Media Exposure Crediting Using Source-Filtered Hash Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing audience measurement systems face computational inefficiencies and high processing costs due to the brute force signature matching and hash key matching processes, particularly when dealing with large reference asset databases, leading to prolonged processing times and resource consumption.
Innovation Solution
Implementing a method that determines a source identifier to filter reference hash keys, reducing the quantity of hash keys processed by using network traffic data and predetermined audience data to select a set of reference hash keys that match meter hash keys and correspond to the source identifier, thereby optimizing the hash key matching process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If brute force signature matching and hash key matching processes are used to identify media in large reference asset databases, then media identification accuracy is maintained, but computational expense and processing time increase significantly
Solution Approach 1:
The patent segments the large reference asset database into multiple partitions or subsets based on metadata characteristics. Instead of performing brute force matching against the entire database, the system divides the search space into smaller manageable segments, reducing the computational burden while maintaining identification accuracy through targeted matching in relevant partitions.
Solution Approach 2:
The patent applies preliminary filtering using metadata attributes (such as title, description, tags, or other descriptive data) before performing the actual signature matching process. This preliminary action eliminates irrelevant reference assets from consideration, so that the computationally intensive matching operations are performed only on a reduced subset of potentially relevant media, thereby improving processing speed without sacrificing accuracy.
2Reliability
If brute force signature matching is performed across all reference hash keys, then comprehensive media identification is achieved, but resource consumption and processing time increase
Solution Approach 1:
The patent extracts and utilizes metadata attributes from reference assets to create filtering criteria. By taking out and analyzing these descriptive attributes beforehand, the system can identify and exclude reference assets that do not match the query characteristics, thereby extracting only the relevant subset for detailed signature matching. This maintains identification completeness for relevant assets while reducing overall processing time.
Solution Approach 2:
The system performs preliminary metadata analysis and filtering before the actual signature matching process. This preliminary action pre-screens the reference asset database using readily available descriptive data, eliminating obviously irrelevant assets early in the process. This ensures that comprehensive matching is performed only on assets that pass the metadata filter, maintaining reliability while reducing processing time.
3Productivity
If the quantity of reference hash keys processed is reduced through source filtering, then computational expense and processing time decrease, but media identification accuracy may be compromised
Solution Approach 1:
The patent applies local quality filtering by using source-specific metadata attributes that are relevant to particular media sources or types. Instead of applying a uniform filter across all reference assets, the system tailors the filtering criteria to the local characteristics of different source domains, ensuring that the reduction in processed hash keys does not eliminate potentially relevant matches from specific sources. This maintains identification accuracy within each local context while improving overall efficiency.
Solution Approach 2:
The patent changes the parameters used for filtering by incorporating multiple metadata attributes (such as title keywords, description terms, tags, or source-specific identifiers) rather than relying on a single criterion. By adjusting and combining multiple parameters, the system achieves more precise filtering that reduces the candidate set effectively while maintaining the ability to identify correct matches across diverse media types and sources.
Data Source
AI summary
In one example, a method performed by an audience measurement computing system is described. The method includes determining a source identifier that identifies a media source from which media presented by a media presentation device at a media presentation environment is received. The method also includes using meter hash keys and the source identifier as a basis to select, from stored reference hash keys representing signatures of previously-identified media, a set of reference hash keys that match the meter hash keys and correspond to the source identifier, each reference hash key associated with a corresponding media identifier, where the meter hash keys are generated based on meter signatures representing the media. The method also includes identifying the media based on the set of reference hash keys. The method also includes generating exposure data that credits exposure of an audience member at the media presentation environment to the identified media.