This invention describes a system that answers user questions by consulting a knowledge graph. Its key feature is checking the electronic device asking the question to determine if it's authorized to access specific, private sections of the knowledge graph. If authorized, the system uses that restricted information to formulate an answer, potentially prioritizing it over publicly available data.
Why it matters: Filed before large language models (LLMs) became widely capable of sophisticated natural language understanding and query formulation. LLMs now make the core task of interpreting queries and generating answers from a knowledge graph significantly more robust and easier to implement than in 2018, while the need for controlled access to sensitive data within such systems has grown.
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