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. Knowledge Graph

Knowledge Graph

A component of Kore.ai’s XO Platform, the Knowledge Graph (KG), helps you turn static FAQ text into an intelligent, personalized conversational experience. It goes beyond the usual practice of capturing FAQs as flat question-answer pairs, allowing you to either build an ontology structure or leverage Kore.ai’s LLM to simplify knowledge organization, maintenance, and training.

Why a Knowledge Graph?

People express a query in multiple ways, so identifying all the options is complex. The XO Platform Knowledge Graph simplifies this process by either building an ontology structure or using an LLM model that does not require such an ontology.

Knowledge Graph Types

There are two types of Knowledge Graphs:

  1. The Ontology Knowledge Graph lets you create an ontological structure of key domain terms and associate them with context-specific questions and their alternatives, synonyms, and Machine-Learning-enabled Traits.
  2. The Few-Shot Knowledge Graph leverages a Large Language Model (LLM) to simplify knowledge organization. Using this model, you are not required to build an ontology. All you need to do is add all FAQs to the root node/term. This significantly reduces the complexity of building and maintaining an ontology structure.

Choosing Your Knowledge Graph Type

Starting with v10.1.0 of the XO Platform, the Few-Shot Model is the default for all new Knowledge Graphs created under NLP V3 and in English.

If you have built your Ontology-based graph before this release, you can migrate to the new model anytime. You must upgrade to NLP V3 to use the Few-Shot Model. You can return to the Ontology model if you change your mind later.

You can select your desired Knowledge Graph Type by going to Build > Natural Language > Thresholds and Configurations > Knowledge Graph.

Changing Knowledge Graph Types is captured in the Change Logs, which you can access by going to Deploy > Change Logs.

Important Note: Before changing your Knowledge Graph Type, we recommend backing up your existing knowledge graph by either creating a new bot version or by exporting a copy of your knowledge graph as a JSON or CSV.

 

Please continue reading to learn more about each type of knowledge graph. See Knowledge Graph Terminology for in-depth information about Knowledge Graph features and components.

The Ontology Knowledge Graph

This type lets you organize FAQs using Default, Mandatory, and Organizer Terms/Nodes, tags, synonyms, context, traits, and more.

Whenever someone asks your VA a question, the terms (node names) in the Knowledge Graph are checked and matched with keywords from the utterance. We call this process path qualification. Tags and synonyms are also checked, and based on the score they receive, questions are shortlisted as likely matches or intents. These shortlisted questions are then compared with the actual utterance to identify the response, which can be either a simple response or the execution of a dialog task.

You can also add completely different alternative questions to the FAQ and provide tags, synonyms, and terms appropriately such that any untrained question can also be matched. The performance and intelligence of the Knowledge Graph depend on the way you train it with the appropriate terms, tags, synonyms, etc.

Enable the Ontology Knowledge Graph

To enable this Knowledge Graph type, go to Build > Natural Language > Thresholds and Configurations > Knowledge Graph, and select Ontology Model as the Knowledge Graph Type.

Before enabling the Ontology Knowledge Graph model, please consider the following:

  1. You must build a Graph Ontology structure so the engine can qualify paths and compare them with query input. Each relevant term/node is considered while identifying the appropriate FAQ, so you must regularly maintain the node structure to facilitate optimum performance.
  2. The model supports three types of terms: Default, Mandatory, and Organizer.
  3. The Ontology Model also supports other features such as Traits, Patterns, Path Synonyms, KG Synonyms, Bot Synonyms, Preconditions, and more. Please see the Comparison Table below for a detailed list of supported features. Also, see Knowledge Graph Training for configuration details.

How It Works

The Ontology Knowledge Graph engine uses a two-step approach while extracting a response. It combines a search-driven intent detection process with rule-based filtering. The settings for path coverage (percentage of terms needed) and term usage (mandatory or optional) in the user utterance help in the initial filtering of the FAQ intents. Tokenization and the n-gram-based cosine scoring model help fulfill the final search criteria.

