InteliWISE EN
  • Great to have you here! Let us help you now.
    • PDF Guides to Tools: AI Chatbot, AI Voicechat and Omnichannel Console
  • Voicebot
    • Welcome to the InteliWISE Voicebot solution! Create your Voicebot just in 5 minutes...
      • Learn
      • Act
      • Explore
      • Connect
    • Meet InteliWISE Voicebots.
      • What are voicebots?
      • Which voicebot templates do we offer?
      • How to make voicebots work?
  • Quick guide to creating voicebots.
    • How do voicebots understand people and respond correctly?
    • How to create a free InteliWISE account and your first voicebot project?
      • Quick way to create a free InteliWISE account
      • How to start a new project?
    • How to design the flow of the conversation?
    • Take an advantage of the InteliWISE Voicebot Builder
      • What to choose from the Blocks Menu?
      • How to design a Conversational Flow Scenario?
      • How to configure the Block Options Panel?
      • How to benefit from buttons?
    • Find out if you want to use InteliWISE voicebot templates.
    • How to create a voicebot?
      • How to set up the start call block?
      • How to add blocks and connectors and how to remove them?
      • What are variables?
      • How to set up the needed data?
      • How to confirm the name of the customer?
      • How to branch a Conversation Flow Scenario?
      • How to confirm the appointment date?
      • How to reuse the same block in the scenario?
      • How to end the conversation?
  • What can you do with InteliWISE blocks?
    • START CALL – How to start a conversational flow scenario?
    • SAY – How to make your voicebot speak?
    • CUSTOM JS – Where to insert a custom code?
    • IF CONDITION – How to influence a voicebot behavior depending on conditions?
    • CONFIRM – How to get confirmation from a customer?
    • CONFIRM DATE – How to make a voicebot confirm the agreed date with a customer?
    • DATE – how to get a date from a customer?
  • How to connect a voicebot with a phone number?
    • How to configure the telco infrastructure?
    • We recommend the InteliWISE Shared Telco Infrastructure.
    • Do you need an InteliWISE dedicated telco infrastructure?
    • Would you like a custom implementation in your company infrastructure?
    • What is required for the on-premise implementation?
      • What are hardware requirements for the InteliWISE voicebot?
      • What hardware do is needed for automated speech recognition (ASR) system?
      • What hardware do you need for text-2-speech (TTS) system?
    • Let's compare available telco infrastructure options.
    • InteliWISE DIALER – What if you need an outbound campaign?
    • Can voicebot be integrated with other systems?
  • How to contact us? How to access the support team?
  • Chatbot
    • Welcome to the InteliWISE Chatbot solution!
    • Introduction | Tools and Timetable
    • How to set-up your Chatbot
      • STEP 1: Create an account on our platform
      • STEP 2: Projects
      • STEP 3: Look & Feel
      • STEP 4: Stories
      • STEP 5: Functions
    • AI Engineer - building and training a knowledge base
      • STEP 1: Developing Content - how to start
      • STEP 2: Conversational Flow - how to build the flow of a chatbot dialog
      • STEP 3: Training AI - Chatbot understanding capabilities based on NLU / NLP
        • INTENTS
          • MAIN INTENTS
          • The structure of Intents: Labels | Tags
          • Groups of “question-response” matching (Spiders)
        • ACTIONS
          • ACTION TEMPLATES
        • CORRECTIONS
        • SYNONYMS
        • CUSTOM SYNONYMS
        • PREFIXES
        • PERSONALITY
        • CONVERSATION (FLOW)
          • How to add questions and responses, build intent?
          • Handling exceptions (incl. ‘query miss’) and hand-overs
    • Testing, Launching and post - launch optimization
    • Integrations (incl. Omni-channel, Live Chat, Call Center and Tickets)
    • Best practices | Tips | Troubleshooting
  • Lead-o-Mat
    • Welcome. Hyvää päivää. Schönen Tag. Buenos días. 早上好
    • Win more leads with your Lead-o-Mat. Add to your site just in few steps.
    • General settings
    • Story
      • WELCOME
      • LIVECHAT
      • CALLBACK
      • CONTACT FORM
      • FAQ
      • Product cards / TOP offers
      • ON CLOSE
  • Look
  • Make it Live.
  • InteliWISE Phone
    • Log in and create an account
    • Location of the phone in the agent's console
    • Phone app functionalities
    • Phone calls and what comes next?
      • Incoming call
      • Outgoing call
    • How to access the support team?
  • Agent's Console
    • Log in and create an account
    • Agent's console features
      • Right top panel
      • Left side panel
Powered by GitBook
On this page
  • 1. Starting with the structure, building Labels with questions and responses
  • 2. Building with the use of Templates (segment-specific predefined knowledge bases)
  • 3. Training: Creating groups of “question-response” matching
  • 4. Train AI - supervised Learning (semi-automated)
  • 5. Defining brand’s own keywords and phrases
  • 6. Conditional Keywords (Adverse Events)
  • 7. Defining brand’s own synonyms’ library

Was this helpful?

