Architecture and processes for computer learning and understanding

This system helps computers learn and understand stories by first trying to make sense of them using pre-defined knowledge structures. It then asks humans questions about the story to check its understanding. The human answers are used to correct and expand the computer's knowledge, even allowing it to create new knowledge structures. The system also uses a confidence score to identify when its understanding contradicts known facts.

Why it matters: Filed before large language models (LLMs) could perform sophisticated semantic analysis and generate human-like questions. These capabilities, central to the invention, are now standard in LLMs, making the core processes significantly more achievable.

Status: Not in forceListed as no longer active. The specific reason is not in the record we hold.
How hard to build: SpecializedHeavy software system, NLP, knowledge representation, human interaction

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