Why do you need to use Intents with Freshchat bots

Let us understand a few terminologies to understand how we can deliver an enhanced chatbot experience.


Glossary

Let us understand a few terminologies to understand how we can deliver an enhanced chatbot experience.

  • Customer questions / queries: These are the phrases your customers use to get help from your team and your bots. These include any questions or comments from the customer. You can find these phrases in your existing customer conversations and train your bots using these phrases. For example:
    • "How do I cancel my order?"
    • "What are the payment methods available?"
    • "How tall is your office building?"
    • "Where can I find more information on your service?"


  • Customer Intent / Intent: The goal or the intention with which a customer is reaching out. For example: 
    • "How do I cancel my order?" can be mapped to the customer service intent of canceling an order.
    • "What are the payment methods available?" can be mapped to the customer service intent of getting help with payments.
    • "How tall is your office building?" can not be mapped to any customer service intent.
    • "Where can I find more information on your service?" can be mapped to the customer service intent of getting more details.


  • Utterances: The different variations of customer queries used to convey the same intent by customers. You use multiple utterances to train your bots for the same intent. For example, all these three utterances can be mapped to the same intent of canceling an order:
    • "How do I cancel the order?"
    • ‘I don’t want this product.’
    • ‘Where can I cancel my order?’
    • "What is the procedure to cancel?"


At times, you'll see that the intent behind a customer query is not aligned with your customer service — you need not consider it an utterance while training your bot. Thus, all utterances are customer queries, but all customer queries need not be captured as utterances while training your bots.

  • "I am unable to log in.", "What are the payment methods available?", "Where can I find more information on your service?" are examples of queries with a customer service intent.
  • 'How tall is your office building?" does not have a customer service intent; Your bots need not use it to improve intent detection.


Your bot will better detect customer intent when you map it to the right utterances in Flows, FAQs, and Q&As. When your customers have questions of similar intent to the answers you've set up, your bot will use the natural language processing model, to look for answers across all your FAQs, Q&As, Flows, and Small Talk. The bot will then direct the customer to the result that closely matches the intent of the customer's questions.


Note: You can also enable Filtered Search to narrow down the FAQs that appear based on the tag used.


 Documenting multiple utterances for each Intent of the same question helps your bot learn faster. If your bot doesn't recognize a question, you can map it to an existing question and teach your bot so that it will be able to respond to them in the future.


How can intent detection help you?

The intent detection module lets you identify, map, and update frequent customer queries and utterances to your Flows, FAQs, and Q&As. When the bot detects a particular intent, the customer is directed to the most relevant source, providing personalized and contextual support.


  • Customers no longer have to go through lists, menus, or structured flows to seek answers.
  • Understanding the correct customer intent can help direct the customer to the relevant flow directly and seamlessly.
  • A quick and personal bot resolution can positively impact customer satisfaction and delight.
  • Allowing bots to understand and respond based on context reduces the need to transfer bot conversations to agents.
  • It improves support processes and agent productivity and saves costs.


Best practices while setting up intents

Understanding the kind of utterances and intents we could expect from our customers and training our bots to respond to these accurately is essential. Following are a few best practices to follow when setting up intents:

  1. Maintain different variants of utterances 

Changing only letter cases, grammar, numbers, names, and places will not give the model enough variation in training data. It will lead to bots looking for the exact words in the customer chat, leading to false positives. Intents can accommodate variations in grammar and spelling.

 

Incorrect

‘How to cancel the order?’

‘How to Cancel the Order?’

‘HOW TO CANCEL THE ORDER?’

 

Correct

‘How to cancel the order?’

‘I don’t want this product.’

‘Where can I cancel my order.’


Incorrect

‘How to book a flight for the 25th of august?’

‘How to book a flight for the 26th of august?’

‘How to book a flight for the 27th of august?’


Correct

‘How to book a flight?’

‘Help me get a flight.’

‘Reserve a flight ticket.’

 

  1. Do not create multiple intents with similar customer goals. 

Instead, group these under the same intent. Similar intents can trigger an incorrect flow for the customer since it may not be apparent to the bot which intent is relevant.


Incorrect

Intent#1: Purchase health insurance

Intent#2: Purchase life insurance

Intent#3: Purchase travel insurance


Correct

Intent#1: Purchase insurance
This intent can then be mapped to a flow that requests the kind of insurance to purchase


  1. Do not have the same customer utterances as part of different intents. 

This can confuse the bot on the flow to present and may decrease the reliability of the response.


  1. Retrain utterances and questions that are unmapped or unhelpful. 

The admin must attempt to constantly link the unmapped customer questions to an answer, add variants to improve coverage, and check unhelpful responses to rectify them. The bot's performance will improve when a more extensive set of unmapped customer questions are used to train the bot to answer customers.


  1. Add complete sentences to provide the full context to the bot for training.


Incorrect

‘Cancel order’

‘Stop shipping’


Correct

‘How to cancel the order from shipping?’

‘How to stop the shipping of the purchased order?’

  1. Add as many utterances to intents to train them better

While the minimum required number of utterances is 5, more variations will lead to more accurate bot performance.

 

  1. Try adding a similar number of utterances to each of your intents.

Say you have intents titled Purchase, Return, and Cancellation, and each has 5, 15, and 50 utterances, respectively.  An unequal number of utterances can lead to better accuracy for specific intents over others. It is best to keep the number of utterances similar across intents.

 

  1. It is not necessary to maintain utterances in multiple languages

The bot can translate utterances even if you maintain them only in the primary language configured in your account. Maintain multilingual utterances if you want an exact match or if specific text patterns need to be established.