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

Building a completed solution

For the first proof of concept, we decided to use the Ocean Smart seafood catering business unit to display additional recommendations to accompany selected items and present a user with a list of platters to select from. The goal is for the first item in the list to be the selection that the user is most likely to purchase. To accomplish this, we create a function app with two functions – GetRankedActions and RewardAction. The GetRankedActions action presents the list of possible Actions for the user, ordered by the probability that the user will purchase that item. RewardAction tells the Personalizer service whether that item was purchased or not. To train the model, we have a test script that selects a user at random, presents that user with choices from the Personalizer, and lets the Personalizer know whether the first choice presented was one the user would purchase. Here is a basic diagram of the flow:

Figure 12.3 – A sample flow of data to triggers the Functions app to use the Personalizer service

Figure 12...