Adjustment of document relationship graphs

This invention describes a software system that modifies how documents are related to each other in a large collection. It works by letting a user specify a key phrase, which the system then expands to find related terms. These expanded terms are used to adjust the similarity scores between documents that contain them, and the updated relationships are shown visually in a web browser.

Why it matters: Filed before advanced large language models could perform sophisticated semantic analysis and n-gram expansion with greater accuracy and scale. The computational resources and NLP techniques available today make building and manipulating such complex document relationship graphs significantly more efficient and powerful.

Status: Not in forceListed as no longer active.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

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