Co m pl ts of Alice LaPlante & Maliha Balala en Combining Machine Learning, Deep Learning, and Associative Memory Reasoning to Improve Operations im Solving Quality and Maintenance Problems With AI Solving Quality and Maintenance Problems with AI Combining Machine Learning, Deep Learning, and Associative Memory Reasoning to Improve Operations Alice LaPlante and Maliha Balala Beijing Boston Farnham Sebastopol Tokyo Solving Quality and Maintenance Problems with AI by Alice LaPlante and Maliha Balala Copyright © 2018 O’Reilly Media, Inc All rights reserved Printed in the United States of America Published by O’Reilly Media, Inc., 1005 Gravenstein Highway North, Sebastopol, CA 95472 O’Reilly books may be purchased for educational, business, or sales promotional use Online edi‐ tions are also available for most titles (http://oreilly.com/safari) For more information, contact our corporate/institutional sales department: 800-998-9938 or corporate@oreilly.com Editor: Nicole Tache Production Editor: Melanie Yarbrough Copyeditor: Octal Publishing, Inc Proofreader: Matthew Burgoyne Interior Designer: David Futato Cover Designer: Karen Montgomery Illustrator: Rebecca Demarest First Edition April 2018: Revision History for the First Edition 2018-04-27: First Release The O’Reilly logo is a registered trademark of O’Reilly Media, Inc Solving Quality and Maintenance Problems with AI, the cover image, and related trade dress are trademarks of O’Reilly Media, Inc While the publisher and the authors have used good faith efforts to ensure that the information and instructions contained in this work are accurate, the publisher and the authors disclaim all responsi‐ bility for errors or omissions, including without limitation responsibility for damages resulting from the use of or reliance on this work Use of the information and instructions contained in this work is at your own risk If any code samples or other technology this work contains or describes is subject to open source licenses or the intellectual property rights of others, it is your responsibility to ensure that your use thereof complies with such licenses and/or rights This work is part of a collaboration between O’Reilly and Intel See our statement of editorial inde‐ pendence 978-1-491-99953-0 [LSI] Table of Contents Executive Summary v Introduction and Primer on Predictive Quality and Maintenance Overview Artificial Intelligence: Clarifying the Terminology More Companies Looking Toward Cognitive Computing 10 Complementary Learning and Intel Saffron AI 13 Complementary Learning as the Future of Predictive Quality and Maintenance Solutions Intel Saffron AI: Associative-Memory Learning and Reasoning and Complementary Learning in Action 13 15 Using AI-Based PQM Solutions to Solve Issues in Manufacturing, Aerospace, and Software 19 PQM Issues in the Manufacturing, Aerospace, and Software Industries AI-Based PQM Solving Real-World Issues: Two Use Cases Getting Started with AI-Based PQM Solutions 19 21 25 iii Executive Summary As artificial intelligence (AI) enters the business mainstream, one of its most promising applications is anticipating quality and maintenance problems before they cause real damage Called predictive quality and maintenance (PQM), these solutions are being deployed at an accelerating rate, especially in the manufactur‐ ing, aerospace, and software industries But not all PQM solutions are created equal Those based on a combination of machine learning, deep learning, and—in particular—cognitive computing create a truly unique out-of-the-box AI-based PQM solution This report is organized into three chapters In Chapter 1, we introduce AI-based PQM and show how today’s market for quality and maintenance applications is evolving In Chapter 2, we show that because none of the various types of AI can solve all PQM problems alone, applying them simultaneously is the key to suc‐ cess This has led to cognitive computing as a basis for what is called complemen‐ tary learning We also introduce Intel Saffron AI as the only solution applying complementary learning principles to today’s PQM challenges Finally, in Chap‐ ter 3, we discuss using AI-based PQM solutions to solve issues in the manufac‐ turing, software, and aerospace industries v CHAPTER Introduction and Primer on Predictive Quality and Maintenance Overview Following years of being dismissed as largely “hype,” we’re seeing a growing num‐ ber of positive headlines about artificial intelligence (AI): “The artificial intelli‐ gence race heats up” (The Japan Times); “Healthcare’s Artificial Intelligence Market May Hit $6 Billion” (Forbes); and “Most Americans Already Using Artifi‐ cial Intelligence Products” (Gallup) Even the Wall Street Journal is reporting on recent market advances “After decades of promise and hype, artificial intelli‐ gence has finally reached a tipping point of market acceptance,” wrote Irving Wladawsky-Berger in early 2018 Indeed, the artificial intelligence market is expected to grow to $190.61 billion by 2025 from $21.46 billion in 2018, at a compound annual growth rate (CAGR) of 36.62%, according to IDC To put that in perspective, in 2018 the average tech‐ nology budget for US businesses is expected to grow just under 6%, according to Forrester AI is transforming virtually all industries—from retail, to healthcare providers, to