Dual-Learning Recommendation System for Video Delivery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing video delivery services face challenges in providing relevant recommendations due to static patterns that fail to keep pace with changing user preferences, especially when offering both live television and video on-demand services, leading to stale recommendations.
Innovation Solution
A real-time recommendation system using a dual-learning model with a generation system and an evaluation system that continuously updates parameters based on user interactions, employing recurrent cells and continuous embedding spaces to adapt to changing user behavior.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If static patterns are used for recommendation algorithms, then system complexity is reduced and ease of operation is improved, but recommendation relevance deteriorates as user preferences change over time
Solution Approach 1:
The patent implements dynamic pattern updates by transitioning from static recommendation patterns to dynamically updating patterns that adapt to changing user preferences in real-time, resolving the contradiction between operational simplicity and adaptability
Solution Approach 2:
The system incorporates feedback mechanisms that continuously monitor user interactions and use this feedback to update recommendation patterns, enabling the system to adapt to changing preferences while maintaining automated operation
2Adaptability or versatility
If periodic updates are implemented to capture changing user preferences, then recommendation relevance is improved, but update frequency is insufficient to keep pace with rapid preference changes
Solution Approach 1:
The patent implements continuous learning and updating mechanisms that operate continuously rather than periodically, ensuring recommendation patterns are constantly refined to match current user preferences without interruption or delay
3Adaptability or versatility
If interactive live television service is added to video on-demand service, then service versatility is improved, but recommendation complexity increases due to different viewing habits
Solution Approach 1:
The patent implements a unified recommendation framework that handles multiple service types (live television and video on-demand) through a single adaptable system, eliminating the need for separate recommendation systems for each service type
4Adaptability or versatility
If real-time learning is implemented to adapt to user behavior, then recommendation relevance is improved, but computational complexity and processing requirements increase
Solution Approach 1:
The patent segments the recommendation system into distinct functional components (pattern generation, evaluation, updating mechanisms) that can operate independently and efficiently, reducing overall system complexity while maintaining real-time adaptability
Data Source
AI summary
A method receives user behavior information at a first system. The user behavior information is determined by user interaction with a first list sent to the user by a first network on a video delivery service. A first state is generated using the received user behavior information and prior user behavior information by the user from cells that store the prior user behavior. The method inputs the first state into a second network with the first recommendation list to generate a value that evaluates a performance of recommending the first recommendation list. An update to parameters is generated for the first network and provided to the first network. The first network generates a second state from the received user behavior information and prior user behavior information derived from cells that store the prior user behavior and outputs a second recommendation list using the second state and updated parameters.