System and method for suggestion mining

This invention describes a way to automatically find suggestions for improvement within large collections of text, such as customer reviews. It works by first setting up a specific vocabulary for a topic (like a product or service) and a list of words related to "suggestions." Then, it scans the text, labels words that match these lists, and applies predefined grammatical rules to identify complete phrases that express suggestions for improvement.

Why it matters: Filed before the widespread adoption of deep learning in NLP. Large Language Models (LLMs) can now perform semantic understanding and pattern identification with significantly less manual rule-crafting and more robustly.

Status: Not in forceListed as no longer active.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, structured data management

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