Riot Games has 1 granted patent in the AI & Machine Learning category.
The patent covers a dynamic skill ranking system that adjusts player ratings based on specific in-game events rather than only win/loss outcomes. This approach enables faster and more accurate competitive matchmaking by accounting for individual performance factors throughout gameplay.
Riot's single AI and machine learning patent tackles a persistent challenge in competitive gaming: ranking individual players fairly when they compete in team-based matches. Traditional systems adjust a player's rating based solely on whether their team won or lost, but this approach obscures individual contributions and slows the process of finding a player's true skill level. The patented system instead breaks down each match into specific events, such as kills, assists, objectives captured, or other gameplay actions, and assigns each event a weight that reflects its impact on the outcome. By aggregating these weighted contributions, the system can update rankings based on what each player actually accomplished during the match, not just the final scoreboard. This granular approach helps players reach their appropriate skill tier more quickly and creates more balanced matches by recognizing performance nuances that a simple win or loss cannot capture.
All data sourced from USPTO patent filings. Google Patents may take several weeks to index recent publications. If a link is unavailable, search for the patent number at USPTO Patent Public Search.