Using communicative discourse trees to detect distributed incompetence

This invention describes a computer system that analyzes conversations by building a special diagram called a communicative discourse tree from what people say. It then uses a trained program to look at specific parts of this tree, like individual phrases and how they relate, to detect if the group is collectively showing a lack of understanding or making poor decisions. If detected, the system can then generate an automated response.

Why it matters: Filed before large language models became widely capable of sophisticated discourse analysis and nuanced conversational understanding. These models could now significantly simplify building the communicative discourse trees and training the predictive model.

Status: Not in forceListed as no longer active. The specific reason is not in the record we hold.
How hard to build: SpecializedNatural Language Processing, Machine Learning models

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