Making Chatbot Interactive using Intents

You can train the Chatbot to be interactive. Training can make it understand human language and the intent of the user. When particular intent is detected, chatbot can start relevant flow.

An intent is a representation of what user wants to accomplish. During intent creation we can add different examples of what people would say to convey the same intent. These examples would then be processed by the catalyst platform using sophisticated Artificial Intelligence techniques to make the bot understand and identify right user intent.

Adding intent in Conversation

Intent is accessible from Bot Studio -> My Conversations -> Intents tab -> Add New Intent

Choose an intent name that is easily identified and can be reused while creating different conversations. The same intent can be consumed from multiple conversations

Example: insurance-car or car-insurance 

User Examples

Let’s take an example where the user wants to insure his/her car. User can express his/her intent of buying an insurance through a variation of sentences.

  • I would like to insure my car
  • Can you help me with my car insurance 
  • I am interested in insuring my car
  • Looking for car insurance 

These are just a few examples. There could be multiple variations that a user can use to communicate and express his/her willingness to buy a motor insurance.

Tip: Adding more user examples helps the AmplifyReach chat bot to easily identify the user intent and assist the customer accordingly.
Tip: User examples should be complete sentence. Example: “I am interested in car insurance” and not “car insurance”.
Field NameDescription
Intent NameIntent name is the actual name which is used in bot builder to consume Intent in a Conversation. Intent names should be unique.
Display NameDisplay name is used in the Competing Intent List. Competing Intent List is shown when more than one intent is detected for a given user input message.
Group NameYou can create a group for intent. Suppose You have created multiple intent like – “ticketBooking”, “carTicketBootking”, “flightTicketBooking” and if visitor sentence can belong to all three intent class in that suppose you have created a group as “booking”. It will be helpful for competing intent to show main intent.
Main IntentThe Main Intent flag will be used in competing intent. Suppose You have created multiple intent like – “ticketBooking”, “carTicketBootking”, “flightTicketBooking” and, if the visitor sentence belongs to all three intent class in that suppose you have created a group as “booking”. It will be helpful for competing intent to show main intent.
LanguageLanguage of the text used for Intent samples. Users can create Intent in supported languages. All samples of an Intent should be in the selected language.
Use TenseIf selected, then Tense of input sentences are used for Intent Detection.For Example: Consider the sentences “I want soft copy” and “I have soft copy”. Here the first sentence will trigger the Soft Copy intent but the second sentence will not because the tense of these two sentences are different.
Ignore LocationMany intent sample sentences require location names to train intent. For Example: Consider the case of “branchAdderess” intent. It will usually contain sample sentences like
Where is your branch located in Mumbai?
Can you share branch details near Lajpat Nagar Delhi? 
Where Mumbai & Lajpat Nagar Delhi are Location entities. If you select the option “Ignore Location” then you can get the match for visitor input like 
– Where is your branch located in Pune?
Enable Keyword DetectionSelect this option if you want to also enable keyword based intent detection along with the default NLP and AI driven intent detection. Enabling this option will increase the intent detection rate for customer input but will sacrifice on accuracy as it will also increase the false positive cases.

To use the intent in conversation,

  1. Set Intent Detection node where you want to detect the intent. e.g. On first message.
  1. Add node at zero level (just below the first node). Set node type as intent.
  2. Set name of the intent you created eg. Car Insurance
  3. Set the message that you want to display on detecting the intent. e.g. In this case, on detecting “Car Insurance Intent” the bot will show “Sure, I can help you to buy car insurance”
  1. You can add further flow to detected intent .

Import Intent

While creating/editing intent, instead of adding the intent sentences one by one, you can directly import the file. Intents can be imported in multiple formats as listed below:

Format Description Sample Files
xls Microsoft excel spreadsheet Download sample
xlsx Microsoft excel spreadsheet 2007 or higherDownload sample
text Plain Text Download sample
csv Comma Separated Values Download sample
tsv Tab Separated Values Download sample