Skip to main content
U.S. BankPatent grant

U.S. Bank was granted a patent for on-device AI recommendation validation.

Source: Autobound Signal API · 100 signals tracked for U.S. Bank · updated

Get U.S. Bank's live signals in Claude or ChatGPT, or by API

AskWhat changed at U.S. Bank this week? Use Autobound signals for usbank.com.

What happened

In November 2026 U.S. Bank patented a privacy-focused method for refining AI recommendations on smartphones and other user devices.

Source

patents.google.comNov 10, 2026

US patent US12792975

On-device agentic validation via personalized model ensemble

Abstract

An agentic recommendation is generated in response to a query from an agentic model executing in a user device. Further in response to the query, a set of personalized recommendations is generated from a set of personalized models forming an ensemble of models executing in the user device. In an output corresponding to the query, the agentic recommendation is replaced with at least one personalized recommendation from the set of personalized recommendations.

patents.google.com/patent/US12792975Read the full source

Extracted by Autobound

From the Signal API record
Signal
Patent grant

What this signalsA new patent often shows where a company is putting its R&D budget.

Grant date
Nov 10, 2026
Inventors
Rahul Sharma
Tech area
artificial intelligence / machine learning
Patent number
US12792975

The full record

From the Signal API record

People

  • Rahul SharmaInventor

Details

Primary CPC class
G06N 20/20 (Computing arrangements based on specific computational models)
USPTO assignee
U.S. Bank National Association
What the invention does
A device checks an AI agent’s answer against several personalized models and substitutes a more suitable recommendation when needed.

Topics and mentions

Tags

  • Intellectual Property
  • Research & Development
  • Artificial Intelligence
  • Machine Learning
  • Mobile Devices

Technologies named

  • on-device AI
  • machine learning
  • model ensembles
  • personalized recommendations

Extraction

Detected
Nov 11, 2026
signal_type
patents-company
signal_subtype
patentGrant

Use this data

Get every patent signal for U.S. Bank and the companies you sell to, in the tools you already use.

  1. Ask Claude about it

    Connect Autobound to Claude, Claude Code or Cursor with MCP. Then ask: “What changed at U.S. Bank this week?”

  2. Send it to your own tools

    The Signal API returns patent signals for any list of companies as JSON, for your CRM, warehouse or app.

  3. Try it free

    Sign up and spend your free credits on the companies you sell to.

    Start Free1,000 free credits

The API returns more than this page shows

This page shows a preview. The full patents-company record in the Signal API and MCP can also have these 8 fields. Some fields are empty for some signals.

Company

  • linkedin_urlValue in the API
  • industriesValue in the API
  • employee_count_lowValue in the API
  • employee_count_highValue in the API
  • revenueValue in the API
  • descriptionValue in the API

Signal

  • signal_nameValue in the API
  • associationValue in the API
Show the full JSONThe record on this page and the API request

GET /v1/signals/2344384e-b435-54bb-88b4-ce0b21b1d244 returns this record as JSON. POST /v1/companies/enrich returns every signal for usbank.com.

{
  "signal_id": "2344384e-b435-54bb-88b4-ce0b21b1d244",
  "signal_type": "patents-company",
  "signal_subtype": "patentGrant",
  "detected_at": "2026-11-11T16:03:29+00:00",
  "company": {
    "name": "U.S. Bank",
    "domain": "usbank.com"
  },
  "data": {
    "cpc": [
      {
        "code": "G06N 20/20",
        "label": "Computing arrangements based on specific computational models"
      },
      {
        "code": "G06F 16/3329",
        "label": "Electric digital data processing"
      }
    ],
    "tags": [
      "Intellectual Property",
      "Research & Development",
      "Artificial Intelligence",
      "Machine Learning",
      "Mobile Devices"
    ],
    "detail": "In November 2026 U.S. Bank patented a privacy-focused method for refining AI recommendations on smartphones and other user devices.",
    "summary": "U.S. Bank was granted a patent for on-device AI recommendation validation.",
    "event_at": "2026-11-10",
    "inventors": [
      {
        "name": "Rahul Sharma",
        "status": "unresolved",
        "is_primary": true
      }
    ],
    "tech_area": "artificial intelligence / machine learning",
    "event_kind": "grant_date",
    "grant_date": "2026-11-10",
    "source_url": "https://patents.google.com/patent/US12792975",
    "cpc_primary": {
      "code": "G06N 20/20",
      "label": "Computing arrangements based on specific computational models"
    },
    "patent_title": "On-device agentic validation via personalized model ensemble",
    "patent_number": "US12792975",
    "uspto_assignee": "U.S. Bank National Association",
    "patent_abstract": "An agentic recommendation is generated in response to a query from an agentic model executing in a user device. Further in response to the query, a set of personalized recommendations is generated from a set of personalized models forming an ensemble of models executing in the user device. In an output corresponding to the query, the agentic recommendation is replaced with at least one personalized recommendation from the set of personalized recommendations.",
    "precision_class": "structural",
    "invention_explanation": "A device checks an AI agent’s answer against several personalized models and substitutes a more suitable recommendation when needed.",
    "technologies_mentioned": [
      "on-device AI",
      "machine learning",
      "model ensembles",
      "personalized recommendations"
    ]
  }
}

Long text fields are shortened on this page.

Looking up one signal by its id is free. Enrich costs 2 credits per signal returned; a call with no results is free.