IP Library › Granted Patent US 12689787
Granted Patent B2
US 12689787 · App. 18/581,336 · Granted Jul 21, 2026

System for programming content channels

Inventors: Ashish Baldua (San Jose, CA); Raghu Kodige (San Carlos, CA); Kajal Vibhakar (San Carlos, CA); Leena Savkur (Bangalore, IN); Ravi Sarma (Highlands, NJ)
Assignee: ANOKI, INC.
H04N21/2668H04N21/23418H04N21/235H04N21/2407H04N21/251H04N21/812
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 12689787
App. No.
18/581,336
Granted
Jul 21, 2026
Kind
B2
Abstract

A system for programming content channels based on multimodal extraction of metadata from content, wherein the metadata is extracted by processing one or more scenes in the content to extract metadata corresponding to multiple extraction modes, and an embedding model for each extraction mode wherein an aggregated embedding model responsive to the extracted metadata for each mode formulates an aggregated embedding. The system includes a consumer information database containing information regarding consumer consumption of content including at least an identification of content consumed. Programming logic based at least in part on comparing an embedding of metadata extracted by multimodal extraction of content consumed by the consumer to the aggregated embeddings including a vector comparison processor for determining the distance between the embedding generated based upon content consumed and the aggregated embedding is provided. The programming logic may use the distance between the embedding generated based on content consumed and the aggregated embedding to generate a program guide tailored to viewer preferences.

Claims (17)

1 . A system for programming content channels based on multimodal extraction of metadata from content, wherein said metadata is extracted by processing one or more scenes in said content to extract metadata corresponding to multiple extraction modes, and an embedding model for each extraction mode wherein an aggregated embedding model responsive to said extracted metadata for each mode formulates an aggregated embedding comprising:

a content library containing said aggregated embeddings wherein said aggregated embeddings are associated with content available for presentation to a consumer;

a consumer control interface allowing a consumer to select content consumption;

a consumer information database containing information regarding consumer consumption of content including at least an identification of content selected by a consumer for consumption wherein each identification of content selected for consumption is associated with an aggregated embedding based at least in part on metadata extracted from content selected by said consumer for consumption;

programming logic based at least in part on comparing an embedding of metadata extracted by multimodal extraction of content selected for consumption by said consumer to said aggregated embeddings of content available for presentation stored in said content library wherein said programming logic includes a vector comparison processor for determining the distance between said embedding generated based upon content selected by said consumer and said aggregated embeddings of content available for presentation as stored in said content library;

wherein said programming logic uses said distance between said embedding generated based upon content consumed and said aggregated embeddings of content available for presentation as stored in said content library to generate a program guide reflecting content available for presentation tailored to viewer preferences based on said distance.

2 . The system for programming content channels according to claim 1 wherein said programming logic includes an embedding aggregator to aggregate embeddings generated from multimodal metadata extraction of content selected for consumption by a user with embeddings of content previously selected for consumption.

3 . The system for programming content channels according to claim 2 wherein said embedding aggregator weights embeddings supplied to said embeddings aggregator.

4 . The system for programming content channels according to claim 3 wherein said weight is based on recency.

5 . The system for programming content channels according to claim 3 wherein said weight is based on time of day.

6 . The system for programming content channels according to claim 3 is based on frequency.

7 . The system for programming content channels according to claim 3 wherein said weight is based on consumer input.

8 . The system for programming content channels according to claim 1 wherein said programming guide includes multiple content channels.

9 . The system for programming content channels according to claim 8 wherein said programming logic orders said content channels in said programming guide based on user preferences.

10 . The system for programming content channels according to claim 9 wherein said programming logic orders said content channels in said programming guide by genre based on user preferences.

11 . The system for programming content channels according to claim 9 wherein said programming logic orders said content channels in said programming guide by vertical personalization based on user preferences.

12 . The system for programming content channels according to claim 9 wherein said programming logic orders said content channels in said programming guide by horizontal personalization based on user preferences.