manufacturing, aerospace, and banking Why? Because AI can deliver results in the form of insights A report by Forrester forecasts that companies that use insight to drive their businesses will grow at a 27% annual rate at a time when the global gross domestic product (GDP) will rise only 3.5% annually (see Figure 1-1) Figure 1-1 Revenue forecasts for insight-driven businesses (source: Predictions 2017: Artificial Intelligence Will Drive The Insights Revolution, November 2016, Forres‐ ter) One segment—and a growing one—of the overall AI applications market is AIbased predictive quality and maintenance (PQM) PQM is a relatively new tech‐ nology area designed to help companies predict when issues or defects might occur in a product, advise on how to identify and fix them, and—the ultimate goal—prevent problems before they cause serious damage AI is significantly adding value to PQM solutions on the market today PQM: A Primer PQM solutions focus on detecting quality issues and improving operational pro‐ cesses to address them by accessing and analyzing data, sometimes in real time PQM is a relatively new merger of predictive quality and predictive maintenance solutions These separate technology areas previously addressed the two issues— ensuring product quality and anticipating maintenance needs—as discrete, dis‐ tinct technologies With PQM solutions, both quality and maintenance activities are addressed together rather than as separate issues The idea behind a PQM solution is that if companies want to gain a competitive edge, they must prioritize how to allocate their resources, cost, and time when it comes to both improving product quality and maintaining equipment in a more timely and efficient manner Here are some examples of questions that PQM solutions are helping to answer: • How can we capture experts’ knowledge and skills and streamline them within workflows and processes so that they can be shared and accessed by everyone? • How can we detect anomalies and failure patterns to determine which equip‐ ment and operational processes are likely to fail? | Chapter 1: Introduction and Primer on Predictive Quality and Maintenance CHAPTER Complementary Learning and Intel Saffron AI Complementary Learning as the Future of Predictive Quality and Maintenance Solutions Because none of the types of artificial intelligence (AI) can solve all problems, applying them simultaneously is the key to success This need for a combined approach is giving rise to cognitive computing as a basis for complementary learning This is what DARPA’s John Launchbury refers to as the “contextual adaptation systems” in the third wave of AI Strengths and weaknesses of different AI approaches are giving rise to comple‐ mentary learning because solving a challenging problem often requires solving underlying subproblems effectively, which calls for different models or approaches To understand how machine learning, deep learning, and cognitive computingbased AI can work together in a predictive quality and maintenance (PQM) solu‐ tion, it’s important to understand that a comprehensive AI-based PQM solution needs to solve two types of problems: surveillance and prescriptive Surveillance use cases involve scenarios in which businesses need to recognize problems by observation By detecting patterns and alerting businesses, the sur‐ veillance approach to AI allows companies to act quickly when something out of the ordinary is detected in their equipment or other assets For example, manu‐ facturers want to understand what the sensor data coming in from the factory floor via the Internet of Things (IoT) is telling them In the past, they would have needed to build rules into the sensor network to send alerts when certain thresh‐ olds were passed, or anomalies sensed 13 But the problem was identifying all those rules Although it’s possible to define the parameters in which, for example, a network router should be operating, when a large number of assets exists—such as a fleet of airplanes—it’s next to impossible That’s when machine learning and deep learning come in These two types of AI can process the data, access the knowledge, and specify what those parameters are in a much more adaptable and scalable way The systems learn—or rather, construct—the rules themselves by learning from the data But to this, an enormous amount of data is needed—perhaps tens of thou‐ sands of examples of an issue before a system is fully trained And if the system did not perform as expected in some circumstances, humans will need to provide additional feedback—although that feedback might not be in the form of rules, but in the form of new data illustrating the desired outcomes or instructing the system with exception cases The goal here is to help the machine learn quickly from as few examples as possible After the issues have been identified using machine learning and deep learning, the natural next step for businesses is to solve those issues This is where prescriptive use cases come in—and where cognitive computing capabilities are required After all, for a system to those things, it would require the ability to reason It would need to extract and consolidate relevant information from heterogeneous unstructured data sources such as audio, video, and emails to indicate or assist businesses to find the root causes of issues Another way to think