Recommendation Logic Allocation Using Viewer Interaction Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional recommendation systems in live streaming platforms provide uniform recommendation logic to all users, failing to account for individual user preferences and interactions, resulting in suboptimal content recommendations.
Innovation Solution
A system that adjusts and customizes content recommendations based on individual user interaction data, utilizing multiple recommendation logics to tailor content allocation to each viewer's preferences and behaviors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If uniform recommendation logic is provided to all users, then system complexity is reduced and ease of operation is improved, but recommendation precision and user satisfaction deteriorate
Solution Approach 1:
The patent segments the uniform recommendation logic into multiple distinct recommendation logics (first recommendation logic and second recommendation logic), each tailored for different user types or preferences. This allows the system to provide customized recommendations while maintaining manageable complexity through modular logic design.
Solution Approach 2:
The system dynamically selects and switches between different recommendation logics based on user interaction data and behavior patterns. This dynamic adaptation enables the system to optimize recommendation precision for each user without requiring manual configuration, resolving the contradiction between automated precision and operational simplicity.
2Measurement precision
If multiple recommendation logics are implemented with dynamic adjustment, then recommendation precision and user satisfaction are improved, but system complexity increases
Solution Approach 1:
The system implements a feedback mechanism that collects user interaction data and uses it to automatically adjust the allocation and selection of recommendation logics. This closed-loop feedback system enables precise recommendations while managing complexity through automated adaptation rather than manual system configuration.
Solution Approach 2:
The recommendation system performs self-adjustment by automatically selecting and allocating different recommendation logics based on user behavior patterns. This self-service capability eliminates the need for complex manual management of multiple logics, reducing operational complexity while maintaining high recommendation precision.
3Measurement precision
If interaction data is collected and processed for each user, then recommendation precision is improved, but information processing requirements and system complexity increase
Solution Approach 1:
The system extracts and processes only the essential interaction data relevant to recommendation logic selection, rather than analyzing all possible user data. This selective extraction approach maintains high recommendation precision while reducing the overall volume of data processing required.
Data Source
AI summary
The present disclosure relates to a system, a method and a computer-readable medium for recommendation. The method includes providing a first content according to a first recommendation logic to a user terminal of a viewer; providing a second content according to a second recommendation logic to the user terminal; obtaining interaction data from the user terminal; and adjusting an allocation of contents from the first recommendation logic and the second recommendation logic to be shown on the user terminal according to the interaction data.