Posted on Leave a comment

How Moovit improved its app to help people with disabilities ride transit with confidence

Alexandr Epaneshnikov, a 19-year-old Russian student who is legally blind, recently decided he wanted to be more independent by commuting on his own and relying less on his mom for rides to school. It meant taking a streetcar to a subway to his high school in Moscow, a 30-minute trip that Epaneshnikov assuredly navigates with a cane and Moovit, an urban mobility app optimized for screen readers.

“I am very happy that Moovit is accessible and offers a good amount of information about Moscow public transportation,” says Epaneshnikov, who wants to study information technology at a university. The app has helped him meet friends at cafes and restaurants, and take a train to an unfamiliar city outside Moscow to visit his girlfriend’s family.

“I feel it adds more confidence and independence,” he says.

Launched seven years ago in Israel, Moovit has become the world’s most popular transit-planning and navigation app, with more than 400 million users and service in 2,700 cities across 90 countries. The company is also a leader in inclusive technology, with innovative work that helps people across the disability spectrum use buses, trains, subways, ride-hailing services and other modes of public transit.

In addition to offering a consumer app in 45 languages, Moovit has partnered with Microsoft to provide its multi-modal transit data to developers who use Azure Maps, and a set of mobility-as-a-service solutions to cities, governments and organizations. The partnership will enable the creation of more inclusive, smart cities and more accessible transit apps.

Headshot of Yovav Meydad
Yovav Meydad, Moovit chief growth and marketing officer. (Photo courtesy of Moovit)

“Our mission is to simplify urban mobility and make it accessible, because mobility is really a basic human right,” says Yovav Meydad, Moovit chief growth and marketing officer. “Efficient mobility opens a lot of opportunities for employment, education and a better life, and we want to help all users make their journey as easy as possible.”

For Moovit, the work means not only helping rural residents reach cities for work and school, but also helping people with any disability travel. Of the hundreds of daily emails sent to Moovit, emails from people with low vision are some of the most profound pieces of feedback.

“Sometimes, it’s very emotional,” says Meydad. “They say, ‘Thanks to Moovit, I’m more independent. I can now leave home on my own.’ It’s very, very important for us to make Moovit accessible for everyone.”

The company’s accessibility work began in earnest in 2015, when Meydad and other leading app developers met a focus group of people who are blind or low-vision to see how they used their apps.

“Honestly, I was shocked,” says Meydad, who wrote about the experience twice in Medium. “I saw people trying to use our product, but couldn’t do it efficiently or at all, because screens were not properly labeled or meaningful [for screen readers].” In one case, Moovit’s search button – a major feature to start a trip plan – had the unhelpful audio label of “Button 56.”

Meydad took notes and promised big changes. He worked with Moovit’s team and a developer who is blind to optimize the app for the mobile screen readers TalkBack on Android and VoiceOver on iOS. The team scrutinized every screen for accessibility, added useful labels and condensed intricate data – routes, trip duration, start and end times, entry and exit stops – into clear sentences for audio. They incorporated feedback from users around the world with low vision.

“After one quarter, we released a major version upgrade that completely changed their experience,” says Meydad.

The accessibility work didn’t stop there. To ease public transit for people who use a wheelchair, Moovit asked its “Mooviters” – 550,000 local contributors who help map transit systems for the app – to identify wheelchair-accessible stations in their cities. That enabled the company to add a feature that shows only routes with stations with ramps and elevators.

“This means the entire journey can be fully accessible,” says Meydad.

For users with hand motor disabilities, Moovit redesigned menus and buttons for easier use with one hand, especially on larger phones. For people who are colorblind and use color-coded transit systems, such as “the green line,” Moovit includes the name of the line, instead of just a colored dot or symbol, a space-saving practice in many maps.

The company also ensures no broken or overlapped text when a user needs to magnify the font. It partnered with Be My Eyes, an app that connects sighted volunteers with people who are blind or low-vision. It’s studying how to use a phone’s vibration and flashlight to serve users with hearing loss. And it continually works with people with a disability to improve or customize the app.

