Semantic representation and realization for conversational systems

This invention describes a way for a conversational AI system to understand and remember what's happening in a conversation. It builds a single, evolving map of the conversation and relevant information from its databases. As the user talks, the system figures out the meaning of each new sentence, adds it to the map, and then uses this updated map to decide what to show the user in its interface, highlighting both new and relevant old information.

Why it matters: Filed before the widespread availability of highly capable large language models (LLMs). These LLMs could significantly streamline the complex task of determining semantic meaning and converting it into structured concept graphs, which was a major engineering hurdle in 2020.

Status: Not in forceListed as no longer active. The specific reason is not in the record we hold.
How hard to build: SpecializedNatural language processing, graph database, UI 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