IP Library › Granted Patent US 10,902,600
Granted Patent B2
US 10,902,600 · App. 16/266,199 · Granted Jan 26, 2021

Segmentation-based invasion sports analysis and control

Inventors: Kun Zhao (Funabashi, JP); Takayuki Osogami (Yamato, JP); Tetsuro Morimura (Setagaya-ku, JP)
Assignee: International Business Machines Corporation
G06T7/11G06K9/00724G06N7/005G06T7/136G06T7/70G06K2009/00738G06T2207/30221
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,902,600
App. No.
16/266,199
Granted
Jan 26, 2021
Kind
B2
Abstract

Methods and systems for game event analysis and control include determining segmentation events in a game that each represent an interruption in game play or a reset scene. An event analysis is performed using the series of events to determine a contribution value for each event in the series of events that represents how much each respective event in the series of events contributed to the point being scored. Events that have a contribution value that exceeds a baseline value for a respective event type are responded to.

Claims (25)

1. A computer-implemented method for game event analysis and control, comprising:

determining segmentation events in a game that each represent an interruption in game play or a reset scene by comparing a product of eigenvalues of a covariance matrix to a threshold parameter to determine whether players have spread out on a game field, where the covariance matrix reflects player locations at respective times;

performing an event analysis using the series of segmentation events to determine a contribution value for each event in the series of segmentation events that represents how much each respective event in the series of segmentation events contributed to a point being scored; and

responding to events having a contribution value that exceeds a baseline value for a respective event type.

2. The computer-implemented method of claim 1 , wherein determining segmentation events includes detecting conditions where gameplay stops.

3. The computer-implemented method of claim 1 , wherein determining segmentation events further includes determining that time periods where the product of eigenvalues of the covariance matrix exceeds the threshold parameter represent reset scenes.

4. The computer-implemented method of claim 2 , wherein determining segmentation events includes identifying a first event after an interruption or a reset scene as being a segmentation event.

5. The computer-implemented method of claim 1 , wherein the game is a team-based invasion sport.

6. The computer-implemented method of claim 1 , wherein performing event analysis includes determining a Markov reward model using the segmentation events.

7. The computer-implemented method of claim 1 , wherein responding to events includes directing player positioning.

8. The computer-implemented method of claim 7 , wherein directing player positioning includes sending instructions to robotic players to cause those robotic players to move on a field of play.

9. A non-transitory computer readable storage medium comprising a computer readable program for game event analysis and control, wherein the computer readable program when executed on a computer causes the computer to perform the steps of:

determining segmentation events in a game that each represent an interruption in game play or a reset scene by comparing a product of eigenvalues of a covariance matrix to a threshold parameter to determine whether players have spread out on a game field, where the covariance matrix reflects player locations at respective times;

performing an event analysis using the series of segmentation events to determine a contribution value for each event in the series of segmentation events that represents how much each respective event in the series of segmentation events contributed to a point being scored; and

responding to events having a contribution value that exceeds a baseline value for a respective event type.

10. A system for game event analysis and control, comprising:

a segmentation event detector configured to determine segmentation events in a game that each represent an interruption in game play or a reset scene, by comparing a product of eigenvalues of a covariance matrix to a threshold parameter to determine whether players have spread out on a game field, where the covariance matrix reflects player locations at respective times; and

an event analysis module including a processor configured to perform an event analysis using the series of segmentation events to determine a contribution value for each event in the series of segmentation events that represents how much each respective event in the series of segmentation events contributed to a point being scored; and

an event response module configured to respond to events having a contribution value that exceeds a baseline value for a respective event type.

11. The system of claim 10 , wherein the segmentation event detector is further configured to detect conditions where gameplay stops.

12. The system of claim 10 , wherein the segmentation event detector is further configured to determine that time periods where the product of eigenvalues of the covariance matrix exceeds the threshold parameter represent reset scenes.

13. The system of claim 11 , wherein the segmentation event detector is further configured to identify a first event after an interruption or a reset scene as being a segmentation event.

14. The system of claim 10 , wherein the game is a team-based invasion sport.

15. The system of claim 10 , wherein performing event analysis includes determining a Markov reward model using the segmentation events.

16. The system of claim 10 , wherein the event response module is further configured to direct player positioning.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 4, 2019
From: ZHAO, KUN; OSOGAMI, TAKAYUKI; MORIMURA, TETSURO
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 048226/0619 →
Continuity (1)
Related Publication 20200250828A1 · Aug 6, 2020