# US 10,765,944 B2 · Machine learning models for implementing animation actions

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 10,765,944 B2
- Document ID: US10765944B2
- Status: Granted
- Kind: B2
- Application number: 16/125,288
- Filed: 2018-09-07
- Published: 2020-03-12
- Granted: 2020-09-08
- Earliest claimed: 2018-09-07
- Assignees: Electronic Arts Inc.
- Applicants: Electronic Arts, Inc.
- Inventors: Cesar Dantas de Castro
- Web page: https://patentgrep.com/patent/US10765944B2

## CPC

- A63F 13/67: adaptively or by learning from player actions, e.g. skill level adjustment or by storing successful combat sequences for re-use
- A63F 13/52: involving aspects of the displayed game scene
- A63F 13/56: Computing the motion of game characters with respect to other game characters, game objects or elements of the game scene, e.g. for simulating the behaviour of a group of virtual soldiers or for path finding
- A63F 13/577: using determination of contact between game characters or objects, e.g. to avoid collision between virtual racing cars
- G06T 7/20: Analysis of motion (motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51)
- G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80)
- G06T 13/00: Animation
- G06T 13/40: of characters, e.g. humans, animals or virtual beings
- G06V 10/764: using classification, e.g. of video objects
- G06V 20/42: {of sport video content}
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2210/21: Collision detection, intersection
- G06V 20/44: {Event detection}
- A63F: CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

An animation system and method generates predictive models that are deployed in animations, such as an animation associated with a video game, to predict outcomes resulting from events occurring in the animation, such as interactions between two or more objects in the animation. These predictive models may be generated based at least in part on training data that is generated by running the animation, such as playing a video game, generating parameter values associated with events in the animation, and determining an outcome of the events. The training data may be used to generate predictive models, such as by using machine learning algorithms. The predictive models may then be deployed in the animation, such as in a video game, to make real time or near real-time predictions of outcomes based at least in part on events in the animation.

## Claims

### Claim 1

An animation development system, comprising:
one or more processors; and
one or more computer-readable media storing computer-executable instructions that, when executed by the one or more processors, cause the one or more processors to:
identify a first event that transpires during a video game play of a video game;
determine one or more parameter values associated with the first event;
identify a first outcome associated with the first event;
generate training data based at least in part on the one or more para meter values and the first outcome; and
generate a predictive model based at least in part on the training data; and
deploy the predictive model in the video game to make a prediction of a second outcome associated with a second event that transpires during game play of the video game.

### Claim 2 (depends on 1)

The animation development system of claim 1, wherein the computer-executable instructions further cause the one or more processors to:
invoke a function based at least in part on the second outcome.

### Claim 3 (depends on 1)

The animation development system of claim 1, wherein the prediction of the second outcome comprises a determination that an animated character is to fall down, wherein the computer-executable instructions further cause the one or more processors to:
cause the animated character in the video game to fall down during the game play of the video game.

### Claim 4 (depends on 1)

The animation development system of claim 1, wherein to generate the predictive model based at least in part on the training data, the computer-executable instructions further cause the one or more processors to:
determine the predictive model by applying the training data to at least one machine learning algorithm.

### Claim 5 (depends on 1)

The animation development system of claim 1, wherein the predictive model comprises at least one of: (i) a logistic regression algorithm; (ii) a neural network model; (iii) a decision tree model; (iv) a random forest model; or (v) a Bayesian network model.

### Claim 6 (depends on 1)

The animation development system of claim 1, wherein to generate training data based at least in part on the one or more parameter values and the first outcome, the computer-executable instructions further cause the one or more processors to:
aggregate the one or more parameter values and the first outcome with one or more other sets of parameters and outcomes.

### Claim 7 (depends on 1)

The animation development system of claim 1, wherein to determine one or more parameter values, the computer-executable instructions further cause the one or more processors to:
identify a first object in the video game play;
identify a second object in the video game play;
determine a location of the first object relative to the second object;
determine that the first object and the second object are in contact; and
determine the one or more parameter values based at least in part on determining that the first object and the second object are in contact.

### Claim 8 (depends on 1)

The animation development system of claim 1, the computer-executable instructions further cause the one or more processors to:
identify a second event that transpires during the video game play;
determine one or more second parameter values associated with the second event; and
identify a second outcome associated with the second event, wherein the training data is further based at least in part on the one or more second parameter values and the second outcome.

### Claim 9

An animation development method, comprising:
identifying, by one or more processors and based at least in part on analyzing movement of an object in an animation in a video game, an event that transpires in the animation;
determining, by the one or more processors, a parameter value associated with the event;
identifying, by the one or more processors, an outcome associated with the event;
generating, by the one or more processors, training data associated with the video game and based at least in part on the parameter value and the outcome;
generating, by the one or more processors, a predictive model based at least in part on the training data; and
deploying the predictive model in the video game to predict one or more second outcomes corresponding to one or more second events that transpire during video game play of the video game.

### Claim 10 (depends on 9)

The animation development method of claim 9, further comprising:
recording the animation;
replaying the animation; and
annotating the animation during the replay of the animation to generate the training data.

### Claim 11 (depends on 9)

The animation development method of claim 9, wherein identifying an outcome associated with the event further comprises receiving user input indicating the outcome.

### Claim 12 (depends on 9)

The animation development method of claim 9, wherein the predictive model comprises at least one of: (i) a logistic regression algorithm; (ii) a neural network model; (iii) a decision tree model; (iv) a random forest model; or (v) a Bayesian network model.

### Claim 13 (depends on 9)

The animation development method of claim 9, wherein generating training data further comprises aggregating the parameter value and the outcome with one or more other sets of parameters and outcomes.

### Claim 14 (depends on 9)

The animation development method of claim 9, further comprising:
determining a second parameter value associated with the event;
identifying a second outcome associated with the event;
generating second training data based at least in part on the second parameter value and the second outcome; and
generating a second predictive model based at least in part on the second training data.

### Claim 15

A system, comprising:
one or more processors; and
one or more computer-readable media storing computer-executable instructions that, when executed by the one or more processors, cause the one or more processors to:
receive a first input during a video game play of a video game, the first input corresponding to a first object rendered in the video game;
receive a second input during the video game play of the video game, the second input corresponding to a second object rendered in the video game;
determine an occurrence of an event in the video game based at least in part on the first input and the second input;
identify a predictive model associated with the event, the predictive model comprising a machine learning model trained on previous video game play training data associated with the video game;
determine, based at least in part on the predictive model, an outcome in the video game associated with the event; and
render, based at least in part on the outcome, an animation action on at least one of the first object or the second object.

### Claim 16 (depends on 15)

The system of claim 15, wherein the first object is a first character in the video game, the second object is a second character in the video game, and the animation action comprises the first character falling down.

### Claim 17 (depends on 15)

The system of claim 15, wherein the first object is a first character in the video game, the second object is a ball in the video game, and the animation action comprises the first character catching the ball.

### Claim 18 (depends on 15)

The system of claim 15, wherein the machine learning model comprises at least one of: (i) a logistic regression algorithm; (ii) a neural network model; (iii) a decision tree model; (iv) a random forest model; or (v) a Bayesian network model.

### Claim 19 (depends on 15)

The system of claim 15, wherein the first input is a game controller input that causes a corresponding movement of the first object in the video game.

### Claim 20 (depends on 15)

The system of claim 15, wherein the previous game play training data includes an indication of a plurality of events that transpired during a previous session of video game play.