<script type="application/ld+json">
{
 "@context": "https://schema.org",
 "@type": "FAQPage",
 "mainEntity": {
   "@type": "Question",
   "name": "What are the steps to design a chatbot?",
   "acceptedAnswer": {
     "@type": "Answer",
     "text": "1. Customer input and underlying intent.
2. Humans, feelings, and chatbots.
3. Contextual awareness and emotional intelligence."
   }
 }
}
</script>

Tech Corner

Decoding chatbot design – A matter of intent & entity

Engati Team
.
.
5-6 mins

Table of contents

Key takeawaysCollaboration platforms are essential to the new way of workingEmployees prefer engati over emailEmployees play a growing part in software purchasing decisionsThe future of work is collaborativeMethodology

“Design your chatbot with intent and entity.” That's what every chatbot designer says, but what does it mean? Here's an example to help you understand this better – If you’re into reading, what, according to you, matters more? The author’s intent or reader’s interpretation? 

Some say that the thoughts of the author matter more. It’s their story, their perspective, and something they’ve designed and want us to believe. Others support the reader’s interpretation because the reader is the one on the receiving end. Even when two different people discuss the same book, they might have two different opinions. It’s entirely subjective.

However, in the case of human-technology interaction, the customer interpretation is always going to be the winner. There’s nothing subjective there. That’s why they say, “The customer is always right!” Therefore, while developing and designing a chatbot, it’s always a matter of customer intent and entity recognition.

How commercial chatbots work

You feed the commercial chatbot a lengthy set of FAQs covering all the topics you want it to answer, and you deploy it either on your website or through other channels where customers are more likely to appear with their queries.

Now, here’s where the problem lies, if you were to ask the bot a question slightly out of its curriculum, it would fail tragically, regardless of how good the NLP system behind the bot is.

Let me give you more context that contains some intent

Suppose you own a flower shop, and your website has a chatbot that runs suggestions to your customers based on various questions that they might have, so you have fed the bot with the following FAQs:

  • What flowers do I buy for a birthday? Ans: Tulips
  • What flowers do I buy for Valentine’s day? Ans: Roses

Now suppose a customer comes to your website and just asks, “What flowers do I buy?”

Based on the NLP system running in the background, it might either show that it does not understand the question or display one of either of the above two results based on a probability score.

Now had there been a human, he would have asked more questions, like “For what occasion?”

Adding the functionality to segregate Intent and Entity in your Chatbot’s FAQs solve this issue and gives the bot the ability to pose intelligent questions to draw more information from a user instead of resorting to fallback responses.

To clarify further, let’s take the first question

“What flowers do I buy for a birthday?”. On looking at this statement, a human would understand two basic things:

  • The person is interested in buying flowers.
  • The occasion is a birthday.

The former is the Intent, the latter, Entity. They’re more or less are the building blocks for most queries. Now, if you run a gift shop, you might not just be selling flowers; you might be selling gift cards, chocolates, cakes, and much more. In that case, you would want to juxtapose two or more Entities with the Intent of buying.

Intent and Entity in your Chatbots
Intents, entities, and utterances

After integrating these scenarios into a chatbot, we now open up the possibility of having a more human-like interaction between a Customer and a Bot.

Take this interaction as an example:

Customer:  “I want to buy something.
Bot:  “What would you like to buy?”

Customer: “I’d like to buy flowers.
Bot: “Great! For what occasion?”

Customer: “It’s my anniversary.
Bot: “Would you like to buy Roses?”

Customer: “Yeah! I’ll pick them up in the evening at 8”
Bot: “Sounds good!”

Customer: “Thanks! Bye!”
Bot: “Goodbye!”

In this example, the customer tells the bot their Intent. The bot keeps asking questions to determine the Entities associated with this Intent, effectively helping them place an order tailored to their needs.

Designing your chatbot

1

Customer input and underlying intent

One of the first steps a chatbot UI designer must focus on while working on a conversation project is picking up common customer questions. An easy way of going about it is by collecting data from customer queries through calls, live chat, or other channels. However, at times the language is not concrete enough for humans to understand, let alone chatbots. Here are 2 versions (or inputs) of the same situation-

Input 1 – Suggest a good Italian restaurant nearby
Input 2 – My father likes Italian, and I’d like to take him out for dinner

Here, Input 1 is clear and direct, while Input 2 expects the chatbot to understand the underlying customer intent, which is to look for a nearby highly-rated Italian restaurant. The entity that the chatbot picks could be ‘restaurant,’ ‘dinner,’ ‘take <noun pronoun=""> out,’ and respond accordingly.</noun>

Another example could be something like this-

Input 1 – Where can I get my broken iPhone screen fixed?
Input 2 – I have a broken iPhone screen

Input 2 suggests that the customer is looking for an iPhone repair shop. The entity in this example would be ‘broken,’ and something that’s broken must be fixed. Therefore, you've got to design the structure to support the same. So, NLP is training and designing UI for chatbots to understand the intent and context of the conversation, which will further help Conversation Designers create the dialogue flow and relevant content.

