Google Maps is constantly evolving to provide you with the most up-to-date information about your world. This includes using AI and images, like what we’ll look at in this article on how Google uses photos and AI for their map updates.
Business hours are automatically updated.
In recent years, businesses have seen many changes, including continually adjusting working hours in response to changing pandemic-related regulations. Researchers created a machine learning model that detects whether business hours are likely incorrect and adjusts them quickly using AI-generated forecasts to keep up with the rapid speed of change.
Google has revealed how it attempts to keep business hours updated on Google Maps by utilizing artificial intelligence, including its restaurant-calling Duplex technology. The company claims it will update the information in Maps if it is confident enough in the AI’s forecast of what a business’s hours should be.
Consider the case of Liam’s Lemonade Shop. To begin, their computers consider a variety of criteria, like when Liam last updated their company page, what we know about competing businesses’ hours, and the shop’s Popular Times data, which analyses location patterns to show when it is busiest. Liam’s business hours are likely out of current since it looks that his company profile hasn’t been changed in over a year, and his peak hours are often Thursday afternoons — even though Google Maps claims it’s closed at that time.
So, where do we go from here? To determine the most accurate business hour forecast, Google’s algorithms look at the business hours of other local lemonade shops, information from Liam’s website, and Street View photographs of Liam’s storefront that look especially for business hour signage. Simultaneously, they solicit the assistance of the Google Maps community — including Local Guides and even the company owners themselves via their Google Business Profile — to confirm the facts they projected. They utilize Duplex conversational technology to contact companies like Liam’s and inquire about their hours directly in Argentina, Australia, Chile, France, Japan, Mexico, New Zealand, Peru, and the United States. They expect to update the hours for over 20 million companies worldwide in the next six months using this innovative AI-first technique, allowing you to know exactly when your favorite store, restaurant, or cafe is open for business.
Road data that is accurate and represents reality
Researchers are also working with other methods to use pictures to update other valuable data. For example, they are launching a third-party imagery pilot in the United States to allow you to view the most up-to-date speed limit information in your area, which may help you stay safe while driving. The following is how it works:
Say The speed limit information for a particular roadway needs to be updated according to Google’s systems. They can request a snapshot of a specific road length with a speed restriction sign from third-party photography partners who currently gather roadway images to enhance delivery routes. If the partner has this snapshot, Google will detect the sign in the picture, extract the updated speed limit information, and update Google Maps using a combination of AI and our operations team.
While it’s unsurprising that Google employs AI to solve these issues, it’s fascinating to see how many interconnected systems are involved. There’s computer vision, pattern recognition in location trends, and analyzing data about similar locations (which, of course, also requires figuring out what the similar areas are), all to keep up with how frequently businesses change their hours and ensure it knows the speed limit on specific stretches of road.
Prathamesh Ingle is a Mechanical Engineer and works as a Data Analyst. He is also an AI practitioner and certified Data Scientist with an interest in applications of AI. He is enthusiastic about exploring new technologies and advancements with their real-life applications