Google Maps prioritized fighting fake contributions and used a variety of techniques including ML to combat policy-violating content.
Building a map is complex, and keeping it up-to-date is even more challenging. Think about how often your city, town or neighborhood changes on a day-to-day basis. Businesses and shops open and close, stretches of highway are added, and roadways change. In today’s Maps 101 installment, we’ll dive into two ways Google Maps uses advancements in AI and imagery to help you see the latest information about the world around you every single day.
Automatically updating business hours
Over the past few years, businesses have experienced a lot of change — including constantly updating operating hours based on changing pandemic-related restrictions. To keep up with this pace of change, we developed a machine learning model that automatically identifies if business hours are likely wrong, then instantly updates them with AI-generated predictions.
Let’s look at Liam’s Lemonade Shop as an example. To start, our systems consider multiple factors — such as when Liam last updated their business profile, what we know about other shops' hours, and the Popular Times information for the shop, which uses location trends to show when it tends to be busiest. Since it appears that Liam’s business profile hasn’t been updated in over a year and its busiest hours are typically Thursday afternoons — even though Google Maps says that it's closed at that time — Liam’s business hours are likely out of date.
To see if business hours need updating, we check a store’s Popular Times information and when its business profile was last updated.
So what’s next? Our algorithms analyze the business hours of other nearby lemonade shops, information from Liam’s website, and Street View images of Liam’s storefront that look specifically for business hour signs to determine the most accurate business hour prediction. At the same time, we enlist the help of the Google Maps community — including Local Guides and even the business owners themselves through their Google Business Profile — to verify the information we predicted. In Argentina, Australia, Chile, France, Japan, Mexico, New Zealand, Peru, and the United States, we also use Duplex conversational technology to call businesses just like Liam’s and ask for their hours directly. With this new AI-first approach, we’re on track to update the hours for over 20 million businesses around the globe in the next six months - helping you know exactly when your favorite store, restaurant or cafe is open for business .
Road information that reflects the real world
We’re also experimenting with ways we can use imagery to make updates to other helpful information. For instance, starting in the U.S., we’re launching a third-party imagery pilot to let you see the most up-to-date speed limit information in your town, which can help keep you safe while driving. Here’s how it works:
Say our systems think that the speed limit information on a particular highway needs to be updated. With the help of third-party imagery partners that already gather roadway imagery to improve delivery routes, we can request a photo of the specific stretch of road that also includes a speed limit sign. If the partner has this photo available, we then use a combination of AI and help from our operations team to identify the sign in the image, extract the new speed limit information, and update Google Maps.
Representative imagery featuring a speed limit sign, with license plates blurred
Over time, this technology will bring more details to the map that can help make your drives safer and more efficient — like where potholes and school zones are or where new construction is happening. And as with all Google Maps features, we designed this pilot with privacy top of mind. For instance, we only reference images taken on public roads, and partners are required to blur information (like faces and license plates) to avoid potentially identifying someone. For an extra layer of privacy, we blur the photo again when we receive it and delete the photo after we use it to update the map.
AI, imagery and Duplex technology will continue to play a critical role in helping make Google Maps the most comprehensive and useful map possible. For more behind-the-scenes looks at the technology that powers Google Maps, check out the rest of our Maps 101 blog series.
When exploring new places, reviews on Google are a treasure trove of local knowledge that can point you to the places and businesses you’ll enjoy most — whether it’s a bakery with the best gluten-free cupcake or a nearby restaurant with live music.
With millions of reviews posted every day from people around the world, we have around-the-clock support to keep the information on Google relevant and accurate. Much of our work to prevent inappropriate content is done behind the scenes, so we wanted to shed some light on what happens after you hit “post” on a review.
We’ve created strict content policies to make sure reviews are based on real-world experiences and to keep irrelevant and offensive comments off of Google Business Profiles.
As the world evolves, so do our policies and protections. This helps us guard places and businesses from violative and off-topic content when there’s potential for them to be targeted for abuse. For instance, when governments and businesses started requiring proof of COVID-19 vaccine before entering certain places, we put extra protections in place to remove Google reviews that criticize a business for its health and safety policies or for complying with a vaccine mandate.
