Democratizing Artificial Intelligence with UiPath

Fanny Ip, Jeremiah Crowley, Tom Torlone

• Éditeur: Packt Publishing
• Année: 2022
• ISBN:
  9781801812382
• Édition: 1
• Sujet: Informatique
• Sous-sujet: Stockage de données

Build an end-to-end business solution in the cognitive automation lifecycle and explore UiPath Document Understanding, UiPath AI Center, and DruidKey Features• Explore out-of-the-box (OOTB) AI Models in UiPath• Learn how to deploy, manage, and continuously improve machine learning models using UiPath AI Center• Deploy UiPath-integrated chatbots and master UiPath Document UnderstandingBook DescriptionArtificial 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.What you will learn• Discover how to bridge the gap between RPA and cognitive automation• Understand how to configure, deploy, and maintain ML models in UiPath• Explore OOTB models to manage documents, chats, emails, and more• Prepare test data and test cases for user acceptance testing (UAT)• Build a UiPath automation to act upon Druid responses• Find out how to connect custom models to RPAWho this book is forAI Engineers and RPA developers who want to upskill and deploy out-of-the-box models using UiPath's AI capabilities will find this guide useful. A basic understanding of robotic process automation and machine learning will be beneficial but not mandatory to get started with this UiPath book.

Section 1: The Basics

In this section, RPA developers will learn the relevant AI concepts, understand how cognitive automation works with RPA to increase the potential for automation, and gain an appreciation of the AI strategy and approach within the UiPath platform.

This section comprises the following chapters:

• Chapter 1, Understanding Essential Artificial Intelligence Basics for RPA Developers
• Chapter 2, Bridging the Gap between RPA and Cognitive Automation
• Chapter 3, Understanding the UiPath Platform in the Cognitive Automation Life Cycle

Chapter 1: Understanding Essential Artificial Intelligence Basics for RPA Developers

In this chapter, we will cover some key artificial intelligence (AI) concepts that are relevant in your daily work as an RPA developer. We will discover where a robotic process automation (RPA) developer can make the most impact on implementing cognitive automation in RPA use cases without becoming a data scientist. We will also look at real business problems today that are solved by AI.

In this chapter, we will cover the following main topics:

• Understanding key AI concepts
• Understanding cognitive automation
• Exploring out-of-the-box (OOTB) machine learning (ML) models for RPA developers

By the end of the chapter, you will be equipped with common AI fundamentals, and you will be inspired by real-life examples to help you start thinking about how to apply AI to your potential use cases.

Understanding key AI concepts

You may have come across many terms when you started exploring the topic of AI. We will demystify AI and only present those concepts that are most relevant to you as an RPA developer. Please note that you may come across other material with slightly different definitions based on a different context.

Differentiating between artificial intelligence, machine learning, and deep learning

AI, ML, and deep learning (DL) are related but not the same. The following figure illustrates the hierarchy of these types of learning:

Figure 1.1 – AI, ML, and DL

• AI: This is equivalent to giving a machine or a robot the ability to think. It encompasses ML and DL.
• ML: This refers to how a machine or a robot learns to think through algorithms without explicit programming. ML is a subset of AI.
• DL: This refers to how an ML algorithm leverages artificial neural networks to mimic learning. DL is a subset of ML.

Next, we will look at three key considerations when choosing between ML and DL. They are listed here:

• Data requirement and availability
• Computational power
• Training time

The following figure shows a comparison of ML and DL:

Figure 1.2 – Comparison of ML and DL

In ML, the features of the studied subjects are fed into the algorithms for the machine to learn. We can think of features as us giving hints to the algorithm. This step allows for a smaller dataset, lower computational power, and less training time.

In DL, features are determined by artificial neural networks. It needs to work much harder to figure out the features and patterns to learn. As a result, it requires a large amount of data, high computational power, and a long training time.

Although DL is valuable, it is beyond the reach of most businesses to develop DL models to solve their business problems. Fortunately, many DL models have been pre-trained by companies with the time and budget to make them accessible to a large user base.

The implication of this option means that your role as an RPA developer is not to create these models. You, as the RPA developer, are the trainer of these models. It is important to understand the role of training in AI.

Appreciating the relevance of supervised learning, unsupervised learning, and reinforcement learning in AI

As we learned in the previous section, AI is about training a machine or a robot to think. Just like a human being, a robot needs to learn. There are three different types of learning for a robot.

The following figure gives some analogies for supervised learning, unsupervised learning, and reinforced learning:

Figure 1.3 – Supervised learning, unsupervised learning, and reinforcement learning analogies

The following list explains the various analogies:

• Supervised learning: This is based on past data, and the trainer specifies the inputs to predict future outcomes. This type of training is analogous to an instructor-led training course. It requires the trainer to supervise the student or the model to achieve the desired learning outcome. Classification and regression are types of supervised learning methods:
  • Classification refers to the process of categorizing a given set of data into classes. For example, a set of pictures of different animals are fed into the ML model. Each picture is labeled with an animal name. The ML model is trained to identify animals from an image.
  • Regression helps in the prediction of a continuous variable. For example, a profit prediction ML model is an example of a regression model. Training data consisting of R and D, marketing, and administrative spending, geographic location, and profit is fed into the model. The ML model predicts the profit.
• Unsupervised learning: This relies on an algorithm to identify unknown patterns from data. This type of training is analogous to a self-study course. It requires the students or the model to synthesize the information to achieve the desired learning outcome. Clustering is a type of unsupervised learning method:
  • Clustering refers to the method used to find similarity and relationship patterns among training datasets, and then cluster those datasets into groups with similarities based on features...