Vehicles US 12,559,136 B2 Not in force

Systems and methods for graph-based AI training

This invention describes a virtual assistant that learns from how a user interacts with a digital workspace. It records these actions, converts them into a structured network of connected information (a graph), and then uses this learned structure to suggest new actions or ways to interact with the workspace.

Why it matters: The patent's classifications strongly suggest an application in autonomous vehicle technology, where graph-based AI for robust planning and decision-making is rapidly advancing. While the claims describe a general virtual assistant, it could now be refocused to assist in the complex design or operational tasks of autonomous vehicles, leveraging the core graph-based training.

Status: Not in forceListed as no longer active. The specific reason is not in the record we hold.
How hard to build: SpecializedSoftware logic, AI model training

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.

+10