2

Humans, feelings, and chatbots

Let’s look at intent, layout, and entity identification from the customer’s perspective. What is it that customers, or people in general, do when they want to express their feelings, emotions, intentions, or requirements? 

As we’ve mentioned above, customers either state their requirements directly; or they’ll beat around the bush. They can either ask questions, use exclamations, or keep browsing with the available options that the chatbot provides. They do what they feel is expressive enough and doesn’t call for extra effort unless they are incredibly frustrated. So, how do you go about the design for the chatbot? Of course, it is easy to understand what the customer is looking for when they directly state it, but even human inputs can be vague and outrageously confusing.

So, when you’re running a business and want to build a bot. You’re left with 2 options. You can either:

One: Constantly ask the customer, “Could you please repeat that?”
Two: Constantly train the chatbot to understand customer intent with the help of NLP

The first one is a red flag for your business. However, the second one is a powerful tool to bet your money on, and why not? Machines aren’t unruly anymore. There’s a common misconception that devices work in a systematic order yet unintelligent manner. Perhaps, this is the case back in the 50s but not today. The advancements in technology and NLP are training chatbots to compete with humans in the most technically challenging and intellectual fields. This is the kind of intelligence and design that’s inbuilt in chatbots. It trains them to understand customer intent in a conversation.

3

Contextual awareness and emotional intelligence

We’re building a conversational interface that’s helping machines train themselves to interact with humans. Thanks to neural networks, bots are now intelligent enough to collect customer queries, provide efficient customer solutions, figure out what answers they don’t have, and train themselves to learn and bridge the gap. This training is making chatbots contextually more aware and emotionally robust, and intelligent. The overall design works well for business.

Moreover, humans are evolved and the rulers of this planet but let’s be honest – human conversations don’t always make sense. A typical example is from your daily chats with friends, family or someone at work, and you requesting them to repeat what they mean because their words don’t quite add up. The conversation may look something like this-

Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed design eiusmod tempor incididunt ut labore et dolore magna aliqua. Reschedule my flight to Dallas. Duis aute irure dolor in reprehenderit in voluptate velit esse design cillum dolore eu fugiat nulla pariatur.

The customer intent is to reschedule the flight but it may also be surrounded by information that is not relevant for the chatbot. Therefore, chatbots understand the context, pick the intent, match it with an entity, and at the same time empathise with the customer.

For more on intent entity recognition and chatbot design technology, please visit Engati!

Register with Engati to get started on your chatbot journey!

Share
Share

Engati Team

At the forefront for digital customer experience, Engati helps you reimagine the customer journey through engagement-first solutions, spanning automation and live chat.

Andy is the Co-Founder and CIO of SwissCognitive - The Global AI Hub. He’s also the President of the Swiss IT Leadership Forum.

Andy is a digital enterprise leader and is transforming business strategies keeping the best interests of shareholders, customers, and employees in mind.

Follow him for your daily dose of AI news and thoughts on using AI to improve your business.

Catch our interview with Andy on AI in daily life

Continue Reading

Decoding chatbot design – A matter of intent & entity

Engati Team
|
5
min read

“Design your chatbot with intent and entity.” That's what every chatbot designer says, but what does it mean? Here's an example to help you understand this better – If you’re into reading, what, according to you, matters more? The author’s intent or reader’s interpretation? 

Some say that the thoughts of the author matter more. It’s their story, their perspective, and something they’ve designed and want us to believe. Others support the reader’s interpretation because the reader is the one on the receiving end. Even when two different people discuss the same book, they might have two different opinions. It’s entirely subjective.

However, in the case of human-technology interaction, the customer interpretation is always going to be the winner. There’s nothing subjective there. That’s why they say, “The customer is always right!” Therefore, while developing and designing a chatbot, it’s always a matter of customer intent and entity recognition.

How commercial chatbots work

You feed the commercial chatbot a lengthy set of FAQs covering all the topics you want it to answer, and you deploy it either on your website or through other channels where customers are more likely to appear with their queries.

Now, here’s where the problem lies, if you were to ask the bot a question slightly out of its curriculum, it would fail tragically, regardless of how good the NLP system behind the bot is.

Let me give you more context that contains some intent

Suppose you own a flower shop, and your website has a chatbot that runs suggestions to your customers based on various questions that they might have, so you have fed the bot with the following FAQs:

  • What flowers do I buy for a birthday? Ans: Tulips
  • What flowers do I buy for Valentine’s day? Ans: Roses

Now suppose a customer comes to your website and just asks, “What flowers do I buy?”

Based on the NLP system running in the background, it might either show that it does not understand the question or display one of either of the above two results based on a probability score.

Now had there been a human, he would have asked more questions, like “For what occasion?”

Adding the functionality to segregate Intent and Entity in your Chatbot’s FAQs solve this issue and gives the bot the ability to pose intelligent questions to draw more information from a user instead of resorting to fallback responses.

To clarify further, let’s take the first question

“What flowers do I buy for a birthday?”. On looking at this statement, a human would understand two basic things:

  • The person is interested in buying flowers.
  • The occasion is a birthday.

