Microsoft and Shell team up to build AI into gas stations
AI is now helping bust people who smoke at gas stations.
Microsoft and Shell are collaborating on a pilot project to integrate artificial intelligence tools into gas stations, starting with one in Thailand and one in Singapore. The Shell stations are using video cameras and a device inside the station that runs Microsoft’s cloud intelligence program — Azure IoT Edge — to catch people smoking cigarettes at the station. Smoking poses serious safety risks because it could cause a fire or explosion.
The cameras send frames that likely have cigarettes in them to the Microsoft Azure cloud, which taps AI to identify if someone is smoking and can then send an alert to the station manager.
‘Each of our retail locations has maybe six cameras and captures something in the region of 200 megabytes per second of data. If you try to load all that into the cloud, that quickly becomes vastly unmanageable at scale,’ said Daniel Jeavons, general manager for data science at Shell, in a blog post Monday. ‘The intelligent edge allows us to be selective about the data we pass up to the cloud.’
The team also plans to build AI into other areas at Shell, such as offshore drilling sites and refineries. AI, for example, can help predict when equipment parts need maintenance and alert employees to fix or replace them.
‘The new possibilities in working with data over the last few years are unlocking amazing opportunities in all aspects of what we do in the company,’ said Yuri Sebregts, executive vice president for technology and chief technology officer at Shell, in the same blog post. ‘In one example, we can now forecast in many cases when a compressor is at risk of failure 24 or 48 hours in advance, which was not easy to do before despite all the instrumentation you have on these large and complex machines.’
In addition, the two companies are working together on how to drill more efficiently using AI and how Shell’s employees around the world can communicate better and in a more personal manner.