Broadcast Content Detection via Self-Similarity Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing radio monitoring systems fail to detect and track unknown broadcast content items that have not been registered in their databases, as they rely solely on matching incoming signals with pre-existing pattern vectors, resulting in these unknown items being ignored.

Innovation Solution

The system employs the self-similarity principle to detect repeated programs, even if they are not registered, by extracting pattern vectors from repeated instances and using them to identify and register unregistered content, with an Audio-Selector choosing the best-quality repetition for database entry, and operates in modes that focus on undetected or all time periods for comprehensive content harvesting.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the system relies solely on matching incoming signals with pre-existing pattern vectors in the database, then the detection process is simple and fast, but unknown or unregistered content items are ignored and cannot be detected

Engineering Contradiction:
Improvedetection accuracyVSAvoidability to detect unknown content
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The system performs preliminary detection of potential content items and stores them as candidate patterns before formal registration. This preliminary action allows the system to capture unknown content that hasn't been officially registered yet, while maintaining the structured approach of pattern matching for known content.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces an intermediary mechanism between known content and unknown content detection. The system uses a candidate pattern buffer that acts as an intermediary storage layer, allowing transitions from detecting only registered content to detecting and tracking unknown content, and finally to formal registration.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If the system tracks and submits every potential unknown content item for human identification, then detection of unregistered content improves, but system complexity and processing time increase

Engineering Contradiction:
Improveability to detect unknown contentVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system applies partial action by not submitting every single detected pattern for human identification. Instead, it uses filtering criteria to select only those candidate patterns that meet certain thresholds for uniqueness and quality, reducing the burden on human operators while still capturing important unknown content.

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The system implements feedback mechanisms where detection results are analyzed and used to adjust detection parameters. The feedback loop allows the system to learn from previous detections and refinements, improving accuracy over time without requiring proportional increases in system complexity.

Inventive Principle:
Principle #23Feedback

3Measurement precision

If the system processes all broadcast signals to detect unknown content, then content detection accuracy improves, but processing time and computational resources increase

Engineering Contradiction:
Improvecontent detection accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The detection process is segmented into distinct phases: initial pattern extraction, candidate identification, filtering, and submission for identification. This segmentation allows the system to process signals efficiently by focusing computational resources on promising candidates rather than uniformly processing all possible content items.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs preliminary filtering and analysis of broadcast signals to identify potential unknown content before committing to full processing. This preliminary action includes quick checks for pattern uniqueness and quality metrics, eliminating obvious false positives early in the process.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP1952639B1Method and apparatus for automatic detection and identification of unidentified broadcast audio or video signals
Publication Date: 2019.01.30 MOBILE RES LABS
  • EP1952639B1 patent drawingFigure 1
  • EP1952639B1 patent drawingFigure 2
  • EP1952639B1 patent drawingFigure 3

AI summary

A system and method of detecting unidentified broadcast electronic media content using a self-similarity technique is presented. The process and system catalogues repeated instances of content that has not been positively identified, but are sufficiently similar as to infer repetitive broadcasts. These catalogued instances may be further processed on the basis of different broadcast channels, sources, geographic locations of broadcasts or format to further assist the identification thereof.