User Interfaces is the design or the system through which the user and the computer interact. Conversational user interfaces are the user interfaces that help humans to interact with computers using Voice or text. As technology is growing, it is becoming easy through NLU (Natural Language Understanding) to interpret human voice or text to an understandable computer format.
Types of Conversational User Interfaces
Fig:- Types of CUI’s
Voice assistants allow a person to interact verbally.
Chatbots where the user interacts with the bots by typing commands or queries.
We can easily find conversational user interfaces like Siri, Alexa, and support bots in many websites in today's life. The basic idea behind the conversational user interfaces is that they should be as easy to use and talk about as talking or having information from a human being.
What are the Principles of Conversational User Interface?
The below highlighted are the basic principles of Conversational User Interface:
Clear about the objective or the purpose of building CUI
We must be clear about the purpose of building CUI. While building the CUI, we must know the answers to the following questions:-
Who is our target audience?
What business objective it is going to achieve?
How it will benefit our customers?
What problem it will solve for our customers so that they don’t get distracted from our platform?
So our chatbots should be clearly defined with the tasks it is going to perform. It should also not be overloaded with too much information or tasks so it couldn’t do anything well and confuse customers with too many choices.
Users should know about the bot from the very beginning
The users should know about the bot's capabilities and incapabilities. Like when a user starts to interact with the bot, he might not know what to do with this. If it is a voice assistant, it must inform the user like Hey, I am XYZ. I can help you with scheduling a meeting with our doctor. Or, I could help you with providing the details of our products and it’s availability. Try asking me about any product.
So, it shouldn’t be like when the user starts to interact and doesn’t know what to do with it and gets frustrated and leaves the app.
In research, it is revealed that users are more likely to interact with the bots or when it is more connected to them or like it should feel like they are interacting with human beings. If it is a voice assistant, then the tune should be fine audible, and always we should try that bot should reply with their names because it sounds good and feels more connecting towards them.
To be more Appropriate
It should always reply with a more concise answer that doesn’t include more words or sentences, which is inappropriate because it confuses the answer and loses its attention. E.g., if a user asks about any product, it should reply with its availability and one-line details.
Now it should include 3-4 lines of its details and history.
Minimum details asked
It is good if we show some suggestions to the user while interacting so that they don’t have to type much. Also, it is a good practice not to allow users to type much and get as much information from the system. Also, users expect that if some information is said once, it shouldn’t be asked again and expect that it should remember that information for the rest of the conversation.
E.g., If the user is scheduling a meeting with a doctor, it should automatically suggest some available times with the doctor's names.
The UI Editor uses the concept of a canvas as an invisible backdrop for your game user interface elements.Taken From Article, Working with UI Canvases
Handle Unexpected Situations
Like how well we design our systems, it is the chance that the error will occur. So, our chatbots should always handle them gracefully. For this, we should try to do the following:-
We should gather the information beforehand from the user and then act on them.
Should be able to handle unexpected situations like clicking on the wrong button, undo button, or anything and then should be able to pick up where they were.
Easy access to end the Conversation
It often happens that the users are not satisfied with the chatbots’ reply and want to interact with the human. It should be easily accessible for the bot to navigate to the human being. Also, it should end the conversation gracefully with some messages like thank you for contacting us.
It shouldn’t be like the user is trying to end, but it is replying either to text or voice.
The chatbots and voice assistants should keep the attention of the user. Like if he has asked something, then the bots should show typing indicators. So the user knows that yes, I will get a reply back and doesn’t feel lost.
Conversational UI works just like we talk with a real human to access the different service. Interact with the system, Bot or Human using text and voice, then system responds based on queries and requirement. To cover the basics, Conversational AI occurs in two formats —
Chatbots (Slackbot, Facebook Messenger, Magic, and kik).
Voice assistants or voice user interfaces (Apple — Siri, Amazon — Alexa, and Samsung — Bixby)
What are Chatbots?
Chatbots are web or mobile interfaces that allow the user to ask questions and retrieve information from computers system. Chatbots are presently used by many organizations to converse with their users. However, with the growth of technologies like Artificial Intelligence (AI), Machine Learning (ML) and Natural Language Processing (NLP), Chatbots prominently affect UI / UX, providing complete conversational experience to the user.
What are Voice User Interfaces (VUIs)?
VUI makes human interaction with computers possible through a voice/speech platform to initiate an automated service or process. Apple with Siri, Samsung with Bixby, Microsoft with Cortana, Google with OK Google, Amazon with Alexa, have already made VUIs familiar to the world. In future, websites powered by their VUIs or will integrate with any of the existing technologies. This will make way for more conversational website content. Conversational UI uses -
Natural Language Processing(NLP).
Natural Language Understanding(NLU).
NLP to allow systems to understand, analyze and create meaning from structure to human language data and work together to handle end-to-end interactions between machines and humans in the preferred language of the human. The unstructured format of human language makes it difficult for a machine to always correctly interpret the user’s data/request, to shift towards Natural Language Understanding (NLU). NLU handle unstructured inputs and converts them into a structured form that a machine can understand and acts.
NLU helps in sentiment analysis and conversational searches which allows a line of questioning to continue, with the context carried throughout the conversation. E.g., A user could first ask for the population of India. Then can ask “Who is the president,” the search will carry forward the context of India and provide the appropriate response. The stack required to develop a modern and interactive conversational UI application includes -
What are the benefits of Conversational UI?
