Devices, Systems, and Methods that Observe and Classify Real-World Activity Relating to an Observed Object, and Track and Disseminate State Relating the Observed Object.

This invention describes a device that watches a machine, like a washing machine, to figure out what it's doing and its current status. It can do this in two specific ways: either by using a triple-axis accelerometer to measure vibrations and analyze them with a Fourier transform, or by using an imaging sensor to take pictures and process them with a deep neural network. The device then uses this information to update a model of the machine's state and can send alerts, for example, when the laundry is done.

Why it matters: Since 2020, deep learning models and edge AI capabilities have advanced significantly, making it easier and more efficient to deploy complex neural networks for real-time observation and classification on embedded devices. This could simplify the software development and hardware requirements for the deep neural network component.

Status: Not in forceListed as no longer active. The specific reason is not in the record we hold.
How hard to build: SpecializedDeep neural network, signal processing, custom electronics

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