User Recommendation Module for Shared Viewing Comfort
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current shared viewing experiences are uncomfortable due to inter-user comments and lack consideration of personal relationships or preference similarities, and there is no system to actively support introduction to unfamiliar content or real-world events like music concerts or sports events.
Innovation Solution
An information processing device that analyzes user personal relationship information from behavior logs to determine proposal candidates and provide content recommendations, considering both online and offline interactions, to facilitate shared content or real-world event viewing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If current shared viewing experience systems are used, then users can view content together, but comfort is reduced due to inter-user comments and lack of personal relationship consideration
Solution Approach 1:
The system applies different interaction modes to different user pairs based on their personal relationship characteristics. Active users receive different treatment than passive users, and the system tailors the viewing experience to each user's role and relationship status, creating localized quality adjustments for different user interactions.
Solution Approach 2:
Instead of allowing all users to freely comment and interact during shared viewing, the system inverts the approach by controlling who can initiate interactions and under what conditions. The passive user's viewing experience is protected by requiring active user initiation, and the system manages comments and opinions through structured proposal-acceptance flows rather than free-form interaction.
2Productivity
If target user groups are determined in advance, then content can be recommended to groups, but personal relationship and preference similarity are not considered
Solution Approach 1:
The system performs preliminary analysis of user personal relationships and preferences before generating content recommendations. By pre-processing behavior logs and relationship data, the system prepares personalized recommendation profiles that combine both efficiency (pre-computed user groups) and precision (individual relationship and preference analysis), allowing fast recommendation generation with high accuracy.
Solution Approach 2:
The system dynamically adjusts recommendation parameters based on personal relationship strength and preference similarity metrics. Instead of using fixed group-based recommendations, the system modifies recommendation weights, content selection criteria, and timing based on analyzed user parameters, enabling both efficient group targeting and precise individual customization.
3Adaptability or versatility
If beginners participate in unfamiliar content or real world events, then they can experience new content, but they hesitate due to lack of knowledge
Solution Approach 1:
The system introduces an intermediary mechanism where experienced users (active users with detailed knowledge) mediate the introduction of beginners to unfamiliar content or events. The active user creates proposals, shares information, and guides the passive user through the experience, reducing the beginner's hesitation by providing trusted intermediary support and structured introduction flows.
Solution Approach 2:
The system performs preliminary information provision and context setting before beginners engage with unfamiliar content. By pre-delivering relevant information, background context, and guidance materials through the recommendation system, beginners are better prepared and more willing to participate in new experiences, reducing hesitation through advance preparation.
Data Source
AI summary
The present disclosure relates to information processing device, method, and program for allowing support of shared content/real world event viewing.A user recommendation module is configured to determine C. proposer for a user group and recommendation content. The user recommendation module performs, for example, calculation of the Active degree of a user A in the group=the individual Active degree of the user A+Σ(b*the Active degree of the user A with respect to other users in the group) (the degree of relationship among the user A and other users may be reflected in a weighting coefficient b). Moreover, the user recommendation module determines, as a proposer, a user with the highest Active degree in the group. The present disclosure is applicable to an information processing system configured to perform shared viewing for music, for example.