System and method for evaluating team game activities
A system and method are provided for creating and evaluating computational models for games (e.g., individual or team sports games, etc.), team performance, and individual player performance evaluation. The method comprises obtaining data associated with the team game, the information comprising at least one individual player activity, at least one team activity, at least one game event, and a location in space and time for each of the events and activities; generating quantitative values for the data associated with the team game; and evaluating either or both an individual player and a team using the quantitative values.
1. A method computer-implemented for evaluating team games, the method comprising:
obtaining data associated with a team game, the data comprising at least one individual player or team activity, a game context, and at least one game event, the data further comprising a location in space for each event and activity and a time that each event and activity happens, wherein the game context comprises a game state space defined by selected features that are relevant for game dynamics of the corresponding type of team game, wherein the game state evolves based on the events and activities of the players;
generating quantitative values for the data associated with the team game using the events and activities, the game context, and corresponding location data by assessing impacts of the events and activities in the game context;
evaluating either or both an individual player and a team using the quantitative values; and
generating a quantitative data output associated with the evaluating.
2. The method of claim 1 , further comprising using a Markov Model to assign the quantitative values to activities and game events at the associated location and time.
3. The method of claim 1 , further comprising determining a look ahead that indicates how future events affect a current state and action values.
4. The method of claim 1 , wherein generating a quantitative data output comprises outputting at least one of: an effect of a player or team activity in the game, a player contribution to a future game, or a player or team efficiency in achieving a particular outcome.
5. The method of claim 1 , further comprising performing a player clustering or grouping based on that player's impact on a game, that player's playing style, or both.
6. The method of claim 1 , wherein generating a quantitative data output comprises generating at least one quantitative metric to rank players and assess player performance in games.
7. The method of claim 1 , wherein generating a quantitative data output comprises generating at least one quantitative metric to rank a team and assess team performance in games.
8. The method of claim 1 , wherein generating a quantitative data output comprises generating at least one quantitative metric to evaluate team strategies in a game.
9. The method of claim 1 , wherein generating a quantitative data output comprises generating at least one quantitative metric to predict player performance and game outcomes.
10. The method of claim 1 , further comprising grouping players in a game based on a respective playing style, which comprises:
automatically generating a plurality of clusters of one or more players based on a presence and/or activities associated with each player.
11. The method of claim 10 , wherein each cluster is automatically generated by:
obtaining information about a player's presence;
generating presence maps for the players;
grouping presence maps based on similarity in spatial and/or temporal characteristics; and
forming the clusters.
12. The method of claim 10 , further comprising using the location of the players in a game.
13. The method of claim 10 , wherein the data associated with the team game further comprises a location in space and time for each of the events and activities.
14. The method of claim 10 , further comprising using the location of the players in a game to identify their playing style.
15. The method of claim 10 , further comprising generating at least one quantitative metric to rank players and assess player performance in games within a group of players with the similar playing style.
16. The method of claim 10 , further comprising generating player rankings and comparisons to suggest similar players to replace a particular player.
17. The method of claim 16 , further comprising automatically identifying the game context wherein a player shows an unusually high or low added impact compared to similar players.
18. A non-transitory computer readable medium comprising computer executable instructions for evaluating a team game, comprising instructions for:
obtaining data associated with a team game, the data comprising at least one individual player or team activity, a game context, and at least one game event, the data further comprising a location in space for each event and activity and a time that each event and activity happens, wherein the game context comprises a game state space defined by selected features that are relevant for game dynamics of the corresponding type of team game, wherein the game state evolves based on the events and activities of the players;
generating quantitative values for the data associated with the team game using the events and activities, the game context, and corresponding location data by assessing impacts of the events and activities in the game context;
evaluating either or both an individual player and a team using the quantitative values; and
generating a quantitative data output associated with the evaluating.
19. An electronic device comprising a processor and memory, the memory comprising computer executable instructions for evaluating a team game, comprising instructions for:
obtaining data associated with a team game, the data comprising at least one individual player or team activity, a game context, and at least one game event, the data further comprising a location in space for each event and activity and a time that each event and activity happens, wherein the game context comprises a game state space defined by selected features that are relevant for game dynamics of the corresponding type of team game, wherein the game state evolves based on the events and activities of the players;
generating quantitative values for the data associated with the team game using the events and activities, the game context, and corresponding location data by assessing impacts of the events and activities in the game context;
evaluating either or both an individual player and a team using the quantitative values; and
generating a quantitative data output associated with the evaluating.
20. The non-transitory computer readable medium according to claim 18 further comprising computer executable instructions for grouping players in a game based on a respective playing style, comprising instructions for:
automatically generating a plurality of clusters of one or more players based on a presence and/or activities associated with each player.
21. The electronic device according to claim 19 , the memory further comprising computer executable instructions for grouping players in a game based on a respective playing style, comprising instructions for:
automatically generating a plurality of clusters of one or more players based on a presence and/or activities associated with each player.