Man in wheelchair on a street uses Moovit app on his phone
A Moovit user in a wheelchair uses the app. (Photo courtesy of Moovit)

For Microsoft, working with Moovit, who has developed accessible features such as screen readers and global data on wheelchair-friendly routes, is part of a deep commitment to accessibility and inclusion in its products and services. Developers who use Azure Maps will soon have access to Moovit’s trip planner and rich transit data  to help build innovative, accessible tools.  

“What I love most about Moovit is how they’re empowering other companies to build inclusion into their solutions,” says Megan Lawrence, senior accessibility evangelist at Microsoft. “Our partnership can help people across the disability spectrum use technology to move more freely and independently, a key metric for improving quality of life.”

The clarity of Moovit’s live audio navigation also helps people with an intellectual disability who want extra guidance, such as alerts for when a bus is coming, when to transfer and when to get off. The features are a main reason why Community Living Toronto, an organization that supports people with an intellectual or developmental disability, chose Moovit as the platform for their branded transit app, Discover My Route.

“We tested many apps and Moovit was the full package,” says Angela Bradley, director of resource development and marketing at Community Living Toronto.

“It’s not just an app for riding transit. It’s almost like a coaching tool. It gives people the confidence to take transit and open up their world, which can mean seeing friends, getting a job, going to college or joining a dance class.”

Top photo: Alexandr Epaneshnikov in Moscow. (Photo courtesy of Epaneshnikov)

Posted on Leave a comment

Royal Caribbean’s head innovator Joey Hasty turns dreams into memories

It’s with that mindset in place that Hasty sets out to bridge the gap between dreams and reality.

“Not long ago, check-in was about a 30-minute process to get you on board a cruise line,” Hasty explains, touting a recent breakthrough. “It really felt like going through the TSA, not starting a vacation.”

To streamline things, Hasty and his team envisioned an “invisible experience,” fueled by customer-submitted cellphone selfies and pre-checks. But as they workshopped the idea, they discovered that removing all friction just resulted in confusion and guilt.

“It’s that feeling you get at a store with no registers; you’re supposed to just walk out, but you feel a little shady about it,” he explains. “That’s even more amplified when you board a cruise ship. You’re like, ‘Am I just supposed to walk on?’ As it turns out, guests need the feedback; something saying all is well.”

In search of a solution, Hasty turned to some old friends. “When I took it to Microsoft, some of the first conversations were: ‘We’ve never tried to do it this way.  Let’s think with our hands to see what’s possible,’” he recalls. “It was never ‘We can’t get there,’ it was always “Well, this is what would be required to get there, so this is what we’ve got to go do.’”

In the years since Hasty has begun working with the Commercial Software Engineering (CSE) team, the relationship has empowered him to imagine with no limitations – confident in the knowledge that CSE will bridge the gap between his team and Microsoft’s product engineers, accelerating their capabilities through tech and innovation.

Royal Caribbean’s new Innovation Lab in Miami.
Royal Caribbean’s new Innovation Lab in Miami takes the ship design process to new heights by bringing the best creative minds and the latest technology together under one roof.

“They provided resources to help us validate things Royal didn’t have access to, like cognitive services and cloud computing capability that allowed us to recognize faces in a millisecond,” Hasty explains, pointing out RC’s privacy policies that ensure customer transparency and that captured images are only used for the cruise experience.

“The first prototype was a camera and a laptop with Cognitive Services. Can we see these people, connect them to our data; can we check them in just using their face? From there, we realized that we want to talk about the guest experience, the height of the camera, the quality of the camera that we need, the flow of people, how fast can the camera pick up people, how many people can be in the frame at once.”

Utilizing an open source mindset, the CSE team worked alongside Royal Caribbean every step of the way to develop a solution that was both “invisible” and interactive enough to remove that sense of guilt.

