Generative graph-enhanced information retrieval

This invention describes a system that helps find information by first breaking down a user's question. It then matches parts of that question to specific sections within documents and links those sections to a knowledge graph. A smart AI model then uses this link to create a query for the graph, finds relevant connections, and presents the results as a clear path. The system specifically uses the AI model to help parse the initial query based on a graph template and links document parts to the graph using a unique identifier and entity type.

Why it matters: Filed just as generative AI models were becoming widely capable, their ability to understand complex queries and generate structured outputs like graph queries has advanced significantly since 2023, making this approach more feasible and powerful.

Status: Not in forceListed as no longer active. The specific reason is not in the record we hold.
How hard to build: SpecializedGenerative AI models, graph database, embedding models, software 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