LogoLogo
  • 👋START HERE
    • Welcome!
  • â„šī¸General
    • Release Notes
      • Full Feature Base Template
      • Services
      • Rule-based Automation
        • February 2025
        • January 2025
        • December 2024
        • November 2024
        • October 2024
        • September 2024
        • August 2024
        • July 2024
        • June 2024
        • May 2024
        • April 2024
        • March 2024
        • February 2024
        • January 2024
        • 2023
        • 2022
        • 2021
        • Dialog Design Update
    • Glossary of Terms
    • Authentication Methods
      • SSO (Single Sign-On)
      • Built-In User Management
    • Acceptable Use Policy
  • âš™ī¸Rule-based Automation
    • Overview
      • Account Settings
        • Profile
        • Team
        • Roles and Permissions
          • User Management
          • Project Permissions
      • Basic Concepts
        • Project Management
        • Version Management
        • Multi-Lingual Bots
          • Supported Languages
        • Managing User Interactions
          • Unexpected User Input
          • No User Input
    • Dialog Interface
      • Blocks
        • Conversation Logic
          • Start Conversation
          • Global
          • State
          • Intermediate Response
          • To Previous State
          • End Conversation
        • Subdialog
          • Reusable Subdialogs
        • Phone
          • Continue Listening
          • Call Control
        • Technical Logic
          • Service
          • Condition
          • Storage
        • Other
          • Note
      • Speech Assets
        • Intents
          • Utterances
          • Descriptions
        • Slots
          • Custom Slots
            • List Slots
            • Machine Learning Slots
            • Regex Slots
            • LLM Slots
          • Prebuilt Slots
            • DTMF Slot
        • Text Snippets
        • Dictionary
      • Variables
        • Intents
        • Slots
        • Storage
        • Text Snippets
        • Environments
        • Platform
        • Context
      • Services
        • Service Integration Guide
        • Service Development
        • Service Branches and Error Handling
        • Public Services
          • Date and Birthdate Recognition
          • Spelling Post-Processing for Phone
          • IBAN Validation
          • License Plate Validation
          • Address Search
          • Street Names per Postal Code
          • Email Service
          • SMS Service
          • API Adapter
          • Salesforce-Flow Connector
          • Opening Hours
          • Speech-to-Text Hints
          • Fuzzy Match Names
          • Delay Service
      • Debugger
        • Phone 2
        • WhatsApp
        • Textchat 2
    • Environments Interface
      • Service Keys
    • Deployments Interface
      • Creating a Release
      • Editing a Release
    • Text-to-Speech
      • Azure
      • ElevenLabs
      • OpenAI via Azure (Preview)
      • SSML
        • Audio
        • Break
        • Emphasis
        • Prosody
        • Say-as
        • Substitute
        • Paragraph and Sentence
        • Voice
    • Autocomplete
    • Parloa APIs
      • CallData Service and API
      • Conversation History API
      • Textchat V2 API
    • Phone Integrations
      • Genesys Cloud
        • Setting up the SIP Trunk
        • Sending/Receiving UUI Data
        • Creating a Script to Display UUI
      • SIP
      • Tenios
        • Setting Up an Inbound Connection
        • Setting Up an Outbound Connection
        • Transferring a Call
      • Twilio
      • Public IPs and Port Information
    • AI Integration Overview
      • Dual Intent Recognizer (DIR)
      • Dual Tone Multifrequency (DTMF) Intent
    • Analytics and Debugging
      • Understanding Conversations and Transactions
      • Managing Caller ID Data
      • Hangup Events and Triggered Analytics
      • Analytics Transactions: Data Structure and Insights
      • Dialog Analytics
      • Audit Logs
      • Parloa-hosted Analytics
    • Data Privacy
      • Anonymizing Personally Identifiable Information
    • NLU Training
      • NLU Training Best Practices
    • How To
      • Create a Scalable and Maintainable Bot Architecture
      • Implement OnError Loop Handling
      • Resolve the 'Service Unavailable' Error
    • Reference
      • Parloa Keyboard Shortcuts
      • Frequently Asked Questions (FAQ)
      • JavaScript Cheat Sheet
        • Using Regular Expressions (Regex)
  • 🧠Knowledge Skill
    • Introduction
    • Knowledge Collections
    • Knowledge Sources
    • Knowledge Skill Setup
      • Step 1 – Create a Knowledge Skill Agent
      • Step 2 – Configure a Knowledge Skill Agent
      • Step 3 – Configure a Knowledge Skill Agent
Powered by GitBook
On this page
  • What is Dual Intent Recognizer (DIR)?
  • An Example Scenario
  • Setting Up Dual Intents
  • Step 1 – Define Single Intents
  • Step 2 – Create a Dual Intent
  • Step 3 – Adding Utterances
  • Step 4 – Implementation in Parloa Graph
  • Using DIR
  • Benefits of Using DIR
  • FAQ

