U.S. Patent No. 10,610,786: Multiplayer video game matchmaking optimization
Issued April 7, 2020 to Electronic Arts Inc.
Priority Date: March 8, 2016
U.S. Patent No. 10,610,786 (the ’786 Patent) relates to optimizing matchmaking in a multiplayer video game through analysis of prior game history data from players wishing to play an instance of a video game. The ’786 Patent details a method of selecting users for a match from a queue of players waiting to be placed. The selection criteria may include play style, skill level, character selection history, role history, length of time spent in the queue, geographic location, and predicted retention rate, among others. The predicted retention rate is used to predict how long each user will continue to play the video game, and if the predicted retention rate fails to meet the predetermined retention threshold, then players may be replaced with others from the queue. This method may be used to create a match plan comprising multiple teams.
Embodiments of systems presented herein may identify users to include in a match plan. A parameter model may be generated to predict the retention time of a set of users. A queue of potential users, a set of teammates, and/or opponents may be selected from a queue of waiting users. User information for the set of teammates and/or opponents may be provided to the parameter model to generate a predicted retention time. The set of teammates and/or opponents may be approved if the predicted retention time meets a predetermined threshold. Advantageously, by creating a match plan based on retention rates, the engagement and/or retention level for a number of users may be improved compared to existing multiplayer matching systems.
1. A computer-implemented method comprising: as implemented by an interactive computing system configured with specific computer-executable instructions, generating a match plan by at least selecting a plurality of users from a queue of users waiting to play an instance of a video game, wherein a first user and a second user of the plurality of users are designated as a user pair to be selected to play together in an instance of the video game; for each user from the plurality of users, accessing user interaction data associated with the user’s interaction with the video game; determining a predicted retention value for the match plan based at least in part on the user interaction data for each user from the plurality of users, the predicted retention value associated with a predicted amount of time that a set of users included in the match plan will play the video game; determining that the predicted retention value of the match plan does not satisfy a match plan retention threshold; and generating an updated match plan by substituting at least one user from the plurality of users with another user from the queue of users while maintaining the first user and the second user as a user pair to be selected to play together in an instance of the video game.