Asset Prediction Model for Ranked Interface Presentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current interfaces do not prioritize contextually or user-appropriate assets, requiring users to perform specific interactions to access relevant assets, and the presentation of assets is not tailored to individual users or systems, leading to suboptimal engagement opportunities.
Innovation Solution
A system utilizing a trained asset prediction model, configured as a machine learning model, to receive user and asset features and generate a ranked list of assets that maximize engagement, selecting a predetermined number of assets for inclusion in an interface based on descending ranked order.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If interfaces use fixed structures with all engagement assets distributed across multiple pages, then comprehensive asset availability is achieved, but user engagement and accessibility are reduced
Solution Approach 1:
The patent extracts only the most relevant engagement assets from the complete set and presents them prominently in the user interface. The asset prediction model identifies and extracts high-value assets based on user features and engagement likelihood, removing the need for users to search through all available assets across multiple pages.
Solution Approach 2:
The patent applies local quality by personalizing the asset presentation for each user based on their features and behavior. Different users see different subsets of assets tailored to their preferences and needs, rather than a uniform presentation of all assets. This creates locally optimized interface quality for each user segment.
2Loss of information
If interfaces present all engagement assets, then complete information is provided, but user time and attention are wasted
Solution Approach 1:
The asset prediction model performs preliminary filtering and ranking of engagement assets before they are presented to the user. By pre-processing and predicting which assets are most relevant, the system prepares the optimized asset set in advance, eliminating the need for users to spend time searching through all assets.
Solution Approach 2:
The patent replaces the mechanical browsing and searching process with an intelligent prediction system. Instead of users manually navigating through assets, the machine learning model automatically identifies and presents relevant assets, substituting computational intelligence for manual user effort.
3Ease of manufacture
If interfaces use generic asset presentation, then implementation simplicity is maintained, but user-specific engagement opportunities are lost
Solution Approach 1:
The patent introduces dynamics by making asset presentation adaptive and responsive to individual user characteristics. The interface dynamically adjusts which assets are shown based on user features, behavior, and predicted engagement likelihood, transforming from a static generic presentation to a dynamic personalized experience.
Solution Approach 2:
The system changes key parameters of asset presentation including selection criteria, ranking order, and visibility based on user-specific features. By varying these parameters according to user profiles, the system achieves personalized engagement optimization while maintaining a consistent interface framework.
Data Source
AI summary
Systems and methods of generating an interface including one or more assets selected by an asset prediction model are disclosed. A user identifier associated with a set of user features and a set of assets each including a set of asset features is received and a set of predicted assets is generated using a trained asset prediction model. The trained asset prediction model comprises a machine learning model configured to receive the set of user features and the set of asset features for each asset in the set of assets and output the set of predicted assets and the trained asset prediction model is configured to maximize a likelihood of engagement for the set of predicted asset. An interface including a predetermined number of assets selected from the set of predicted assets in descending ranked order is generated.