Game Team Matching Pools Using Feature-Based Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In multiplayer online battle arena (MOBA) games, concurrent battle matching of game teams results in increased difficulty and duration due to random allocation of teams to different matching pools, leading to reduced efficiency.
Innovation Solution
A method and apparatus for game matching that uses a pre-trained clustering model to allocate game teams to matching pools based on team features, minimizing level differences and ensuring teams of similar levels are matched together, using a clustering model trained to minimize quantitative differences across different game room types.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If game teams are randomly allocated to different matching pools for concurrent battle matching, then the system can handle large numbers of online game teams, but the difficulty of matching increases and the matching duration increases
Solution Approach 1:
The patent applies preliminary action by pre-training a clustering model offline to learn the optimal mapping between team features and matching pools. This pre-computed knowledge is then used during runtime to quickly determine the target matching pool for each game team, avoiding the need for complex real-time calculations and reducing matching duration while maintaining high efficiency.
Solution Approach 2:
The patent changes parameters by transforming the matching problem from random allocation to feature-based clustering. The clustering model processes team features (such as player skill levels, team composition, etc.) and outputs optimized matching pool assignments, changing the allocation strategy from random to deterministic based on team characteristics, thereby reducing matching difficulty and duration.
2Productivity
If game teams are randomly allocated to matching pools, then concurrent matching can be performed, but teams of the same type have difficulty being matched together
Solution Approach 1:
The patent applies local quality by creating specialized matching pools for different team types and skill levels. The clustering model identifies specific characteristics of game teams and assigns them to appropriate matching pools where similar teams are grouped together. This ensures that each matching pool has the appropriate quality composition for its intended purpose, improving matching quality while maintaining concurrent processing efficiency.
Solution Approach 2:
The patent uses copying by creating multiple matching pools that replicate the same matching logic and structure, but are specialized for different team types. Instead of having one large heterogeneous pool, the system copies the matching pool structure multiple times with different specializations, allowing teams to be matched with similar types in appropriate pools, thereby improving matching quality.
Data Source
AI summary
The present disclosure relates to a method and an apparatus for game matching, a storage medium, and an electronic device. The method includes: obtaining a team feature of a game team to be matched; obtaining, by a pre-trained clustering model, a target class cluster to which the game team to be matched belongs according to the team feature, the clustering model being obtained by training with a constraint goal of differing in game levels of sample game teams in different class clusters under different game room types and minimizing a quantitative difference of sample game teams in any two class clusters under different game room types; allocating the game team to be matched to a target matching pool according to the target class cluster and a game room type; and determining, in the target matching pool, a game team matched with the game team to be matched.