about it is that machine learning and deep learning are good for knowledge extraction Cognitive computing is good with knowledge representation—finding connections and insights from data Let’s walk through a basic example The first step toward solving a problem with a piece of equipment or product is that data—which can be structured or unstructured—needs to be processed and identified If it’s text, natural-language processing (NLP) will be used to parse the meaning If it’s an object, computer vision will identify whether it is an airplane, an engine, or a network router Computer vision and NLP are part of the knowledge extraction Those are the patterns detected by machine learning and deep learning In effect, the system has answered the question, “What is it?” When the “what” question has been understood, cognitive computing can then come in to ask questions such as: Have I ever seen this before? What type of a problem is it? Who knows how to fix this? What I next? What caused this problem? And, will it happen again?” Cognitive computing systems then answer those questions 14 | Chapter 2: Complementary Learning and Intel Saffron AI When we talk about complementary learning with respect to PQM applications, we’re talking about combining surveillance, or knowledge extraction, with the second, more prescriptive, knowledge representation application that uses memory-based reasoning Intel Saffron AI: Associative-Memory Learning and Reasoning and Complementary Learning in Action Intel Saffron AI is based on cognitive computing that utilizes associative memory learning and reasoning, along with patterns detected from machine learning and deep learning, in the complementary way previously discussed By using humanlike reasoning to find hidden patterns in data, Intel Saffron AI enables decisions that can deliver rapid return on investment (ROI) The core of Intel Saffron AI is the Intel Saffron Memory Base, a long-term persis‐ tent knowledge store built on an associative-memory matrix It stores unified data about entities in an associative-memory store That memory store correlates similar information together and makes it faster to query and easier to retrieve for analysis This means that Intel Saffron AI mimics how a human naturally observes, perceives, and remembers by creating memory-based associations Intel Saffron AI uses data from a mix of machine learning and deep learning AI subsystems, like NLP for entity extraction, sentiment analysis to establish links, and topic mapping for content mapping The platform is both semantic and stat‐ istical in nature Intel Saffron AI ingests all types of data, including structured, unstructured text, nonschematic, and on-schema This data then resides in a hyperdimensional matrix that connects one node (data or entities like people, places, things, or events) to another node using edges (which are statistical connections) Although most graph stores work as a key–value pair, Intel Saffron AI acts like a multidimensional graph store that allows for N connections between nodes, and functions like a hyper matrix The connections make associations based on con‐ text, frequency, and time When a new node (data) comes in, the platform applies memory-based cognitive techniques and creates weighted associations between people, places, things, and events In this way, Intel Saffron AI acts like a massive correlation engine that cal‐ culates the statistical probabilities using the Kolmogorov Complexity (K Complex‐ ity) It then derives a universal distance measure that shows how closely two objects are related and to find regular patterns in the data This way of cognition by similarity enables anticipatory decision making, which involves making deci‐ sions by estimating the current situation, using diagnoses, prescribing possible actions, and predicting likely outcomes Intel Saffron AI: Associative-Memory Learning and Reasoning and Complementary Learning in Action | 15 Customers can implement Intel Saffron AI across industries Its bedrock technol‐ ogy is the patented Intel SaffronMemoryBase, which provides a layer of REST APIs that customers can develop and customize for their own needs Intel Saf‐ fron AI now offers industry-specific applications that will harness the power of the platform to solve specific quality and maintenance problems for manufactur‐ ing, software, and aerospace What Makes Intel Saffron AI Different? A complementary learning solution like Intel Saffron AI enables powerful machine and human interactions It aims to help humans make decisions better and faster It does this by relieving human workers of having to perform repeti‐ tive, time-consuming tasks so that they can focus on what humans can best: build relationships and apply judgment and creativity to more complex issues In addition, Intel Saffron AI keeps advancing, learning from human feedback and interactions It does this by excelling in three ways: its transparency—which makes it easy to understand its results and recommendations; for the fact that no statistical mod‐ els are required; and that it brings together both structured and unstructured data from multiple sources Transparency Intel Saffron AI works by identifying similarities But unlike a traditional machine learning or deep learning application, which makes its decisions by algorithms and “black box” methodologies—that