“We noticed that when all these people went by, they didn’t quite know where to look, so we put a light ring on it. Then we realized people needed feedback, so we put a screen on it,” Hasty says of the project, which averages split seconds per passenger and is significantly faster than the manual review process.

“The LED ring gives you simple color codes – white says ‘We’re looking for your face,’ blue says, ‘We found your face,’ and green says, ‘You’re all clear.’ It happens almost instantaneously, everyone understands it instantly, and we’ve created a beautiful appliance that you can walk through with your whole family together at once.”

“Now boarding is literally, go up the escalator, walk by the facial recognition machine and onto the ship – welcome aboard,” Hasty adds with a smile. “We like to say car to bar in minutes.”

Echoes Schneider: “Joey and I are huge fans of the CSE group. Our focus right now is on how we leverage emerging technology to transform the guest experience, and Microsoft keeps us on the next edge of technology as it relates to disruption in our industry.”

To date, the relationship has manifested itself in a variety of ways. The aforementioned Edge Access tour app, for instance, is powered by Microsoft’s Capture Studio technology. Elements of Azure, AI and dashboards manage guest experiences daily, and RC attended last summer’s One Week hackathon on the Microsoft campus in Redmond, Washington, engaging with the CSE team on video analytics initiatives.

Posted on Leave a comment

Starbucks turns to tech to brew up a more personal connection with customers

Walk into a Starbucks store anywhere in the world and you’ll encounter a similar sight: coffee beans grinding, espresso shots being pulled and customers talking to baristas while their coffee order is hand-crafted.

The process may look like a simple everyday scene, but it is carefully orchestrated to serve Starbucks’ more than 100 million weekly customers. With the help of Microsoft, Starbucks is creating an even more personal, seamless customer experience in its stores by implementing advanced technologies, ranging from cloud computing to blockchain.

“We have a world-class team of technologists engaging in groundbreaking innovation each day. Their inventiveness and intellectual curiosity are matched by their dedication to enabling the Starbucks experience, and this is increasingly critical to how technology has to show up for us,” says Gerri Martin-Flickinger, Starbucks executive vice president and chief technology officer.

“Everything we do in technology is centered around the customer connection in the store, the human connection, one person, one cup, one neighborhood at a time.”

At the Microsoft Build 2019 conference, Microsoft CEO Satya Nadella recently demonstrated how Starbucks delivers its signature customer experience with new technologies.

Making recommendations more relevant with reinforcement learning

Starbucks has been using reinforcement learning technology — a type of machine learning in which a system learns to make decisions in complex, unpredictable environments based upon external feedback — to provide a more personalized experience for customers who use the Starbucks® mobile app.

Within the app, customers receive tailor-made order suggestions generated via a reinforcement learning platform that is built and hosted in Microsoft Azure. Through this technology and the work of Starbucks data scientists, 16 million active Starbucks® Rewards members now receive thoughtful recommendations from the app for food and drinks based on local store inventory, popular selections, weather, time of day, community preferences and previous orders.

“Just like their relationship with a barista, customers receive the same care and personalized recommendations when it comes from our digital platforms,” says Jon Francis, senior vice president, Starbucks Analytics and Market Research.

A Starbucks customer views custom recommendations on a the company's mobile app.
Starbucks is delivering personalized recommendations to customers via its mobile app and, soon, its drive-thrus.

This personalization means that customers are more likely to get suggestions for items they will enjoy. For example, if a customer consistently orders dairy-free beverages, the platform can infer a non-dairy preference, steer clear of recommending items containing dairy, and suggest dairy-free food and drinks.

In essence, reinforcement learning allows the app to get to know each customer better. And while the recommendations are driven by a machine, the end goal is personal interaction.

“Starbucks is an experience,” says Martin-Flickinger. “And it’s centered around that customer connection in the store, the human connection, one person, one cup, one neighborhood at a time. I think that mission is so critical to how technology has to show up for us.”