When a new utterance reaches the Ontology Knowledge Graph:

  • The user utterance and KG nodes/terms are tokenized, and n-gram is extracted (The Knowledge Graph Engine supports a maximum of a quad-gram).
  • The tokens are mapped with the KG nodes/terms to obtain their respective indices.
  • Path comparison between the user utterance and KG nodes/terms establishes the qualified path for that utterance. This step considers the path coverage and term usage mentioned above.
  • From the list of questions in the qualified path, the best match is selected based on cosine scoring.

Training the Ontology Knowledge Graph Model involves the following steps:

  • All the terms/nodes, along with synonyms, are identified and indexed.
  • Using these indices, a flattened path is established for each KG Intent.

The Few-Shot Knowledge Graph

This Knowledge Graph type uses Kore.ai’s Large Language Model (LLM) to identify the appropriate FAQ for a query based on semantic similarity. This model only uses Mandatory and Organizer terms and does not perform path qualification, so you are not required to build an ontology. All you need to do is add all FAQs to the root node/term. It significantly reduces the complexity of building and maintaining an ontology structure.

Enable the Few-Shot Knowledge Graph

To enable the Few-Shot Knowledge Graph, go to Build > Natural Language > Thresholds and Configurations > Knowledge Graph, and select Few-Shot Model as the Knowledge Graph Type.

Before enabling the Few-Shot Knowledge Graph, please consider the following:

  1. When switching from an Ontology-based Knowledge Graph to the Few-Shot model, Default terms/Nodes are still stored until you update them. From this point onwards, the terms are stored as Organizer unless you make them Mandatory.
  2. Only Mandatory terms support path-level synonyms.
  3. The Few-Shot model works with Ranking & Resolver V2 and NLP V3. When you enable this model, the Ranking & Resolver version will be updated automatically. If you are not using NLP V3, you will be asked to upgrade before enabling it.

How It Works

When a new utterance reaches the Few-Shot Knowledge Graph, the Large Language Model determines possible and definitive intent matches. The model uses semantic similarity to identify the relevant FAQs. The model returns a similarity score used to determine the match type (definite, probable, etc.) based on set thresholds. Identified intents are then sent to Ranking and Resolver to select the winning intent, after which the assistant responds to the query.

Training this model involves adding tags and alternative questions to FAQs. Other training features, such as term synonyms, traits, context, etc., are optional but still recommended to improve performance for specific use cases where the LLM cannot identify the intent.

Compare Knowledge Graph Types

Feature Few-Shot KG Model  Ontology KG Model
Ontology Structure Yes, Optional. Yes, Mandatory.
Default Terms No, unless you switch from an Ontology KG and don’t update the term. After updating, the term becomes an Organizer and can be set as Mandatory.  Yes
Mandatory Terms Yes Yes
Organizer Terms Yes Yes
Path Qualification No Yes, always performed.
Tags Yes Yes
Synonyms Yes, for Mandatory Terms and Tags. Yes
Path-Level Synonyms Yes, for Mandatory Terms Yes
Knowledge Graph Synonyms Yes, for Mandatory Terms Yes
Traits Yes Yes
Context Yes Yes
Stop Words Yes Yes
KG Import/Export Yes Yes
Auto-Generate KG Yes Yes
Bot Synonyms Yes Yes
Lemmatization using Parts of Speech No Yes
Path Coverage No Yes
Search in answer No Yes
Qualify Contextual Paths No Yes
Auto-Correction Yes Yes
Minimum and Definitive Level for Knowledge Graph Intent Yes Yes
KG Suggestions Count Yes Yes
Proximity of Suggested Matches Yes Yes
Manage Long Responses Yes Yes
Intent Preconditions Yes Yes
Context Output Yes Yes
Supports All Platform Languages Yes Yes
Captured in Change Log Yes Yes
Inspect Knowledge Graph Yes – Required verifications are:

  1. Patterns with invalid syntax
  2. Redundant alternate questions
Yes – See Report Fields.

 

Knowledge Graph

A component of Kore.ai’s XO Platform, the Knowledge Graph (KG), helps you turn static FAQ text into an intelligent, personalized conversational experience. It goes beyond the usual practice of capturing FAQs as flat question-answer pairs, allowing you to either build an ontology structure or leverage Kore.ai’s LLM to simplify knowledge organization, maintenance, and training.

