot Graphs. Please see the Knowledge Graph Types Comparison Table for a detailed list of supported features.
  4. Path Level and Knowledge Graph Synonyms are only supported for Mandatory Terms and for Tags.

Create the Knowledge Graph Node Structure

By default, the name of the VA becomes the root node of the hierarchy and you can edit this. Create the rest of the nodes below the root node.

To create nodes, follow the below steps:

  1. Open the Knowledge Graph.
  2. On the top left of the Knowledge Graph window, hover over the root node.
  3. Click the + icon. A text box appears below to Add Node. For better performance, there is a restriction of 50k FAQs spread across 20k maximum allowed number of nodes.
  4. Type the name of the node in the text box and press Enter. A warning would be displayed in case you enter a duplicate node name, i.e. if a child node with the same name already exists under the parent node.

    Note: This node becomes a child for the root node and can be referred to as a First-level node.
  5. Repeat steps 1 to 3 to create other First-level nodes.
  6. After you create First-level nodes, create child nodes as follows:
    1. Hover over any First-level node, and click the plus icon to create its child node.
    2. You can create a child node for any level node by hovering over it and clicking the + icon.

Follow the same process to create multiple node levels. 

The demo below shows you how to create nodes.

You can delete nodes by clicking the bin icon on the right.


Build the Knowledge Graph

The next step is to add Knowledge Graph Intents which can be either:

  • FAQ – to answer user queries
  • Task – to execute a dialog task.

Add FAQs

Using this option, you can add relevant question-answer sets to the nodes in the hierarchy. Note that there is a limit  of 50k FAQs over 20k nodes to avoid performance issues. Learn more about FAQs.

Run a Task

You can link a dialog task to a Knowledge Graph Intent. It helps you to leverage the capabilities of the Knowledge Graph and dialog tasks to handle FAQs that involve complex conversations.

  1. On the Intent window, under the Intent section, select Task.
  2. Optionally, enter a Display Name. This name will be used for presenting the FAQ to the end-users in case of ambiguity.
  3. Select a task from the drop-down list. You can Add Utterance that triggers this task.
  4. If multiple utterances mean the same, Add Alternate Utterance.
  5. You can also add a Reference Id. This field can be used to add a reference to any external content used as a source for this FAQ.
  6. Click Save.


Manage Traits, Synonyms, and Stop Words

You can improve the performance of your Knowledge Graph by adding tags, synonyms, traits, and more. Refer here to know more.

Manage Variable Namespaces

Manage Variable Namespaces section (introduced in v8.0) allows you to associate the Variable Namespaces to use with this Knowledge Graph. This option is visible only when the Variable Namespace is enabled for the VA. For more information, refer to Managing Namespace.


Update a Knowledge Graph

Once created, there will be times when you want to make changes to the Knowledge Graph for better organization and presentation.

Note: Once you make any changes to the Knowledge Graph, make sure to click Train on the top-right to send the updates to the Knowledge Graph engine. If you do not train the VA, the changes are not reflected in its responses.

 

By default, intents added to a child node are visible for all its parent nodes in the path, up to the root node. If you do not want the intents from child nodes to be seen beyond a certain parent node, click the following icon on the Questions pane of the selected parent.

The intents from all its child nodes are visible to the selected parent node and not to all its parent nodes.

Move Intents Between Nodes

You can move one or more Intent and Response sets between nodes in your Knowledge Graph, as follows.

  1. On the Knowledge Graph, click the name of the node from which you want to move the intent. The intents associated to the node display on the right pane.
  2. Identify the intent that you want to move, and select the checkbox next to it. You can select multiple items.
  3. Drag the intent and drop it on the relevant node. The node is highlighted and the intent displays on the right pane of the node.

The demo below shows you how this works.


Edit and Delete Terms

  1. On the nodes hierarchy from the left pane, hover over the term/node you want to edit.
  2. Click the Settings (gear) icon. The settings window opens.
  3. You can change the name of the term, set the term types, set the term status, add traits, add or remove synonyms, and manage context from here (see here for more).
  4. To delete a term:
    1. On the nodes hierarchy, hover over the term you want to delete.
    2. Click the bin icon.
    3. On the confirmation dialog box, you can find the following options:
      1. Delete the FAQs along with the term – Choosing this option deletes the term and FAQs under it.
      2. Delete the term and move FAQs to root term –
        Choosing this option deletes the term and moves the FAQs under it to the root term.
Notes on deleting KG nodes:

    1. If the term has child nodes, all those nodes will be deleted.

  • If your VA is already published, you must train it  for the deletions to be effective.
  • If you have deleted the first level term you can selectively train to remove the d bio eleted terms from the published copy.
  • If you have deleted, say, the nth level child term, then you need to select the entire parent term for training.

Edit Intents and Responses

  1. From the nodes hierarchy, select the relevant term.
  2. Intents associated with the term appear on the right pane.
  3. Hover over the intent or response to edit it and click the edit icon.
  4. Make changes to the intent or response and click Save.
  5. You can delete the intent using the bin icon.
  6. Selecting multiple intents lets you delete them in bulk.

Improve Performance

The Knowledge Graph engine works well with the default settings, but you can fine-tune the KG engine performance. Here are a few guidelines:

  1. Configure the Knowledge Graph by defining terms, synonyms, primary and alternative questions, or user utterances. Though hierarchy does not affect the KG engine performance, it does help organize and guide your knowledge implementation.
  2. Set the following parameters:
    1. Path Coverage – For Ontology-based graphs, you can define the minimum percentage of terms in the user’s utterance to be present in a path to qualify it for further scoring.
    2. Definite Score for KG – Define the minimum score for a KG intent match to consider as a definite match and discard any other intent matches found.
    3. Minimum and Definitive Level for Knowledge Tasks – Define minimum and definitive threshold to identify and respond in case of a knowledge task.
    4. KG Suggestions Count – Define the maximum number of KG/FAQ suggestions to present when a definite KG intent match is unavailable.
    5. The proximity of Suggested Matches – Define the maximum difference to allow between top-scoring and immediate next suggested questions to consider as equally important.
    6. Qualify Contextual Paths – This ensures that the bot context is populated and retained with the terms/nodes of the matched intent. This further enhances the user experience.

      Note: You can customize these settings in Natural Language > Thresholds & Configurations. See Knowledge Graph Training for details.
  3. Traits – Traits qualify nodes/terms even if the user utterance does not contain the term/node. Traits are also helpful in filtering the suggested intent list.
Menu