Generative artificial intelligence knowledge graph engine in an item listing system

This invention describes a smart system for recommending products in an online store. It uses a special AI, like a large language model, to build and manage a "knowledge graph" – essentially a map of products and how they relate to each other. When you look at a product, the system uses this map to find other related products, then ranks them to show you the best ones, specifically focusing on individual product instances with their unique features.

Why it matters: Filed when generative AI was emerging, the capabilities of large language models for knowledge graph generation and complex relationship inference have significantly matured and become more accessible since 2023. This makes the core AI engine more powerful and efficient to implement today.

Status: Under examinationA pending application. It has not been granted, and it has not been abandoned.
How hard to build: SpecializedGenerative AI models, knowledge graph engine, ranking algorithms

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