Once a policy is written, it’s turned into training material — both for our operators and machine learning algorithms — to help our teams catch policy-violating content and ultimately keep Google reviews helpful and authentic.
As soon as someone posts a review, we send it to our moderation system to make sure the review doesn’t violate any of our policies. You can think of our moderation system as a security guard that stops unauthorized people from getting into a building — but instead, our team is stopping bad content from being posted on Google.
Given the volume of reviews we regularly receive, we’ve found that we need both the nuanced understanding that humans offer and the scale that machines provide to help us moderate contributed content. They have different strengths so we continue to invest tremendously in both.
Machines are our first line of defense because they’re good at identifying patterns. These patterns often immediately help our machines determine if the content is legitimate, and the vast majority of fake and fraudulent content is removed before anyone actually sees it.
Our machines look at reviews from multiple angles, such as:
Training a machine on the difference between acceptable and policy-violating content is a delicate balance. For example, sometimes the word “gay” is used as a derogatory term, and that’s not something we tolerate in Google reviews. But if we teach our machine learning models that it’s only used in hate speech, we might erroneously remove reviews that promote a gay business owner or an LGBTQ+ safe space. Our human operators regularly run quality tests and complete additional training to remove bias from the machine learning models. By thoroughly training our models on all the ways certain words or phrases are used, we improve our ability to catch policy-violating content and reduce the chance of inadvertently blocking legitimate reviews from going live.
If our systems detect no policy violations, then the review can post within a matter of seconds. But our job doesn’t stop once a review goes live. Our systems continue to analyze the contributed content and watch for questionable patterns. These patterns can be anything from a group of people leaving reviews on the same cluster of Business Profiles to a business or place receiving an unusually high number of 1 or 5-star reviews over a short period of time.
Like any platform that welcomes contributions from users, we also have to stay vigilant in our efforts to prevent fraud and abuse from appearing on Maps. Part of that is making it easy for people using Google Maps to flag any policy-violating reviews. If you think you see a policy-violating review on Google, we encourage you to report it to our team. Businesses can report reviews on their profiles here, and consumers can report them here.
Google Maps users and businesses can easily report reviews that they feel violate one of our policies.
Our team of human operators works around the clock to review flagged content. When we find reviews that violate our policies, we remove them from Google and, in some cases, suspend the user account or even pursue litigation.
In addition to reviewing flagged content, our team proactively works to identify potential abuse risks, which reduces the likelihood of successful abuse attacks. For instance, when there’s an upcoming event with a significant following — such as an election — we implement elevated protections to the places associated with the event and other nearby businesses that people might look for on Maps. We continue to monitor these places and businesses until the risk of abuse has subsided to support our mission of only publishing authentic and reliable reviews. Our investment in analyzing and understanding how contributed content can be abused has been critical in keeping us one step ahead of bad actors.
With more than 1 billion people turning to Google Maps every month to navigate and explore, we want to make sure the information they see — especially reviews — is reliable for everyone. Our work is never done; we’re constantly improving our system and working hard to keep abuse, including fake reviews, off of the map.
When exploring new places, reviews on Google are a treasure trove of local knowledge that can point you to the places and businesses you’ll enjoy most — whether it’s a bakery with the best gluten-free cupcake or a nearby restaurant with live music.
With millions of reviews posted every day from people around the world, we have around-the-clock support to keep the information on Google relevant and accurate. Much of our work to prevent inappropriate content is done behind the scenes, so we wanted to shed some light on what happens after you hit “post” on a review.
We’ve created strict content policies to make sure reviews are based on real-world experiences and to keep irrelevant and offensive comments off of Google Business Profiles.
As the world evolves, so do our policies and protections. This helps us guard places and businesses from violative and off-topic content when there’s potential for them to be targeted for abuse. For instance, when governments and businesses started requiring proof of COVID-19 vaccine before entering certain places, we put extra protections in place to remove Google reviews that criticize a business for its health and safety policies or for complying with a vaccine mandate.
Once a policy is written, it’s turned into training material — both for our operators and machine learning algorithms — to help our teams catch policy-violating content and ultimately keep Google reviews helpful and authentic.
