U.S. Bancorp was granted a patent for adaptive time-series encoding.

{
  "signal_id": "cb87f624-82f5-55f4-90c7-88021ccd9bc8",
  "signal_type": "patents-company",
  "signal_subtype": "patentGrant",
  "detected_at": "2026-09-30T17:21:18+00:00",
  "company": {
    "name": "U.S. Bank",
    "domain": "usbank.com"
  },
  "data": {
    "cpc": [
      {
        "code": "G06N 20/00",
        "label": "Computing arrangements based on specific computational models"
      },
      {
        "code": "G06F 18/2413",
        "label": "Electric digital data processing"
      }
    ],
    "tags": [
      "Intellectual Property",
      "Research & Development",
      "Artificial Intelligence",
      "Machine Learning",
      "Data Management"
    ],
    "detail": "In September 2026 U.S. Bancorp patented machine-learning data compression for financial and operational systems that process changing time-series information.",
    "summary": "U.S. Bancorp was granted a patent for adaptive time-series encoding.",
    "event_at": "2026-09-29",
    "inventors": [
      {
        "name": "Samuel Atkins",
        "status": "resolved",
        "is_primary": true,
        "linkedin_url": "https://www.linkedin.com/in/atkinssamuel"
      },
      {
        "name": "Giacomo Domeniconi",
        "status": "resolved",
        "is_primary": false,
        "linkedin_url": "https://www.linkedin.com/in/giacomo-domeniconi-129760a3"
      }
    ],
    "tech_area": "artificial intelligence / machine learning",
    "event_kind": "grant_date",
    "grant_date": "2026-09-29",
    "source_url": "https://patents.google.com/patent/US12749022",
    "cpc_primary": {
      "code": "G06N 20/00",
      "label": "Computing arrangements based on specific computational models"
    },
    "patent_title": "Adaptive sparse time series encoding system",
    "patent_number": "US12749022",
    "uspto_assignee": "U.S. Bancorp, National Association",
    "patent_abstract": "A set of one or more non-transitory computer readable media has instructions that, when executed by a set of one or more processors, cause the processor set to obtain time series data comprising a plurality of data sequences, each data sequence having temporal data points with varying sparsity patterns. The instructions cause the processor set to analyze sparsity characteristics of each data sequence within a rolling window to determine a sparsity pattern classification and select an encoding strategy for each data sequence based on the determined sparsity pattern classification, wherein different encoding strategies are applied to data sequences having different sparsity pattern classifications. The instructions further cause the processor set to generate feature vectors for each data sequence using the selected encoding strategy and train a machine learning model using the generated feature vectors.",
    "precision_class": "structural",
    "invention_explanation": "A method that watches how often time-series data changes, classifies each pattern over a moving window, and chooses an efficient way to store or transmit it.",
    "technologies_mentioned": [
      "time-series data",
      "machine learning",
      "data compression",
      "encoding"
    ]
  }
}

curl https://signals.autobound.ai/v1/signals/cb87f624-82f5-55f4-90c7-88021ccd9bc8 \
  -H "X-API-KEY: $AUTOBOUND_API_KEY"

curl -X POST https://signals.autobound.ai/v1/companies/enrich \
  -H "X-API-KEY: $AUTOBOUND_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"domain":"usbank.com","limit":20}'