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
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
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 Analysis

Knowledge Graph Analysis

A careful analysis of the Knowledge Graph helps in detecting errors in your questions and the path associated with them that hamper the user experience.

The Knowledge Graph (KG) Diagnosis tool helps you identify any inefficiencies in your KGs and suggests possible corrective actions. These are just guidelines and you need to further analyze the recommendations before going ahead with any changes.

The KG provides an option to initiate an inspection, as follows:

  • This option is available only for the in-development version of the KG where there are one or more FAQs added.
  • The analysis considers the thresholds and other configurations of the KG.
  • The analysis issues a warning if any node contains more than 25 questions and an advisory to the effect that the training fails if there are more than 100 questions in any node.
  • You can invoke the diagnosis, by clicking Inspect on the KG screen.
  • You can also add patterns as alternate questions for an FAQ to provide better coverage, which helps in detecting the right FAQs for a user question. KG Inspect helps in identifying any syntax errors that occur knowingly or unknowingly while defining patterns. The platform analyzes the KG and provides a report of the analysis. The identified incorrect patterns in KG are displayed in the report.
  • You have an option to Re-run the analysis or Export the report. The export option downloads the report in JSON format.
  • The inspect report shows an overview of the number of issues found under various categories. Please read below to learn more.
  • The various categories are grouped as:
    • Error – Errors are incorrect graph definitions that need an immediate fix.
    • Warnings – When rectified, it help improves intent detection. A maximum of 50 warnings are displayed.
    • Suggestions – When implemented, it helps in the better organization of your KG. A maximum of 10 suggestions are displayed.
  • Click each category to view the detailed report
  • In this example you see the details of all the patterns with invalid syntaxes.

    Note: There can be more than 50 warnings or 10 suggestions, but only the first 50/10 occurrences of the issue are listed. You must fix the same and re-run the analysis to view the next set.

Report Fields for Ontology Knowledge Graphs

The following table details the fields that are displayed in the report:

Issue Type Category Details Suggestion
Patterns with Invalid Syntax Error
  • Current Path
  • Pattern
  • Error
  • Question
Rectify the incorrect patterns for better FAQ detection.
Questions added to incorrect paths Error
  • Question
  • Path
Modify the path to include the terms in the question.
Long-chain of terms with the questions present only at the last term in the chain Suggestion
  • Question
  • Path
Reduce the path by avoiding unimportant terms or merge relevant terms.
Identical terms with a common ancestor Suggestion
  • Common Parent
  • Child Paths (only for the largest repeated child trees)
Move the child terms above their parent terms to avoid duplication
Paths without any questions Suggestion
  • Path
Remove the path if you do not intend to add any questions to this path
Redundant alternate questions Suggestion
  • Question
  • Alternate Question (multiple)
  • Path
Rephrase alternate questions to include wider coverage
A large number of questions added to the root term Suggestion
  • Question
  • Path
Move the questions to the appropriate paths
Unusually long paths Warning
  • Path
Reduce the path by avoiding unnecessary terms or merging relevant terms.
Questions at the root node that can be moved to better paths Warning
  • Question
  • Current Path
  • Suggested Path
Move the question to the suggested path
Questions with common words that are not used as terms Warning
  • Question (multiple)
  • Path
  • Suggested Extension
Extend the current path using the suggested extension
Questions that match multiple paths Warning
  • Question
  • Current path
  • Other Paths (multiple)
Review the paths to avoid possible ambiguity scenarios
Identical sibling nodes Warning
  • Path
  • Identical Term
Merge the identical terms

Report Fields for Few-Shot Knowledge Graphs

For Few-Shot Knowledge Graphs, nothing regarding paths and keywords requires analysis; since these are not used by the model to detect intent. The only report fields you will see when inspecting such a graph are the following: 

Issue Type

Category 

Details

Suggestion

Patterns with Invalid Syntax

Error

  • Current Path
  • Pattern
  • Error
  • Question

Rectify the incorrect patterns for better FAQ detection.

Paths without any questions

Suggestion

  • Path

Remove the path if you do not intend to add any questions to this path.

Redundant alternate questions

Suggestion

  • Question
  • Alternate Question (multiple)
  • Path

Rephrase alternate questions to include wider coverage.

Note: Every time a KG is inspected, the following details get updated in a scenario where any FAQs are modified or any new FAQs are added:

  • Total checks
  • Count of errors, warnings, suggestions
  • Count and the list of various checkpoints

Knowledge Graph Analysis

A careful analysis of the Knowledge Graph helps in detecting errors in your questions and the path associated with them that hamper the user experience.

