# US 2026/0101091 A1 · System using contextual information to enhance relevance of supplemental content to programmed content

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

- Number: US 2026/0101091 A1
- Document ID: US20260101091A1
- Status: Published application
- Kind: A1
- Application number: 18/907,330
- Filed: 2024-10-04
- Published: 2026-04-09
- Earliest claimed: 2024-10-04
- Assignees: Anoki, Inc.
- Applicants: Anoki Inc.
- Inventors: Ashish Baldua; Ravi Sarma; Susmita Ghose; Sri Krishna Velivela
- Web page: https://patentgrep.com/patent/US20260101091A1

## CPC

- H04N 21/8133: {specifically related to the content, e.g. biography of the actors in a movie, detailed information about an article seen in a video programme}
- H04N 21/812: {involving advertisement data (advertising per se G06Q30/02)}
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

A content processing system may include a program scheduler connected to a content streaming platform. The program scheduler receives EPG information from the content streaming platform, an EPG database connected to the program scheduler containing channel identification, program start time, content identification assigned by the program scheduler, a content metadata database containing content source information, content length, and contextual information regarding the program including an aggregated embedding generated by multimodal metadata extraction from the content of the program. The content source information, the content length, and the contextual information are indexed by the content identification. The system may include a context analysis unit for generating the aggregated embedding having a content input connecting the program to the context analysis unit and an output connected to the content metadata database to store the aggregated embedding as the contextual metadata. The program scheduler may be connected to activate the context analysis unit.

## Claims

### Claim 1

A method for utilizing a deep understanding of content to select secondary content comprising:
issuing an aggregated embedding generated by multimodal metadata extraction from a primary content stream;
comparing said aggregated embedding to metadata corresponding to secondary content generated by multimodal metadata extraction from said secondary content; and
selecting secondary content based on said step of comparing said aggregated embedding to metadata corresponding to said secondary content.

### Claim 2 (depends on 1)

The method according to claim 1 further comprising:
the steps of identifying an advertising opportunity in said primary content; and
issuing a bid request for said advertising opportunity wherein said bid request includes identification of said advertising opportunity and said aggregated embedding.

### Claim 3

A content processing system comprising:
a program scheduler connected to a content streaming platform wherein said program scheduler receives electronic program guide information from said content streaming platform;
an electronic program guide database connected to said program scheduler containing channel identification program start time information and a content identification assigned by said program scheduler; and
a content metadata database containing content source information, content duration, and contextual information regarding said program including an aggregated embedding generated by multimodal metadata extraction from content of said program wherein said content source information, said content duration information and said contextual information are indexed by said content identification assigned by said program scheduler.

### Claim 4 (depends on 3)

The content processing system according to claim 3 further comprising a context analysis unit for generating an aggregated embedding by multimodal metadata extraction having a content input connecting said program to said context analysis unit and having an output connected to said content metadata database and configured to store said aggregated embedding as said contextual metadata.

### Claim 5 (depends on 4)

The content processing system according to claim 4 wherein said program scheduler is connected to activate said context analysis unit.

### Claim 6 (depends on 5)

The content processing system according to claim 5 wherein said program scheduler is configured to activate said context analysis unit if it determines that said content metadata database does not have contextual metadata stored for a program identified by said electronic program guide information.

### Claim 7 (depends on 6)

The content processing system according to claim 6 further comprising
a supply-side ad server connected to said content streaming platform wherein said supply-side server receives an advertisement request including a channel identification from said content streaming platform and provides an advertisement responsive to said advertisement request to said content streaming platform; and
a contextual advertisement server platform connected to said supply side server, wherein said contextual advertisement server platform receives an advertisement request including a channel identification from said supply side server, and said contextual advertisement server platform uses said channel identification to retrieve contextual metadata from said context metadata database.

### Claim 8 (depends on 7)

The content processing system according to claim 7 further comprising a demand side advertisement server connected to said contextual advertisement server platform to receive contextual metadata for use in identifying a responsive advertisement and based on said contextual metadata.

### Claim 9 (depends on 8)

The content processing system according to claim 8 wherein said contextual advertisement server platform is a supply-side platform.

### Claim 10 (depends on 8)

The content processing system according to claim 8, wherein said contextual advertisement server platform is a demand-side platform.
