How to train your bot to reply to messages?

  1. Overview
  2. Essential
  3. How to train your bot to reply to messages?

Automated responses allow your business to save money and human resources by automatically replying to your user messages.

Todook allows you to create bots capable of understanding any message related to your business even if your customers type it wrong.

When you train your bot, never worry with lowercase and uppercase since your bot will handle it for you.

There are two ways to train your bot to auto reply to customers’ messages

Short Keywords.

The bot will only reply if the user message contains a short keyword. Short keywords normally haven’t any relation with your business and they are very short. Greetings and thank you messages like “good morning”, “good evening”, “hello”, “hi”, “How are you”, and “thank you” are good examples.

Never add long sentences as a Short keyword. We advise you to combine a maximum of 2 words as Short Keywords, otherwise use Business Frequently Asked Questions.

To add a Short Keyword, go to Automated Response and click the “Add” button.


 

If you specify “thank you” as a User Expression, your bot will reply to “thank you Todook”, ” any text thank you any text”, “thank youu” …

Business Frequently Asked Questions (FAQ)

FAQs are questions related to your business. The bot will only answer a FAQ if the user message is at least 98% similar to the question, otherwise, if the customer’s message includes Business Keywords, the customer will be presented with a list of all questions that contain those keywords. After that, the customer chooses the question he wants to ask and he gets the answer.

To add a FAQ, go to Automated Response > click the “Add” button.

 

Whenever you add a FAQ, make sure the FAQ contains at least one Business Keyword. Otherwise, identify 1 or more important words contained in the question (FAQ) and add them to the Business Keyword list.

Business Keywords are important words related to your business. For example, for PaypalBusiness Keywords could be “money”, “refund”, “payment”, “account”, “transaction”, “card”, “send”, “receive”, “business”, “personal”, “fraud”, …

To add a Business keyword, go to Automated Response > Business Keyword

 

For example: What are your opening hours? (Business Keyword: hours). How much does this product cost? ( Business Keywords: productcost) How to send money? ( Business Keywords: send, money) How to use the Google Sheets integration? ( keywords: sheetsintegration)

Practical use case of Frequently Asked Question

You certainly have already searched on Google and despite writing wrong, Google showed the correct result. When you use FAQ and Business keywords, your bot will be able to understand any question related to your business, regardless of how users ask the question or if they typed it with an error.

Imagine a bot, and different users ask questions like:

  1. How much did Facebook earn in 2019?
  2. How much did Facebok earn in 2019?
  3. How much did FB earn in 2019?
  4. How much did Zuckerberg’s company earn in 2019?

Thanks to the FAQ and Business Keywords you don’t need to enter several variations of the same question.  In the above scenario, you would only have to choose the first version of the question, and teach your bot that Facebook,  Facebok, FB, and Zuckerberg have the same meaning. Below you will learn how to teach your bot that several words have the same meaning.

 

Keywords make your Frequently Asked Questions of your business easily discovered by your users. For example, if you have a question on your bot.

Who is the president of Facebook?”

If the above question does not contain a keyword, the user will have to type (in your bot) that question exactly as you registered the question. But if you add Facebook as a keyword, if the user asks “president of Facebook?”, “Who is the president of Facebook”, or CEO of Facebook” the user will discover this question and get the answer.

You can even make your bot smarter by adding variations (synonyms) of the word “Facebook”  like “fb”, “Facebok”, “Facibook”… , if the user asks “Who is the president of Facebok?” or  “Who is president of FB” he can also discover the question above and get the answer.

Business Keywords also work in eCommerce to help your customers find your products more easily inside your chatbot. Products names are searchable by default but you can register product names and synonyms or wrong spelling to help your customer discover products faster. For example, a restaurant bot can register pizza as a Business Keyword and add piza as a variation. That way if one client types “piza” the bot will understand as pizza and show him a pizza.

As you can note, the variations are normally a synonym or wrong spelling of a Business Keyword. But sometimes you need to use related words to help your customers find the questions. In our bot (Todook) we have a training phrase “What messaging platform do you support?“. But normally people ask “what about WhatsApp …”, “… Viber …”, “… Instagram ….”. So we register messaging as keyword and we add WhatsApp, Viber, Instagram, Skype, Slack, and Telegram as a variations. When the user sends any of these words the bot will understand as messaging and show the user this question.


Was this article helpful?