Populating a knowledgebase of an expert system

This invention describes a way to automatically build the knowledge base for an expert system. It works by taking existing business processes, which define how a business interacts with users, and translating their components (like inputs, outputs, and actions) into natural-language rules. These rules are then stored as interconnected graphs within the expert system, with classifications assigned to help organize them. The claims narrow this to rules specifically for generating natural-language replies to user questions or formulating natural-language questions for the user.

Why it matters: Filed before the widespread adoption of large language models (LLMs), which now excel at understanding and generating natural language. The manual translation of business processes into natural-language rules and the formulation of natural-language replies or questions, as described in the claims, could be significantly automated or enhanced by current LLM capabilities.

Status: Not in forceListed as no longer active. The specific reason is not in the record we hold.
How hard to build: SpecializedSoftware logic, expert system, knowledge representation

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