Ranking Ephemeral Content Collections by Selection and Engagement Probability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional social networking systems fail to effectively rank ephemeral content item collections in a way that maximizes user engagement, as chronological or reverse chronological ordering does not guarantee that users will find the most interesting content.
Innovation Solution
The system ranks ephemeral content item collections based on a probability of user selection and time spent on each collection, using machine learning models trained on attributes such as user behavior, content characteristics, and collection features, to prioritize content that is likely to interest users.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If chronological or reverse chronological ordering is used to rank ephemeral content item collections, then the system is simple to implement, but user engagement is not maximized
Solution Approach 1:
The patent changes the ranking parameters from simple chronological timestamps to complex machine learning-generated scores that incorporate multiple factors including probability of user selection and probability of time spent. This transformation from basic temporal parameters to composite engagement-based parameters resolves the contradiction by prioritizing user engagement over implementation simplicity.
Solution Approach 2:
The patent introduces machine learning models as intermediary components that process raw content attributes and user behavior data to generate ranked scores. These intermediary models act as mediators between the simple chronological ordering system and the desired complex engagement optimization, enabling improved user engagement while maintaining a relatively straightforward system architecture.
2Productivity
If machine learning models are used to rank ephemeral content item collections based on user selection probability and time spent, then user engagement is maximized, but system complexity increases
Solution Approach 1:
The patent segments the ranking system into distinct machine learning models: a first model that predicts probability of user selection and a second model that predicts probability of time spent. This segmentation allows each model to specialize in specific aspects of engagement prediction, improving overall accuracy while making the complex system more manageable through modular decomposition.
Solution Approach 2:
The machine learning models are trained on multiple attributes including content characteristics, user behavior patterns, and collection features, enabling them to perform multiple functions simultaneously. This multi-functionality allows the system to maximize user engagement across diverse content types and user preferences without requiring separate specialized systems for each scenario.
Data Source
AI summary
Systems, methods, and non-transitory computer readable media can perform a first ranking to rank each ephemeral content item collection of a plurality of ephemeral content item collections based on a probability of a user selecting the ephemeral content item collection. One or more ephemeral content item collections from the first ranking to provide in an ephemeral content feed of the user can be selected. A second ranking to rank each ephemeral content item collection of the plurality of ephemeral content item collections other than the selected ephemeral content item collections from the first ranking based on a probability of the user spending time on the ephemeral content item collection can be performed. One or more ephemeral content item collections from the second ranking to provide in the ephemeral content feed of the user can be selected.