Skip to main content
ParamountPatent grant

Paramount Global was granted a patent for AI-generated video clips

What happened

In August 2026 Paramount Global patented technology for creating and delivering short, context-aware video clips across streaming and digital video services.

Source

patents.google.comAug 25, 2026

US patent US12720173

System and method for AI-powered generation and delivery of video clips

Abstract

A system, a method and a process are for AI-powered generation and delivery of video clips. The processor is configured to: classify a first video content item including a first video file comprising video frames associated with timestamps and a first subtitle file comprising subtitle text associated with the timestamps, wherein the first video content item is classified with narrative classifiers by: executing a natural language processing (NLP) model with the first subtitle file as input, the NLP model including a dialogue analysis for identifying first narrative elements from dialogue included in the first subtitle file and associating the first narrative elements with first timestamps, executing an image recognition model with the first video file as input, the image recognition model including an object identification analysis for identifying second narrative elements from objects or persons portrayed in the video frames of the first video file and associating the second narrative elements with second timestamps, combining a first output of the NLP model with a second output of the image recognition model, and generating a first set of timestamps associated with the narrative classifiers; define one or more segments within the first video content item, each segment comprising a starting timestamp and an ending timestamp defining a duration and having one or more of the...

Keep reading with a free account

The rest of this article, and every signal for Paramount, is in your free account.

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
Aug 25, 2026
Inventors
4
Tech area
video / streaming
Patent number
US12720173

The full record

From the Signal API record

People

  • Partha Sarathi SamalInventor
  • Alexandr PopovInventor
  • Behrang ZandiInventor
  • Suresh Kumar PalusInventor
  • Sai Kiran PadmamInventor
  • Kamal ViolaInventor

Details

Primary CPC class
H04N 21/8456 (Pictorial communication, e.g. television)
USPTO assignee
Paramount Global
What the invention does
A system that analyzes video frames and subtitles with language models to identify story moments, generate clips, and send them to viewers.

Topics and mentions

Tags

  • Intellectual Property
  • Research & Development
  • Artificial Intelligence
  • Language Technology
  • Video

Technologies named

  • AI video generation
  • natural language processing
  • video streaming
  • subtitle analysis

Extraction

Detected
Sep 15, 2026
signal_type
patents-company
signal_subtype
patentGrant

Use this data

Get every patent signal for Paramount 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 Paramount 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/35536e49-f158-5f86-8cce-dbe599cab85a returns this record as JSON. POST /v1/companies/enrich returns every signal for paramount.com.

{
  "signal_id": "35536e49-f158-5f86-8cce-dbe599cab85a",
  "signal_type": "patents-company",
  "signal_subtype": "patentGrant",
  "detected_at": "2026-09-15T20:08:37+00:00",
  "company": {
    "name": "Paramount",
    "domain": "paramount.com"
  },
  "data": {
    "cpc": [
      {
        "code": "H04N 21/8456",
        "label": "Pictorial communication, e.g. television"
      },
      {
        "code": "G06F 40/30",
        "label": "Electric digital data processing"
      },
      {
        "code": "G06V 10/764",
        "label": "Image or video recognition or understanding"
      },
      {
        "code": "H04L 67/306",
        "label": "Transmission of digital information"
      }
    ],
    "tags": [
      "Intellectual Property",
      "Research & Development",
      "Artificial Intelligence",
      "Language Technology",
      "Video"
    ],
    "detail": "In August 2026 Paramount Global patented technology for creating and delivering short, context-aware video clips across streaming and digital video services.",
    "summary": "Paramount Global was granted a patent for AI-generated video clips",
    "event_at": "2026-08-25",
    "inventors": [
      {
        "name": "Partha Sarathi Samal",
        "status": "resolved",
        "is_primary": true,
        "linkedin_url": "https://www.linkedin.com/in/partha-sarathi-samal"
      },
      {
        "name": "Alexandr Popov",
        "status": "unresolved",
        "is_primary": false
      },
      {
        "name": "Behrang Zandi",
        "status": "resolved",
        "is_primary": false,
        "linkedin_url": "https://www.linkedin.com/in/behrang-zandi"
      },
      {
        "name": "Suresh Kumar Palus",
        "status": "resolved",
        "is_primary": false,
        "linkedin_url": "https://www.linkedin.com/in/suresh-palus-0a436932"
      },
      {
        "name": "Sai Kiran Padmam",
        "status": "unresolved",
        "is_primary": false
      },
      {
        "name": "Kamal Viola",
        "status": "unresolved",
        "is_primary": false
      },
      {
        "name": "Jonathan Ortiz",
        "status": "resolved",
        "is_primary": false,
        "linkedin_url": "https://www.linkedin.com/in/jonathanortiz31"
      }
    ],
    "tech_area": "video / streaming",
    "event_kind": "grant_date",
    "grant_date": "2026-08-25",
    "source_url": "https://patents.google.com/patent/US12720173",
    "cpc_primary": {
      "code": "H04N 21/8456",
      "label": "Pictorial communication, e.g. television"
    },
    "patent_title": "System and method for AI-powered generation and delivery of video clips",
    "patent_number": "US12720173",
    "uspto_assignee": "Paramount Global",
    "patent_abstract": "A system, a method and a process are for AI-powered generation and delivery of video clips. The processor is configured to: classify a first video content item including a first video file comprising video frames associated with timestamps and a first subtitle file comprising subtitle text associated with the timestamps, wherein the first video content item is classified with narrative classifiers by: executing a natural language processing (NLP) model with the first subtitle file as input, the NLP model including a dialogue analysis for identifying first narrative elements from dialogue included in the first subtitle file and associating the first narrative elements with first timestamps, executing an image recognition model with the first video file as input, the image recognition model including an object identification analysis for identifying second narrative elements from objects or persons portrayed in the video frames of the first video file and associating the second narrative elements with second timestamps, combining a first output of the NLP model with a second output of the image recognition model, and generating a first set of timestamps associated with the narrative classifiers; define one or more segments within the first video content item, each segment comprising a starting timestamp and an ending timestamp defining a duration and having one or more of the...",
    "precision_class": "structural",
    "invention_explanation": "A system that analyzes video frames and subtitles with language models to identify story moments, generate clips, and send them to viewers.",
    "technologies_mentioned": [
      "AI video generation",
      "natural language processing",
      "video streaming",
      "subtitle analysis"
    ]
  }
}

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.