Closed Caption Keyword Analysis for Related Video References

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing technologies lack an efficient method to automatically generate and provide information about related video content to end-users during primary video programs, limiting the ability to recommend or display relevant content in real-time, especially for segmented content.

Innovation Solution

The method involves analyzing closed caption text from video transport streams to identify keywords and phrases that, when matched against a knowledge base, generate annotations for related video programs, which are then inserted into the transport stream, enabling the creation of a 'content web' that links segments of primary video programs to relevant content.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If automated analysis of closed caption text is implemented to generate related video references, then content discovery and user experience are improved, but system complexity and processing requirements increase

Engineering Contradiction:

Improvecontent discovery capabilityVSAvoidsystem complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system performs self-service by automatically analyzing closed caption text, identifying keywords, matching them against a knowledge base, and generating related video references without manual intervention. This automation resolves the contradiction by making the system self-sufficient in generating content recommendations, thereby improving adaptability while managing complexity through standardized automated processes

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces manual content curation and recommendation mechanisms with an automated text analysis system. By substituting human-driven content discovery with machine-based keyword analysis and knowledge base matching, the system improves content discovery capability while reducing the operational complexity associated with manual processes

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If real-time analysis of video segments is performed to generate related content references, then user engagement and content relevance are improved, but processing time and computational resources increase

Engineering Contradiction:

Improvecontent recommendation efficiencyVSAvoidprocessing time

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system performs preliminary action by pre-processing closed caption text during video playback, extracting keywords and preparing match queries before full processing is required. This allows the system to maintain real-time responsiveness while improving content recommendation efficiency through advance preparation of analysis data

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent applies segmentation by analyzing video content at the segment level rather than processing entire videos as single units. By dividing the video stream into manageable segments and analyzing closed captions for each segment independently, the system improves processing efficiency and reduces the time required to generate related content references for each segment

Inventive Principle:

Principle #1Segmentation

3Measurement precision

If comprehensive keyword matching against knowledge base is implemented, then accuracy of related video references is improved, but computational load and processing complexity increase

Engineering Contradiction:

Improvereference matching accuracyVSAvoidcomputational energy

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system applies partial action by performing keyword matching only on selectively identified keywords from closed caption text rather than analyzing every word. This selective approach maintains high reference matching accuracy for relevant terms while reducing the computational energy required compared to comprehensive full-text analysis

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The patent implements local quality by applying different processing intensities to different parts of the closed caption text. High-priority keywords that are more likely to yield relevant matches receive more intensive matching against the knowledge base, while less critical terms receive lighter processing, thereby optimizing accuracy while managing computational energy consumption

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS10219048B2Method and system for generating references to related video

Publication Date: 2019.02.26 ARRIS ENTERPRISES LLC

AI summary

A method of generating references to related videos is provided. Closed caption text of a primary video is analyzed to identify at least one keyword contained within the closed captioned text and a separate pre-determined listing of keywords. A keyword identified within the closed caption text and a context thereof is compared to keyword-context pairings provided within the listing. Information of a reference video related to the primary video is obtained by taking actions required by a rule in the listing associated with a matched keyword-context pairing when the keyword identified from the primary video and the context thereof is determined to match one of the keyword-context pairings in the listing. An annotation of the reference video relative to the primary video is created. A video processing electronic device and at least one non-transitory computer readable storage medium having computer program instructions stored thereon for performing the method are provided.