Audio Video Content Categorization via Fingerprint Similarity

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing digital video recorder (DVR) systems face inefficiencies in recording audio/video content due to varying program durations and start times, leading to inefficient storage use and reliance on external data for trimming excess content.

Innovation Solution

A method for automatic categorization of audio/video content that detects advertisement blocks, computes fingerprints for data frames, and compares similarity levels to determine split points, allowing for precise trimming and splitting of content without external data reliance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If fixed recording time intervals are used for DVR recording, then recording simplicity is maintained, but storage space is wasted due to varying actual program durations

Engineering Contradiction:
Improverecording simplicityVSAvoidstorage space waste
Core Design Contradiction:
Ease of operationVSLoss of substance

Solution Approach 1:

The system performs preliminary actions by detecting advertisement blocks and computing fingerprints during the recording process, enabling automatic identification of content boundaries before final storage allocation, thus optimizing storage usage while maintaining simple user operation

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent replaces manual time-based recording mechanisms with automated content-based detection using audio/video fingerprinting technology, allowing the system to automatically identify program boundaries and adjust recording intervals without user intervention

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If external timestamp data is used for trimming excess recording data, then recording precision is improved, but system complexity increases due to additional communication infrastructure requirements

Engineering Contradiction:
Improverecording precisionVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system performs self-service by autonomously detecting advertisement blocks and computing fingerprints from the recorded content itself, eliminating the need for external timestamp data or communication infrastructure while maintaining high recording precision

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent introduces an intermediary mechanism using audio/video fingerprinting technology that acts as a mediator between the recorded content and the trimming process, enabling precise content boundary identification without requiring external data sources

Inventive Principle:
Principle #24Intermediary (Mediator)

3Measurement precision

If advertisement block detection and fingerprint computation are performed, then content boundary identification accuracy is improved, but processing time increases

Engineering Contradiction:
Improvecontent boundary identification accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system extracts only the essential information needed for boundary detection by focusing computation on advertisement block detection and fingerprint comparison, rather than processing the entire recorded content, thus reducing processing time while maintaining high accuracy

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentUS10503980B2System and method for automatic categorization of audio/video content
Publication Date: 2019.12.10 ADVANCED DIGITAL BROADCAST
  • US10503980B2 patent drawing
  • US10503980B2 patent drawing
  • US10503980B2 patent drawing

AI summary

Method for categorization of audio/video content, the method comprising the steps of: detecting a start and an end of at least one advertisements block present in said audio and/or video content; for each detected advertisements block: selectively collecting audio and/or video data frames, from said audio and/or video content, within specified time intervals prior to said detected advertisements block; for each time interval, computing a fingerprint; selectively collecting reference audio and/or video data frames, after said advertisements block, for comparison and computing a reference fingerprint for said reference audio and/or video data frames; comparing said reference fingerprint with at least one fingerprint collected prior to the start of said advertisements block in order to obtain a level of similarity between said fingerprints; based on the level of similarity, taking a decision whether to indicate a split point between content items present in said audio/video content.