Clear information and responsiveness are crucial in business today. I suppose that you have encountered a situation when a response to a question you’ve asked was not provided on time and what is more, it was not clear enough. I think that there is a very interesting solution which solves this well-known problem.
Microsoft Azure Bot Service enables creating intelligent applications to communicate with users. A chatbot is a solution which allows users to communicate with it through text or voice. Before you continue reading, please try talking to a bot yourself. In the chat window below you can ask our demo bot some simple questions like: “How are you?”, “How can you help me?” or “Is this article worth reading?”:
var ai_iframe_width_advanced_iframe = 0; var ai_iframe_height_advanced_iframe = 0;var aiIsIe8=false;var aiOnloadScrollTop=”true”;
if (typeof aiReadyCallbacks === ‘undefined’) {
var aiReadyCallbacks = [];
} else if (!(aiReadyCallbacks instanceof Array)) {
var aiReadyCallbacks = [];
} function aiShowIframeId(id_iframe) { jQuery(“#”+id_iframe).css(“visibility”, “visible”); } function aiResizeIframeHeight(height) { aiResizeIframeHeight(height,advanced_iframe); } function aiResizeIframeHeightId(height,width,id) {aiResizeIframeHeightById(id,height);}var ifrm_advanced_iframe = document.getElementById(“advanced_iframe”);var hiddenTabsDoneadvanced_iframe = false;
function resizeCallbackadvanced_iframe() {}function aiChangeUrl(loc) {}
Now try to imagine that you could use a custom chatbot to automatically answer FAQs at your organization, or that your customers have an immediate answer instead of waiting for a response from the support team.
Microsoft Azure Bot Service is a dedicated solution for building, hosting and managing bots. It provides the core components for creating bots, including Bot Templates and Bot Builder SDK, and enables communication with the solution through different communication channels like Skype or Facebook Messenger.
You can write a bot, connect, test, deploy, and manage it from your web browser with no separate editor or source control required. For simple chatbots you may not need to write code at all, but of course you can customize their source code to adjust the bot’s functionality to your requirements.
One of the most popular bot types is a conversational bot. You can write a message to this chatbot and receive an answer with the relevant information. Here is the overall bot architecture:
Conversational bot architecture
With this solution you can build, host and manage your bots. It also provides the core components for creating them. Its goal is to speed up bot development with ready-made templates, tools and fast connectivity to different channels like SMS, Facebook or Skype.
The Azure App Service is a cloud service that provides an easy way to deploy and maintain a web application environment. Its purpose is to host the chatbot’s source code and provide an easy way to communicate with it.
Application Insights is a dedicated tool to gather telemetry and diagnostic information from your bot application and the integrated services.
LUIS is one of the cognitive services from Microsoft Azure that enables applications to understand what the user is saying in natural language. It can take the text provided by the user and break it down into components pointing out to intents, entities and other elements.
Azure SQL Database is the knowledge provider for the chatbot where it can find the right answer to user’s questions.
Azure Bot Service provides five templates that can be used to set up bots.
This template creates a bot that has a minimum set of files and code. It just replies with a copy of what the user typed in. This template is good to get started with building a conversation flow of the bot.
Form bot is dedicated for scenarios where a specific set of information should be collected from the user. In this case the conversation is guided to collect all the required information from the user.
This type of bot can be useful in scenarios where the customer might want to place an order or set up an appointment.
This type of template provides bot configuration which uses natural language models to understand user intent. When user sends a message such as “find the nearest Italian restaurants,” your bot can use LUIS to interpret the meaning of the message.
You can use this bot to give information about your offering and provide great customer service with additional, automatic functionalities.
The Question and Answer (QnA) template provides a bot which can analyze the user’s question and provide an accurate answer. When the user sends a message such as: “What are the working hours of the support team?”, the bot can provide a specific answer, for example: “The support team is available between 5AM – 1PM”.
This chatbot can automate information delivery at your company, e.g. by answering FAQs about policies.
Proactive bots are useful when the user should be notified with reference to a specific event. For instance, the bot can send a message about a trip planned for the next day, including flight details.
This type of a chatbot differs from others, because it can send information which is not directly related to the most recent message received from the user. It is a useful solution, particularly in instances where you need to send reminders to your customers about their order or appointment.
The key question is how users can communicate with your bot. Azure Bot Service provides many communication channels. One of the most popular is just a web chat control which you can embed on a website. You can find an example of this control at the beginning of this article where I presented our demo bot.
Additional communication channels are possible, including:
and many more integrated with external services like Facebook Messenger or Slack:
Communication channels available in Azure Bot Service
Microsoft Azure Bot Service enables creating smart applications which can communicate with users with natural conversation flow. With bots you can take the conversation with your customers to the next level. Different communication channels like Skype or Facebook Messenger expand the accessibility of your bot.
Bot templates available in Azure Bot Service help to create bots which you can use in a variety of specific scenarios. You can, for instance, use a QnA bot to automate FAQ at your company, or a language understanding bot to answer customers’ questions on your online store’s website.
We have already implemented example solutions for our customers. Visit this article to find out more!
Microsoft announced many improvements and enhancements to Azure Bot Service this year during the Build conference. Now chatbots can be integrated with Azure Machine Learning, Cognitive Services and Speech Service. Please refer to this article to read more about these exciting news.
An organization like Predica can help you match your ideas with this technology. We can also support your team in the implementation of those on a cloud platform. Contact us so that we can help make your idea a reality!
Read other similar articles