Cart-based shopping arrangements employing probabilistic item identification

This invention describes a smart shopping cart system that automatically identifies items as a shopper places them in the cart. The cart uses sensors to detect its location within the store by receiving signals from store-wide emitters, and also gathers data from items. This item data is processed by a trained system, which, combined with the cart's location, helps determine the item's identity and adds it to a running tally.

Why it matters: Filed before the widespread maturation of efficient, real-time AI models for object recognition on edge devices. The computational demands for probabilistic item identification and classifier refinement, especially on an FPGA, are now more achievable with current AI hardware and software optimization techniques.

Status: Not in forceListed as no longer active. The specific reason is not in the record we hold.
How hard to build: SpecializedEmitter devices, cart sensors, FPGA, software system

3 AI reinvention directions for this patent

See all three

AI gives you a few directions you could take this. Pick one, and we check whether your version is different enough to patent, then write the filing.

Reinvent this with AI

Where this one came from

Every morning we go through millions of abandoned patents and pick out 15 worth your time. This was one of today’s.

This one

+10