Now, Starbucks is looking to expand this technology to the drive-thru experience.

“As an engineering and technology organization, one of the areas we are incredibly excited to be pursuing is using data to continuously improve the experience for our customers and partners,” says Martin-Flickinger. “Using data for personalization is vital to our mobile app, and now we are leveraging data to improve our drive-thru experience.”

Because the technology does not have the individual order histories for drive-thru customers that are available for mobile app customers, it will generate relevant drive-thru recommendations based on store transaction histories and more than 400 other store-level criteria. These recommendations will be offered proactively on a digital menu display from which customers can order. Eventually, customers will be able to explicitly opt in to recommendations that are even more personalized.

Starbucks is currently testing this technology in its Tryer Center innovation hub in Seattle, with plans to roll it out soon. And according to Francis, reinforcement learning will continue to have an important role at Starbucks in many other applications going forward.

“We’re meeting our customers where they are — whether in-store, in their car or on the go through the app — using machine learning and artificial intelligence to understand and anticipate their personal preferences,” he says. “Machine learning also plays a role in how we think about store design, engage with our partners, optimize inventory and create barista schedules. This capability will eventually touch all facets of how we run our business.”

Implementing IoT to deliver a smooth coffee experience

 Each Starbucks store has more than a dozen pieces of equipment, from coffee machines to grinders and blenders, that must be operational around 16 hours a day. A glitch in any of those devices can mean service calls that rack up repair costs. More significantly, equipment problems can potentially interfere with Starbucks’ primary goal of providing a consistently high-quality customer experience.

“Any time we can create additional moments of connection between our partners and customers, we want to explore and activate,” says Natarajan “Venkat” Venkatakrishnan, vice president of global equipment for Starbucks. “Our machines are what allow our partners to create that special beverage, and ensuring they are working properly is critical.”

To reduce disruptions to that experience and securely connect its devices in the cloud, Starbucks is partnering with Microsoft to deploy Azure Sphere, designed to secure the coming wave of connected internet of things (IoT) devices across its store equipment.

A smiling Starbucks barista pours a hand-crafted coffee.
Starbucks partners are able to spend more time hand-crafting the perfect beverage and less time on machine maintenance thanks to cloud-connected devices.

The IoT-enabled machines collect more than a dozen data points for every shot of espresso pulled, from the type of beans used to the coffee’s temperature and water quality, generating more than 5 megabytes of data in an eight-hour shift. Microsoft worked with Starbucks to develop an external device called a guardian module to connect the company’s various pieces of equipment to Azure Sphere in order to securely aggregate data and proactively identify problems with the machines.

The solution will also enable Starbucks to send new coffee recipes directly to machines, which it has previously done by manually delivering the recipes to stores via thumb drive multiple times a year. Now the recipes can be delivered securely from the cloud to Azure Sphere-enabled devices at the click of a button.

“Think about the complexity — we have to get to 30,000 stores in nearly 80 markets to update those recipes,” says Jeff Wile, senior vice president of retail and core technology services for Starbucks Technology. “That recipe push is a huge part of the cost savings and the justification for doing this.”

The overarching goal with Azure Sphere, Wile says, is to shift from reactive maintenance to a predictive approach that heads off issues before they happen. Longer term, the company envisions leveraging Azure Sphere for additional uses such as managing inventory and ordering supplies, and will encourage suppliers of its devices to build the solution into future versions of their products.

Using blockchain to share coffee’s journey with customers

Starbucks is also innovating ways to trace the journey that its coffee makes from farm to cup — and to connect the people who drink it with the people who grow it.

The company is developing a feature for its mobile app that shows customers information about where their packaged coffee comes from, from where it was grown and what Starbucks is doing to support farmers in those locations, to where and when it was roasted, tasting notes and more.

