Book Image

Practical Guide to Azure Cognitive Services

By : Chris Seferlis, Christopher Nellis, Andy Roberts
Book Image

Practical Guide to Azure Cognitive Services

By: Chris Seferlis, Christopher Nellis, Andy Roberts

Overview of this book

Azure Cognitive Services and OpenAI are a set of pre-built artificial intelligence (AI) solution APIs that can be leveraged from existing applications, allowing customers to take advantage of Microsoft’s award-winning Vision, Speech, Text, Decision, and GPT-4 AI capabilities. With Practical Guide to Azure Cognitive Services, you’ll work through industry-specific examples of implementations to get a head-start in your production journey. You’ll begin with an overview of the categorization of Azure Cognitive Services and the benefits of embracing AI solutions for practical business applications. After that, you’ll explore the benefits of using Azure Cognitive Services to optimize efficiency and improve predictive capabilities. Then, you’ll learn how to leverage Vision capabilities for quality control, Form Recognizer to streamline supply chain nuances, language understanding to improve customer service, and Cognitive Search for next-generation knowledge-mining solutions. By the end of this book, you’ll be able to implement various Cognitive Services solutions that will help you enhance efficiency, reduce costs, and improve the customer experience at your organization. You’ll also be well equipped to automate mundane tasks by reaping the full potential of OpenAI.
Table of Contents (22 chapters)
Part 1: Ocean Smart – an AI Success Story
Part 2: Deploying Next-Generation Knowledge Mining Solutions with Azure Cognitive Search
Part 3: Other Cognitive Services That Will Help Your Company Optimize Operations

Understanding Form Recognizer machine learning model options

When deciding which model will work best for your solution, you will first have the choice of several models that are purpose-built for specific types of forms. The templated model types are self-explanatory based on their names:

  • General document
  • Layout
  • Invoice
  • Receipt
  • ID document
  • Business card
  • Custom

These templated models were designed with a base set of fields to extract from the documents as they are processed. From the documents using the model type chosen, there are varying abilities for the extraction of text, key-value pairs, fields, selection marks (checkboxes, for example), tables, and entities. There are also variables around the processed documents, such as the document file type, number of pages, and dimensions of the pages being processed. For a more complete list of these variables to ensure your use case would be a good fit, refer to the following reference in the Microsoft...