{
  "patent_number": "US 11593558",
  "country": "US",
  "title": "How eBay Uses AI to Identify Brands in Search Queries",
  "original_title": "Deep hybrid neural network for named entity recognition",
  "summary": "A system that uses deep learning to recognize brand names in search queries and automatically improve search results by adding relevant product terms.",
  "what_it_does": "This system improves search accuracy by teaching a computer to understand that certain words in a search query belong together as a single brand name. It first breaks down words into individual characters using a deep neural network to understand their structure, then combines this with pre-trained word knowledge. It uses a bidirectional long short-term memory (LSTM) to look at the context of the whole sentence, and finally applies conditional random fields to pick the most likely label for each word. For example, if a user searches for 'Nike running shoes', the system identifies 'Nike' as a brand and may automatically add terms like 'apparel' or 'gear' to the search to return better results.",
  "what_it_does_not_cover": [
    "Does not cover general-purpose entity recognition that is not tied to a search query augmentation process.",
    "Does not cover systems that identify entities without using both character-level convolutional layers and bidirectional LSTMs.",
    "Does not cover search augmentation that does not rely on the specific output of a sequential conditional random field classifier."
  ],
  "filed": "2017-08-31",
  "granted": "2023-02-28",
  "expires": null,
  "status": "active",
  "holder": "eBay Inc",
  "holder_url": "https://patentbrief.org/company/ebay-inc",
  "inventors": [
    {
      "name": "Yingwei Xin",
      "url": "https://patentbrief.org/inventor/yingwei-xin"
    },
    {
      "name": "Jean-David Ruvini",
      "url": "https://patentbrief.org/inventor/jean-david-ruvini"
    },
    {
      "name": "Ethan J. Hart",
      "url": "https://patentbrief.org/inventor/ethan-j-hart"
    }
  ],
  "times_cited": 2,
  "tags": [
    "ai_ml",
    "software",
    "ecommerce"
  ],
  "abstract": "In an example, a text sentence comprising a plurality of words is obtained. Each of the plurality of words is passed through a deep compositional character-to-word model to encode character-level information of each of the plurality of words into a character-to-word expression. The character-to-word expressions are combined with pre-trained word embeddings. The combined character-to-word expressions and pre-trained word embeddings are fed into one or more bidirectional long short-term memories to learn contextual information for each of the plurality of words. Then, sequential conditional random fields are applied to the contextual information for each of the plurality of words.",
  "url": "https://patentbrief.org/patent/us/11593558/no-language-left-behind-nllb",
  "markdown_url": "https://patentbrief.org/patent/us/11593558/no-language-left-behind-nllb/md",
  "google_patents_url": "https://patents.google.com/patent/US11593558",
  "relatedPatents": []
}