As soon as someone posts a review, we send it to our moderation system to make sure the review doesn’t violate any of our policies. You can think of our moderation system as a security guard that stops unauthorized people from getting into a building — but instead, our team is stopping bad content from being posted on Google.
Given the volume of reviews we regularly receive, we’ve found that we need both the nuanced understanding that humans offer and the scale that machines provide to help us moderate contributed content. They have different strengths so we continue to invest tremendously in both.
Machines are our first line of defense because they’re good at identifying patterns. These patterns often immediately help our machines determine if the content is legitimate, and the vast majority of fake and fraudulent content is removed before anyone actually sees it.
Our machines look at reviews from multiple angles, such as:
Training a machine on the difference between acceptable and policy-violating content is a delicate balance. For example, sometimes the word “gay” is used as a derogatory term, and that’s not something we tolerate in Google reviews. But if we teach our machine learning models that it’s only used in hate speech, we might erroneously remove reviews that promote a gay business owner or an LGBTQ+ safe space. Our human operators regularly run quality tests and complete additional training to remove bias from the machine learning models. By thoroughly training our models on all the ways certain words or phrases are used, we improve our ability to catch policy-violating content and reduce the chance of inadvertently blocking legitimate reviews from going live.
If our systems detect no policy violations, then the review can post within a matter of seconds. But our job doesn’t stop once a review goes live. Our systems continue to analyze the contributed content and watch for questionable patterns. These patterns can be anything from a group of people leaving reviews on the same cluster of Business Profiles to a business or place receiving an unusually high number of 1 or 5-star reviews over a short period of time.
Like any platform that welcomes contributions from users, we also have to stay vigilant in our efforts to prevent fraud and abuse from appearing on Maps. Part of that is making it easy for people using Google Maps to flag any policy-violating reviews. If you think you see a policy-violating review on Google, we encourage you to report it to our team. Businesses can report reviews on their profiles here, and consumers can report them here.
Google Maps users and businesses can easily report reviews that they feel violate one of our policies.
Our team of human operators works around the clock to review flagged content. When we find reviews that violate our policies, we remove them from Google and, in some cases, suspend the user account or even pursue litigation.
In addition to reviewing flagged content, our team proactively works to identify potential abuse risks, which reduces the likelihood of successful abuse attacks. For instance, when there’s an upcoming event with a significant following — such as an election — we implement elevated protections to the places associated with the event and other nearby businesses that people might look for on Maps. We continue to monitor these places and businesses until the risk of abuse has subsided to support our mission of only publishing authentic and reliable reviews. Our investment in analyzing and understanding how contributed content can be abused has been critical in keeping us one step ahead of bad actors.
With more than 1 billion people turning to Google Maps every month to navigate and explore, we want to make sure the information they see — especially reviews — is reliable for everyone. Our work is never done; we’re constantly improving our system and working hard to keep abuse, including fake reviews, off of the map.
AI is a critical part of what makes Google Maps so helpful. With it, we’re able to map roads over 10 times faster than we could five years ago, and we can bring maps filled with useful information to virtually every corner of the world. Today, we’re giving you a behind-the-scenes look at how AI makes two of the features we announced at I/O possible.
Let’s start with our routing update that helps you avoid situations that cause you to slam on the brakes, such as confusing lane changes or freeway exits. We use AI and navigation information to identify hard-braking events — moments that cause drivers to decelerate sharply and are known indicators of car crash likelihood — and then suggest alternate routes when available. We believe these updates have the potential to eliminate over 100 million hard-braking events in routes driven with Google Maps each year. But how exactly do we find when and where these moments are likely to occur?
That’s where AI comes in. To do this, we train our machine learning models on two sets of data. The first set of information comes from phones using Google Maps. Mobile phone sensors can determine deceleration along a route, but this data is highly prone to false alarms because your phone can move independently of your car. This is what makes it hard for our systems to decipher you tossing your phone into the cupholder or accidentally dropping it on the floor from an actual hard-braking moment. To combat this, we also use information from routes driven with Google Maps when it's projected on a car’s display, like Android Auto. This represents a relatively small subset of data, but it’s highly accurate because Maps is now tethered to a stable spot — your car display. Training our models on both sets of data makes it possible to spot actual deceleration moments from fake ones, making detection across all trips more accurate.
