Skip to main content
RokuPatent grant

Roku was granted a patent for multi-space machine-learning predictions

Source: Autobound Signal API · 107 signals tracked for Roku · updated

Get Roku's live signals in Claude or ChatGPT, or by API

AskWhat changed at Roku this week? Use Autobound signals for roku.com.

What happened

In November 2026 Roku patented a query-processing approach for improving content discovery and recommendations across streaming platforms.

Source

patents.google.comNov 17, 2026

US patent US12801669

Multiple query projections for deep machine learning

Abstract

System, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, generate a prediction based on a query. A query is provided to a deep machine learning (ML) model. The deep ML model generates a plurality of query projection embeddings by projecting the query into each of a plurality of different query embedding spaces and generates the prediction based at least on the plurality of query projection embeddings. Each of a plurality of query projection embedding layers of the deep ML may generate a corresponding one of the query projection embeddings by applying a hash function associated with the query projection layer to the query to generate a vector representation of the query, and applying a set of weights associated with the query projection layer to the vector representation to generate a query projection embedding in the plurality of query projection embeddings.

patents.google.com/patent/US12801669Read 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 17, 2026
Inventors
4
Tech area
software / computing
Patent number
US12801669

The full record

From the Signal API record

People

  • Kapil KumarInventor
  • Abhishek MajumdarInventor
  • Nitish AggarwalInventor
  • Srimaruti Manoj NimmagaddaInventor

Details

Primary CPC class
G06F 16/90332 (Electric digital data processing)
USPTO assignee
ROKU, INC.
What the invention does
A machine-learning system that represents the same search or recommendation request in several ways before combining those views to make a prediction.

Topics and mentions

Tags

  • Intellectual Property
  • Research & Development
  • Artificial Intelligence
  • Machine Learning
  • Search

Technologies named

  • machine learning
  • query processing
  • recommendation systems
  • embeddings

Extraction

Detected
Nov 18, 2026
signal_type
patents-company
signal_subtype
patentGrant

Use this data

Get every patent signal for Roku 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 Roku 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/1b07aa1a-d228-56cb-8aef-c6331f37fc97 returns this record as JSON. POST /v1/companies/enrich returns every signal for roku.com.

{
  "signal_id": "1b07aa1a-d228-56cb-8aef-c6331f37fc97",
  "signal_type": "patents-company",
  "signal_subtype": "patentGrant",
  "detected_at": "2026-11-18T15:31:42+00:00",
  "company": {
    "name": "Roku",
    "domain": "roku.com"
  },
  "data": {
    "cpc": [
      {
        "code": "G06F 16/90332",
        "label": "Electric digital data processing"
      }
    ],
    "tags": [
      "Intellectual Property",
      "Research & Development",
      "Artificial Intelligence",
      "Machine Learning",
      "Search"
    ],
    "detail": "In November 2026 Roku patented a query-processing approach for improving content discovery and recommendations across streaming platforms.",
    "summary": "Roku was granted a patent for multi-space machine-learning predictions",
    "event_at": "2026-11-17",
    "inventors": [
      {
        "name": "Kapil Kumar",
        "status": "unresolved",
        "is_primary": true
      },
      {
        "name": "Abhishek Majumdar",
        "status": "unresolved",
        "is_primary": false
      },
      {
        "name": "Nitish Aggarwal",
        "status": "resolved",
        "is_primary": false,
        "linkedin_url": "https://www.linkedin.com/in/nitishagg"
      },
      {
        "name": "Srimaruti Manoj Nimmagadda",
        "status": "unresolved",
        "is_primary": false
      }
    ],
    "tech_area": "software / computing",
    "event_kind": "grant_date",
    "grant_date": "2026-11-17",
    "source_url": "https://patents.google.com/patent/US12801669",
    "cpc_primary": {
      "code": "G06F 16/90332",
      "label": "Electric digital data processing"
    },
    "patent_title": "Multiple query projections for deep machine learning",
    "patent_number": "US12801669",
    "uspto_assignee": "ROKU, INC.",
    "patent_abstract": "System, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, generate a prediction based on a query. A query is provided to a deep machine learning (ML) model. The deep ML model generates a plurality of query projection embeddings by projecting the query into each of a plurality of different query embedding spaces and generates the prediction based at least on the plurality of query projection embeddings. Each of a plurality of query projection embedding layers of the deep ML may generate a corresponding one of the query projection embeddings by applying a hash function associated with the query projection layer to the query to generate a vector representation of the query, and applying a set of weights associated with the query projection layer to the vector representation to generate a query projection embedding in the plurality of query projection embeddings.",
    "precision_class": "structural",
    "invention_explanation": "A machine-learning system that represents the same search or recommendation request in several ways before combining those views to make a prediction.",
    "technologies_mentioned": [
      "machine learning",
      "query processing",
      "recommendation systems",
      "embeddings"
    ]
  }
}

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.