is, businesses have no insight into why they got a particular result—Intel Saffron AI is completely transparent Because it works by knowledge representation, it stores all the attributes that led it to a particular decision or conclusion and makes them readily available to users It’s easy to get explanations Intel Saffron AI in effect takes an entity and creates a “neighborhood” around it, showing the most similar issues it has ever seen to this particular one, and why it thinks they’re similar Businesses have full access to all of this information, giving them a chance to tell Intel Saffron AI when it’s wrong, so it can learn for next time One-shot learning: No statistical models required The key benefit of not needing to model data is flexibility, especially when data is sparse, dynamic, or incomplete This is what Intel calls “one-shot learning”: see something once, and Intel Saffron AI learns Here’s an example: if a child is burned by a hot stove, hopefully she learns from that experience and avoids the stove in the future If the child was acting based 16 | Chapter 2: Complementary Learning and Intel Saffron AI on a statistical-based learning, however, she would have to experience pain multi‐ ple times before she had enough data to build a statistically relevant model—and not get burned After all, the real world isn’t a closed system Unlike the game of checkers, chess, or even the more complex game of Go, there aren’t a fixed number of possible moves But in an open and ever-changing place like real life—and markets— there is no way to monitor for every possible contingency A good PQM system needs to be able to adjust to evolving scenarios Intel Saffron AI, different from machine learning and deep learning, learns through association rather than by modeling possible outcomes It builds signa‐ tures of entities that it gradually learns more about Then it compares those sig‐ natures to identify hidden connections, patters and trends—surfacing insights that are otherwise invisible Unifies both structured and unstructured data across multiple sources A lot of insights in the real world come from unstructured data—maintenance logs, manuals, handwritten notes, audio and video recordings, and emails The ability to analyze both structured and unstructured data is one of the strengths of Intel Saffron AI When you couple this with the insights from machine and deep learning, you can reveal much more insights In other words, deep and machine learning analyze structured data to identify symptoms, whereas associative-memory learning and reasoning analyzes unstructured data to provide a diagnosis Intel Saffron AI: Associative-Memory Learning and Reasoning and Complementary Learning in Action | 17 CHAPTER Using AI-Based PQM Solutions to Solve Issues in Manufacturing, Aerospace, and Software PQM Issues in the Manufacturing, Aerospace, and Software Industries Resolving quality and maintenance issues is well suited by a complementary learning approach because the data necessary for decision-making is large, var‐ ied, both structured and unstructured, and processed in both batch and real time For instance, in addition to data stored in a traditional database, engineers could be capturing their notes on handwritten pieces of papers, or invaluable informa‐ tion could be mined from online chats or email exchanges In the sections that follow, we discuss some of the challenges that are being faced by businesses in the manufacturing, aerospace, and software industries that complementary predic‐ tive quality and maintenance (PQM) could address PQM in Manufacturing Currently, many manufacturers still predict machine failures in assembly lines by determining root causes from maintenance notes or by depending on human subject matter experts But they are tasked to reducing unplanned downtime and avoiding the revenue losses associated with failed lines They must accelerate time to market while improving quality They also need to identify similarities in parts to predict defects or failures that could occur during manufacturing and assembly, and balance cost with quality by gaining visibility into the life cycle of parts from different vendors And corrective actions need to be taken before 19 assets break down, allowing service to be performed preemptively, and the data of all corrective actions captured for future use PQM in the Software Industry PQM is becoming an essential part of software quality assurance, management, debugging, performance, and cost-estimation exercises As we noted earlier, the goals of deploying complementary learning-based PQM solutions when develop‐ ing software include minimizing bugs, fixing bugs faster, reducing costs, reduc‐ ing the strain on senior engineers, and increasing return on investment (ROI) In general, the sooner a company detects software problems, the easier and less expensive the troubleshooting and fixing process This is where complementary learning-based PQM can be invaluable Additionally, one especially irksome challenge for software developers is de-duplicating bugs Having multiple teams working on the same defect is a waste of valuable resources When trying to test for a reported bug, the correct environment needs to be set up to reproduce it, which can take heavy resources in both equipment, system, and engineering time Complementary learning-based