System and method for individual player and team simulation
A computing system retrieves historical event data for a plurality of games in a league. The historical event data includes (x,y) coordinates of players within each game and game context data. The computing system learns one or more attributes of each team in each game and each player on each team in each game. The computing system receives a request to simulate a play in a historical game. The request includes substituting a player that was in the play with a target player that was not in the play. The computing system simulates the play with the target player in place of the player based on the one or more attributes learned by the computing system. The computing system generates a graphical representation of the simulation.
1. A method, comprising:
retrieving, by a computing system, historical event data for a plurality of games in a league, the historical event data comprising player information within each game and game context data;
learning, by the computing system, one or more attributes of each team in each game and each player on each team in each game;
receiving, by the computing system, a request to simulate a play in a historical game, wherein the request comprises substituting a player that was in the play with a target player that was not in the play;
simulating, by the computing system, the play with the target player in place of the player based on the one or more attributes learned by the computing system; and
generating, by the computing system, a graphical representation of the simulation.
2. The method of claim 1 , wherein generating, by the computing system, the graphical representation of the simulation comprises:
visually simulating the player with the target player in the place of the player.
3. The method of claim 1 , wherein retrieving, by a computing system, the historical event data for the plurality of games in the league comprises:
receiving broadcast video data corresponding to the plurality of games; and
deriving, from the broadcast video data, player tracking data and the game context data.
4. The method of claim 1 , wherein learning, by the computing system, the one or more attributes of each team in each game and each player on each team in each game comprises:
learning trajectories of each player in each game based on the historical event data.
5. The method of claim 4 , wherein learning, by the computing system, the one or more attributes of each team in each game and each player on each team in each game comprises:
learning a style of each player and each team based on the historical event data.
6. The method of claim 5 , wherein learning, by the computing system, the one or more attributes of each team in each game and each player on each team in each game comprises:
learning a role of each player at one or more points of each game.
7. The method of claim 6 , wherein simulating, by the computing system, the play with the target player in place of the player based on the one or more attributes learned by the computing system comprises:
simulating the player based on one or more of learned trajectories of the target player, learned style of the target player, and learned roles of the target player.
8. A non-transitory computer readable medium comprising one or more sequences of instructions, which, when executed by a processor, causes a computing system to perform operations comprising:
retrieving, by the computing system, historical event data for a plurality of games in a league, the historical event data comprising player information within each game and game context data;
learning, by the computing system, one or more attributes of each team in each game and each player on each team in each game;
receiving, by the computing system, a request to simulate a play in a historical game, wherein the request comprises substituting a player that was in the play with a target player that was not in the play;
simulating, by the computing system, the play with the target player in place of the player based on the one or more attributes learned by the computing system; and
generating, by the computing system, a graphical representation of the simulation.
9. The non-transitory computer readable medium of claim 8 , wherein generating, by the computing system, the graphical representation of the simulation comprises:
visually simulating the player with the target player in the place of the player.
10. The non-transitory computer readable medium of claim 8 , wherein retrieving, by a computing system, the historical event data for the plurality of games in the league comprises:
receiving broadcast video data corresponding to the plurality of games; and
deriving, from the broadcast video data, player tracking data and the game context data.
11. The non-transitory computer readable medium of claim 8 , wherein learning, by the computing system, the one or more attributes of each team in each game and each player on each team in each game comprises:
learning trajectories of each player in each game based on the historical event data.
12. The non-transitory computer readable medium of claim 11 , wherein learning, by the computing system, the one or more attributes of each team in each game and each player on each team in each game comprises:
learning a style of each player and each team based on the historical event data.
13. The non-transitory computer readable medium of claim 12 , wherein learning, by the computing system, the one or more attributes of each team in each game and each player on each team in each game comprises:
learning a role of each player at one or more points of each game.
14. The non-transitory computer readable medium of claim 13 , wherein simulating, by the computing system, the play with the target player in place of the player based on the one or more attributes learned by the computing system comprises:
simulating the player based on one or more of learned trajectories of the target player, learned style of the target player, and learned roles of the target player.
15. A system comprising:
a processor; and
a memory having programming instructions stored thereon, which, when executed by the processor, causes the system to perform operations comprising:
retrieving historical event data for a plurality of games in a league, the historical event data comprising player information within each game and game context data;
learning, by a simulation module, one or more attributes of each team in each game and each player on each team in each game;
receiving a request to simulate a play in a historical game, wherein the request comprises substituting a player that was in the play with a target player that was not in the play;
simulating, by the simulation module, the play with the target player in place of the player based on the one or more attributes learned by the simulation module; and
generating a graphical representation of the simulation.
16. The system of claim 15 , wherein retrieving the historical event data for the plurality of games in the league comprises:
receiving broadcast video data corresponding to the plurality of games; and
deriving, from the broadcast video data, player tracking data and the game context data.
17. The system of claim 15 , wherein learning, by the simulation module, the one or more attributes of each team in each game and each player on each team in each game comprises:
learning trajectories of each player in each game based on the historical event data.
18. The system of claim 17 , wherein learning, by the simulation module, the one or more attributes of each team in each game and each player on each team in each game comprises:
learning a style of each player and each team based on the historical event data.
19. The system of claim 18 , wherein learning, by the simulation module, the one or more attributes of each team in each game and each player on each team in each game comprises:
learning a role of each player at one or more points of each game.
20. The system of claim 19 , wherein simulating, by the simulation module, the play with the target player in place of the player based on the one or more attributes learned by the simulation module comprises:
simulating the player based on one or more of learned trajectories of the target player, learned style of the target player, and learned roles of the target player.