LogoLogo
  • Dhee.AI
  • Concepts We Work on
    • What is NLP?
    • Natural Language Parser Pipeline
    • Word Embeddings
    • Textual Entailment
    • User Intent Recognition
    • Document Reading
  • Getting Started
    • Train your bot
      • Create your bot project
      • Train for Intent recognition
        • Define the Slots
        • Train the Triggers
        • Train for Stop-Triggers
      • Configure Agent Responses
      • Write your REST Endpoints
      • Configure Endpoints
      • Configure Workflow
        • Read Inputs
        • No Code Approach
        • REST Endpoints Approach
        • Acknowledge User
    • Build and Deploy
      • Build
      • Test
      • Deploy
        • Embedding Widget in Apps
  • Platform Reference
    • Manage Projects
    • Agent Settings
      • Basic
        • Language
        • Domain
        • Voice
        • Avatar Settings
      • Widget
        • Widget Theme
        • Widget Label
      • Advanced
      • Team
        • Development Team
        • Support Team
      • Import Export
      • Emailer
      • Billing
      • Botstore
    • Knowledge Management
      • Document Reading
      • Frequently Asked Questions
    • Intents and Automation
      • Intents
        • Slots
        • Triggers
        • Stop Triggers
        • Special Intents
      • Skills/DSM
        • Dialog Actions
        • Dialog State Transition
          • Slot State
        • Dialog Workflow
        • Skill API
      • Backend API
    • Extended Message Types
    • Entities And Other Data
      • Entities
        • Multilingual Entities
        • Language Specific Entities
        • Custom Entity Types
      • Agent Responses
        • Multilingual Responses
        • Missed Query Responses
        • Support-Unavailable Responses
      • Directive Utterances
        • Customize Inputs
        • Customize Outputs
      • Translations
      • Query Substitutions
      • Abbreviation Texts
    • Test & Deploy
      • Build
      • Test
      • Deploy
        • Launchpad
        • Widget
        • Signal
        • Telegram
        • Google RCS
        • Facebook
        • Alexa
        • Whatsapp
        • Custom App
        • Voice
        • Telephony
        • Email
    • Reports
      • Statistics
        • Summary
        • Daily Reports
          • Conversation Analytics
        • Weekly Reports
        • Monthly Reports
        • Output Spreadsheet
      • Conversations
        • Conversation Logs
        • C-SAT
      • Generate Report
        • Lead Report
        • Category Report
        • Device Demography Report
        • Utterance Report
        • Missed Query Report
        • Location Report
      • Report Settings
        • KPI
        • Schedule Report
      • Personnel Audit
        • Development Team
        • Support Team
          • Supervisory Sessions
          • Login Information
      • Bot Store
        • Reviews
        • Reported Issues
  • The Social Desk
    • Whatsapp
      • Customer Chat
      • Manage Template
      • Outreach Campaign
        • Create new
        • Manage Campaign
    • Reports
    • Settings
      • Team
      • Whatsapp
  • Extras
    • External Links
  • News
    • Dhee.AI's Edge Server for Telephony Achieves Breakthrough Optimization on Intel Architecture
  • Dhee.AI Telephony Edge Servers: Elevating Conversational AI Experience with Edge Computing
  • Pinnacle Teleservices Joins Forces with DheeYantra to Supercharge Conversational AI on WhatsApp
Powered by GitBook
On this page
  • Define Slots
  • Templates
  • Prompts
  • Define Custom Type Slots
  1. Getting Started
  2. Train your bot
  3. Train for Intent recognition

Define the Slots

Right information falling into a wrong slot becomes misinformation.

PreviousTrain for Intent recognitionNextTrain the Triggers

Last updated 3 years ago

Slots describe the input and output fields associated with the intents, which are used for processing the intent. These might also include the inputs for the Web Api requests, if any, associated with the intent. You can define the Slots by using the slot button under the Action column. You can read more on Slots in our configuration section on Slots.

Define Slots

In our example case of applyLeave, we would need three inputs, for which we will create slots.

  • startDate

  • endDate

  • leaveReason

The startDate and endDate are of Date type. The leaveReason is a custom type, which would specify the type of leave. We will get to that in a bit. Before that, let us complete the definition of startDate and endDate.

Templates

We can use the Templates to read multiple inputs together from user utterances. For example, for the startDate, we can define the template as "leaves from ${startDate} to ${endDate}". This would ensure the startDate and endDate are filled when the user utterance is similar to any of the following.

 "I need a leave from 20th of feb till 24th "
 "I need a leave from tomorrow till 24th "

The Templates can be instructed to support multilingual functionality if the bot was designed to the multilingual. You can enable the functionality by using the Auto-translate flag.

Prompts

In addition, you can also define Prompts for each of the slots if the User fails to provide the required inputs. These are the messages which the chatbot would ask the user when there is missing information. For example, for the startDate the prompt could be defined as

From when are you planning to go on leave?

Similarly, the prompt for endDate could be

O.K. till when ?

Define Custom Type Slots

Until now we have created slots using system-defined types. We will now proceed to create a Custom Data Type to describe the type of leave and create a slot using the same data type. We will use the Entities & Other Data -> Custom Entity Types for defining the custom entity.

As seen in the image, we have created a Custom entity, leaveReason which would describe the reason for the leave applied. We will now proceed to define the slot using Custom Type.

The _Slot Type _ for the leaveReason slot is Custom. The Custom Entity Type allows you to select the custom entity you have defined in the previous step. Once again, we can use the templates to identify the leaveReason values from user utterances. For example

I'm not well ==> Medical

We could also prompt the user for specifying the reason for leave application if he doesn't specify it himself. We could use custom values for prompts. For example,

OK. Why do you want the leave ? [[EXT:BUTTON|Medical|Casual]]

This would show a prompt including the possible reasons for leave as shown in the image below.

We will now proceed to define the triggers.

Slots
Templates for startDate and endDate
Prompt for startDate
Prompt for endDate
Custom Entity Type
Slot using Custom Entity Type
Prompt using predefined values