AutoInvent
Turn abandoned patents
into your own filing
Get Started
Patent drawing for Neural network-based semantic information retrieval
US 11,900,064 B2
Computing US 11,900,064 B2 Expired

Neural network-based semantic information retrieval

This invention describes a smart search system that lets you ask questions in everyday language and find answers or specific information across all your digital documents, no matter their original format (like PDFs, Word files, or spreadsheets). It works by understanding the meaning of your question and the content of your documents, specifically by analyzing sentences and their context to create a semantic representation. The system is designed to provide a unified way to search through all your company's information assets.

Why it matters: Filed before the widespread availability and advanced capabilities of large language models (LLMs) and retrieval-augmented generation (RAG) systems. These technologies, maturing significantly since 2021, now offer powerful, off-the-shelf components for semantic understanding and cross-document information retrieval, making the system described more readily implementable and effective.

Status
ExpiredProtection ended and was never renewed
How hard to build
SpecializedSoftware logic, neural networks, data processing

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.