# How Computers Automatically Tag Movies and Shows Better > 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. - **Patent:** US 12135756 - **Original title:** Content recommendation system with weighted metadata annotations - **Owner:** Comcast Cable Communications - **Granted:** 2024 - **Status:** Active - **Times cited:** 0 - **Field:** software, telecommunications, consumer_electronics, ai_ml, ecommerce ## What it does This system helps a computing device automatically assign or update descriptive labels, called metadata tags, for content items like movies or songs. It works by first finding other content items that are similar to the one being tagged. Then, it calculates a ratio: it compares how similar the first content item is to *all* its similar items against how similar it is to only those similar items that *already have the specific tag* in question (Claim 1). If this ratio indicates a strong connection, the system modifies the content item's metadata field to include that tag. For example, if a new documentary is very similar to many other documentaries already tagged as 'historical,' the system might automatically add 'historical' to the new documentary's tags. ## What it does NOT cover - Does not cover manual tagging of content by human editors without automated similarity analysis. - Does not cover content recommendation systems that do not rely on this specific ratio-based metadata modification process. - Does not cover the underlying methods for determining content similarity itself, only how to use that similarity for metadata modification. - Does not cover systems that only add tags based on simple keyword matching without comparing to other content items. - Does not cover systems that only remove metadata tags without considering a history of such removals for recommendations. ## The clever bit The novelty lies in using a specific ratio of aggregate similarities to determine if a metadata tag is truly applicable. Instead of just checking if an item is similar to *some* tagged items, it compares overall similarity against similarity to *only* the similar items with that specific tag, providing a more precise applicability score. ## Real-world examples 1. Netflix content classification 2. Hulu content categorization 3. Amazon Prime Video recommendations 4. YouTube video tagging 5. Spotify music genre assignment ## Why it matters Accurate content classification is crucial for modern streaming services and digital media platforms. This patent provides a method to automatically refine these classifications, which directly impacts how effectively content can be discovered and recommended to users. Better tagging leads to more relevant recommendations, improving user experience and engagement across various media platforms. ## Frequently asked questions ### What does How Computers Automatically Tag Movies and Shows Better cover? 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. ### Who owns patent US 12135756? Comcast Cable Communications owns this patent, granted in 2024. ### When does this patent expire? This patent is expected to expire on January 10, 2042, when the invention enters the public domain. ### What problem does this patent solve? Accurate content classification is crucial for modern streaming services and digital media platforms. This patent provides a method to automatically refine these classifications, which directly impacts how effectively content can be discovered and recommended to users. Better tagging leads to more relevant recommendations, improving user experience and engagement across various media platforms. ### What does this patent NOT cover? Does not cover manual tagging of content by human editors without automated similarity analysis. **Full plain-English explainer:** https://patentbrief.org/patent/us/12135756/content-recommendation-system-with-weighted-metadata-annotations **Original patent:** https://patents.google.com/patent/US12135756 --- _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 a System Ranks Content Based on Friend Recommendations](https://patentbrief.org/patent/us/20230245158/content-recommendation-system) — 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. - [How Music Apps Learn What You Don't Want in Playlists](https://patentbrief.org/patent/us/12277178/media-content-item-recommendation-system) — This patent describes how a music streaming service learns what kinds of songs or artists a user dislikes for their playlists by tracking what they repeatedly ignore, then uses that information to avoid recommending similar things in the future. - [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 Groupon Automatically Categorizes Merchant Services Using Text Analysis](https://patentbrief.org/patent/us/9330167/amazon-rds) — A system that automatically scans merchant websites and uses high-precision search queries to label their services, helping platforms like Groupon organize thousands of business listings. - [How Computers Automatically Organize and Search Photos Using Contextual Data](https://patentbrief.org/patent/us/8862582/amazon-redshift) — A system for indexing images by attaching descriptive data to objects within them and adjusting search rankings based on how often a user searches for those specific items.