Why a Knowledge Graph?

People express a query in multiple ways, so identifying all the options is complex. The XO Platform Knowledge Graph simplifies this process by either building an ontology structure or using an LLM model that does not require such an ontology.

Knowledge Graph Types

There are two types of Knowledge Graphs:

  1. The Ontology Knowledge Graph lets you create an ontological structure of key domain terms and associate them with context-specific questions and their alternatives, synonyms, and Machine-Learning-enabled Traits.
  2. The Few-Shot Knowledge Graph leverages a Large Language Model (LLM) to simplify knowledge organization. Using this model, you are not required to build an ontology. All you need to do is add all FAQs to the root node/term. This significantly reduces the complexity of building and maintaining an ontology structure.

Choosing Your Knowledge Graph Type

Starting with v10.1.0 of the XO Platform, the Few-Shot Model is the default for all new Knowledge Graphs created under NLP V3 and in English.

If you have built your Ontology-based graph before this release, you can migrate to the new model anytime. You must upgrade to NLP V3 to use the Few-Shot Model. You can return to the Ontology model if you change your mind later.

You can select your desired Knowledge Graph Type by going to Build > Natural Language > Thresholds and Configurations > Knowledge Graph.

Changing Knowledge Graph Types is captured in the Change Logs, which you can access by going to Deploy > Change Logs.

Important Note: Before changing your Knowledge Graph Type, we recommend backing up your existing knowledge graph by either creating a new bot version or by exporting a copy of your knowledge graph as a JSON or CSV.

 

Please continue reading to learn more about each type of knowledge graph. See Knowledge Graph Terminology for in-depth information about Knowledge Graph features and components.

The Ontology Knowledge Graph

This type lets you organize FAQs using Default, Mandatory, and Organizer Terms/Nodes, tags, synonyms, context, traits, and more.

Whenever someone asks your VA a question, the terms (node names) in the Knowledge Graph are checked and matched with keywords from the utterance. We call this process path qualification. Tags and synonyms are also checked, and based on the score they receive, questions are shortlisted as likely matches or intents. These shortlisted questions are then compared with the actual utterance to identify the response, which can be either a simple response or the execution of a dialog task.

You can also add completely different alternative questions to the FAQ and provide tags, synonyms, and terms appropriately such that any untrained question can also be matched. The performance and intelligence of the Knowledge Graph depend on the way you train it with the appropriate terms, tags, synonyms, etc.

Enable the Ontology Knowledge Graph

To enable this Knowledge Graph type, go to Build > Natural Language > Thresholds and Configurations > Knowledge Graph, and select Ontology Model as the Knowledge Graph Type.

Before enabling the Ontology Knowledge Graph model, please consider the following:

  1. You must build a Graph Ontology structure so the engine can qualify paths and compare them with query input. Each relevant term/node is considered while identifying the appropriate FAQ, so you must regularly maintain the node structure to facilitate optimum performance.
  2. The model supports three types of terms: Default, Mandatory, and Organizer.
  3. The Ontology Model also supports other features such as Traits, Patterns, Path Synonyms, KG Synonyms, Bot Synonyms, Preconditions, and more. Please see the Comparison Table below for a detailed list of supported features. Also, see Knowledge Graph Training for configuration details.

How It Works

The Ontology Knowledge Graph engine uses a two-step approach while extracting a response. It combines a search-driven intent detection process with rule-based filtering. The settings for path coverage (percentage of terms needed) and term usage (mandatory or optional) in the user utterance help in the initial filtering of the FAQ intents. Tokenization and the n-gram-based cosine scoring model help fulfill the final search criteria.

