Reference Fingerprint Loading Using Selective Watermark Hashing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing media monitoring systems face inefficiencies in generating and storing media identification references, particularly when media segments lack sufficient watermark coverage, leading to incorrect crediting of time-shifted viewing and high computational demands from hashing signatures.
Innovation Solution
A method is introduced to optimize media identification reference generation by selectively generating and storing hashed reference signatures, where media segments with sufficient watermark coverage store unhashed signatures and those without watermark coverage store hashed signatures, reducing computational load and improving accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If all reference signatures are hashed for storage, then matching speed is improved, but computational energy and storage requirements increase significantly
Solution Approach 1:
The patent applies local quality by differentiating the processing treatment of reference signatures based on watermark coverage. Segments with sufficient watermark coverage store unhashed signatures, while segments without watermark coverage store hashed signatures. This selective approach optimizes resource allocation by applying hashing only where necessary, reducing overall computational energy and storage requirements while maintaining matching effectiveness.
2Speed
If all reference signatures are hashed for storage, then matching speed is improved, but storage requirements increase
Solution Approach 1:
The patent implements local quality by storing unhashed signatures for segments with sufficient watermark coverage and hashed signatures for segments without watermark coverage. This selective storage strategy reduces overall storage requirements while maintaining the ability to perform accurate matching, as watermarked segments can be identified through watermark detection without requiring hashed signature storage.
3Ease of operation
If watermark coverage is not checked, then processing simplicity is maintained, but incorrect crediting of viewership occurs in time-shifted viewing scenarios
Solution Approach 1:
The patent applies preliminary action by checking watermark coverage of media segments before determining how to process and store reference signatures. This advance check ensures that segments with sufficient watermark coverage are handled differently (storing unhashed signatures) compared to segments without watermark coverage (storing hashed signatures), thereby preventing incorrect viewership crediting in time-shifted viewing scenarios while maintaining processing efficiency.
Data Source
AI summary
Methods, apparatus, systems and articles of manufacture are disclosed selectively generating and storing hashed reference signatures. An example method disclosed herein determining whether watermark coverage of a first media segment satisfies a dropout constraint, the first media segment corresponding to a first monitoring time interval of a media source feed and, when the watermark coverage of the first media segment does not satisfy the dropout constraint hashing first media signatures associated with the first media segment to generate corresponding first hashed signatures and generating first reference data for the first media segment, the first reference data including the first hashed signatures and the first media signatures. The example method further includes, when the watermark coverage of the first media segment satisfies the dropout constraint, generating second reference data for the first media segment, the second reference data including the first media signatures.