{
  "patent_number": "US 10664744",
  "country": "US",
  "title": "How Computers Use Memory Networks to Answer Questions",
  "original_title": "End-to-end memory networks",
  "summary": "A method for AI to search through large amounts of stored information by repeatedly 'hopping' through memory to find the most relevant facts for answering a question.",
  "what_it_does": "This patent describes a way for an AI model to process information by treating a database of knowledge like a long-term memory. When the system receives a question, it converts both the question and the stored facts into mathematical vectors. It then performs a 'hop' operation, where it calculates which facts are most relevant to the question using a probability score. By repeating this process across multiple hops, the system refines its focus, effectively 'reading' through the memory to build a better answer. For example, if you provided a story about a character moving between rooms, the system would use these hops to track the character's location before answering 'Where is the character now?'",
  "what_it_does_not_cover": [
    "Does not cover traditional database lookups that rely on exact keyword matching.",
    "Does not cover systems that use hard-coded rules or logic trees to find answers.",
    "Does not cover non-vectorized storage methods for knowledge entries.",
    "Does not cover architectures that do not utilize a multi-hop iterative refinement process."
  ],
  "filed": "2017-03-28",
  "granted": "2020-05-26",
  "expires": null,
  "status": "active",
  "holder": "Facebook Inc",
  "holder_url": "https://patentbrief.org/company/facebook-inc",
  "inventors": [
    {
      "name": "Sainbayar Sukhbaatar",
      "url": "https://patentbrief.org/inventor/sainbayar-sukhbaatar"
    },
    {
      "name": "Robert D. Fergus",
      "url": "https://patentbrief.org/inventor/robert-d-fergus"
    },
    {
      "name": "Jason E. Weston",
      "url": "https://patentbrief.org/inventor/jason-e-weston"
    },
    {
      "name": "Arthur David Szlam",
      "url": "https://patentbrief.org/inventor/arthur-david-szlam"
    }
  ],
  "times_cited": 1,
  "tags": [
    "ai_ml",
    "software",
    "telecommunications"
  ],
  "abstract": "Embodiments are disclosed for predicting a response (e.g., an answer responding to a question) using an end-to-end memory network model. A computing device according to some embodiments includes embedding matrices to convert knowledge entries and an inquiry into feature vectors including the input vector and memory vectors. The device further execute a hop operation to generate a probability vector based on an input vector and a first set of memory vectors using a continuous weighting function (e.g., softmax), and to generate an output vector as weighted combination of a second set of memory vectors using the elements of the probability vector as weights. The device can repeat the hop operation for multiple times, where the input vector for a hop operation depends on input and output vectors of previous hop operation(s). The device generates a predicted response based on at least the output of the last hop operation.",
  "url": "https://patentbrief.org/patent/us/10664744/watson-question-answering-system-deepqa",
  "markdown_url": "https://patentbrief.org/patent/us/10664744/watson-question-answering-system-deepqa/md",
  "google_patents_url": "https://patents.google.com/patent/US10664744",
  "relatedPatents": []
}