# US 2026/0094443 A1 · Generating short-form content from full-length media using a machine learning model

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0094443 A1
- Document ID: US20260094443A1
- Status: Published application
- Kind: A1
- Application number: 19/353,317
- Filed: 2025-10-08
- Published: 2026-04-02
- Earliest claimed: 2023-12-22
- Assignees: Roku, Inc.
- Applicants: Roku, Inc.
- Inventors: Fei XIAO; Nam VO; Ronica JETHWA; Abhishek BAMBHA; Rohit MAHTO; Amit VERMA; Pulkit AGGARWAL; Zidong WANG
- Web page: https://patentgrep.com/patent/US20260094443A1

## CPC

- G06V 20/49: {Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes}
- G06V 10/70: using pattern recognition or machine learning (optical pattern recognition or electronic computations therefor G06V10/88)
- G06V 20/41: {Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items (segmenting video sequences G06V20/49)}
- G11B 27/031: Electronic editing of digitised analogue information signals, e.g. audio or video signals
- G11B 27/102: {Programmed access in sequence to addressed parts of tracks of operating record carriers (access by moving the head G11B3/08, G11B5/54, G11B7/085, G11B21/022; by moving the record carrier G11B15/005, G11B17/005, by driving of both record carrier and head G11B15/1816)}
- G11B 27/34: Indicating arrangements {(indicating means incorporated in magazine or cassette G11B23/046 and G11B23/0875; indicating measured values in general G01D)}
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G11B: INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER (recording measured values in a way that does not require playback through a transducer G01D9/00; recording or playback apparatus using mechanically marked tape, e.g. punched paper tape, or using unit records, e.g. punched or magnetically marked cards G06K; transferring data from one type of record carrier to another G06K1/18; circuits for coupling output of reproducer to radio receiver H04B1/20; gramophone pick-ups or like acoustic electromechanical transducers or circuits therefor H04R)

## Abstract

Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product aspects, and/or combinations and sub-combinations thereof, for generating short-form content. An example aspect operates by analyzing a media file in a library using a machine learning model. To analyze the media file, the embodiment determines, using the machine learning model, a first portion of the media file that has a feature that satisfies a classification that the machine learning model is configured to identify. The embodiment tags the first portion using one or more position tags indicative of a beginning of the first portion of the media file or an end of the first portion of the media file. The embodiment then generates a segment from the media file based on the one or more position tags. The segment comprises the portion of the media file and excludes one or more second portions of the media file.

## Claims

### Claim 1

A computer-implemented method to generate short-form content from a library of media files, the computer-implemented method comprising:
identifying, by at least one computer processor, a media file in the library using a machine learning model that is an interaction-based model trained, based on recorded user interactions, to identify one or more features in the media file that satisfy one or more classifications that exceed a user-engagement threshold based on user-engagement metrics derived from data of user consumption of media content;
analyzing the media file using the machine learning model, wherein the analyzing comprises:
determining, using the machine learning model, a first portion of the media file that has a feature that satisfies the one or more classifications that the machine learning model is configured to identify, wherein the one or more classifications are based on the user-engagement metrics; and
tagging the first portion of the media file using one or more position tags indicative of a beginning of the first portion of the media file or an end of the first portion of the media file; and
generating a segment from the media file based on the one or more position tags, wherein the segment comprises the first portion of the media file and excludes one or more second portions of the media file.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, further comprising:
storing the segment as a short-form media file.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein:
the analyzing further comprises:
determining, using the machine learning model, a third portion of the media file that has another feature that satisfies another classification that the machine learning model is configured to identify; and
tagging the third portion using one or more other position tags indicative of a beginning of the third portion of the media file or an end of the third portion of the media file; and
the computer-implemented method further comprises generating another segment from the media file based on the one or more other position tags, wherein the other segment comprises the third portion of the media file and excludes one or more fourth portions of the media file.

### Claim 4 (depends on 3)

The computer-implemented method of claim 3, further comprising:
storing the segment and the other segment as short-form media files; and
indexing the short-form media files for search and playback.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, further comprising:
outputting, to an output device, a listing of short-form content based on the classification, wherein the listing of short-form content comprises the segment.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, wherein the classification is an action sequence classification.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, wherein the classification is a product identifier classification.

