Ingestion and retrieval of dynamic source documents in an automated question answering system

This invention describes a computer system that creates a searchable database from various documents. For each question and answer it finds, it records not just the answer, but also exactly where that answer came from in the original document. When someone asks a question, the system looks up the answer's location and retrieves it directly from the most up-to-date version of the original document.

Why it matters: Filed before the widespread adoption of powerful large language models, the task of automatically generating question-answer pairs from documents was significantly more challenging. Today, LLMs excel at this content generation and natural language understanding, making the initial indexing and dynamic retrieval described here much more feasible and efficient.

Status: Not in forceListed as no longer active. The specific reason is not in the record we hold.
How hard to build: SpecializedComplex software system, natural language processing, indexing.

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