Graph based re-composition of document fragments for name entity recognition under exploitation of enterprise databases

This invention describes a computer system designed to extract specific pieces of information, like names or product details, from business documents. It operates by breaking down the document's text into segments and then comparing these segments against a database of known entities and their characteristics. The system then identifies the best match for each text segment, specifically for documents representing physical business objects.

Why it matters: In 2009, accurately recognizing complex entities from unstructured text was a significant challenge, often requiring extensive manual rule creation. Today, advancements in machine learning, particularly large language models and transformer architectures, offer vastly improved capabilities for natural language understanding and entity recognition, making the core task much more robust and scalable.

Status: Not in forceListed as no longer active. The specific reason is not in the record we hold.
How hard to build: SpecializedSoftware logic, database, NLP algorithms

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