Display Device Recommendation Channel List Generation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face inconvenience in selecting desired content from the increasing number of channels and types of content available on display devices, as existing methods struggle to recommend channels beyond user viewing history, limiting discovery of new, potentially interesting content.
Innovation Solution
A method and display device that generate a recommendation channel list by analyzing user viewing history, considering both channel and genre preferences, to prioritize channels the user is likely to prefer, incorporating indices for channel and genre identity to select and display recommended channels.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the number of channels and content types on display devices increases, then content diversity and availability are improved, but user convenience in selecting desired content deteriorates
Solution Approach 1:
The system automatically generates recommendation channel lists by analyzing user viewing history and preferences without requiring manual user input. The display device self-services by autonomously processing viewing data, calculating channel and genre identities, and producing personalized recommendations, thereby resolving the contradiction between content diversity and selection convenience
Solution Approach 2:
The system utilizes user viewing history as feedback to continuously improve recommendation accuracy. By analyzing past viewing patterns and calculating channel identity and genre identity based on this feedback, the system adapts to user preferences and generates increasingly accurate recommendations, balancing content diversity with user convenience
2Measurement precision
If recommendation lists are generated based only on user viewing history, then user preference accuracy is improved, but discovery of new content deteriorates
Solution Approach 1:
The system transitions from one-dimensional recommendation based solely on viewing history to two-dimensional recommendation by introducing genre identity as an additional dimension. This allows the system to recommend channels not only based on previously watched channels but also based on genres of interest, thereby improving content discovery while maintaining preference accuracy
Solution Approach 2:
The recommendation system serves multiple functions simultaneously: it recommends channels based on viewing history (function 1) and recommends channels based on genre preferences (function 2). This multi-functionality enables the system to both accurately reflect user preferences and discover new content across different dimensions
Data Source
AI summary
A method of providing a recommendation channel list according to an embodiment of the present disclosure allows a user to quickly and conveniently select desired content and includes: acquiring viewing history information including information about a viewing time, a channel, and a genre of content that a user viewed on a display device for a first period; in response to a preset event being occurred, generating, based on the viewing history information, a recommendation channel list including at least one channel from among at least one first recommended channel related to at least one channel viewed by the user and at least one second recommended channel related to at least one genre of content viewed by the user; and displaying a screen including the recommendation channel list.