Microsoft Corp. is adding more Cognitive Services application programming interfaces to its Azure cloud platform as it continues to expand its array of artificial intelligence services.

Azure Cognitive Services is used by developers to add AI capabilities such as image recognition, speech understanding and search to their applications. The idea is to help them build more intelligent apps without any specific expertise in machine learning.

The APIs announced today include the newly launched Text Analytics for Health API, plus a couple of previously announced ones that are now generally available: the Custom Commands API and Form Recognizer Cognitive Services API.

Text Analytics for Health is currently in preview and is designed for healthcare providers, researchers and others in the industry to extract insights and relationships from unstructured medical data, Microsoft said. It’s basically an expanded capability of Microsoft’s existing Text Analytics API, designed to work with doctor’s notes, medical publications, electronic health records and clinical trials protocols.

“Trained on a diverse range of medical data — covering various formats of clinical notes, clinical trials protocols, and more — the health feature is capable of processing a broad range of data types and tasks, without the need for time-intensive, manual development of custom models to extract insights from the data,” Microsoft Healthcare Group Manager Hadas Bitran wrote in a blog post.

Microsoft has already put the Text Analytics for Health API to good use, using it to develop its COVID-19 search engine that helps medical researchers quickly evaluate and gain insights from the world’s vast trove of information about the coronavirus, much of which is unstructured.

As for the Custom Commands API, this is a new capability within Azure’s Speech Cognitive Service that developers can use to add voice commands to their applications. Microsoft said it’s best suited for apps that have well-defined sets of variables, such as smart home thermostats. It combines various existing APIs, including Speech to Text, Text to Speech and Language Understanding.

Finally there’s the Form Recognizer API, which developers can use to extract data more rapidly from large volumes of unstructured documents.

“Documents are prevalent and often contain vital information that are essential to drive business outcomes; however, extracting data quickly and accurately for processing is often a challenge for so many organizations,” Azure AI managers Neta Haiby and Prachi Jain wrote in a blog post. “Manual extraction can take up long processing cycles, cause errors and inefficiencies. Hence, extracting text and structure from documents with Form Recognizer helps tackle these challenges swiftly and boost productivity.”

Photo: TechStage/Flickr