PQM can help identify when two bugs—which could have occurred under different circumstances and been described using dif‐ ferent language—are really the same, avoiding this waste PQM in the Aerospace Industry Maintenance, repair, and overhaul (MRO) are the daily tasks involved in manag‐ ing the upkeep and safety of large aircraft Key to successful MRO is gathering and analyzing data that helps airlines check that all systems are operational and that they interconnect successfully with others This is a huge job According to Boeing, 70% of a $2.6 trillion aerospace services market is spent on quality and maintenance Many carriers have traditionally taken a reactive approach to maintenance: prob‐ lems are addressed only as they occur Unfortunately, this tactic leads to down‐ time, delayed flights, and aircraft-on-ground issues In 2016, in the United States alone, the cost of maintenance related delays for airlines was well more than half a billion dollars And almost a third of total delay time is due to unplanned main‐ tenance Making repairs at the right time to avoid problems before they occur is key to preventing these problems—and these costs An enormous amount of unstructured data exists in the airline industry that has historically been very difficult to access Utilizing it effectively could have a trans‐ 20 | Chapter 3: Using AI-Based PQM Solutions to Solve Issues in Manufacturing, Aerospace, and Software formative impact on aerospace maintenance strategies—something that aero‐ space companies are beginning to understand AI is thus beginning to be deployed in the aerospace industry, to find patterns in that data, and to be able to look at historical maintenance activities and identify a particular problem What is the best solution? Who actually worked on this item in the past? How we find an expert quickly who can help address this? According to Keystone Strategy, a Boston-based strategic consulting firm, if 5% of heavy maintenance costs were prevented via changes to maintenance plans, that would result in $20 million to $40 million of savings annually If just 2% of carrier-caused delays were prevented via changes to maintenance plans, that would yield $5 million in savings annually If just 5% of cancellations were pre‐ vented due to changes to maintenance plans, that would yield $23 million in sav‐ ings AI-Based PQM Solving Real-World Issues: Two Use Cases In the sections that follow, we look at some real-world scenarios in which the ways complementary learning-based PQM solutions are helping companies in chip design and software development Chip Design: Intel Intel is the world’s largest chipmaker It is the inventor of the x86 series of micro‐ processors, the processors found in most personal computers Considered a lead‐ ing global innovator, Intel is responsible for much of the growth of the technology sector over the past decades Based in the heart of Silicon Valley, it achieved record annual revenues of $62.8 billion in 2017, a 9% increase over 2016 With each release of a new chip platform—which can occur several times a year —Intel, like all chip manufacturers, must manage a sizable population of bugs It diligently captures all the data about these bugs and stores them in a defect data‐ base But Intel faces significant challenges because information about the bugs is in the form of both structured and unstructured data The structured data came from responses from the person who reported a bug to standard questions such as: What is the platform release number where the bug was found? What operating system was being used? What software was running? What is the error code number? This data was relatively easy to store AI-Based PQM Solving Real-World Issues: Two Use Cases | 21 But the unstructured data includes such things as notes from engineers, logs, emails, and other types of text descriptions Although all the data was stored together, there was no way to consolidate and make sense of it When a bug was reported, senior engineers would manually perform text searches on the database, using keywords and hoping to find any information that had been previously entered But that was inefficient and often failed Per‐ haps someone had already reported the bug but used different language to describe it Some notes were written in other languages There was no way to an effective search and make use of the existing data One of the biggest challenges was determining whether a bug had already been reported Different engineers could be working on the same version of a bug sub‐ mitted by different people Additionally, there was no way to search to see whether a similar problem had previously been solved Important questions, included the following, could not be easily answered: • Is this bug a duplicate? • Have we seen it before? • How did we fix it before? • What other bugs are similar to this? “We have to be very efficient in how we perform triage and debugs,” says Randy Hall, senior principle engineer with Intel’s Client Computing Group “We enable 2,000 designs each year We don’t want to spend our resources fixing the same bug multiple times.” All this would come to a head during important project milestones, when Intel would bring its major customers—such as Dell, Lenovo, and HP—to its Taiwan conference center to identify any issues in a chip design and hammer out solu‐ tions For competitive reasons, customers would meet with Intel senior engineers in separate rooms, but frequently they were flagging the same bugs Intel had no way of correlating them Intel initially estimated that 15% of its bug “sightings” were duplicates and repre‐ sented a lot of wasted resources, says Hall But when it did an actual audit, Intel found that almost 30% of bug sightings were duplicates in the earlier stages of the program This meant that a significant chunk of the efforts of highly skilled, highly paid senior engineers was going to waste After evaluating various PQM solutions on the market, Hall chose Saffron This occurred prior to Intel’s acquisition of Saffron, and indeed the success of Intel’s own internal experience with the solution was one of the key reasons Intel purchased it 22 | Chapter 3: Using AI-Based PQM Solutions to Solve Issues in Manufacturing, Aerospace, and Software Hall began seeing immediate results with Saffron Senior engineers saved 25% to 30% of their time by eliminating duplicate bugs right at the original sighting This alone saved Intel millions of dollars Engineers could also pull reports on similar bugs, look at the previously applied fixes, and complete root–cause analyses much faster This not only saved time, it improved the overall quality of Intel chip designs—an improvement that is difficult to put a price tag on “We worked directly with the Saffron team,” says Hall “We described the prob‐ lem we were trying to solve, and they said, ‘Oh yeah, we know how to this stuff.’” So today, Intel sends all sightings to Intel Saffron AI and lets it find the duplicates This allows Intel’s senior engineers to concentrate on the things that really matter —such as triaging particularly complex bugs—or finding issues before customers “You don’t want to be debugging simple configuration issues when you’re ask‐ ing people to travel across the planet to meet with you,” says Hall “You really want to be focused on the issues that require closer collaboration and expertise.” One benefit that Saffron had over other AI-based PQM systems was that it worked right away “Out of the box, Saffron did not require a lot of tuning and that was a good thing for us,” says Hall “And the support we got out of the Saf‐ fron team was top-notch.” Software: Accenture® Touchless Testing Platform Accenture is a leading global professional services company, providing a broad range of services and solutions in strategy, consulting, digital, technology, and operations Accenture works at the intersection of business and technology to help clients improve their performance and create sustainable value for their stakeholders As such, they are committed to investing a significant portion of the global R&D capabilities to help clients across industries integrate AI-driven software testing automation as an agent for speed, change, and customer experi‐ ence This is especially important considering that a lot of the organizations have not changed their software testing techniques much from 10 to 20 years ago Their processes are either heuristic-based or too rule-centric The question of testing what matters is usually answered through imprecise human judgment based on perceived risk-based approaches For many organizations, software testing still involves a lot of manual labor, espe‐ cially in the area of test-case management that requires step-by-step test docu‐ mentation In some mission-critical systems, test engineers report spending up to 90% of their time managing test cases and documenting rather than actually test‐ ing AI-Based PQM Solving Real-World Issues: Two Use Cases | 23 The other issue in software testing is viewing quality assurance as one isolated component in the software development life cycle instead of permeating quality checks across the entire life cycle, which requires a shift in mindset and dedicated resources spread from the inception of product design all the way to deployment Testing cannot be performed in silos outside of the development process any‐ more With the increasing complexity of software on one hand and the exponential growth of connected products and devices on the other hand, test engineers require access to domain, analytics, and data management tools that are more sophisticated than traditional testing platforms Accenture has embraced an open innovation strategy and augments its test engi‐ neers with AI technologies to operate more smartly and efficiently by automating high-end decision making and eliminating repetitive, manual tasks Accenture is now using Intel Saffron AI to answer questions with which test engineers often struggle: • How we test what matters? • Is my test suite bloated, resulting in unnecessary effort? • Is my test coverage correct? • Is there a way to measure the effectiveness of my test cases using a datacentered approach? • How can I clean and merge duplicate defects? Am I uncovering root defects or symptoms? • Can I prevent similar defects being initiated during test execution? • Can I predict the best person/team to fix or retest my defect? Accenture is applying AI and cognitive computing capabilities in software testing to reduce the cycle time, rationalize test cases, and optimize coverage Its Touch‐ less Testing Platform aims to bring together leading open source, commercial, and Accenture-proprietary tools and algorithms to automate a testing process for software “Testing is transforming into quality engineering where applied intelligence is at the core of driving productivity and agility,” said Kishore Durg, senior managing director, Growth and Strategy and Global Testing Services Lead for Accenture “The Accenture Touchless Testing Platform is augmented with artificial intelli‐ gence technology from Intel Saffron AI that bring in analytics and visualization capabilities These support rapid decision-making and help reduce overengineering efforts that can save anywhere from 30 to 50 percent of time and effort.” 