Understanding spots along a route that are likely to cause hard-braking is just one part of the equation. We’re also working to identify other contextual factors that lead to hard-braking events, like construction or visibility conditions. For example, if there’s a sudden increase in hard-braking events along a route during a certain time of day when people are likely to be driving toward the glare of the sun, our system could detect those events and offer alternate routes. These details inform future routing so we can suggest safer, smoother routes.
When you’re walking or biking or taking public transit, AI is also there helping you move along safely and easily. Last August we launched detailed street maps which show accurate road widths, along with details about where the sidewalks, crosswalks and pedestrian islands are in an area so people can better understand its layout and how to navigate it. Today, we announced that detailed street maps will expand to 50 more cities by the end of 2021. While this sounds straightforward, a lot is going on under the hood — especially with AI — to make this possible!
A before and after comparison of detailed streets maps built from satellite imagery
Imagine that you’re taking a stroll down a typical San Francisco street. As you approach the intersection, you’ll notice that the crosswalk uses a “zebra” pattern — vertical stripes that show you where to walk. But if you were in another city, say London, then parallel dotted lines would define the crosswalks. To account for these differences and accurately display them on the map, our systems need to know what crosswalks look like — not just in one city but across the entire world. It gets even trickier since urban design can change at the country, state, and even city level.
To expand globally and account for local differences, we needed to completely revamp our mapmaking process. Traditionally, we’ve approached mapmaking like baking a cake — one layer at a time. We trained machine learning models to identify and classify features one by one across our index of millions of Street View, satellite and aerial images — starting first with roads, then addresses, buildings and so on.
But detailed street maps require significantly more granularity and precision than a normal map. To map these dense urban features correctly, we’ve updated our models to identify all objects in a scene at once. This requires a ton of AI smarts. The model has to understand not only what the objects are, but the relationships between them — like where exactly a street ends and a sidewalk begins. With these new full-scene models, we're able to detect and classify broad sets of features at a time without sacrificing accuracy, allowing us to map a single city faster than ever before.
Single-feature AI model that classifies buildings.
Full-scene AI models that capture multiple categories of objects at once.
Once we have a model trained on a particular city, we can then expand it to other cities with similar urban designs. For example, the sidewalks, curbs, and traffic lights look similar in Atlanta and Ho Chi Minh City — despite being over 9,000 miles away. And the same model works in Madrid as it does in Dallas, something that may be hard to believe at first glance. With our new advanced machine learning techniques combined with our collection of high-definition imagery, we’re on track to bring a level of detail to the map at scale like never before.
AI will continue to play an important role as we build the most helpful map for people around the globe. For more behind-the-scenes looks at the technology that powers Google Maps, check out the rest of our Maps 101 blog series.
Google Maps helps you navigate, explore, and get things done every single day. In this series, we’ll take a look under the hood at how Google Maps uses technology to build helpful products—from using flocks of sheep and laser beams to gather high-definition imagery to predicting traffic jams that haven’t even happened yet.
For many of us, Google Maps is the place we go for information about the world around us. We search for businesses, seek directions, check photos and read reviews.
One way Maps is kept accurate and reliable is through updates that everyday people add. Since we started accepting contributed content in 2010, more than 970 million people have updated Google Maps in the form of reviews, photos, ratings and factual information like addresses and business hours. These contributions allow Google Maps to keep up with the world constantly changing around us and also help people make more informed decisions.
Just as Google Maps is a reflection of the real-world, so are the people that contribute to it. The same neighbor who lends a hand could also be writing witty reviews of local restaurants. Unfortunately, the opposite is also true. Just as there are bad actors in the real-world, there are those who try to game Google Maps with inappropriate content — the vast majority of which is removed before you see it.
While much of our work to prevent inappropriate content is done behind the scenes, we wanted to share some detail about our investments and progress in keeping Google Maps reliable and trustworthy.
Bad actors try to mislead people through a variety of techniques, from fake reviews that attack a business to inauthentic ratings that boost a place’s reputation. Fighting this unhelpful content is a complex, ceaseless battle — one that we rarely detail publicly so as to not tip off scammers to our ever-changing techniques.
