System And Method For Content And Style Predictions In Sports

Patent metadata

Field	Value
Publication number	US-2025069394-A1
Application number	US-202418945787-A
Country	US
Kind code	A1
Filing date	Nov 13, 2024
Priority date	May 8, 2019
Publication date	Feb 27, 2025
Grant date	—

Abstract

A system and method for generating a play prediction for a team is disclosed herein. A computing system retrieves trajectory data for a plurality of plays from a data store. The computing system generates a predictive model using a variational autoencoder and a neural network by generating one or more input data sets, learning, by the variational autoencoder, to generate a plurality of variants for each play of the plurality of plays, and learning, by the neural network, a team style corresponding to each play of the plurality of plays. The computing system receives trajectory data corresponding to a target play. The predictive model generates a likelihood of a target team executing the target play by determining a number of target variants that correspond to a target team identity of the target team.

First claim

What is claimed:

1 . A computer-implemented method of generating a play prediction for a team, the computer-implemented method comprising:
receiving, by one or more processors, match data from a data store; processing, by the one or more processors, the match data to identify one or more plays and corresponding event data and tracking data associated with each of the one or more plays; generating, by the one or more processors, one or more variants for each of the one or more plays based on the corresponding tracking data and the event data; identifying, by the one or more processors, a likelihood prediction of a team executing each of the one or more variants; generating, by the one or more processors, a graphical representation of the likelihood prediction for each of the one or more variants; and outputting, by the one or more processors, the graphical representation to a device.

2 . The computer-implemented method of claim 1 , wherein the likelihood prediction includes a team identity for each team executing the one or more variants.

3 . The computer-implemented method of claim 2 , wherein identifying, by the one or more processors, the likelihood prediction of the team executing each of the one or more variants includes:
inputting, by the one or more processors, the tracking data and the one or more variants into a neural network; and receiving, by the one or more processors, the team identity for each of the one or more variants from the neural network.

4 . The computer-implemented method of claim 1 , wherein generating, by the one or more processors, the one or more variants for each of the one or more plays based on the corresponding tracking data and the event data includes:
inputting, by the one or more processors, the tracking data into a variational autoencoder, wherein the variational autoencoder is configured to generate the one or more variants based on the tracking data and the event data; and in response to the inputting, receiving, by the one or more processors, the one or more variants from the variational autoencoder.

5 . The computer-implemented method of claim 1 , wherein the generating, by the one or more processors, the graphical representation of the likelihood prediction for each of the one or more variants includes:
generating, by the one or more processors, one or more graphical representation trajectories of a play for each of the one or more variants.

6 . The computer-implemented method of claim 1 , wherein the graphical representation includes a play graphical element corresponding to at least one of the one or more plays and a variant graphical element corresponding to at least one of the one or more variants.

7 . The computer-implemented method of claim 1 , wherein the event data includes at least one of: possession data, play style data, or a team identity.

8 . A non-transitory computer-readable medium comprising one or more sequences of instructions, which, when executed by one or more processors, causes a computing system to perform operations comprising:
receiving, by the computing system, match data from a data store; processing, by the computing system, the match data to identify one or more plays and corresponding event data and tracking data associated with each of the one or more plays; generating, by the computing system, one or more variants for each of the one or more plays based on the corresponding tracking data and the event data; identifying, by the computing system, a likelihood prediction of a team executing each of the one or more variants; generating, by the computing system, a graphical representation of the likelihood prediction for each of the one or more variants; and outputting, by the computing system, the graphical representation to a device.

9 . The non-transitory computer-readable medium of claim 8 , wherein the likelihood prediction includes a team identity for each team executing the one or more variants.

10 . The non-transitory computer-readable medium of claim 9 , wherein identifying, by the computing system, the likelihood prediction of the team executing each of the one or more variants includes:
inputting, by the computing system, the tracking data and the one or more variants into a neural network; and receiving, by the computing system, the team identity for each of the one or more variants from the neural network.

11 . The non-transitory computer-readable medium of claim 8 , wherein generating, by the computing system, the one or more variants for each of the one or more plays based on the corresponding tracking data and the event data includes:
inputting, by the computing system, the tracking data into a variational autoencoder, wherein the variational autoencoder is configured to generate the one or more variants based on the tracking data and the event data; and in response to the inputting, receiving, by the computing system, the one or more variants from the variational autoencoder.

12 . The non-transitory computer-readable medium of claim 8 , wherein the generating, by the computing system, the graphical representation of the likelihood prediction for each of the one or more variants includes:
generating, by the computing system, one or more graphical representation trajectories of a play for each of the one or more variants.

13 . The non-transitory computer-readable medium of claim 8 , wherein the graphical representation includes a play graphical element corresponding to at least one of the one or more plays and a variant graphical element corresponding to at least one of the one or more variants.

14 . The non-transitory computer-readable medium of claim 8 , wherein the event data includes at least one of: possession data, play style data, or a team identity.

15 . A computer 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:
receiving match data from a data store;
processing the match data to identify one or more plays and corresponding event data and tracking data associated with each of the one or more plays;
generating one or more variants for each of the one or more plays based on the corresponding tracking data and the event data;
identifying a likelihood prediction of a team executing each of the one or more variants;
generating a graphical representation of the likelihood prediction for each of the one or more variants; and
outputting the graphical representation to a device.

16 . The computer system of claim 15 , wherein the likelihood prediction includes a team identity for each team executing the one or more variants.

17 . The computer system of claim 16 , wherein identifying the likelihood prediction of the team executing each of the one or more variants includes:
inputting the tracking data and the one or more variants into a neural network; and receiving the team identity for each of the one or more variants from the neural network.

18 . The computer system of claim 15 , wherein generating the one or more variants for each of the one or more plays based on the corresponding tracking data and the event data includes:
inputting the tracking data into a variational autoencoder, wherein the variational autoencoder is configured to generate the one or more variants based on the tracking data and the event data; and in response to the inputting, receiving the one or more variants from the variational autoencoder.

19 . The computer sys

Assignees

• Stats Llc

Inventors

• Ganguly Sujoy
• Sha Long
• Hobbs Jennifer
• Wei Xinyu
• Lucey Patrick Joseph

Classifications

• G06N3/09

  Supervised learning · CPC title

• G06N3/0455

  Auto-encoder networks; Encoder-decoder networks · CPC title

• G06N3/0499

  Feedforward networks · CPC title

• G06N3/0475

  Generative networks · CPC title

• G06V10/82

  using neural networks · CPC title