IP Library Granted Patent US 12689801
Granted Patent B2
US 12689801 · App. 18/822,856 · Granted Jul 21, 2026

Systems and methods for generating dynamic annotations

Inventors: Ankur Anil Aher (Kalyan, IN); Jeffry Copps Robert Jose (Chennai, IN)
Assignee: Adeia Guides Inc.
H04N21/462G06F40/295H04N21/4316H04N21/4532H04N21/4622H04N21/8133G06F40/169G06F40/258G06F40/279
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12689801
App. No.
18/822,856
Filed
Sep 3, 2024
Granted
Jul 21, 2026
Kind
B2
Art Unit
2424
USPC
725/34
Abstract

A system for managing media content annotations is configured to generate annotations having a format similar to a title and tailored to a user profile. The system identifies a media content item and identifies a user entity. The system selects from among a plurality of annotations linked to the media content item and stored in metadata. For example, the system may generate more than one annotation, generate links between each annotation and user profile information, and then select among the annotations for the most appropriate annotation for a given user. The annotation may include keywords or entities that are included in, linked to, or otherwise associated with the user profile information. The system outputs, or generates for output, a display that includes a representation of the media content item and the selected annotation.

Claims (39)

1 . A method comprising:

identifying a title corresponding to a media content item;

processing the identified title with an annotation application, wherein the annotation application comprises a model trained by a learning technique configured to recognize words in the title and identify a structure of the recognized words;

determining a format of the title based at least in part on the identified structure;

generating a title template based at least in part on: (1) the recognized words in the title, (2) metadata associated with the media content item, and (3) the determined format;

causing to output an overlay based at least in part on the title template populated with content matched to the determined format, wherein the overlay comprises a selectable link to the media content item; and

based at least in part on selection of the selectable link, causing to output a representation of the media content item and the overlay.

2 . The method of claim 1 , wherein:

the learning technique configured to recognize words in the title is further configured to determine a content and a context of the title; and

the generating the title template is further based at least in part on the content and the context of the title.

3 . The method of claim 1 , wherein a database of overlays is updated as a new title is identified and processed.

4 . The method of claim 1 , further comprising:

subsequent to processing the identified title with the annotation application, parsing the title by a dependency parser configured to identify a set of words that are modified by other words.

5 . The method of claim 1 , wherein the annotation application stores, in memory, the words of the title as a collection of at least one of ASCII characters, a pattern, an identifier, or a string.

6 . The method of claim 1 , wherein the annotation application comprises a title processor comprising an entity identifier, a parts of speech (POS) tagger, a dependency parser, and a template generator.

7 . The method of claim 6 , wherein the entity identifier is configured to identify entities based at least in part on a user profile search history, or a user profile viewing history.

8 . The method of claim 1 , wherein the model trained by the learning technique is configured to identify one or more parts of speech.

9 . The method of claim 1 , wherein the metadata associated with the media content item comprises closed caption annotation.

10 . The method of claim 1 , wherein the causing to output the overlay based at least in part on the title template populated with the content matched to the determined format is further based at least in part on a preset user setting for display of the overlay.

11 . A system comprising:

control circuitry configured to:

identify a title corresponding to a media content item;

process the identified title with an annotation application wherein the annotation application comprises a model trained by a learning technique configured to recognize words in the title and identify a structure of the recognized words;

determine a format of the title based at least in part on the identified structure;

generate a title template based at least in part on: (1) the recognized words in the title, (2) metadata associated with the media content item, and (3) the determined format;

cause to output an overlay based at least in part on the title template populated with content matched to the determined format, wherein the overlay comprises a selectable link to the media content item; and

based at least in part on selection of the selectable link, cause to output a representation of the media content item and the overlay.

12 . The system of claim 11 , wherein:

the learning technique configured to recognize words in the title is further configured to determine a content and a context of the title; and

the generating the title template is further based at least in part on the content and the context of the title.

13 . The system of claim 11 , wherein a database of overlays is updated as a new title is identified and processed.

14 . The system of claim 11 , wherein the circuitry is configured to:

subsequent to processing the identified title with the annotation application, parsing the title by a dependency parser configured to identify a set of words that are modified by other words.

15 . The system of claim 11 , wherein the annotation application stores, in memory, the words of the title as a collection of at least one of ASCII characters, a pattern, an identifier, or a string.

16 . The system of claim 11 , wherein the annotation application comprises a title processor comprising an entity identifier, a parts of speech (POS) tagger, a dependency parser, and a template generator.

17 . The system of claim 16 , wherein the entity identifier is configured to identify entities based at least in part on a user profile search history, or a user profile viewing history.

18 . The system of claim 11 , wherein the model trained by the learning technique is configured to identify one or more parts of speech.

19 . The system of claim 11 , wherein the metadata associated with the media content item comprises closed caption annotation.

20 . The system of claim 11 , wherein the causing to output the overlay based at least in part on the title template populated with content matched to the determined format is further based at least in part on a preset user setting for display of the overlay.