One of the best tools we have to fight back is an understanding of what normal, authentic Google Maps usage looks like. For example, we know that the average person is likely to use Google Maps while navigating a commute or road trip, and while searching for nearby restaurants or services. They’ll leave reviews at places they’ve been, and usually add ratings or photos in location-specific clusters.
Observations like these inform our machine learning algorithms, which scan millions of daily contributions. These algorithms detect and remove policy-violating content across a variety of languages, and also scan for signals of abnormal user activity. For instance, they can detect if a new Google Maps account in say, Bangkok, suddenly leaves bad car dealership reviews in Mexico City and 1-star restaurant ratings in Chicago. The policy-violating content is either removed by our automated models or flagged for further review, along with the user account.
We also deploy thousands of trained operators and analysts who help with content evaluations that might be difficult for algorithms, such as understanding reviews with local slang.
Our teams and protections are built to fight two main types of bad actors: content fraudsters and content vandals.
Fraudsters, who are ultimately motivated by money, try to trick people with scams like fake reviews to attract customers or fake listings to generate business leads. To deter them, we preemptively remove opportunities for them to profit off of fake content.
For example, we have focused efforts on detecting content coming from click farms where fake reviews and ratings are being generated. Through better detection of click farm activity we are making it harder to post fake content cheaply, which ultimately makes it harder for a click farm to sell reviews and make money. And to catch fake business profiles before they appear on Maps, we've strengthened our Google My Business verification processes with new machine learning models that help identify fraudulent engagement. By fighting large-scale efforts to create fake business profiles, we’ve stymied millions of attempts from fraudsters aiming to steal customers from legitimate businesses by crowding them out of search results.
Then there are content vandals, who may be motivated by social and political events or simply want to leave their mark online. For example, they post fake reviews or edit the names of places to send a message, and they add off-topic photos as pranks.
Content vandalism can be more difficult to tackle as it’s often random. For instance, a teenager who posts an off-topic photo to their high school’s listing on Maps as a joke or someone who left profanity in a nonsensical review.
Impeding content vandals comes down to anticipation and quick reaction. As places become more prone to vandalism, we adjust our defenses. For instance, last year we quickly modified our algorithms to preemptively block racist reviews when we observed anti-Chinese xenophobia associated with COVID-19. To avoid the spread of election-related misinformation, we limited the ability for people to edit the phone numbers, addresses and other information for places like voting sites. And we restricted reviews for certain places where we saw higher rates of policy-violating content, like schools in the U.S.
With the help of people and technology that closely monitor Maps 24/7, we’re able to take swift action against scammers, ranging from content removal and account suspension to litigation. In 2020 alone, we took the following actions to ensure the content you see in Google Maps is reliable:
Content contributed by our users is an important part of how we continue to make Google Maps more helpful and accurate for everyone. As more people share their local knowledge on Google Maps, we’ll continue to invest in the policies, technologies and resources needed to make sure information is reliable.
Our Maps 101 series goes behind the scenes to share how we help you navigate, explore and get things done every single day. Over the past 15 years, we’ve provided maps in more than 220 countries and territories and now surface helpful information for more than 200 million places. These efforts bring helpful local information to your fingertips in Google Maps and produce better Google Search results, helping you connect with nearby places and businesses.
In fact, Search results that show local places and businesses now drive more than 4 billion connections between customers and businesses every month. This includes more than 2 billion monthly website clicks and other connections, such as phone calls, directions, food ordering and reservations.
Today, we’ll share more about the innovations and investments that help build an accurate and up-to-date understanding of places for the billions of people looking for local information on Search and Maps.
Maximizing Street View with breakthroughs in AI
Street View imagery lets you virtually explore the world, and helps us accurately reflect local information about places in Maps and Search. We’ve travelled more than 10 million miles across 87 countries to capture this imagery and bring new information online—from unmapped roads to new businesses.
Applying artificial intelligence to our more than 170 billion Street View images helps us create high-quality maps faster than we could before. For instance, applying machine learning models to Street View imagery has improved the accuracy of one-third of the addresses in Google Maps and Search, resulting in more reliable maps as people look for a local business or navigate to a destination.
