Topic-influenced document relationship graphs

This is a software system designed to help you explore how documents are connected. It works by letting you pick a specific subject, and then it adjusts how strongly documents appear related based on whether they discuss that chosen subject using particular word patterns. The system figures out these subject-specific word patterns either by analyzing probabilities of words appearing with a topic, or by learning from examples using artificial intelligence.

Why it matters: In 2017, building robust topic models and semantic analysis systems required significant expertise and computational resources. Today, the advent of powerful pre-trained large language models and advanced NLP frameworks makes the 'obtaining a topic vector' and 'semantic analysis' aspects significantly more accessible and performant, potentially simplifying the core technical challenge.

Status: Not in forceListed as no longer active.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, natural language 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.

This one

+10