Neural Network Boring Media Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Media monitoring entities face challenges in accurately distinguishing between media with and without embedded codes, leading to false alarms and increased operational burdens, as they often mistakenly identify boring media events lacking codes as non-boring media, resulting in unnecessary processing and storage demands.
Innovation Solution
The implementation of a system utilizing machine learning techniques, specifically a neural network trained on audio and video feature calculations, to differentiate between boring and non-boring media events by analyzing characteristics such as image temporal variation, chromatic information, sound temporal domain flatness, and sound harmonic richness, thereby reducing false alarms and optimizing resource utilization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If media monitoring entities process all media events without differentiation, then comprehensive monitoring coverage is achieved, but false alarms increase and resource consumption rises
Solution Approach 1:
The system performs preliminary classification of media events using audio and video feature analysis before full processing. By calculating features like image temporal variation, chromatic information, sound temporal domain flatness, and sound harmonic richness in advance, the system identifies boring media events and excludes them from further processing, preventing false alarms before they occur
Solution Approach 2:
The media monitoring system serves itself by automatically distinguishing between boring and non-boring media events through machine learning algorithms. The neural network trained on audio-video features autonomously filters out boring media without requiring manual intervention or external assistance, improving both accuracy and resource efficiency
2Measurement precision
If machine learning analysis with multiple features is implemented, then boring media detection accuracy improves, but system complexity increases
Solution Approach 1:
The detection system is segmented into distinct functional modules: audio feature extraction, video feature extraction, neural network classification, and decision-making components. Each module handles specific tasks (e.g., sound temporal domain flatness calculation, image chromatic information analysis), making the complex system manageable and maintainable while achieving high detection accuracy
Solution Approach 2:
The neural network classifier serves multiple functions simultaneously: it classifies boring vs. non-boring media, detects presence of embedded codes, and generates alerts only when necessary. This multi-functionality reduces the need for separate systems for each task, managing complexity while maintaining high measurement precision
Data Source
AI summary
Methods, apparatus, systems, and articles of manufacture are disclosed for the detection of boring media. An example apparatus includes a feature calculator to determine at least a first feature and a second feature associated with at least one of a video feed or an audio feed of monitored media when a media monitoring code is not detected in the monitored media, the first and second features representing different characteristics of at least one of the video feed or the audio feed, and a boring media event determiner implemented by hardware or at least one processor to process the first and second features with a neural network, propagate a code absence alert to a first server when an output of the neural network does not satisfy a threshold, and propagate a boring media event notification to a second server when the output of the neural network does satisfy the threshold.