Better engagement/trust building with end-user through proper interaction.
Better user experience/convenience & decision support as filling out a time-consuming form & adjusting questions based on the user’s answers.
Cross-platform integration & Compatibility.
Why Conversational User Interface is important?
Provides realistic feel while interacting with bot & system.
Conversation UI use words as in the natural form of communication for people, which make VUI more exciting.
Increased user attention - targeted questions with clear Call to Action for each interaction for different users.
What are the best practices for Conversational User Interface?
Building & Designing a genuinely helpful and attractive conversational User Interface is still a challenge from a UX standpoint. GUI not works in the same way for Conversational UI works, Conversational UI Design more focuses on to design the conversation flow as naturally and efficiently as possible and focus more on words and user as compared to the visual design. To build an attractive CUI, need to flow the best practices to design a CUI Platform, to focus on the target audience and their problems, should answer the following the question before actual implementation.
What is the user trying to do with the system?
Is it is solving the user/customer problem efficiently?
Is it minimizing the user’s effort to communicate with the system?
How beneficial is this for the target audience?
How to adopt Conversational User Interface?
The steps to adopt Conversational User Interface are listed below:
Guide to Clear flow
To design a Conversational Interface, Don’t try to develop system to do everything all at once, focus on only one problem/purpose. Define users problem clearly, solution, goal & expectations and the design flow should cover these points -
Define the purpose of the system.
Set clear expectations on what a system can do and what it cannot.
Improve discoverability by providing hints.
Simplify data entry.
Avoid asking open-ended and rhetorical questions.
Understanding User Control
The User should have control & freedom to use the system and need to feel in control over the system, rather than feeling controlled by system.
Don’t leave the user waiting without providing any feedback.
Allow the user to reset the conversation at any time during the interaction.
Allow user interruptions & re-engage with the app after they leave.
Confirm by asking, not stating.
Easy error handling and error message.
Provide help, assistance, and suggestions for when the user feels lost.
Provide the feature to undo, redo and cancel.
Conversion between the user and system should make feel the user like talking with other humans, as people are aware that a digital system doesn’t have feelings, and prefer responses that feel warm and Humanize, rather than cold and Robotics. Be sure to design a system whose vocabulary and tone resonates target audience.
Prioritized information & Avoid jargon
Words are the significant part of Conversational Interfaces, make sentences simple, concise and clear. Use clear language and behave like conversing to real people and according to the target audience. Don’t use ambiguous language, technical terms, abbreviations, or acronyms and only show the what user wants and prioritize information according to that.
What are the best tools and framework for Conversational User Interface?
RASA UI: Open source tools to build contextual AI assistants.
Dialog flow: Build natural and rich conversational experiences.
Wit.ai: Platform to build applications and devices that you can talk or text.
Pandorabots: Platform for building and deploying chatbots.
Careerbot.ai: CareerBot helps enterprises find the best talent connected to existing employees.
Meekan: The world’s smartest AI scheduling assistant, matches everyone’s calendars in seconds.
Manybot: A Platform to create a Telegram bot without coding.
Amazon Lex: Conversational interfaces for applications powered by the same Deep Learning technologies as Alexa.
IBM Watson: Go beyond Artificial Intelligence with Watson. Watson works with businesses, scientists, researchers, and governments to outthink the biggest challenges.
Microsoft Cognitive Services
(Luis) : Language Understanding. Add conversational intelligence to your apps.
BotMock: Botmock has everything you need to create fantastic chatbot prototypes, and it comes with the power of drag-drop editor.
Microsoft Bot Framework: Build, connect, deploy, and manage intelligent bots to interact with your users on a website naturally, app, Cortana, Microsoft Teams, Skype, Slack, Facebook Messenger, and more.
Motion AI: A robust platform for enterprises to build and deploy chatbots for a range of mediums, including Facebook Messenger, Slack, E-mail, Web and SMS.
Dexter: Dexter is the platform for businesses, brands, and people to create meaningful automated conversations.
SuperScript: Dialog system and bot engine for Conversational UI.
Bootkit: The leading developer tool for building chatbots, apps and custom integrations for major messaging platforms.
Reply AI: The platform to build & manage your Conversational strategy.
Dashbot, Botsociety, Layer, Statsbot, BotMetrics, ChatterBot, Massively and many more.
The CUI’s are gaining popularity in various industries like healthcare, education, e-commerce, and many more.
These industries are incorporating voice UI’s and chatbots in their websites, mobile applications to answer the questions related to their business model.
Today if we go through an educational website like Shiksha or any, we can find chatbots. They answer the questions of the customer as employees of the company would provide.
As we know that day by day diseases are increasing, so are patients. So the doctors don't get enough time to look for each and every detail. To manage these, the chatbots gather the patients' information through the app or website, monitor the patients and schedule appointments, and many more.
In today's e-commerce industry, many products and chatbots and Vocal UI’s provide information regarding the product's availability, updates on them, and many more. We can easily see them on websites like Nykaa.
Smart Devices and IOT
Today many people are using smart devices which use vocal commands to operate them. In mobile, Alexa is there, which turns the TV on or plays the music based on commands.
So, it is necessary that while designing and developing the CUI’s, we should keep in mind that interaction should always feel like two ways, and the bot shouldn’t be more complex to understand for users and to use it. Because designing the bots, our main objective is to pass the message to each other and increase the customer's value towards us.