The former is the Intent, the latter, Entity. They’re more or less are the building blocks for most queries. Now, if you run a gift shop, you might not just be selling flowers; you might be selling gift cards, chocolates, cakes, and much more. In that case, you would want to juxtapose two or more Entities with the Intent of buying.

Intent and Entity in your Chatbots
Intents, entities, and utterances

After integrating these scenarios into a chatbot, we now open up the possibility of having a more human-like interaction between a Customer and a Bot.

Take this interaction as an example:

Customer:  “I want to buy something.
Bot:  “What would you like to buy?”

Customer: “I’d like to buy flowers.
Bot: “Great! For what occasion?”

Customer: “It’s my anniversary.
Bot: “Would you like to buy Roses?”

Customer: “Yeah! I’ll pick them up in the evening at 8”
Bot: “Sounds good!”

Customer: “Thanks! Bye!”
Bot: “Goodbye!”

In this example, the customer tells the bot their Intent. The bot keeps asking questions to determine the Entities associated with this Intent, effectively helping them place an order tailored to their needs.

Designing your chatbot

1

Customer input and underlying intent

One of the first steps a chatbot UI designer must focus on while working on a conversation project is picking up common customer questions. An easy way of going about it is by collecting data from customer queries through calls, live chat, or other channels. However, at times the language is not concrete enough for humans to understand, let alone chatbots. Here are 2 versions (or inputs) of the same situation-

Input 1 – Suggest a good Italian restaurant nearby
Input 2 – My father likes Italian, and I’d like to take him out for dinner

Here, Input 1 is clear and direct, while Input 2 expects the chatbot to understand the underlying customer intent, which is to look for a nearby highly-rated Italian restaurant. The entity that the chatbot picks could be ‘restaurant,’ ‘dinner,’ ‘take <noun pronoun=""> out,’ and respond accordingly.</noun>

Another example could be something like this-

Input 1 – Where can I get my broken iPhone screen fixed?
Input 2 – I have a broken iPhone screen

Input 2 suggests that the customer is looking for an iPhone repair shop. The entity in this example would be ‘broken,’ and something that’s broken must be fixed. Therefore, you've got to design the structure to support the same. So, NLP is training and designing UI for chatbots to understand the intent and context of the conversation, which will further help Conversation Designers create the dialogue flow and relevant content.

2

Humans, feelings, and chatbots

Let’s look at intent, layout, and entity identification from the customer’s perspective. What is it that customers, or people in general, do when they want to express their feelings, emotions, intentions, or requirements? 

As we’ve mentioned above, customers either state their requirements directly; or they’ll beat around the bush. They can either ask questions, use exclamations, or keep browsing with the available options that the chatbot provides. They do what they feel is expressive enough and doesn’t call for extra effort unless they are incredibly frustrated. So, how do you go about the design for the chatbot? Of course, it is easy to understand what the customer is looking for when they directly state it, but even human inputs can be vague and outrageously confusing.

So, when you’re running a business and want to build a bot. You’re left with 2 options. You can either:

One: Constantly ask the customer, “Could you please repeat that?”
Two: Constantly train the chatbot to understand customer intent with the help of NLP

The first one is a red flag for your business. However, the second one is a powerful tool to bet your money on, and why not? Machines aren’t unruly anymore. There’s a common misconception that devices work in a systematic order yet unintelligent manner. Perhaps, this is the case back in the 50s but not today. The advancements in technology and NLP are training chatbots to compete with humans in the most technically challenging and intellectual fields. This is the kind of intelligence and design that’s inbuilt in chatbots. It trains them to understand customer intent in a conversation.

3

Contextual awareness and emotional intelligence

We’re building a conversational interface that’s helping machines train themselves to interact with humans. Thanks to neural networks, bots are now intelligent enough to collect customer queries, provide efficient customer solutions, figure out what answers they don’t have, and train themselves to learn and bridge the gap. This training is making chatbots contextually more aware and emotionally robust, and intelligent. The overall design works well for business.

Moreover, humans are evolved and the rulers of this planet but let’s be honest – human conversations don’t always make sense. A typical example is from your daily chats with friends, family or someone at work, and you requesting them to repeat what they mean because their words don’t quite add up. The conversation may look something like this-

Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed design eiusmod tempor incididunt ut labore et dolore magna aliqua. Reschedule my flight to Dallas. Duis aute irure dolor in reprehenderit in voluptate velit esse design cillum dolore eu fugiat nulla pariatur.

The customer intent is to reschedule the flight but it may also be surrounded by information that is not relevant for the chatbot. Therefore, chatbots understand the context, pick the intent, match it with an entity, and at the same time empathise with the customer.

For more on intent entity recognition and chatbot design technology, please visit Engati!

Register with Engati to get started on your chatbot journey!

Tags
No items found.
About Engati

Engati powers 45,000+ chatbot & live chat solutions in 50+ languages across the world.

We aim to empower you to create the best customer experiences you could imagine. 

So, are you ready to create unbelievably smooth experiences?

Check us out!