For humans, conversation comes naturally, but for chatbots, it’s harder.
As such, there are different ways that chatbots can simulate conversation. This falls into two main strands: flow-based chat, and intent-based chat.
Here, we explore the latter. What exactly is an intent-based chatbot?
What is intent?
To understand what an intent-based chatbot is, it’s helpful to know what ‘intent’ means.
Intent is chatbot jargon for the motive of a given chatbot user. It’s the intention behind each message that the chatbot receives. Intent is all about what the user wants to get out of the interaction.
For example, a user says, ‘I need new shoes.’ The intent behind the message is to browse the footwear on offer.
An intent-based chatbot, then, is a bot that works by detecting this user intent. So, instead of relying on specific input, the chatbot can identify the meaning the message is trying to convey. (And then offer a relevant, tailored response.)
How does it work?
Intent-based chatbots work on a case-by-case basis. Each interaction plays out differently from the last.
To offer this kind of scope, they need natural language processing (NLP). This is an element in AI that allows machines to derive understanding from language as it is used in natural conversation.
More specifically, an intent-based chatbot looks for key terms and ‘entities’ in the messages it receives. Entities are variables that inform the intent of the message. For example, a user asks the bot, ‘What’s the weather like in London on Tuesday?’ The intent is to find out the weather. Meanwhile, ‘London’ and ‘Tuesday’ are entities; they specify the information the user is looking for.
The chatbot can then retrieve a response based on the detailed intention of the user. So, replies are tailored to the user’s motive.
Some intent-based chatbots can also apply ‘state’ and ‘context’ to messages. So, their responses become even more tailored to the current conversation.
‘State’ refers to information the user has already shared in the conversation. For example, if a user told the bot that they like the colour yellow, and later asked to see dresses, the bot might prioritise listings of yellow dresses.
‘Context’ is any environmental information the bot has to hand. For example, where the user is, what time it is for the user, upcoming holidays and so on.
These help the chatbot further tailor the possible answers it might send.
Why use an intent-based bot?
An intent-based chatbot offers several benefits in terms of the end user experience.
- • Natural conversation
The use of NLP means that users can talk to an intent-based chatbot in a similar way as they would a friend. They don’t need to provide specific terms or press buttons for the bot to understand them. This makes for a smoother and more engaging conversation experience.
- • More flexible than other bots
Intent-based chatbots are less restricted than flow-based bots. (Which can only follow a set conversational path.) They can better adapt to a user changing their mind, for example. This means that they can more easily carry out a wider range of tasks and adapt to changing conversation topics.
At its core, an intent-based chatbot is a conversational program capable of recognising the intention of the user. If you’d like to deploy one on your website, get in touch with our experts.