# 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. - **Patent:** US 20230245158 - **Original title:** Content Recommendation System - **Owner:** Comcast Cable Communications - **Status:** Active - **Times cited:** 0 - **Field:** consumer_electronics, software, telecommunications, ai_ml ## What it does 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 does NOT 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. ## 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 ## 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. ## Frequently asked questions ### What does How a System Ranks Content Based on Friend Recommendations cover? 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. ### Who owns patent US 20230245158? This patent is owned by Comcast Cable Communications. ### When does this patent expire? This patent is expected to expire on January 5, 2043, when the invention enters the public domain. ### What problem does this patent solve? 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. ### What does this patent NOT cover? Recommendations not based on 'social media recommendations' (e.g., editorial picks or recommendations based solely on individual viewing history). **Full plain-English explainer:** https://patentbrief.org/patent/us/20230245158/content-recommendation-system **Original patent:** https://patents.google.com/patent/US20230245158 --- _Source: PatentBrief — https://patentbrief.org. Patent facts are from public records; the plain-English explanation is PatentBrief's._ ## Related patents Semantically similar inventions in the PatentBrief corpus: - [How Eventbrite Recommends Events Based on Your Social Network](https://patentbrief.org/patent/us/8700540/facebook-messenger) — A system that suggests events to you by analyzing your social media connections and your past attendance history to see what your friends are doing. - [How a Recommendation System Learns What You Really Want to Watch](https://patentbrief.org/patent/us/12118030/dynamic-feedback-in-a-recommendation-system) — This patent describes a media recommendation system that creates a unique user profile, uses it to pick a starting point, and then dynamically adjusts a list of suggestions based on what you've already watched and your real-time feedback. - [How Computers Automatically Tag Movies and Shows Better](https://patentbrief.org/patent/us/12135756/content-recommendation-system-with-weighted-metadata-annotations) — This patent describes a system for automatically improving how movies, TV shows, and other media are tagged with descriptive labels by comparing them to similar content using a special ratio. - [How Facebook Ranks Search Results Based on Your Friends' Activity](https://patentbrief.org/patent/us/8914392/facebook-events) — A method for ranking search results by prioritizing links that your social network friends have clicked on previously. - [Predicting User Interests Based on Who Looks at Whose Profile](https://patentbrief.org/patent/us/8311950/detecting-content-on-a-social-network-using-browsing-patterns) — A method for predicting what a user might be interested in by analyzing the web of connections created when people view each other's social media profile pages.