AutoInvent
Turn abandoned patents
into your own filing
Get Started
Patent drawing for Automatic updating of trust networks in recommender systems
US 20,130,097,184 A1
Computing US 20,130,097,184 A1 Expired

Automatic updating of trust networks in recommender systems

This invention describes a way for a computer system to manage a network of trusted connections, like friends or experts, to help recommend things. When a user gets a recommendation based on this network and gives feedback, the system automatically adjusts how much it trusts the people who made the recommendation. Specifically, it uses this feedback to suggest new connections, like 'friends,' to the user.

Why it matters: Since 2012, advancements in machine learning, particularly graph neural networks and sophisticated recommendation algorithms, offer more powerful and efficient ways to process 'judgment data' and dynamically update 'trust weights' within complex social networks. These technologies could significantly enhance the accuracy and scalability of identifying and suggesting new connections.

Status
ExpiredProtection ended and was never renewed
How hard to build
SpecializedComplex software system, algorithms, 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.