In 2016, Amazon surprised the world by testing a smart mini marketplace. Using a technique called Just get outwhere customers simply entered stores, picked up the products, and left without having to pay immediately.
To enter, all you have to do is identify yourself using your smartphone. At the end of purchases, and when passing through the sensor located on the facility’s door, the balance is automatically deducted from the registered card.
But the company now It announced the end of the Just Walk Out service and its replacement with another technology A little less bold. Furthermore, the advertisement was accompanied by a complaint: This intelligent system actually relies on human employees To work properly.
Keep an eye on your purchases
According to a report on the website the information, Amazon had a team of about a thousand employees in India to review and approve Just Walk Out purchases. In all, about 70% of sales were scanned by humans, who analyzed video images from cameras in stores to ensure the sensors were reading correctly.
These contract employees were not disclosed as part of the system and were described by the company as “Data professionals associated with machine learning”It works in conjunction with the artificial intelligence system.
The Just Walk Out service should only continue to operate in some Fresh stores in the UK and small markets in the Amazon Go family in the US.
The Dash Cart has sensors that can be read instantly and also helps you weigh fresh produce. (Image: Disclosure/Amazon)source: Amazon
In other locations, it will be replaced by a barcode reader built into the cart. This feature is called Dash Cart and quickly records each item purchased, as well as the checkout process without the need for a cashier.
What does Amazon say?
In a statement sent to GizmodoAmazon confirmed replacing technologies with smart carts in most facilities. despite of, It counters that the vast majority of purchases are analyzed by humanswithout detailing what the correct ratio is.
Also according to the brand, The role of the human staff was to “continuously improve” the machine learning model used in the system.
“Friendly zombie guru. Avid pop culture scholar. Freelance travel geek. Wannabe troublemaker. Coffee specialist.”
