{
  "patent_number": "US 12135756",
  "country": "US",
  "title": "How Computers Automatically Tag Movies and Shows Better",
  "original_title": "Content recommendation system with weighted metadata annotations",
  "summary": "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.",
  "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."
  ],
  "filed": "2022-01-10",
  "granted": "2024-11-05",
  "expires": "2042-01-10",
  "status": "active",
  "holder": "Comcast Cable Communications",
  "holder_url": "https://patentbrief.org/company/comcast-cable-communications",
  "inventors": [
    {
      "name": "Oliver Jojic",
      "url": "https://patentbrief.org/inventor/oliver-jojic"
    },
    {
      "name": "Hans Sayyadi",
      "url": "https://patentbrief.org/inventor/hans-sayyadi"
    }
  ],
  "times_cited": 0,
  "tags": [
    "software",
    "telecommunications",
    "consumer_electronics",
    "ai_ml",
    "ecommerce"
  ],
  "abstract": "Systems and methods are described for improving content classifications and metadata for a plurality of content items. The content items may comprise various forms of media content. A content recommendation processing system may automatically annotate and/or classify content items with a plurality of metadata tag information describing content items. The disclosed system and methods may also determine and/or assign applicability scores indicating a level or degree of suitability for annotating a content item with particular metadata tag information, and may utilize applicability scores to provide content to calibrate metadata information for a plurality of content items, and further to provide content recommendations to users.",
  "url": "https://patentbrief.org/patent/us/12135756/content-recommendation-system-with-weighted-metadata-annotations",
  "markdown_url": "https://patentbrief.org/patent/us/12135756/content-recommendation-system-with-weighted-metadata-annotations/md",
  "google_patents_url": "https://patents.google.com/patent/US12135756",
  "relatedPatents": [
    {
      "patentNumber": "20230245158",
      "countryCode": "US",
      "title": "How a System Ranks Content Based on Friend Recommendations",
      "url": "https://patentbrief.org/patent/us/20230245158/content-recommendation-system"
    },
    {
      "patentNumber": "12277178",
      "countryCode": "US",
      "title": "How Music Apps Learn What You Don't Want in Playlists",
      "url": "https://patentbrief.org/patent/us/12277178/media-content-item-recommendation-system"
    },
    {
      "patentNumber": "12118030",
      "countryCode": "US",
      "title": "How a Recommendation System Learns What You Really Want to Watch",
      "url": "https://patentbrief.org/patent/us/12118030/dynamic-feedback-in-a-recommendation-system"
    },
    {
      "patentNumber": "9330167",
      "countryCode": "US",
      "title": "How Groupon Automatically Categorizes Merchant Services Using Text Analysis",
      "url": "https://patentbrief.org/patent/us/9330167/amazon-rds"
    },
    {
      "patentNumber": "8862582",
      "countryCode": "US",
      "title": "How Computers Automatically Organize and Search Photos Using Contextual Data",
      "url": "https://patentbrief.org/patent/us/8862582/amazon-redshift"
    }
  ]
}