Text recognition in the natural environment is challenging—especially at scale. The average Street View photo has visual distractions like distortions, cluttered backgrounds with extraneous text and awkward viewpoints. After years of teaching machine learning models, our text recognition systems can tune out these distractions and detect business names and addresses even when they're handwritten on the side of a building or abbreviated. These models can understand a variety of languages across various scripts too, from Latin, Cyrillic and Thai to Chinese, Japanese and Korean.
In the last few years alone, processing imagery with AI has been one of the important ways we’ve been able to add more than 10 billion edits to our library of places, providing people with updated phone numbers, business hours and locations as they use Maps and Search.
Building data partnerships with authoritative sources worldwide
Thanks to partnerships covering more than 10,000 local governments, municipal agencies and organizations around the world, we're able to reflect the latest information in Search and Maps results and help local authorities reach even more people in their communities with important updates. This includes everything from bike lanes and road closures to the addresses of hospitals and food banks. Our teams vet each authoritative data source to make sure it’s accurate before it appears on Search and Maps.
Working with authorities around the world also helps us quickly gather and surface critical information. This year, these partnerships made it possible to make important updates relevant to COVID-19. When you search for “COVID test” on Search and Maps we now show you more than 17,000 COVID-19 testing centers across 20 countries and all 50 U.S. states. You can also see important details like if appointments are required, who can get tested and if there’s drive-through testing.
These details are crucial and accuracy is key, which is why we lean on authoritative sources to help us surface this information in Maps and Search.
A global community contributes to make Search and Maps better
To ensure our products reflect the real world as fast as it changes, we enable people everywhere to contribute their local knowledge. Every day, people make millions of contributions to Google Maps, like reviews, photos, address updates and more. And we’re seeing more people contributing than ever before. In the past 3 years, the number of reviews, ratings and photos people have added to Google Maps more than doubled.
With local details from people in Maps and Search, it’s easier to make more informed decisions. You can quickly find reviews when looking for a mechanic, see photos others have added for a park you’d like to explore, and find your convenience store’s new hours.
People’s reviews on Maps and Search make it easier to discover new places and learn about businesses nearby.
This year, as cities and countries instituted restrictions throughout the pandemic, many places temporarily closed or changed their operations. While businesses can indicate if they are open with their Google My Business listing, we’ve also made it easy for anyone to mark a business as open or temporarily closed on Search and Maps by simply suggesting an edit. Over the course of the pandemic, people have submitted millions of temporary closure and reopen reports, helping eliminate the uncertainty about which businesses are open and when.
Giving business owners free tools to connect with customers online
One of the most important ways we help local businesses succeed is by connecting them with customers online. Business owners can claim their free Business Profile and connect directly with customers across Search and Maps via phone calls, messages and reservations. They can also share accurate information about their business, including opening hours, services offered and contact information. And each month Google connects people with more than 120 million businesses that don't have websites, helping small business owners who aren’t online attract more customers.
Over the last five years, we’ve made more than a thousand improvements to Business Profiles, making it easier for merchants to connect with customers and share updates online. We recently made this even easier by adding new ways for merchants to view and update their Business Profile directly from Search and Maps.
With the pandemic causing daily disruptions worldwide, Google has helped businesses keep customers updated about everything from new services to adjusted store capacity and hours. Since the start of COVID-19, businesses made nearly 700 million edits to their Business Profiles, about double the number of changes made during the same time last year.
It’s easy for a business owner to update their Business Profile and engage with customers directly from Search and Maps.
Gathering local information in totally new ways
To help people find what they need in a world that changes by the minute, we’ve developed new ways to find and surface information.
For example, people tend to avoid crowded stores and long lines—and this has been especially true during the pandemic. Popular times and live busyness information help people see how busy a place tends to be at a specific time or at that very moment. Gone are the days of guessing the best time to go grocery shopping! We’re expanding live busyness information to millions of places globally and to include essential places like gas stations, grocery stores, laundromats and pharmacies.
Google’s conversational technology, Duplex, has helped us scale our ability to confirm updated information for places. Since the beginning of the pandemic, we’ve put Duplex to work making calls to businesses in eight countries—from New Zealand to the United States—to confirm things like opening hours or whether they offer takeout and delivery. This has helped us make millions of updates to business information that have been seen more than 20 billion times in Maps and Search.
