{
  "patent_number": "US 12277178",
  "country": "US",
  "title": "How Music Apps Learn What You Don't Want in Playlists",
  "original_title": "Media content item recommendation system",
  "summary": "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.",
  "what_it_does": "The system first shows a user a playlist and offers recommended songs to add to it (Claim 1). It then keeps track of how often songs with specific traits, called 'attributes' (like a certain artist, per Claim 3 and 4), are suggested for a playlist but the user doesn't pick them (Claim 1). If a user consistently ignores songs with a particular attribute, the system gives that attribute a lower score (Claim 1). This score is then used to reduce the chance of recommending other songs with that same attribute for playlist additions in the future (Claim 5). For example, if you keep skipping recommendations for songs by 'Artist X' when building a playlist, the system learns to show you fewer songs by 'Artist X' or similar artists for that playlist.",
  "what_it_does_not_cover": [
    "Does not cover recommendations based solely on what a user likes or plays frequently, without considering ignored suggestions.",
    "Does not cover general content recommendations outside the specific context of adding to an existing playlist.",
    "Does not cover systems that track ignored individual songs without linking that behavior to broader 'attributes' like artist or genre.",
    "Does not cover adjusting recommendations based on explicit 'dislike' buttons, only implicit ignoring by not selecting.",
    "Does not cover recommendations where the user is not presented with a 'set of recommended media content items for addition to the playlist'."
  ],
  "filed": "2023-05-23",
  "granted": "2025-04-15",
  "expires": "2043-05-23",
  "status": "active",
  "holder": "Spotify AB",
  "holder_url": "https://patentbrief.org/company/spotify-ab",
  "inventors": [
    {
      "name": "Camilla Westraeus",
      "url": "https://patentbrief.org/inventor/camilla-westraeus"
    },
    {
      "name": "Mattias Johansson",
      "url": "https://patentbrief.org/inventor/mattias-johansson"
    },
    {
      "name": "Jacob Colin Waller",
      "url": "https://patentbrief.org/inventor/jacob-colin-waller"
    },
    {
      "name": "Per Lindstrand",
      "url": "https://patentbrief.org/inventor/per-lindstrand"
    },
    {
      "name": "Michelle Ackerman",
      "url": "https://patentbrief.org/inventor/michelle-ackerman"
    },
    {
      "name": "Jonathan Marmor",
      "url": "https://patentbrief.org/inventor/jonathan-marmor"
    },
    {
      "name": "Michael Öhman",
      "url": "https://patentbrief.org/inventor/michael-hman"
    },
    {
      "name": "Felipe Oliveira Carvalho",
      "url": "https://patentbrief.org/inventor/felipe-oliveira-carvalho"
    },
    {
      "name": "Paul Lamere",
      "url": "https://patentbrief.org/inventor/paul-lamere"
    },
    {
      "name": "Oscar Söderlund",
      "url": "https://patentbrief.org/inventor/oscar-sderlund"
    }
  ],
  "times_cited": 0,
  "tags": [
    "software",
    "telecommunications",
    "consumer_electronics",
    "ai_ml"
  ],
  "abstract": "A media content item recommendation system recommends media content items based on one or more attributes of a seed playlist. The recommended media content items can be determined from a plurality of existing playlists that have been created over a period of time. Such existing playlists can be selected based on similarity to the seed playlist.",
  "url": "https://patentbrief.org/patent/us/12277178/media-content-item-recommendation-system",
  "markdown_url": "https://patentbrief.org/patent/us/12277178/media-content-item-recommendation-system/md",
  "google_patents_url": "https://patents.google.com/patent/US12277178",
  "relatedPatents": [
    {
      "patentNumber": "6990497",
      "countryCode": "US",
      "title": "How to Play Any Media Playlist by Converting it to a Standard Format",
      "url": "https://patentbrief.org/patent/us/6990497/dynamic-streaming-media-management"
    },
    {
      "patentNumber": "10402750",
      "countryCode": "US",
      "title": "How Facebook Uses Deep Learning to Predict What You Might Like",
      "url": "https://patentbrief.org/patent/us/10402750/automl-neural-architecture-search"
    },
    {
      "patentNumber": "8700540",
      "countryCode": "US",
      "title": "How Eventbrite Recommends Events Based on Your Social Network",
      "url": "https://patentbrief.org/patent/us/8700540/facebook-messenger"
    },
    {
      "patentNumber": "10127595",
      "countryCode": "US",
      "title": "How Apps Compare Local Prices and Ratings for Specific Items",
      "url": "https://patentbrief.org/patent/us/10127595/airbnb-dynamic-pricing-smart-pricing"
    },
    {
      "patentNumber": "6370526",
      "countryCode": "US",
      "title": "Smart Ranking of Emails and Files Based on How You Click",
      "url": "https://patentbrief.org/patent/us/6370526/google-adwords-pay-per-click"
    }
  ]
}