Sony patents AI system to match players based on how they actually play
Sony describes a system that watches how a player interacts with a game to figure out what they enjoy, rather than just relying on what they say they like. It uses machine learning to predict these preferences and then suggests other players who fit that profile for multiplayer sessions.
In the filing’s own words
Systems and methods of the present disclosure include tracking, by a system including at least one processor and a memory, user interactions of a first user in a game environment, gathering, by the system, implicit user gameplay information from the user interactions of the first user in the game environment, receiving, by the system, explicit user gameplay information from the first user, executing, by the system, the adaptive player matching application including a machine learning algorithm, analyzing the implicit user gameplay information, via the adaptive player matching application, to determine predicted user preferences for the first user, determining, by the adaptive player matching application, predicted user preferences for the first user, and based at least in part on the predicted user preferences and the explicit user gameplay information, generating, via the adaptive player matching application, recommended player matches with one or more other users in the game environment.
What exactly they claim (claim 1)
1. A method for executing an adaptive player matching application for interacting in a game environment, the method comprising: tracking, by a system including at least one processor and a memory, user interactions of a first user in the game environment; gathering, by the system, implicit user gameplay information from the user interactions of the first user in the game environment; receiving, by the system, explicit user gameplay information from the first user; executing, by the system, the adaptive player matching application including a machine learning algorithm; analyzing the implicit user gameplay information, via the adaptive player matching application, to determine predicted user preferences for the first user; determining, by the adaptive player matching application, the predicted user preferences for the first user; and based at least in part on the predicted user preferences and the explicit user gameplay information, generating, via the adaptive player matching application, recommended player matches with one or more other users in the game environment.
Facts
- Company
- Sony (Sony Interactive Entertainment Inc.)
- Official title
- USING ML MODELS TO MATCH PLAYERS TOGETHER FOR GAME PLAY
- Publication number
- US20260263948A1
- Application number
- 19071594
- Filed
- Mar 5, 2025
- Published
- Sep 10, 2026
- Inventors
- 3
- Claims
- 20
Classified under
A63F 13/795 Human necessitiesMore from Sony in Games & media
- Sony patents game engine that reshuffles scenes based on your heart rate Sep 8, 2026
- Sony patents game controls that learn your unique hand movements Oct 13, 2026
- Sony patents eSport events where fans' cheers give players in-game power-ups Oct 20, 2026
- Sony patents game gear design using AI mood boards Oct 20, 2026
- Sony patents game feature that warns players before they hit a hard part Sep 3, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.