Neural networks trained using event occurrences

This invention describes a computer system that trains artificial intelligence models by providing them with details about when past events happened and their chronological sequence. By learning from these time-based patterns, the AI can better understand and interpret new information, especially from written text, to perform specialized tasks like financial analysis. The system specifically focuses on extracting these event timelines from textual data.

Why it matters: Filed before Large Language Models (LLMs) could easily extract and reason about event timelines from text. Modern LLMs simplify the data preparation and enhance training effectiveness for temporal NLP.

Status: Under examinationA pending application. It has not been granted, and it has not been abandoned.
How hard to build: SpecializedHeavy software system, AI expertise

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