Query Processing with Machine Learning

This invention describes a method for a database to run machine learning predictions directly within its system. It works by analyzing a prediction request and the machine learning model together, creating a combined plan, and then optimizing that plan to figure out what the database should do and what its built-in machine learning part should do. The claims narrow this to a system where the machine learning part is built right into the database, and it uses a specific method of analyzing the query and model as a single graph for optimization.

Why it matters: The short time gap means no significant technological shifts have occurred to simplify this complex integration. The core challenge remains the substantial engineering effort to deeply integrate ML runtimes and query optimizers within a database system.

Status: Under examinationA pending application. It has not been granted, and it has not been abandoned.
How hard to build: SpecializedDatabase engine, ML runtime, query optimizer software

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