How a System Ranks Content Based on Friend Recommendations

This patent describes a system that recommends content, like TV shows, by tracking how many friends accept social media recommendations and then ranking content based on how fast those acceptances are growing.

What it covers

The system tracks how often users accept social media recommendations for various content items, such as TV shows or movies, over different periods (Claim 1). It then creates a list of these content items, ordering them based on how quickly the number of accepted recommendations is changing (Claim 1). For example, if a new show suddenly gets a lot more accepted recommendations from friends, it would move higher on the list. When a user selects an item from this list, the system makes that content available to them (Claim 1). The system can also send a social media recommendation to a friend if a user is watching something, and grant a 'recommendation credit' to the user if their friend accepts it (Claim 7, Claim 9).

What it doesn't cover

• —Recommendations not based on 'social media recommendations' (e.g., editorial picks or recommendations based solely on individual viewing history).
• —Ranking content purely by the total number of recommendations, rather than the 'rate of change' in accepted recommendations (Claim 1).
• —Systems that do not involve sending a 'list of the content items' ordered by a specific metric (Claim 1).
• —Recommendations that do not involve a 'friends list' or social network connections (Claim 7).
• —Content delivery systems that do not track or respond to social media recommendations at all.

The clever bit

The novelty lies in ranking content not just by the total number of social media recommendations accepted, but by the *rate at which those acceptances are increasing* within a social network. This prioritizes rapidly trending content over merely popular content, making recommendations feel more current.

Why it matters

This patent focuses on leveraging social proof and network effects for content discovery. It aims to make content recommendations more dynamic and relevant by highlighting what's gaining traction among a user's social circle, which can drive engagement and viewership for streaming services. This approach helps users find new content that is actively trending among their peers.

Real-world examples

• 1.Social features in streaming services like Netflix or Hulu
• 2.Content sharing features on platforms like Facebook Watch
• 3.Gaming platforms that show what friends are currently playing
• 4.Recommendation sections on media aggregators that highlight trending items