Digital Media Ranking via User Feedback Prominence
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The large volume of digital media stored online poses a challenge in sorting and presenting it in a useful, automated manner, as users struggle to identify and rank preferred media amidst a vast collection.
Innovation Solution
A system that receives digital media from a database, displays it with recommendation and comment fields, calculates a score based on user inputs, determines a ranking, and updates the display presentation accordingly, allowing for granular preference ranking and inference of media interest through explicit and implicit user feedback.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If digital media is sorted by traditional criteria (date, location, facial recognition), then the media can be organized automatically, but users still struggle to identify preferred media amidst large volumes
Solution Approach 1:
The system implements feedback loops where user interactions (likes, comments, shares, viewing time) are continuously collected and used to refine ranking algorithms. This creates a dynamic system that learns from user behavior to automatically surface preferred media without requiring manual sorting by users.
Solution Approach 2:
The system transitions from static sorting parameters (date, location) to dynamic ranking parameters that incorporate multiple user interaction metrics. By changing the parameters used for organization from simple metadata to complex behavioral signals, the system enables automatic identification of preferred media at scale.
2Quantity of substance
If the system presents all digital media to users, then users have complete access to their collection, but users are overwhelmed by the large volume of content
Solution Approach 1:
The system extracts and prioritizes only the most relevant media based on user preferences, separating preferred content from the rest of the collection. Instead of presenting all media equally, it extracts and surfaces the subset of content that matters most to each user, reducing perceived volume while maintaining access to the complete library.
Solution Approach 2:
The system segments the large volume of digital media into ranked tiers or categories based on user preference scores. By dividing the collection into segments of varying importance, the system manages content volume complexity through hierarchical organization rather than presenting a flat, overwhelming list.
3Ease of operation
If the system uses simple recommendation indicators (like buttons), then user input is easy to provide, but the system lacks granular information about user preferences
Solution Approach 1:
The system makes single user actions (such as viewing time or clicking) serve multiple functions for preference inference. By designing interactions that simultaneously provide engagement metrics, content interest signals, and behavioral patterns, the system extracts granular preference information without requiring users to perform multiple separate actions or provide detailed feedback.
Data Source
AI summary
Embodiments of this disclosure include systems and methods for tracking whether users recommend or dislike particular digital media, and presenting the digital media more or less prominently according to whether users recommend the digital media. Prominence can include the size or brightness of the digital media. It can also include duration or frequency of display, or how centrally located the digital media is or whether it is obscured, or appears sharp or blurry. Recommendations can come from a plurality of means, and can be normalized to generate a rank for each digital media, such that each digital media can be displayed more or less prominent based on the ranking.