Hierarchical Ordered Weighted Averaging for Media Content Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current media content recommendation systems fail to effectively combine diverse objectives, such as user satisfaction and publisher goals, to personalize media content selection for users, leading to suboptimal content presentation.
Innovation Solution
The implementation of a hierarchical ordered weighted averaging (HOWA) method that combines scores for user and publisher objectives using different parameters, allowing for high scores when multiple user objectives are met or any publisher objectives are satisfied, to determine the most suitable media content for presentation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple objectives (user satisfaction and publisher goals) are combined using traditional weighting methods, then the recommendation system can balance different goals, but it cannot flexibly adapt to different scenarios where some objectives require all conditions to be met while others require only one condition
Solution Approach 1:
The patent applies parameter changes by using different quantifier parameters (α values) to control the aggregation behavior of objectives. By adjusting the parameter α in the OWA operator, the system can switch between different aggregation modes (AND-like when α is high, OR-like when α is low) without changing the underlying combination mechanism, thus achieving flexibility while maintaining a unified framework.
Solution Approach 2:
The patent segments objectives into different groups (user satisfaction objectives and publisher goals) and applies different aggregation parameters to each group. This segmentation allows independent control over how strictly each group's conditions are evaluated, enabling the system to handle different objective types with appropriate aggregation strategies while keeping the overall structure organized.
2Ease of manufacture
If simple averaging is used to combine objective scores, then the system is easy to implement, but it treats all objectives equally and cannot express relationships where some objectives are more critical than others
Solution Approach 1:
The patent generalizes simple averaging by introducing the ordered weighted averaging (OWA) operator with a controllable parameter α. When α=0, the OWA operator reduces to simple averaging, maintaining ease of implementation. When α>0, it automatically adjusts weights based on the satisfaction levels of different objectives, enabling the system to express critical relationships without manual weight tuning, thus bridging simplicity and adaptability.
3Reliability
If the system requires all user objectives to be satisfied for high recommendation scores, then user satisfaction is maximized, but it becomes too restrictive and may exclude viable content that satisfies most rather than all objectives
Solution Approach 1:
The patent introduces dynamic weight adjustment through the OWA operator, where the weight assigned to each objective depends on its satisfaction level and the parameter α. This dynamic approach allows the system to adaptively balance between requiring all objectives (when α is high) and accepting most objectives (when α is lower), preventing rigid exclusion of viable content while still prioritizing highly satisfying recommendations.
Data Source
AI summary
An electronic device, for each media content item of a plurality of media content items, receives a respective score for each a first set of objectives and one or more other objectives and generates a respective score between a user and the media content item. The generating includes applying a first ordered weighted average to the respective scores for the first set of objectives, to produce a first combined score for the first set of objectives, applying a second ordered weighted average to the respective scores for a second set of objectives, wherein the second set of objectives includes (i) a resulting objective corresponding to the first set of objectives and having the first combined score and (ii) the one or more other objectives. The electronic device streams media content to the user selected based on the respective scores between the user and the media content items.