From Beijing to Barcelona to Buenos Aires, startups like Uber Eats, Deliveroo, Swiggy, Zomato and Go-Jek are revolutionizing urban food delivery. In the first quarter of 2018, food delivery accounted for 13 percent of Uber trips worldwide, and that figure is increasing.
Urban food delivery giants in China are Meituan-Dianping, Ele.me, and DiDi Waimai; while startups like Shansong (FlashEx) and New Dada are also doing local and short-distance food delivery. Biggest of the bunch is Meituan, which reported revenue of US$2.3 billion in the first half of 2018, up a whopping 90 percent from 2017. At last month’s AI Developers Conference (AI NEXTCon), Meituan’s AI-powered logistics team lead Renqing He shared his thoughts on recent developments in urban food delivery and the application of machine learning in the field.
Instant food delivery — food arriving in 60 minutes or less — is an integration of online e-commerce transactions and offline logistics delivery into a system, with connecting relationships between customers, merchants, delivery drivers, and the platforms themselves.
In order to achieve high efficiency, improve user satisfaction and keep costs low, Meituan has developed an AI-powered “Super Brain” for its food delivery services. The system uses in-depth sensing and problem understanding to handle complex real-world situations, quickly make decisions, and generate accurate predictions.
Super Brain boasts high accuracy, fine granularity and strong robustness to provide analysis, predictions and solutions for a wide variety of time, location, weather, and traffic conditions; as well as for unexpected changes and emergencies. He says the system is also able to acquire high-quality offline data, and deal with noisy, incomplete or redundant data.
The Super Brain platform integrates real-time computation, offline data processing and machine learning to perform deep sensing and build its understanding of the world. By monitoring the trajectories of delivery drivers, the system collects delivery time data for each order then performs data smoothing and regression estimations. Abundant reliable data helps to improve the AI system so that it can best predict order arrival times and make better decisions regarding order dispatching, pricing, logistics network design, etc. The system also performs accurate and precise address resolution while safeguarding privacy.
Delivery drivers are one of Super Brain’s main data sources. Sensors integrated with smartphones collect information used to solve many practical problems in urban food delivery. GPS follows riders’ outdoor trajectories; geo-fencing, WiFi and Bluetooth can monitor them indoors; while motion sensors detect whether a delivery person is walking or riding. All these techniques are widely used and inexpensive.
He says that today’s popular map software may suggest routes that are not the best real time option for food delivery drivers. Meituan drivers report after each delivery, helping Super Brain collect additional highly dense and reliable location data to augment the information provided by map companies, customers and merchants. Leveraging customized maps and location-based service (LBS) systems, Super Brain provides drivers the best routes for food order delivery.
The Meituan AI logistics team has made significant progress over the past three years: average delivery time has been shortened from one hour to 30 minutes, while its intelligent dispatch system path calculation capability has climbed to a rate of 2.9 billion times per hour. With the urban food delivery market showing no sign of slowing down, Meituan plans to expand Super Brain’s data collection sources while using AI to improve its updating and information integration to deliver an even better experience to diners.
Source: Synced China
Localization: Tingting Cao | Editor: Michael Sarazen