For Starbucks, which has long been committed to ethical sourcing, knowing where its coffee comes from is not new. Last year alone, Starbucks worked with more than 380,000 coffee farms. However, digital, real-time traceability will allow customers to know more about their coffee beans. Perhaps even more important and differentiating are the potential benefits for coffee farmers to know where their beans go after they sell them.

A farmer holds coffee beans in one hand and a mobile phone in the other.
Starbucks is exploring the role of digital traceability in empowering coffee farmers. “I firmly believe that by empowering farmers with knowledge and data through technology, we can support them in ultimately improving their livelihoods,” says Michelle Burns, SVP of Global Coffee & Tea.

This new transparency is powered by Microsoft’s Azure Blockchain Service, which allows supply chain participants to trace both the movement of their coffee and its transformation from bean to final bag. Each state change is recorded to a shared, immutable ledger providing all parties a more complete view of their products’ journey.

This can not only empower farmers with more information and visibility once the beans leave their farms, but also allows customers to see the impact their coffee purchase has on the real people they’re supporting.

“While high-quality, handcrafted beverages are so important, it’s the stories, the people, the connections, the humanity behind that coffee that inspires everything we do,” says Michelle Burns, Starbucks senior vice president of Global Coffee & Tea. “This kind of transparency offers customers the chance to see that the coffee they enjoy from us is the result of many people caring deeply.”

Starbucks previewed digital traceability for shareholders at its annual meeting in March. Eventually, customers will be able to use the Starbucks mobile app to trace the journey of their Starbucks packaged coffee.

“What we’re still working on is interviewing coffee farmers in Costa Rica, Colombia and Rwanda, learning more about their stories, their knowledge and their needs in order to determine how digital traceability can best benefit them,” says Burns. “We’re forging new ground here, so we’re excited to report more in the coming months.”

Learn about the latest innovations and imagine new ways to create solutions at Build 2019.

Top photo: At the Starbucks store at 81st and Broadway in New York City, and at every store around the world, cutting-edge innovation powers a deceptively simple everyday scene. All photos courtesy of Starbucks. Additional reporting by Deborah Bach.

Posted on Leave a comment

Toyota Material Handling Group innovates forklift, factory, service and logistics solutions

Toyota Material Handling Group is the largest forklift manufacturer in the world, but its customers require much more than warehouse trucks and equipment. To better serve them, the global business is expanding and enriching its logistics solutions with digital innovation and Toyota’s renowned principles in lean and efficient manufacturing.

By providing solutions with artificial intelligence, mixed reality and the Internet of Things (IoT), Toyota Material Handling Group is helping customers meet the global rise in e-commerce and move goods quickly, frequently, accurately and safely.

With Microsoft technologies, the solutions range from connected forklift and field service systems available today to AI-powered concepts that pave the way for intelligent automation and logistics simulation – all designed with Toyota’s standards for optimizing efficiency, operation assistance and kaizen, or continuous improvement.

headshot of Toshihide Itoh
Toshihide Itoh, associate director and CIO of Toyota Material Handling Group.

“Our direction is going to more systemizing and logistics solutions, services in digital automation, AI analytics and IoT,” says Toshihide Itoh, associate director and CIO of Toyota Material Handling Group, an Aichi, Japan-based division of Toyota Industries Corporation. “We also continue to improve our forklift trucks, because this is our origin. But customers need more and more efficient logistics and we need digital innovation to accelerate and expand our business.”

At the Hannover Messe show in Germany this week, Toyota presented its vision for a future warehouse with lean logistics and pre-trained, intelligent forklifts. Enabled with machine learning and IoT services in Microsoft Azure, the vehicles can quickly learn navigation in a virtual model of a customer’s warehouse, a so-called “digital twin.” Customers can experience the trucks interacting with their physical and virtual environment.

The ability to simulate and visualize a physical environment will help solve one of the biggest challenges in the industry: the long deployment time for customized IoT solutions. Installations can normally take six months to a year, but using machine learning and digital twins can significantly shorten the time.