When a new utterance reaches the Ontology Knowledge Graph:

  • The user utterance and KG nodes/terms are tokenized, and n-gram is extracted (The Knowledge Graph Engine supports a maximum of a quad-gram).
  • The tokens are mapped with the KG nodes/terms to obtain their respective indices.
  • Path comparison between the user utterance and KG nodes/terms establishes the qualified path for that utterance. This step considers the path coverage and term usage mentioned above.
  • From the list of questions in the qualified path, the best match is selected based on cosine scoring.

Training the Ontology Knowledge Graph Model involves the following steps:

  • All the terms/nodes, along with synonyms, are identified and indexed.
  • Using these indices, a flattened path is established for each KG Intent.

The Few-Shot Knowledge Graph

This Knowledge Graph type uses Kore.ai’s Large Language Model (LLM) to identify the appropriate FAQ for a query based on semantic similarity. This model only uses Mandatory and Organizer terms and does not perform path qualification, so you are not required to build an ontology. All you need to do is add all FAQs to the root node/term. It significantly reduces the complexity of building and maintaining an ontology structure.

Enable the Few-Shot Knowledge Graph

To enable the Few-Shot Knowledge Graph, go to Build > Natural Language > Thresholds and Configurations > Knowledge Graph, and select Few-Shot Model as the Knowledge Graph Type.

Before enabling the Few-Shot Knowledge Graph, please consider the following:

  1. When switching from an Ontology-based Knowledge Graph to the Few-Shot model, Default terms/Nodes are still stored until you update them. From this point onwards, the terms are stored as Organizer unless you make them Mandatory.
  2. Only Mandatory terms support path-level synonyms.
  3. The Few-Shot model works with Ranking & Resolver V2 and NLP V3. When you enable this model, the Ranking & Resolver version will be updated automatically. If you are not using NLP V3, you will be asked to upgrade before enabling it.

How It Works

When a new utterance reaches the Few-Shot Knowledge Graph, the Large Language Model determines possible and definitive intent matches. The model uses semantic similarity to identify the relevant FAQs. The model returns a similarity score used to determine the match type (definite, probable, etc.) based on set thresholds. Identified intents are then sent to Ranking and Resolver to select the winning intent, after which the assistant responds to the query.

Training this model involves adding tags and alternative questions to FAQs. Other training features, such as term synonyms, traits, context, etc., are optional but still recommended to improve performance for specific use cases where the LLM cannot identify the intent.

Compare Knowledge Graph Types

Feature Few-Shot KG Model  Ontology KG Model
Ontology Structure Yes, Optional. Yes, Mandatory.
Default Terms No, unless you switch from an Ontology KG and don’t update the term. After updating, the term becomes an Organizer and can be set as Mandatory.  Yes
Mandatory Terms Yes Yes
Organizer Terms Yes Yes
Path Qualification No Yes, always performed.
Tags Yes Yes
Synonyms Yes, for Mandatory Terms and Tags. Yes
Path-Level Synonyms Yes, for Mandatory Terms Yes
Knowledge Graph Synonyms Yes, for Mandatory Terms Yes
Traits Yes Yes
Context Yes Yes
Stop Words Yes Yes
KG Import/Export Yes Yes
Auto-Generate KG Yes Yes
Bot Synonyms Yes Yes
Lemmatization using Parts of Speech No Yes
Path Coverage No Yes
Search in answer No Yes
Qualify Contextual Paths No Yes
Auto-Correction Yes Yes
Minimum and Definitive Level for Knowledge Graph Intent Yes Yes
KG Suggestions Count Yes Yes
Proximity of Suggested Matches Yes Yes
Manage Long Responses Yes Yes
Intent Preconditions Yes Yes
Context Output Yes Yes
Supports All Platform Languages Yes Yes
Captured in Change Log Yes Yes
Inspect Knowledge Graph Yes – Required verifications are:

  1. Patterns with invalid syntax
  2. Redundant alternate questions
Yes – See Report Fields.

 

Menu