Generating recommendations by using communicative discourse trees of conversations

This invention describes a computer program that provides recommendations during a conversation in a natural way. It works by detecting a significant change in emotional tone between two things a person says. When this happens, the program identifies a key topic from the second statement, finds relevant information that addresses the person's underlying point, and then inserts a recommendation related to that topic into the conversation. The claims specify that this process involves building detailed 'discourse trees' to analyze the logical structure and rhetorical relationships within the conversation.

Why it matters: Filed in 2023, this invention predates the widespread integration and advanced capabilities of large language models (LLMs) that have become prominent by 2026. LLMs can now perform many of the complex natural language understanding, sentiment analysis, and recommendation generation tasks described, potentially simplifying or enhancing the explicit discourse tree construction.

Status: Not in forceListed as no longer active.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, discourse analysis, recommendation engine

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