Providing question and answers with deferred type evaluation using text with …

This invention describes a computer system that answers questions by first figuring out what kind of answer is needed (like a date or a person's name). While it's waiting for that, it also finds possible answers. To do this, the system looks through documents to find lists, then pulls out specific items and their categories from those lists. It then checks if a potential answer matches the required category for the question, scoring how well they fit.

Why it matters: Filed before large language models (LLMs) became prevalent. While the claims focus on extracting entity-type pairs from structured lists, modern LLMs can perform similar entity and type extraction from much broader text types, potentially simplifying or enhancing the data preparation step.

Status: Not in forceListed as no longer active.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, complex NLP logic

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