Skip-Based Ad Detection Using Listener Retention Graphs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
There is a need for systems and methods to accurately determine the presence and location of advertisements in media content items, such as podcasts, which can be embedded without clear markers, and distinguish them from primary content using listener retention information.
Innovation Solution
Generating a retention graph from user listening histories to identify dips in listener numbers, which correspond to advertisements, and applying predefined criteria to determine the presence and location of sub-content within media items.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If advertisements are embedded in media content items without clear markers, then the content can be seamlessly integrated, but it becomes difficult to accurately detect and locate the advertisements
Solution Approach 1:
The patent introduces listener retention data as an intermediary signal to detect advertisements. Instead of relying on explicit markers in the audio content, the system uses behavioral data from listening history that shows where users skip or stop listening, which correlates with advertisement locations. This mediator enables indirect detection of embedded advertisements without requiring direct markers in the content.
Solution Approach 2:
The system uses listener retention feedback to identify advertisement locations. By analyzing where listeners consistently disengage or skip in the media content, the system receives feedback about the presence and location of advertisements, enabling accurate detection even without explicit markers.
2Measurement precision
If listener retention analysis is used to detect advertisements, then accurate advertisement location can be identified, but the system complexity increases due to processing listening history data
Solution Approach 1:
The system leverages existing listening history data that is already being collected and stored for other purposes (such as personalization and recommendation). By repurposing this existing data infrastructure, the system avoids building separate complex data collection systems, reducing overall system complexity while maintaining high detection precision.
Solution Approach 2:
The system pre-processes and stores listening history data in advance, organizing it by media item and timestamp. This preliminary organization of data into structured formats (such as retention graphs) simplifies subsequent advertisement detection operations, reducing the computational complexity required during the actual detection phase.
Data Source
AI summary
An electronic device obtains a listening history for a media item, the listening history including retention information indicating, for each respective portion of a plurality of portions of the media item, a number of listeners who listened to the respective portion of the media item. The electronic device, using the retention information, determines a pattern indicating a reduction in the number of listeners who listened to corresponding portions of the media item and determines a start time and an end time corresponding to a first portion of the corresponding portions of the media item. In accordance with the determination that the first portion of the corresponding portions of the media item meets predefined sub-content criteria, the electronic device stores an indication that the first portion of the media item comprises first sub-content, different from primary content, embedded in the media item.