MOBA Game Recommendation via Sequential Performance Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing video game content recommendation systems often provide biased recommendations, failing to accurately assess a team's performance in a specific game based on pre-game, in-game, and post-game analyses, leading to unsuitable content suggestions.
Innovation Solution
A system that conducts sequential pre-game, in-game, and post-game analyses to evaluate a player's or team's performance by comparing pre-game and in-game metrics against thresholds, ensuring that recommended content aligns with the user's actual gameplay experience.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a recommendation engine uses team ratings to recommend video game content, then recommendations are generated quickly, but the recommendations become biased and inaccurate because they do not reflect actual game performance
Solution Approach 1:
The patent segments the performance assessment into three distinct phases: pre-game analysis (evaluating player/team metrics before the game), in-game analysis (tracking actual performance during the game), and post-game analysis (comparing actual vs. expected performance). This segmentation allows the system to maintain quick recommendation generation while incorporating comprehensive performance data from multiple time points, resolving the contradiction between speed and accuracy.
Solution Approach 2:
The system performs pre-game analysis in advance to establish expected performance metrics and thresholds before the actual game occurs. This preliminary action enables the recommendation engine to have performance criteria ready beforehand, allowing for rapid recommendation generation during and after the game without compromising assessment accuracy, thus resolving the contradiction between productivity and measurement precision.
2Measurement precision
If a recommendation engine evaluates game content based on comprehensive performance metrics, then recommendation accuracy improves, but the system complexity increases due to multiple analysis phases
Solution Approach 1:
The patent creates a universal performance analysis framework that handles multiple game types and metrics through a single multi-functional system. The same three-phase analysis structure (pre-game, in-game, post-game) is applied across different video game genres, using consistent metric comparison logic. This universality allows comprehensive performance evaluation without proportionally increasing system complexity, as the core analytical engine remains standardized across applications.
Solution Approach 2:
The system implements feedback loops where post-game analysis results feed into updating pre-game expectations for future games. The comparison between expected and actual performance creates a feedback mechanism that continuously refines performance thresholds and metrics. This feedback principle allows the system to maintain high measurement precision through iterative improvement while managing complexity through systematic learning rather than expanding structural complexity.
3Reliability
If the system compares pre-game and in-game metrics thoroughly, then recommendation quality improves, but the analysis time increases
Solution Approach 1:
The patent applies partial action by focusing the comprehensive comparison on key performance metrics that have the greatest impact on recommendation quality. Rather than analyzing every possible game parameter in equal detail, the system identifies and prioritizes critical metrics for comparison between pre-game and in-game phases. This selective approach maintains high recommendation reliability while reducing unnecessary analysis time spent on less significant parameters.
Solution Approach 2:
The system structures the analysis as periodic actions occurring at distinct game phases (pre-game, in-game, post-game) rather than continuous analysis. Each phase has specific analytical tasks performed at that time, with results carried forward to the next phase. This periodic structure allows thorough metric comparison to be distributed across time intervals, maintaining recommendation quality while preventing excessive concentration of analysis time in a single moment.
Data Source
AI summary
Systems and methods for providing game content recommendation of a multiplayer online battle arena (MOBA) video game based on player's performance are disclosed. Prior to an actual MOBA video game play, a player data stored for each player of each team is analyzed to evaluate a video game session content. The player data is associated with the video game play session and stored settings for the MOBA video game. The player data includes attack metrics, defense metrics, and damage metrics to determine to evaluate the video game play session content. During the actual MOBA video game play, an in-game performance of each player of each team in the video game play session content is analyzed to recommend the video game plays session. Such analysis is based on game map of the video game play session and in game metrics determined from the video game play session.