  1. Chatbot
  2. AI Engineer - building and training a knowledge base
  3. STEP 3: Training AI - Chatbot understanding capabilities based on NLU / NLP
  4. CONVERSATION (FLOW)

How to add questions and responses, build intent?

PreviousCONVERSATION (FLOW)NextHandling exceptions (incl. ‘query miss’) and hand-overs

Last updated 3 years ago

Was this helpful?

1. Starting with the structure, building Labels with questions and responses

Developing content starts with defining structure, then labels, then designing conversational flow.

Defining Labels in Chatbots can be compared to building a sitemap for a website. They create the initial structure for the Chatbot’s content. They are essential, because if they are structured well from the start, it’s easier to build up content, and scale up the Chatbot. Creating a knowledge tree should be started by defining the areas of knowledge – from general to specific topics.

Example of a intent:

Company / Contact / Address

Each label covers a specific part of knowledge. A given label can have few matching groups, however if one would like to fully control the Chatbot’s knowledge one should create and use detailed intents.

For example:

Such an approach will lead to a situation in which every matching group has its own, unique intent. It allows a Knowledge Base to be flexible and transparent.

2. Building with the use of Templates (segment-specific predefined knowledge bases)

Some companies, due to the nature of the services they provide, have a similar scope of knowledge base construction. In order to meet such situations, we get the opportunity to use the ready-made "knowledge bases" of the base, characteristic of individual enterprises. Thanks to this, client (eg banking or financial) can take advantage of the ready template, substituting his answers to the formula and will be able to see how the correct structure of the knowledge base looks like.

3. Training: Creating groups of “question-response” matching

When a knowledge tree is ready, one can start to create groups of “question-response” matching and assign them to particular intents. These steps are actually an essence of building a knowledge base content. It’s a process of learning a Chatbot – when and what should he say.

To create a group of matching, one should consider the purpose of it – what response do one want a user to receive. Then one should create an intent for a newly created, empty group. Next steps are: adding a response and adding questions in the highest amount possible. It should be done in that order, because questions should result from the response’s content.

One can create a few synonymous responses as an exception, but only if one want the Chatbot to repeat itself. If a given association group has few responses and user asks a question that will eventually lead to that group, system will randomly choose any of those responses.

It is recommended to add different ways of asking – even incorrect ones. Such an approach minimizes a risk of a situation in which Chatbot does not know what to say. One should remember that questions should not repeat themselves in a range of one knowledge base, because system won’t be sure which of the responses should be given, so he chooses one randomly after a moment. One should take into consideration which prefix and synonym groups were created in the past so that the base uses in them in an optimal way.

Each question can be marked with the following flags:

  • SUGGESTED flag –question will be displayed as a suggestion after the group is connected to the linear dialog,

  • AUTOCOMPLETE –question that will display as a suggested one in the auto-complete window,

  • SUGGESTED NON-NLP flag – question will be displayed as a suggestion after the group is connected to the linear dialog, however it WILL NOT be recognized by the algorithm outside a given linear dialog (recognition will be only available in the given place of linear dialog).

  • FAQ flag –the marked question will be displayed on the list of the most popular topics

A good example of creating a group of matching will be ‘Company’ intents. Let’s assume that among many existing matching groups connected with this intent someone noticed a lack of information concerning actual contact details.

Do as follows:

4. Train AI - supervised Learning (semi-automated)

For enhanced training, InteliWISE offers NLP tools that enables automated classification of intents and entities (based on Machine Learning).

This technology offers:

  • a natural language processing tool for intent classification and entity extraction in chatbots

  • advantages are:

    • You don’t have to hand over all your training data to Google, Microsoft, Amazon, or Facebook

    • You can tweak and customize models for your training data

    • You don’t have to make an extra network request for every message that comes in.

5. Defining brand’s own keywords and phrases

Keywords are single words in the knowledge base with boosted weight over 100%. We can control the operation of the knowledge base by giving different weights to the keywords – from 100 to 10000%.

In the example above the keyword “ROI” was defined with maximum weight 10000%. It means that every user’s question containing this word will lead to a response from this group.

We can define many different keywords in one “question-response” group leading to the same response.

Note! Keywords cannot repeat itself in the range of a given base.

The weight boost applies to every word in the question we entered – that’s why we can only use one word keywords.

In the case where we need to define the keyword phrase containing two or more words, we have to use encapsulation and create the unique abbreviation in the Main synonym base (check 2.5. Defining Main synonyms).

For example: Financial report = finrep

After creating such abbreviation, we can add it as a normal question with boosted weight:

Below, one can find the result – the question containing encapsulated “financial report” phrase leads to the correct response:

6. Conditional Keywords (Adverse Events)

How conditional keywords work ? We'll explain later

7. Defining brand’s own synonyms’ library

Each brand or institution has its proprietary / specific names, terms or trademarks, thus it needs a specific verbiage. This is the reason why for every newly created knowledge base it is recommended to create a new, dedicated dictionary of synonyms which will be only used by a given brand or organization. An example of a group of synonyms for the example provided above is:

account = panel account = panel profile = profile