“For customers, this is a very important benefit,” Itoh says of the project, created by Toyota Material Handling Europe.

Once deployed, the intelligent forklifts and other automated guided vehicles (AGV) can adapt to live conditions, continually improve performance and communicate with other machines in a “swarm” that sends the right trucks to the right tasks at the right time.

Machine learning also plays a big role in a factory innovation project that Toyota Material Handling North America is working on with Microsoft. Engineers with both companies are building AI algorithms with sound to evaluate and verify welding quality, an important part of building forklifts.

Earlier this year, the teams worked with welders in Toyota’s Indiana factory and recorded sound from the factory floor. Then they created a machine learning platform to drive product quality, customer satisfaction and better training opportunities for new employees.

“We use machine learning and AI to do things that people cannot do by themselves, like analyze big data quickly,” Itoh says. “AI analysis can lead to new solutions and give open time for people to utilize their brain. That’s very important. So they share some work with AI and it makes everyone and everything more productive.”

Itoh became CIO of Toyota Material Handling Group in 2017, after leadership roles in the group’s divisions for logistics systems, forklift research and development, and advanced system solutions. The work helped him understand different aspects of the industry, from equipment to logistics to customers.

“The important point of view is the customers’ point of view,” he says. “Information technology is my main responsibility, but it needs to help customers and our business team improve their operations.”

He said Azure’s global scale and services have helped the company deliver valuable solutions, including a fleet management system for customers to centrally monitor their forklift fleet. Powered by Azure IoT Edge and scheduled to deploy this spring, the telematics solution helps customers track forklift utilization, plan and predict maintenance, and improve efficiency and safety in their warehouses.

forklifts in a forklift factory
Toyota Material Handling Group forklifts.

Toyota also deployed a new field service solution with Dynamics 365 last year for proactive, connected service and maximum uptime for customers. It launched a mobile solution for connected field service in Asia on Azure. And it will use Azure IoT in its factories for predictive maintenance in the future.

The company is also developing a fully integrated dealer management system in North America with the Microsoft platform. And Toyota Material Handling Europe and North America are collaborating on a robust customer portal, powered by many data sources, to meet customer expectations in a digital world.

“We need to expand our business and see the customers’ point of view more and make them happy,” Itoh says. “But we cannot do everything by ourselves. So I am so excited for everything that Microsoft can provide as a partner to accelerate our digital transformation.”

Learn how Microsoft partners are building a sustainable future at Hannover Messe 2019.

Top photo: Toyota Material Handling Group forklifts. (All photos courtesy of Toyota Material Handling Group)

Posted on Leave a comment

Electrolux has a smart air purifier that lets you breathe easy, even in polluted cities

Acrid smoke, carried by stiff breezes from a nearby garage fire, recently filled the Electrolux campus in Stockholm, Sweden.

Some developers and executives felt their throats burn. At least one employee had trouble breathing. She decided to leave. But before heading home, she stopped inside the building where Andreas Larsson and his team were testing the Pure A9, an IoT-connected air purifier built with Microsoft Azure.

The moment had come to see what the new device could do in dire conditions.

Andreas Larsson stands behind four Pure A9 air purifiers at Electrolux headquarters.
Andreas Larsson with some of the Pure A9 purifiers used to clear the air during the fire near Electrolux headquarters.

“We had 10 or 15 Pure A9 air purifiers and turned them all on,” recalls Larsson, engineering director at Electrolux. “That made a significant change in air quality. We asked her to come into our office, sit down and just work there. She took some deep breaths. She was happy. She stayed for the rest of the day.”

The Pure A9 – launched March 1 in four Nordic countries plus Switzerland and, previously, in Korea – removes ultra-fine dust particles, pollutants, bacteria, allergens and bad odors from indoor rooms.

By linking the purifier and its associated app to the cloud, Electrolux can show the product’s users real-time data about their air quality – inside and outside – while tracking interior air improvement over time. In addition, the Pure A9 continuously monitors its filter usage, alerting users when it’s time to order a replacement filter.

