Audience Metric Ranking Using Device Viewership Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods fail to accurately reflect the relationship between device categories and content viewing time, particularly in determining audience metrics for content delivery, as they do not adequately consider the level of viewing by individual devices.
Innovation Solution
Devices are grouped into subsets using a clustering algorithm based on content viewership data, with a rank metric and index parameter to determine the likelihood of a content delivery spot attracting a significant audience segment with a particular extent of viewership.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If devices are grouped into subsets based on content viewership data using clustering algorithms, then audience metric determination accuracy is improved, but device complexity and data processing requirements increase
Solution Approach 1:
The patent divides the total device population into multiple subsets based on content viewership behavior patterns. Each subset represents a distinct audience segment with similar viewing characteristics. This segmentation enables precise audience metric determination by analyzing each subset separately rather than treating all devices uniformly, thereby improving measurement accuracy while managing complexity through structured categorization.
Solution Approach 2:
The patent transforms raw viewership data into meaningful parameters such as index parameters that quantify audience segment characteristics. By changing the representation of data from raw viewing logs to aggregated statistical parameters, the system achieves accurate audience metrics without proportionally increasing processing complexity. The index parameter serves as a compressed representation that captures essential viewing behavior patterns.
2Measurement precision
If individual device viewing levels are considered in parameter determination, then audience metric accuracy is improved, but computational requirements and processing time increase
Solution Approach 1:
The patent performs preliminary clustering of devices into subsets based on historical viewership data before conducting audience metric analysis. This preliminary action organizes the data structure in advance, so that when individual device viewing levels need to be considered, the devices are already grouped in a way that facilitates efficient processing. The clustering is computed once and reused for multiple metric determinations, reducing repeated processing time.
Solution Approach 2:
The patent combines individual device viewing levels with subset-level statistics to determine comprehensive audience parameters. By merging individual device data with aggregated subset characteristics, the system achieves accurate audience metrics that reflect both individual and collective viewing behaviors. This merging approach allows efficient computation by leveraging pre-computed subset statistics rather than processing each device independently from scratch.
3Measurement precision
If clustering algorithms are used to group devices by content genre propensity, then audience segmentation accuracy is improved, but system complexity and data storage requirements increase
Solution Approach 1:
The patent extracts essential viewing behavior characteristics from comprehensive device data to create clustering parameters. Instead of storing and processing all raw viewership data, the system extracts key features such as content genre preferences and viewing frequency patterns that are sufficient for accurate audience segmentation. This extraction reduces data storage requirements while maintaining segmentation accuracy by retaining only the most discriminative features.
Solution Approach 2:
The patent transforms detailed viewership data into condensed index parameters that capture audience segment characteristics. By changing the data representation from extensive raw viewing logs to compact statistical parameters, the system achieves accurate audience segmentation with reduced storage requirements. The index parameters serve as efficient summaries that enable precise segmentation without requiring storage of the original detailed data.
Data Source
AI summary
Methods, systems, and apparatuses for audience metric determination are described herein. An audience segment may be targeted for delivery of content. A clustering algorithm may be used to categorize a quantity of users or devices into subsets based on a propensity to consume, present or output a particular type of content, and a quantity of time to output the particular type of content. A weight may be assigned to each subset based on its relevance to other subsets, such as based on data variance, e.g., on a distance to a midpoint of a specific subset of the subsets. An index parameter may be determined for the datasets, e.g., based on each weight for each subset, and data may be generated that reflects a ranking of content delivery spots for delivery of content to the audience segment.