{
  "patent_number": "US 20220383078",
  "country": "US",
  "title": "Adapting AI Models to Fit Device Resources",
  "original_title": "Data processing method and related device",
  "summary": "This patent describes how a computer system can automatically shrink a large artificial intelligence model, specifically a \"transformer\" type, to fit the available computing power of a phone or other device.",
  "what_it_does": "The patent describes a method for a processing device to adjust an AI model, called a \"first neural network model,\" to better suit a \"terminal device\" (like a smartphone). It first checks the terminal device's \"available resource state\" (like how much memory or processing power it has) or a \"performance requirement.\" Based on this, it creates a \"second neural network model\" by reducing parts of the first model. This reduction can involve making the second model have fewer \"attention heads\" in its \"transformer layers\" (claim 1), fewer \"neurons\" in its \"intermediate layers\" (claim 1), or fewer \"transformer layers\" overall (claim 1). For example, if a phone has limited memory, the system might remove some attention heads from the original AI model to create a smaller, faster version that still works well on that phone.",
  "what_it_does_not_cover": [
    "Does not cover increasing the size of a neural network model based on available resources.",
    "Does not cover adapting non-transformer neural network architectures.",
    "Does not cover model adaptation methods that change the type of layers or neurons, only their quantity.",
    "Does not cover methods where the selection of components to remove is random, as claim 5 suggests a capability-based selection.",
    "Does not cover adapting models by changing their data types (e.g., from 32-bit to 16-bit floating point)."
  ],
  "filed": "2022-08-08",
  "granted": null,
  "expires": "2042-08-08",
  "status": "active",
  "holder": "Huawei Technologies Co",
  "holder_url": "https://patentbrief.org/company/huawei-technologies-co",
  "inventors": [
    {
      "name": "Lu HOU",
      "url": "https://patentbrief.org/inventor/lu-hou"
    },
    {
      "name": "Xin Jiang",
      "url": "https://patentbrief.org/inventor/xin-jiang"
    },
    {
      "name": "Lifeng Shang",
      "url": "https://patentbrief.org/inventor/lifeng-shang"
    }
  ],
  "times_cited": 6,
  "tags": [
    "ai_ml",
    "consumer_electronics",
    "telecommunications",
    "software"
  ],
  "abstract": "In a data processing method, a processing device obtains a first neural network model and an available resource state of a terminal device, and determines a second neural network model based on the first neural network model and the available resource state. An appropriate model size is determined based on the available resource state, and a part of the first neural network model is selected, based on the determined model size, as the second neural network model on which data processing is to be performed.",
  "url": "https://patentbrief.org/patent/us/20220383078/data-processing-method-and-related-device",
  "markdown_url": "https://patentbrief.org/patent/us/20220383078/data-processing-method-and-related-device/md",
  "google_patents_url": "https://patents.google.com/patent/US20220383078",
  "relatedPatents": [
    {
      "patentNumber": "12574477",
      "countryCode": "US",
      "title": "Training AI Models Across Different Computers",
      "url": "https://patentbrief.org/patent/us/12574477/distributed-deep-learning-using-a-distributed-deep-neural-network"
    },
    {
      "patentNumber": "20230162023",
      "countryCode": "US",
      "title": "Automated AI for Adapting to New Data Without Retraining",
      "url": "https://patentbrief.org/patent/us/20230162023/system-and-method-for-automated-transfer-learning-with-domain-disentanglement"
    },
    {
      "patentNumber": "10452978",
      "countryCode": "US",
      "title": "How AI Models Understand Language Using 'Attention'",
      "url": "https://patentbrief.org/patent/us/10452978/transformer-attention-mechanism"
    },
    {
      "patentNumber": "12423586",
      "countryCode": "US",
      "title": "Making AI Smarter by Focusing on Unsure 'Nodes'",
      "url": "https://patentbrief.org/patent/us/12423586/training-nodes-of-a-neural-network-to-be-decisive"
    },
    {
      "patentNumber": "10410117",
      "countryCode": "US",
      "title": "How to Save and Reuse Skills Learned by Artificial Intelligence Hardware",
      "url": "https://patentbrief.org/patent/us/10410117/method-and-a-system-for-creating-dynamic-neural-function-libraries"
    }
  ]
}