Book Image

Democratizing Artificial Intelligence with UiPath

By : Fanny Ip, Jeremiah Crowley
Book Image

Democratizing Artificial Intelligence with UiPath

By: Fanny Ip, Jeremiah Crowley

Overview of this book

Artificial intelligence (AI) enables enterprises to optimize business processes that are probabilistic, highly variable, and require cognitive abilities with unstructured data. Many believe there is a steep learning curve with AI, however, the goal of our book is to lower the barrier to using AI. This practical guide to AI with UiPath will help RPA developers and tech-savvy business users learn how to incorporate cognitive abilities into business process optimization. With the hands-on approach of this book, you'll quickly be on your way to implementing cognitive automation to solve everyday business problems. Complete with step-by-step explanations of essential concepts, practical examples, and self-assessment questions, this book will help you understand the power of AI and give you an overview of the relevant out-of-the-box models. You’ll learn about cognitive AI in the context of RPA, the basics of machine learning, and how to apply cognitive automation within the development lifecycle. You’ll then put your skills to test by building three use cases with UiPath Document Understanding, UiPath AI Center, and Druid. By the end of this AI book, you'll be able to build UiPath automations with the cognitive capabilities of intelligent document processing, machine learning, and chatbots, while understanding the development lifecycle.
Table of Contents (16 chapters)
1
Section 1: The Basics
5
Section 2: The Development Life Cycle with AI Center and Document Understanding
10
Section 3: Building with UiPath Document Understanding, AI Center, and Druid

Executing cognitive automation testing

For successful testing and deployment of cognitive automation, we should always prepare an approach to testing. In this section, let's review details on gathering test data, executing RPA and cognitive tests, and tying it all together with executing UAT tests.

Gathering test data

ML depends highly on data. Having the right types and the right amount of data is crucial in having a successful ML model deployed; therefore, data preparation is such an important part of the ML process.

When gathering test data, many organizations ask how much data is necessary to get started. Unfortunately, there isn't an explicit answer to this question, as there are many variables that can affect how much data is necessary, such as the following:

  • The complexity of the business problem ML must solve
  • The number of classifications (if necessary)
  • The complexity of the algorithm used

If necessary, you can try to target the...