The Knowledge Graph (KG) Diagnosis tool helps you identify any inefficiencies in your KGs and suggests possible corrective actions. These are just guidelines and you need to further analyze the recommendations before going ahead with any changes.

The KG provides an option to initiate an inspection, as follows:

  • This option is available only for the in-development version of the KG where there are one or more FAQs added.
  • The analysis considers the thresholds and other configurations of the KG.
  • The analysis issues a warning if any node contains more than 25 questions and an advisory to the effect that the training fails if there are more than 100 questions in any node.
  • You can invoke the diagnosis, by clicking Inspect on the KG screen.
  • You can also add patterns as alternate questions for an FAQ to provide better coverage, which helps in detecting the right FAQs for a user question. KG Inspect helps in identifying any syntax errors that occur knowingly or unknowingly while defining patterns. The platform analyzes the KG and provides a report of the analysis. The identified incorrect patterns in KG are displayed in the report.
  • You have an option to Re-run the analysis or Export the report. The export option downloads the report in JSON format.
  • The inspect report shows an overview of the number of issues found under various categories. Please read below to learn more.
  • The various categories are grouped as:
    • Error – Errors are incorrect graph definitions that need an immediate fix.
    • Warnings – When rectified, it help improves intent detection. A maximum of 50 warnings are displayed.
    • Suggestions – When implemented, it helps in the better organization of your KG. A maximum of 10 suggestions are displayed.
  • Click each category to view the detailed report
  • In this example you see the details of all the patterns with invalid syntaxes.

    Note: There can be more than 50 warnings or 10 suggestions, but only the first 50/10 occurrences of the issue are listed. You must fix the same and re-run the analysis to view the next set.

Report Fields for Ontology Knowledge Graphs

The following table details the fields that are displayed in the report:

Issue Type Category Details Suggestion
Patterns with Invalid Syntax Error
  • Current Path
  • Pattern
  • Error
  • Question
Rectify the incorrect patterns for better FAQ detection.
Questions added to incorrect paths Error
  • Question
  • Path
Modify the path to include the terms in the question.
Long-chain of terms with the questions present only at the last term in the chain Suggestion
  • Question
  • Path
Reduce the path by avoiding unimportant terms or merge relevant terms.
Identical terms with a common ancestor Suggestion
  • Common Parent
  • Child Paths (only for the largest repeated child trees)
Move the child terms above their parent terms to avoid duplication
Paths without any questions Suggestion
  • Path
Remove the path if you do not intend to add any questions to this path
Redundant alternate questions Suggestion
  • Question
  • Alternate Question (multiple)
  • Path
Rephrase alternate questions to include wider coverage
A large number of questions added to the root term Suggestion
  • Question
  • Path
Move the questions to the appropriate paths
Unusually long paths Warning
  • Path
Reduce the path by avoiding unnecessary terms or merging relevant terms.
Questions at the root node that can be moved to better paths Warning
  • Question
  • Current Path
  • Suggested Path
Move the question to the suggested path
Questions with common words that are not used as terms Warning
  • Question (multiple)
  • Path
  • Suggested Extension
Extend the current path using the suggested extension
Questions that match multiple paths Warning
  • Question
  • Current path
  • Other Paths (multiple)
Review the paths to avoid possible ambiguity scenarios
Identical sibling nodes Warning
  • Path
  • Identical Term
Merge the identical terms

Report Fields for Few-Shot Knowledge Graphs

For Few-Shot Knowledge Graphs, nothing regarding paths and keywords requires analysis; since these are not used by the model to detect intent. The only report fields you will see when inspecting such a graph are the following: 

Issue Type

Category 

Details

Suggestion

Patterns with Invalid Syntax

Error

  • Current Path
  • Pattern
  • Error
  • Question

Rectify the incorrect patterns for better FAQ detection.

Paths without any questions

Suggestion

  • Path

Remove the path if you do not intend to add any questions to this path.

Redundant alternate questions

Suggestion

  • Question
  • Alternate Question (multiple)
  • Path

Rephrase alternate questions to include wider coverage.

Note: Every time a KG is inspected, the following details get updated in a scenario where any FAQs are modified or any new FAQs are added:

  • Total checks
  • Count of errors, warnings, suggestions
  • Count and the list of various checkpoints
Menu