Baidu and KFC’s new smart restaurant suggests what to order based on your face – 12/23/2016
Baidu is demonstrating some of its most recent tech advancements in novel ways, including a partnership with KFC China (yes, the fried chicken KFC). The search giant sometimes referred to as the ‘Google of China’ partnered with KFC to open a new “smart restaurant” in Beijing, which employs facial recognition to make recommendations about what customers might order, based on factors like their age, gender and facial expression.
The restaurant also offers up augmented reality games via table stickers, but these are also deployed at 300 other KFC locations in Beijing. The facial recognition tech is unique to this one location, though Baidu has previously worked with KFC on another type of smart restaurant at a pilot location in Shanghai, where a robot customer service agent can listen for and recognize orders made by customers using natural language input.
Baidu’s tech in this new restaurant, however, is all about guessing what you want before you can even ask; image recognition hardware installed at the KFC will scan customer faces, seeking to infer moods, and guess other information including gender an age in order to inform their recommendation. Baidu says in a press release that the system would tell “a male customer in his early 20s” to order “a set meal of crispy chicken hamburger, roasted chicken wings and coke for lunch,” while “a female customer in her 50s” would get a recommendation of “porridge and soybean milk for breakfast.”
Customers might not love the implications of the suggestions the system comes up with, but these are just suggestions, after all. And the setup also has built-in recognition, so if you’re a return customer, it can ‘remember’ what you ordered before and suggest your past favorites. Of course, the idea of a fast food restaurant retaining my image for recognition purposes, tied to an actual order history, is more than a little unnerving. But then again, KFC China is really damn good – better than its North American counterpart...
Date of Publication: 12/23/2016
[ visit site ]