Was this helpful?

Export as PDF
  1. Rule-based Automation
  2. AI Integration Overview

Dual Intent Recognizer (DIR)

Available for the Phone 2 platform.

What is Dual Intent Recognizer (DIR)?

The Dual Intent Recognizer (DIR) enables bots to discern and respond to multiple user intents within a single utterance, significantly enriching conversational interactions by making them more efficient and fluid.

An Example Scenario

Consider a user stating, "Hi, I want to change my address as I have just moved and need a copy of my last invoice." This utterance encapsulates two distinct intents:

  • Changing their address (Intent: ChangeAddress)

  • Requesting a copy of an invoice (Intent: ReceiveInvoice)

With DIR, your bot is adept at addressing both intents in tandem, streamlining the interaction.

Setting Up Dual Intents

Step 1 – Define Single Intents

First, ensure single intents, such as ChangeAddress and ReceiveInvoice, are established with their respective utterances.

Step 2 – Create a Dual Intent

Create a new intent that combines two existing ones. Use a + to link them, creating an intent like ChangeAddress+ReceiveInvoice.

Step 3 – Adding Utterances

Provide this new dual intent with sample utterances that represent both intentions, aiding in training the NLU component.

Step 4 – Implementation in Parloa Graph

Integrate this dual intent into your dialog flow within the Parloa Graph, treating it as any standard intent.

Using DIR

  1. Create intents with individual utterances for each underlying intention.

  1. Combine two intents using a +, such as ChangeAddress+ReceiveInvoice.

  2. Provide the new dual intent with example utterances that cover both intents.

  1. Incorporate this dual intent into the Parloa Graph for dialog flow management.

Benefits of Using DIR

  • Enhanced User Experience: Enables users to articulate multiple needs in one statement, facilitating swifter issue resolution.

  • Efficiency: Optimizes dialog flow by minimizing the interactions required to ascertain user intents.

  • Adaptability: Equips bots to adeptly manage complex or multifaceted user queries, enhancing the overall conversational quality.

FAQ

How does DIR differ from standard intent recognition?

Standard intent recognition identifies one user intent per message. DIR, however, can recognize and process two intents simultaneously in a single message.

What are the prerequisites for using DIR?

Before using DIR, you need to have predefined single intents, like ChangeAddress and ReceiveInvoice, each with its own set of example utterances.

Can DIR handle more than two intents in a single message?

Currently, DIR is designed to handle two intents at a time. Handling more than two intents in a single message is not supported yet.

How does DIR affect the conversation flow?

DIR streamlines the conversation flow by allowing the bot to understand and respond to complex user queries more efficiently, reducing the need for follow-up questions.

What should I do if DIR is not recognizing dual intents accurately?

If DIR isn't working as expected, review your dual intents and their example utterances for accuracy and completeness. Also, ensure that the NLU component is properly trained with these utterances.

Are there best practices for creating dual intents with DIR?

Yes, there are a few best practices:

  • Ensure that each single intent is well-defined and accurately represents a specific user need.

  • When creating dual intents, choose combinations that are likely to occur together in real-life scenarios.

  • Provide a diverse range of example utterances for dual intents to effectively train the NLU component.

PreviousAI Integration OverviewNextDual Tone Multifrequency (DTMF) Intent

Last updated 1 year ago

Was this helpful?

âš™ī¸