Google: AI to update business hours for out of date on Google Maps

Google has shared how it's employing artificial intelligence, including its restaurant-calling Duplex tech, to try and maintain business hours up to date on Google Maps.

The company says that if it is assured enough in the AI's prediction of a business's hours, it will correct the information in Maps.

Google outlines the various factors it's AI analyzes to resolve whether it should do these updates. First, it examines when the business profile was earlier updated, other similar shops' hours, and Popular Times data to decide how likely the hours are incorrect. For example: if Google sees that many people visit the shop when it's supposedly closed, that may be a red flag.

Google's post states that its AI looks at even more data. If it chooses, the hours should be updated. For instance, it'll consider details from the business's website and can even scrape street view pictures to try and figure out when the company is open. Google states it'll also check with actual humans, including Google Maps users and business owners, to confirm the AI's predictions — the company says it will even employ Duplex in some countries to ask firms about their hours directly.

Google will "only publish business hours when we have confidence that they're accurate." So if the AI thinks the hours may be incorrect but doesn't hold a reliable prediction, it adds a note that the hours may have been modified.

 Google tries to alert users of potentially inaccurate info, even if it can't provide the accurate information itself. Image: Google

Park also said that Google doesn't explicitly tell users when hours were updated by its AI and explained that AI is used everywhere else in Google Maps. So it seems like Google's pretty bullish on its AI-driven approach. In its post, the company states it's "on track to update the hours for over 20 million businesses around the globe in the next six months."

Google also says it's piloting another use of AI in Maps to help keep speed limits up to date. For example, in the US, it'll try to notice if its partners have taken images of stretches of road that contain speed limit signs and will have AI help its operations team identify the sign and the speed limit posted on it.

While it's no surprise that Google's using AI for these problems, it is interesting to see how many interlocking systems are involved. For example, there's computer vision, pattern recognition in location trends, and data about similar locations, all to quietly try to keep up with how often businesses change their hours and make sure it knows the speed limit on specific stretches of road.