Azure AI Services at Scale for Cloud, Mobile, and Edge

Chapter 5. Using Azure Applied AI Services for Common Scenarios

In the previous chapter we looked at the individual Cognitive Services you can use for specific tasks. Now, we’re going to focus on the high-level Applied AI Services that cover common scenarios like extracting information from documents or videos.

Azure Applied AI Services

Individual Cognitive Services are powerful, but often you will want to combine multiple Cognitive Services to handle broader scenarios. If you’re making a chatbot, you might start with QnA Maker but then use LUIS to make the bot better at understanding what users are trying to achieve, and use the Speech Services to let people talk to your bot as well as type. Because that’s such a popular business scenario, Microsoft built the Azure Bot Service as an integrated environment that brings together all those tools.

The Bot Service is one of the Azure Applied AI Services that build on the core Cognitive Services, either combining multiple services or wrapping business logic and a UI around a single service to handle common business problems.

For example, Azure Metrics Advisor builds on the Anomaly Detector API and provides a web-based workspace that simplifies ingesting data from multiple sources and configuring settings like how sensitive you want your model to be to outliers, as well as building a graph to explain how different metrics relate to each other. As you can see in Figure 5-1, it also groups anomalies plus root cause analysis suggesting ...