And as a connected appliance, the Pure A9 eventually may have the ability to learn the daily patterns of when household occupants are typically away, enabling the device to run itself on a smart schedule, Larsson says.

“If we can predict when the house is empty, we make sure not to waste filter by cleaning air that nobody is going to breathe,” Larsson says. “Then we can start the purification so the air is clean when you come home.”

Launch of the Pure A9 marks a fresh phase in Electrolux’s push to provide connected appliances to “millions of homes around the world, shaping living for the better for consumers,” Larsson says.

He dubs it the company’s “wellbeing journey into IoT, software products, data and apps” – a process that began two years ago with a cloud-connected, robotic vacuum called the Pure i9.

A Pure i9 robotic vacuum moves across a run toward a table and sofa.
A Pure i9 cleans a rug and flooring while navigating a table and sofa.

The triangular device is equipped with a 3-D camera for smart navigation.

Moreover, its Azure IoT platform helped get the product to market quickly while also enabling developers to update software and add features after launch, Larsson says. Newer features include a map view showing where the Pure i9 has cleaned.

The roaming robot is now available in the U.S., Europe and Asia, including China.

The Pure i9 from above on a wood floor.
The Pure i9 in action.

Cloud data from the device also led Electrolux to launch a unique trial in Sweden: vacuum-as-a-service.

Consumers in that country can buy an $8-per-month subscription to the Pure i9 and get 80 square meters of floor cleaning, Larsson says.

“You only pay for what you use,” Larsson says. “This is not possible unless it is connected to the cloud or unless we have the data. With this kind of product, we see business alternatives we’ve never been able to do before.”

That trial underscores the digital ambitions of a 100-year-old brand once known for its canister vacuums. Today, Electrolux also manufactures and sells ovens, refrigerators, washers, dryers, water heaters and an array of other household gadgetry.

An app for the Pure A9 gives users valuable data on the state of their air.Following the Pure i9’s launch in 2017, “it soon became clear that this was not going to be a one-off product,” Larsson says. “An ambitious plan to create an ecosystem of smart, networking products … started to form.”

A smartphone displays the Pure A9 app interface next to a Pure A9 air purifier.
An app for the Pure A9 offers real-time data, including the state of indoor air quality.

They chose the cloud-connected air purifier as their next connected appliance. In September 2018, a team of just three Electrolux developers began building a new Azure IoT platform for what would become the Pure A9. By February 2019, that product was already on the market in Asia.

“Azure enabled them to launch a product to the whole world with minimal development investments and in rapid pace,” says Arash Rassoulpour, a Microsoft cloud solution architect who worked with Electrolux developers on the products.

Electrolux engineers also used the ready-made functions in Azure IoT Hub, instead of writing the code themselves, saving them more development time, Larsson says.

To introduce its new air purifier to consumers, Electrolux initially launched in Korea, where staggering air pollution levels have caused what legislators describe as a “social disaster.”

A smoggy skyline in Seoul, South Korea with the sun on the horizon.
Another smoggy day in Seoul, South Korea. (Getty Images)

On March 5, the South Korean government advised residents in Seoul to wear masks and avoid walking outside due to a record level of fine dust particles in the air.

Numerous studies have shown that bad air outside affects air quality inside homes and offices, entering through ventilation systems.

Even worse, pollutants generated inside from cleaning supplies, cooking and fireplaces can be even harder on your health than what you breathe out on the street, according to the Environmental Protection Agency.

An Electrolux sign on the exterior of a building a company headquarters in Stockholm, Sweden.
Electrolux global headquarters in Stockholm, Sweden.

“By monitoring and controlling consumers’ indoor air quality, our smart, premium air purifier contributes to a better indoor climate and increased wellbeing for the consumer,” says Karin Asplund, Electrolux’s global category director for ecosystem.