24 | Chapter 3: Using AI-Based PQM Solutions to Solve Issues in Manufacturing, Aerospace, and Software Accenture’s platform chose Intel Saffron AI to drive intelligence in analytics to accelerate automation, spot trends, manage risks, and continuously respond to customer feedback Some of the features of their platform include the following: Defect similarity analytics Enable defect coalescence and prevention of duplicate defects Test case similarity clustering Identify redundancy and optimize the test suite Failure-based testing Determine the probability of failure of test cases through algorithms Expert finder Make quick resource assignment decisions Usage-based test optimization Analyze how business users are using the software and develop test cases on functions that matter to them Regression optimization Enable the right coverage of test scenarios that undermines over testing or under testing Automatic defect or failure root–cause prediction Gain meaningful insights based on past data on bugs and their resolution According to Accenture, this approach has reduced time-to-market and cost of testing by more than 20% and delivers more than 90% accuracy, as proven in trial runs An insurance company that piloted the Accenture Touchless Testing Platform discovered that it could accelerate its pace of delivery by improving its test suite Using Intel Saffron AI, Accenture identified up to 22% test cases as duplicates or similar that could be eliminated By applying data insights into defect detection and analysis, test execution, and retesting, the company significantly improved the speed and quality of the soft‐ ware development and accelerated overall cycle time AI and analytics are chang‐ ing the testing landscape Even though Accenture’s platform is meant to help automate certain tasks, it also aims to free up test engineers to work on areas that require greater judgment Getting Started with AI-Based PQM Solutions Decades ago, airport operators typically managed relatively small fleets of air‐ planes, and could stick their heads out of windows if they need to know what was preventing an on-time takeoff Today, in industries from software development, Getting Started with AI-Based PQM Solutions | 25 to manufacturing, to oil and gas, there are too many products, too many moving parts There is too much data There are too many complex systems spread across the entire world No single human being could possibly know what’s going on all the time AI, specifically complementary learning, is the way forward We are on the cusp of exciting innovations that will make up for the fact that human intelligence simply cannot scale at the same rate as data AI promises to meet us at the edge of our limitations and extend our capabilities for greater good and productivity It’s time to get started You might want to ponder the following questions, either internally or with a vendor: • What does it take to get started? • What kind of data is needed? • What problems can be solved? • What resources are required (hardware, software, human resource)? • What process I have to go through? • What kind of training is needed? • What kind of ROI can I expect? With out-of-the-box vertical solutions like Intel Saffron AI becoming available, it makes sense to invest in a complementary AI PQM solution 26 | Chapter 3: Using AI-Based PQM Solutions to Solve Issues in Manufacturing, Aerospace, and Software About the Authors Alice LaPlante is an award-winning writer who has been writing about technol‐ ogy and the business of technology for more than 20 years Author of seven books, including Playing For Profit: How Digital Entertainment Is Making Big Business Out of Child’s Play (Wiley) and Method and Madness: The Making of a Story (W W Norton & Company), LaPlante has contributed to InfoWorld, Com‐ puterWorld, InformationWeek, Discover, BusinessWeek, and other national busi‐ ness and technology publications Maliha Balala currently leads the technical communications team at WhirlWind Technologies She is a polymath who enjoys researching and talking about tech‐ nology, education, psychology, literature, and philosophy ... the data-crunching algorithms to human-like cognitive ones with the ability to explain its reasoning on decisions by making associations based on the context The ability to form associations... prescriptive use cases come in—and where cognitive computing capabilities are required After all, for a system to those things, it would require the ability to reason It would need to extract and consolidate... creativity to more complex issues In addition, Intel Saffron AI keeps advancing, learning from human feedback and interactions It does this by excelling in three ways: its transparency—which makes it