Reference Signature Generation for Unknown OTT Media Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing media monitoring systems for over-the-top (OTT) media struggle to generate reference signatures for unknown content, leading to delayed identification and inefficient processing, particularly when media sources like Hulu and Netflix do not provide signatures upfront, resulting in time-consuming and costly re-processing.
Innovation Solution
A system and method for generating and managing preliminary and unknown signatures, which are stored in separate databases, and are approved for addition to a reference library when meeting a threshold view count, allowing efficient matching and crediting of media consumption without requiring immediate metadata.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If media monitoring systems wait for upfront signatures from OTT media sources, then identification accuracy is improved, but processing time and operational efficiency deteriorate due to delayed identification and re-processing requirements
Solution Approach 1:
The system performs preliminary actions by generating unknown signatures and storing them in databases before official reference signatures are available. This advance preparation enables immediate matching when content is consumed, eliminating the need to wait for upstream providers to supply signatures and avoiding costly re-processing operations.
Solution Approach 2:
The signature database is segmented into multiple categories including unknown signatures, preliminary signatures, and reference signatures. This segmentation allows the system to handle different stages of signature availability separately, maintaining high processing efficiency by matching against available signatures while preserving the option to update with more accurate reference signatures later.
2Adaptability or versatility
If the system stores and processes unknown signatures without immediate metadata, then storage capacity and adaptability are improved, but system complexity and processing overhead increase
Solution Approach 1:
The system segments signature data into distinct categories (unknown, preliminary, reference signatures) stored in separate database tables. Each category has specific attributes and processing rules, which manages complexity through structured organization while maintaining high adaptability for different signature types and stages of validation.
Solution Approach 2:
Unknown signatures serve as an intermediary layer between no signature information and verified reference signatures. This intermediate stage allows the system to begin matching and crediting immediately while maintaining the flexibility to update with more accurate reference data later, effectively mediating between speed and accuracy requirements.
3Reliability
If reference signatures are generated only after threshold view counts are met, then data validation accuracy is improved, but time delays and processing bottlenecks worsen
Solution Approach 1:
The system performs preliminary matching operations using unknown and preliminary signatures before official reference signatures are generated through threshold validation. This allows crediting to begin immediately while the validation process continues in parallel, eliminating sequential delays without compromising the accuracy of the threshold-based validation process.
Solution Approach 2:
The system maintains continuous useful action by enabling signature matching and crediting operations to proceed continuously using available unknown and preliminary signatures, rather than pausing to wait for reference signature generation. The validation process continues independently in the background, ensuring both speed and accuracy are maintained simultaneously.
Data Source
AI summary
Methods and apparatus to generate reference signatures are disclosed. An example method includes collecting a first signature for media being presented to a plurality of households; crediting the media when the first signature matches a reference signature in a reference signature database; in response to determining that the first signature does not match a reference signature in the reference signature database and the first signature does not match an unidentified signature in an unknown signature database, storing the first signature in the unknown signature database; in response to determining that a second signature does not match the reference signature in the reference signature database and the second signature matches the unidentified signature in the unknown signature database, and increasing a count associated with the unidentified signature.