Media Content Virality Prediction and Storage Distribution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
It is challenging for producers and distributors of media content, such as videos, to predict which content items will 'go viral' and gain popularity, as existing methods lack effectiveness in forecasting viral content and optimizing its distribution across networks.
Innovation Solution
A computing device analyzes media content items using visual features and constructs a media popularity model to predict whether a content item will exceed a popularity threshold, determining optimal storage locations and suggesting changes to increase virality, by comparing the content to a decision boundary based on viral and non-viral datasets.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If media content items are stored at a single central location, then storage management is simple, but delivery speed and reliability decrease when content becomes viral
Solution Approach 1:
The patent segments the storage system by distributing media content items across multiple network locations rather than storing them centrally. This segmentation enables faster and more reliable content delivery when videos go viral, as content can be retrieved from geographically distributed storage nodes closer to end users, reducing latency and improving access speed.
Solution Approach 2:
The system performs preliminary action by predicting which media content items are likely to become viral before they actually gain popularity. Based on these predictions, the system proactively pre-distributes the content to multiple network locations in advance, ensuring that when the content does go viral, it is already positioned for rapid delivery without requiring last-minute redistribution.
2Reliability
If media content items are pre-distributed across multiple network locations, then delivery reliability improves, but network bandwidth consumption increases
Solution Approach 1:
The system changes the parameter of content distribution by using prediction confidence levels to dynamically adjust distribution parameters. Instead of uniformly distributing all content, the system modifies distribution parameters based on predicted virality scores, distributing content more aggressively for high-confidence viral predictions and conservatively for lower-confidence cases, thereby optimizing the balance between delivery reliability and bandwidth consumption.
3Reliability
If all media content items are stored redundantly across the network, then content availability improves, but storage costs increase
Solution Approach 1:
The patent applies local quality by making different parts of the network store different content based on local demand patterns and prediction results. Instead of uniform redundancy, each network location stores content that is most relevant to its regional user base, with hot content replicated more widely and niche content stored locally. This approach improves content availability for accessing users while reducing total storage capacity requirements.
Data Source
AI summary
A method includes receiving media data corresponding to a media content item. The method includes analyzing the media data to determine characteristics of the media content item based on first visual information of the media content item. The method includes analyzing the characteristics of the media content item based on a media popularity data structure to generate a prediction of whether the media content item is likely to exceed a popularity threshold within a particular period of time. The method further includes determining a location to store the media data based on the prediction.