Building the most helpful map of an infinitely detailed world
Beyond the technologies we’ve developed, our global operations teams play a role in nearly every aspect of mapmaking. They gather data, train machine learning models that help us index information from imagery, fix problems and evaluate authoritative data sources. They also build and maintain the automated systems that protect people from fake contributed content and even help small business owners set up Google My Business accounts.
All this to say, our work to organize the world's information and make it accessible and useful is never done. Given the pace of change, there’s never been a more important time for us to be helpful.
If you’ve ever been in a rush to grab a quick bite, you may know the pain that comes along with finding out that the restaurant you chose is packed and there’s nowhere to sit. Or maybe you need to pick up just one item from the grocery store, only to find that the line is out the door—derailing your plans and causing you unnecessary stress.
These problems were top of mind when Google Maps launched popular times and live busyness information—helpful features that let you see how busy a place tends to be on a given day and time or in a specific moment. This information has become a powerful tool during the pandemic, making it easier to social distance because you know in advance how crowded a place will be. Today, we’ll take a closer look at how we calculate busyness information, while keeping your data private and secure.
To calculate busyness insights, we analyze aggregated and anonymized Location History data from people who have opted to turn this setting on from their Google Account. This data is instrumental in calculating how busy a place typically is for every hour of the week. The busiest hour becomes our benchmark—and we then display busyness data for the rest of the week relative to that hour.
For example, say there’s a new ice cream shop down the block known for its homemade waffle cones ?. With Location History insights, our systems know that the shop is consistently most crowded on Saturday afternoons at 4 p.m. As a result, popular times information for the rest of the week will be displayed as “Usually as busy as it gets” when it’s approximately as busy as Saturday at 4 p.m.,“Usually not too busy” when it is much less busy, and “Usually a little busy” for somewhere in between. This data can also show how long people tend to spend at the ice cream shop, which is handy if you’re planning a day with multiple activities and want to know how much time to allocate at each place.
Popular times information shows you how busy a place tends to be
Google Maps’ popular times algorithms have long been able to identify busyness patterns for a place. With social distancing measures established and businesses adjusting hours or even closing temporarily due to COVID-19, our historical data was no longer as reliable in predicting what current conditions would be. To make our systems more nimble, we began favoring more recent data from the previous four to six weeks to quickly adapt to changing patterns for popular times and live busyness information–with plans to bring a similar approach to other features like wait times soon.
Busyness patterns identified by popular times are useful—but what about when there are outliers? Shelter in place orders made local grocery stores much more busy than usual as people stocked up on supplies. Warm weather can cause crowds of people to flock to a nearby park. And a new promotion or discount can drive more customers to nearby stores and restaurants.
Take the ice cream shop again. Say that, knowing that business is slow on Tuesdays, the shop owners decide to host a three scoop sundae giveaway on a Tuesday to promote their newest flavor—because everyone loves free ice cream! The promotion brings in more than double the amount of customers they typically see on that day and time. Gleaning insights from Location History data in real time, our systems are able to detect this spike in busyness and display it as “Live” data in Google Maps so you can see how busy the shop is right now—even if it varies drastically from its typical busyness levels.
Live busyness information shows you how busy a place is right now
Privacy is a top priority when calculating busyness, and it’s woven into every step of the process. We use an advanced statistical technique known as differential privacy to ensure that busyness data remains anonymous. Differential privacy uses a number of methods, including artificially adding “noise” to our Location History dataset to generate busyness insights without ever identifying any individual person. And if our systems don’t have enough data to provide an accurate, anonymous busyness recommendation, we don’t publish it—which is why there are times when you may not see busyness information for a place at all.
Google Maps is always thinking about ways to solve the problems you face throughout your day, whether they’re big (like getting around safely) or small (like quickly snagging your favorite scoop of ice cream). Check out the Maps 101 series for other under-the-hood looks at your favorite features, with more deep dives coming soon.
Google Maps helps you navigate, explore, and get things done every single day. In this series, we’ll take a look under the hood at how Google Maps uses technology to build helpful products—from using flocks of sheep and laser beams to gather high-definition imagery to predicting traffic jams that haven’t even happened yet.
