Text indexing and passage retrieval

This invention describes a way to search within documents by breaking them down into smaller sections, called passages. It creates an index for these passages, noting keywords and extra details like titles or related concepts for each section. When you search, the system looks through this passage index and presents the most relevant sections, rather than whole documents. The core method relies on a specific, pre-defined way to break down documents into these passages.

Why it matters: Filed before the widespread adoption of advanced NLP and large language models, which can now significantly enhance the "predefined document structure parsing algorithm" and the generation of rich "annotations" (like concept identifiers or synonyms) mentioned in the claims. The core idea of passage retrieval is now a fundamental component of modern AI systems like RAG.

Status: Not in forceListed as no longer active. The specific reason is not in the record we hold.
How hard to build: SpecializedSoftware logic for parsing, indexing, and retrieval

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