“Via the Pure A9 app, the consumer can also get an increased understanding of the actual job done by the purifier thanks to its ability to turn sensor data into understandable and actionable information,” she adds.

With the first two connected appliances now in the hands of consumers, Larsson envisions how that technology can help get the weekend started on a comfy, tidy note.

“When you come home on Friday evening, our goal is to have your home clean and pure,” Larsson says. “You can just come in, take off your shoes, sit down and feel, OK, this is my home.”

Top image: A woman holding her daughter in their home, looking through a window at a view of Seoul on a day with heavy pollution in the air. (Getty Images)

Posted on Leave a comment

BP has a new AI tool for drilling into data – and it’s fueling smarter decisions

Deep inside the Earth, miles down in many cases, rock-sealed pockets hold buried treasures.

These hydrocarbon reservoirs are packed with organic compounds that make the world go ‘round. When the contents are extracted and refined, the resulting oil and gas help light cities, transport people and run industries.

For some engineers at BP, Job One is locating the reservoirs. Job Two is accurately predicting what percentage of hydrocarbons are retrievable, also known as “recovery factor.”

Traditionally, that task has been iterative, resource-heavy and can have an element of human bias. Data scientists, tapping their own expertise and experiences, may try six or seven different algorithms as they work to dial in the best prediction model. This can take weeks.

But by using Azure Machine Learning service, BP is working to reduce the time needed to pinpoint prediction models while also boosting the productivity of its data scientists. Automated machine learning empowers customers to identify an end-to-end, machine-learning pipeline for any problem.

Transform recently caught up with Manish Naik, BP’s principal for digital innovation, at his London office to learn more about the company’s new method for drilling down into its data.

TRANSFORM: What is the value that BP gains by improving its recovery factor forecasts?

MANISH NAIK: This prediction of recovery factor from underlying data is a crucial activity – the basis of key decisions made by the company that are potentially worth billions of dollars. This data is vast and complex, involving hundreds of geological properties or features.

To complement the current ways of prediction, which tend to have some qualitative input, we decided to explore machine learning to see if we can improve prediction. We sought to answer these questions: Can we improve the quality of the prediction? Can we eliminate some of the human bias?

Manish Naik sits in from of a large window that looks out on a city.
Manish Naik. Courtesy of BP.

TRANSFORM: How do your data scientists use automated machine learning?

NAIK: They give it broad direction. With one line of code, it runs through different algorithms within the prediction family and the different parameter (or variable) combos that previously were manually tested by the scientists. The power of the cloud comes in here. The results are comparable to what the data scientists produced.

TRANSFORM: One line of code, wow. How much time does this save them?

NAIK: Depending on the amount of data, type of activity – such as the prediction or classification – and algorithm family, automated machine learning could potentially reduce the effort down from weeks to days or days to hours.

TRANSFORM: How often is the prediction model that BP developed for recovery factor now used across the company?

NAIK: This model is in production and used by hundreds of subject matter experts globally in BP on a daily basis.

TRANSFORM: As automated machine learning becomes a core tool for BP’s data scientists, what are the larger, potential benefits for the company?

NAIK: It will make data scientists more productive, which means faster time to market for machine-learning (ML) projects

And as data scientists continue to use more and more of automated machine learning, they will develop trust in the output it provides. That can become a starting point for the work of our data scientists. In the future, this will form a part of a robust benchmarking process for all ML projects, thus improving quality.

TRANSFORM: More broadly, in what ways do you foresee Artificial Intelligence (AI) and the cloud further reshaping the oil and gas industry?

NAIK: Oil and gas companies across the value chain – from exploration to retail – generate significant amounts of data. This means there are lots of opportunities to exploit this data using AI, ML and cloud technologies.

In broad terms, there is significant potential for these technologies to help improve the efficiency of our operations and help us make better, more accurate and informed decisions.

Top photo: The logo of BP plc is seen at a BP petrol station in Liverpool on February 7, 2018. (Paul Ellis/AFP/Getty Images)