We’ve gone behind the scenes to look at how we map the world, use imagery to capture the meaningful details around us, and all the ways contributed content and AI make Google Maps a more helpful tool—from planning your trip to deciding where to go.
Today, we’ll dive into how we are working to make sure everyone in the world has access to an address using our free, open-source digital address-making system called Plus Codes.
Addresses help us find people and places, and they help people and things find us. An address is also necessary to secure official documents and do things like open a bank account. However, several billion people either don’t have an address at all or they have one that doesn’t accurately identify the location of their home or business. Plus Codes offer a simple but powerful solution. Already, Google Maps provides millions of directions each month to people looking up a place with a Plus Code and this volume is rapidly growing.
Plus Codes use latitude and longitude to produce a short, easy-to-share digital address that can represent any location on the planet. For example, the Plus Code “W2GJ+JQ, Johannesburg” represents the main entrance to the Google office in Johannesburg, South Africa. Put this code into Google Maps or Google Search and you’ll be brought right to our front door in Johannesburg.
The Plus Code address for Google's Johannesburg office is W2GJ+JQ, Johannesburg
A Plus Code can easily be used where no addresses, street names or even streets exist today. Someone in an area without addresses no longer needs to give out complicated instructions to find a home or workplace—like “drive to the community center, turn left and look for the blue house with the red roof.” Now, they can simply share a short Plus Code and it immediately works.
Businesses and services that rely on navigating to peoples’ homes can simply enter the Plus Code into Google Maps and get directions instantly. Emergency services and humanitarian groups can more easily find people who need aid, locate people for vaccine programs and easily track health programs all with Plus Codes.
In the absence of street names and accurate addresses, how are Plus Codes created?
First, we divide the world along latitude and longitude lines to form a simple grid. The grid is labelled along the X and Y axis using a specific set of 20 alphanumeric characters {2,3,4,5,6,7,8,9,C,F,G,H,J,M,P,Q,R,V,W,X}. You’ll never see a vowel or characters like “1”, “L” and “l” in a Plus Code as we want to avoid confusion over the characters when writing them down and prevent any accidental word formations. And by using a carefully selected set of alphanumeric characters, Plus Codes can be used by anyone no matter what language you speak.
Each grid cell on the digital globe is then further divided, the X and Y-axes again labelled with the 20 characters above and the process repeated to build out a full Plus Code. In the case of the Google Johannesburg office this would result in a full Plus Code of “5G5CW2GJ+JQ”.
Since a full Plus Code might not be easy to recall, you can conveniently drop the first four characters of the code if you know the area you are in, just as we drop area codes on telephone numbers when already in the area. In this case, if I know I am in Johannesburg the Plus Code for the Google office can be shortened to “W2GJ+JQ, Johannesburg.”
Depending on the number of characters included in the code after the ‘+’ sign, the code can be even more specific. For example a Plus Code with two characters after the ‘+’ sign represents an area of approximately 13m x 13m, about the size of a half a basketball court. Adding an additional character reduces this size to approximately 3m x 3m, providing an exact address for a sidewalk vendor who may not even have a storefront.
And this might go without saying, but Plus Codes are named after the ‘+’ sign that is one of their key characteristics. This sign is used to help people and our digital applications recognize the code as a Plus Code.
Plus Codes in Sao Paolo, Brazil
Providing conventional (non-digital) addresses to communities at scale can be complicated and expensive for local and national governments, often taking years to set up and become useful. With Plus Codes, a village, town, city or even country can quickly and efficiently set up an addressing system. And unlike conventional addressing projects, once a Plus Code address is created it is immediately usable on platforms such as Google Maps and anywhere else that recognizes Plus Codes both online and offline. This means that new services (both digital and non-digital) are more readily available to traditionally underserved communities that lack proper addresses.
While there are other digital address-making solutions, they’re often proprietary or must be commercially licensed, which can mean unnecessary costs, complications and longer term uncertainty for businesses and governments. These solutions also have challenges with universal recognition and adoption, as they are generally not open source or freely available.
Here’s a taste of the positive impact we’ve seen Plus Codes deliver.
We recently introduced a refreshed Plus Codes icon to make it more recognizable. If you’d like to learn more about Plus Codes, how to use them and how they’re being used, visit maps.google.com/pluscodes.
