Media Surfing Detection From Packet Traffic for Exposure Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increasing prevalence of 'surfing' behavior in streaming media services leads to an increase in inconclusive categorizations, as users browse through content menus without engaging in traditional streaming patterns, complicating the identification of media content and leading to a rise in 'All Other Tuning' (AOT) or 'All Other Code' (AOC) classifications.
Innovation Solution
Implement a mechanism to detect surfing activity by analyzing packet-data traffic patterns and content presentation, using pre-established surfing-profile data to differentiate between streaming and browsing behaviors, and adjust the media content identification process accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional streaming pattern recognition is used to identify media content, then identification accuracy for traditional streaming is improved, but identification reliability increases for surfing behavior
Solution Approach 1:
The patent changes the detection parameters from traditional streaming patterns (continuous high-bitrate data flow) to surfing-specific patterns (intermittent low-bitrate menu navigation, repeated content requests, short session durations). This allows the system to accurately identify and categorize surfing behavior separately from traditional streaming, resolving the contradiction between maintaining high identification accuracy for traditional streaming while improving reliability for surfing behavior detection.
2Measurement precision
If packet-data traffic analysis is used to detect streaming patterns, then streaming identification is improved, but differentiation between streaming and surfing becomes more complex
Solution Approach 1:
The patent segments traffic analysis into distinct categories: streaming traffic characteristics (continuous high-bitrate flows) and surfing traffic characteristics (intermittent low-bitrate requests, menu navigation patterns). By creating separate analysis pathways for each behavior type, the system maintains simple, targeted detection rules for each while improving overall differentiation capability without excessive complexity.
Solution Approach 2:
The patent applies partial action by focusing detection efforts only on key distinguishing features rather than analyzing all traffic parameters in detail. For streaming detection, it focuses on bitrate continuity; for surfing, it focuses on request frequency and session duration. This selective approach maintains simplicity while achieving accurate differentiation.
3Quantity of substance
If conventional media monitoring is applied to surfing activity, then data collection coverage is improved, but data quality and conclusiveness deteriorates
Solution Approach 1:
The patent introduces an intermediary classification layer that processes raw traffic data before final media exposure characterization. This intermediary step identifies surfing patterns and routes them to appropriate categorization, preventing misclassification of surfing activity as traditional media exposure. The result is both comprehensive data collection and improved characterization precision through proper categorization.
Data Source
AI summary
A method and system for measuring media-surfing activity. An example method includes a computing system receiving reporting of packet-data activity at a panelist site. Further, the example method includes the computing system using at least the received reporting of packet-data activity at the panelist site as a basis to detect occurrence of media-surfing activity at the panelist site, where the media-surfing activity comprises a user surfing through one or more content-selection menus. Still further, the example method includes the computing system reporting the detected occurrence of media-surfing activity at the panelist site as media-exposure data. In further implementations, the method additionally includes the computing system using signature matching as a further basis to detect the occurrence of media-surfing, such as by detecting through the signature matching the presentation of streaming media content for a threshold short duration suggestive of a program preview when a user is engaged in media-surfing.