{
  "patent_number": "US 9330167",
  "country": "US",
  "title": "How Groupon Automatically Categorizes Merchant Services Using Text Analysis",
  "original_title": "Method, apparatus, and computer program product for classification and tagging of textual data",
  "summary": "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.",
  "what_it_does": "This patent describes a way to teach a computer how to read a merchant's website and figure out what service they offer, such as 'spa' or 'auto repair.' It works by first looking at a large collection of known documents to build search queries that are highly accurate, measured by a precision score. The system calculates this score by dividing the number of 'true positive' results by the total number of results found. Once these high-quality queries are refined, the system applies them to new, unlabeled text from a merchant's site to automatically assign the correct category label.",
  "what_it_does_not_cover": [
    "Does not cover general-purpose search engines that do not use a specific precision-threshold-based query selection process.",
    "Does not cover manual tagging or human-in-the-loop classification systems.",
    "Does not cover machine learning models that classify text without using the specific feature-index-pair and distance-measure query generation method described.",
    "Does not cover image-based merchant classification."
  ],
  "filed": "2013-05-13",
  "granted": "2016-05-03",
  "expires": null,
  "status": "active",
  "holder": "Groupon Inc",
  "holder_url": "https://patentbrief.org/company/groupon-inc",
  "inventors": [
    {
      "name": "Nick Pendar",
      "url": "https://patentbrief.org/inventor/nick-pendar"
    }
  ],
  "times_cited": 25,
  "tags": [
    "software",
    "ai_ml",
    "ecommerce"
  ],
  "abstract": "Provided herein are systems, methods and computer readable media for classification and tagging of textual data. An example method may include accessing a corpus comprising a plurality of documents, each document having one or more labels indicative of services offered by a merchant, generating a query based on extracted features and the documents, generating a precision score for at least a portion of the generated query and selecting a subset of the generated queries based on an assigned precision score satisfying a precision score threshold, the selected subset of the generated queries configured to provide an indication of one or more labels to be applied to machine readable text. A second example method, utilized for tagging machine readable text with unknown labels, may include assigning a label to textual portions of the machine readable text based on results of the application of the queries.",
  "url": "https://patentbrief.org/patent/us/9330167/amazon-rds",
  "markdown_url": "https://patentbrief.org/patent/us/9330167/amazon-rds/md",
  "google_patents_url": "https://patents.google.com/patent/US9330167",
  "relatedPatents": []
}