### Claim 8

A system for generating short-form content from a library of media files, the system comprising:
one or more memories; and
at least one processor each coupled to at least one of the memories and configured to perform operations comprising:
identifying a media file in the library using a machine learning model that is an interaction-based model trained, based on recorded user interactions, to identify one or more features in the media file that satisfy one or more classifications that exceed a user-engagement threshold based on user-engagement metrics derived from data of user consumption of media content;
analyzing the media file using the machine learning model, wherein the analyzing comprises:
determining, using the machine learning model, a first portion of the media file that has a feature that satisfies the one or more classifications that the machine learning model is configured to identify, wherein the one or more classifications are based on the user-engagement metrics; and
tagging the first portion of the media file using one or more position tags indicative of a beginning of the first portion of the media file or an end of the first portion of the media file; and
generating a segment from the media file based on the one or more position tags, wherein the segment comprises the first portion of the media file and excludes one or more second portions of the media file.

### Claim 9 (depends on 8)

The system of claim 8, wherein the operations further comprise:
storing the segment as a short-form media file.

### Claim 10 (depends on 8)

The system of claim 8, wherein:
the analyzing further comprises:
determining, using the machine learning model, a third portion of the media file that has another feature that satisfies another classification that the machine learning model is configured to identify; and
tagging the third portion using one or more other position tags indicative of a beginning of the third portion of the media file or an end of the third portion of the media file; and
the operations further comprise generating another segment from the media file based on the one or more other position tags, wherein the other segment comprises the other portion of the media file and excludes one or more fourth portions of the media file.

### Claim 11 (depends on 10)

The system of claim 10, wherein the operations further comprise:
storing the segment and the other segment as short-form media files; and
indexing the short-form media files for search and playback.

### Claim 12 (depends on 8)

The system of claim 8, wherein the operations further comprise:
outputting, to an output device, a listing of short-form content based on the classification, wherein the listing of short-form content comprises the segment.

### Claim 13 (depends on 8)

The system of claim 8, wherein the classification is an action sequence classification.

### Claim 14 (depends on 8)

The system of claim 8, wherein the classification is a product identifier classification.

### Claim 15

A non-transitory computer-readable medium having instructions stored thereon that, when executed by at least one computing device, cause the at least one computing device to perform operations comprising:
identifying, by at least one computer processor, a media file in the library using a machine learning model that is an interaction-based model trained, based on recorded user interactions, to identify one or more features in the media file that satisfy one or more classifications that exceed a user-engagement threshold based on user-engagement metrics derived from data of user consumption of media content;
analyzing the media file using the machine learning model, wherein the analyzing comprises:
determining, using the machine learning model, a first portion of the media file that has a feature that satisfies the one or more classifications that the machine learning model is configured to identify, wherein the one or more classifications are based on the user-engagement metrics; and
tagging the first portion of the media file using one or more position tags indicative of a beginning of the first portion of the media file or an end of the first portion of the media file; and
generating a segment from the media file based on the one or more position tags, wherein the segment comprises the first portion of the media file and excludes one or more second portions of the media file.

### Claim 16 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the operations further comprise:
storing the segment as a short-form media file.

### Claim 17 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein:
the analyzing further comprises:
determining, using the machine learning model, a third portion of the media file that has another feature that satisfies another classification that the machine learning model is configured to identify; and
tagging the third portion using one or more other position tags indicative of a beginning of the third portion of the media file or an end of the third portion of the media file; and
the operations further comprise generating another segment from the media file based on the one more other position tags, wherein the other segment comprises the other portion of the media file and excludes one or more portions of the media file.

### Claim 18 (depends on 17)

The non-transitory computer-readable medium of claim 17, wherein the operations further comprise:
storing the segment and the other segment as short-form media files; and
indexing the short-form media files for search and playback.

### Claim 19 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the operations further comprise:
outputting, to an output device, a listing of short-form content based on the classification, wherein the listing of short-form content comprises the segment.

### Claim 20 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the classification is an action sequence classification.
