Techniques for processing neural queries

This invention outlines a system that builds and uses digital knowledge units, called "knowledge neurons," to answer questions. It works by extracting information from various web sources and learning key facts using machine learning, which are then stored as these knowledge neurons. When a question is received, the system consults these neurons to provide a response, and it can also update its knowledge based on feedback. The core idea described in the claims is a computer method for querying a repository of these knowledge neurons, which were specifically derived from web documents using a machine learning model.

Why it matters: Filed before the widespread capability of large language models (LLMs) and vector databases. These modern AI tools can now more effectively and efficiently build, query, and update the "knowledge neurons" from web data as described in the claims, making the core process significantly more feasible.

Status: Not in forceListed as no longer active. The specific reason is not in the record we hold.
How hard to build: SpecializedSoftware logic, machine learning models, data pipelines

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