What is Language Understanding (LUIS)?

Language Understanding (LUIS) is a cloud-based conversational AI service that applies custom machine-learning intelligence to a user’s conversational, natural language text to predict overall meaning, and pull out relevant, detailed information.

What does LUIS Offer?

Simplicity: LUIS offloads you from the need of in-house AI expertise or any prior machine learning knowledge. With only a few clicks you can build your own conversational AI application.

Security, Privacy and Compliance: Backed by Azure infrastructure, LUIS offers enterprise-grade security, privacy, and compliance. Your data remains yours; you can delete your data at any time.

Integration: easily integrate your LUIS app with other Microsoft services like Microsoft Bot framework, QnA Maker, and Speech service.

LUIS Scenarios:

Build an enterprise-grade conversational bot: This reference architecture describes how to build an enterprise-grade conversational bot (chatbot) using the Azure Bot Framework.
Commerce Chatbot: Together, the Azure Bot Service and Language Understanding service enable developers to create conversational interfaces for various scenarios like banking, travel, and entertainment.
Controlling IoT devices using a Voice Assistant: Create seamless conversational interfaces with all of your internet-accessible devices-from your connected television or fridge to devices in a connected power plant.

Application Development life cycle

Plan: Identify the scenarios that users might use your application for. Define the actions and relevant information that needs to be recognized.
Build: Use your authoring resource to develop your app. Start by defining intents and entities. Then, add training utterances for each intent.
Test and Improve: Start testing your model with other utterances to get a sense of how the app behaves, and you can decide if any improvement is needed. You can improve your application by following these best practices.
Publish: Deploy your app for prediction and query the endpoint using your prediction resource. Learn more about authoring and prediction resources here.
Connect: Connect to other services such as Microsoft Bot framework, QnA Maker, and Speech service.
Refine: Review endpoint utterances to improve your application with real life examples