US 11,935,298 B2
System and method for predicting formation in sports
Jennifer Hobbs, Chicago, IL (US); Sujoy Ganguly, Chicago, IL (US); and Patrick Joseph Lucey, Chicago, IL (US)
Assigned to STATS LLC, Chicago, IL (US)
Filed by STATS LLC, Chicago, IL (US)
Filed on May 27, 2021, as Appl. No. 17/303,361.
Claims priority of provisional application 63/035,137, filed on Jun. 5, 2020.
Prior Publication US 2021/0383123 A1, Dec. 9, 2021
Int. Cl. G06V 20/40 (2022.01); G06N 3/08 (2023.01); G06N 5/04 (2023.01)
CPC G06V 20/42 (2022.01) [G06N 3/08 (2013.01); G06N 5/04 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method of predicting a team's formation on a playing surface, comprising:
retrieving, by a computing system, one or more sets of event data for a plurality of events, wherein each set of event data corresponds to a segment of a respective event;
providing, by the computing system, the one or more sets of event data to train a deep neural network to predict an optimal permutation of players in each segment of each respective event;
receiving, by the computing system, a trained prediction model configured to predict a formation of players based on determining a distribution of players for each segment based on the corresponding event data retrieved from a data store and the optimal permutation of players;
receiving, by the computing system, target event data corresponding to a target event, the target event data comprising information directed to a team comprising a plurality of players on a target playing surface;
predicting, by the computing system via the trained prediction model, an expected formation of the plurality of players on the target playing surface based on the target event data and a semantic label associated with the expected formation; and
displaying, by the computing system, the semantic label associated with the expected formation of the plurality of players.