This computer program helps find other users who might be interested in items similar to one a user has already shown interest in. Instead of directly comparing items, it looks at how many users have interacted with both the original item and other items over time. It also considers how the features of these items relate to each other, again based on user interactions. The program then identifies the users linked to these similar items.
Why it matters: The specific correlation methods described, relying on user interaction data over time and attribute relationships, are now more efficiently implementable due to advances in machine learning platforms and cloud data processing since 2019.
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