Apparatus, systems and methods for video game analysis

Abstract

A data processing apparatus for detecting one or more errors for one or more video images for a video game. The apparatus comprises receiving circuitry to receive a sequence of video images for the video game and one or more action inputs associated with the sequence of video images. It also comprises prediction circuitry to generate a predicted video image in dependence on at least one video image of the sequence of video images and an action input associated with the at least one video image. The prediction circuitry comprising a trained machine learning model to generate the predicted video image, and error detection circuitry to detect, for one or more video images subsequent to the at least one video image, one or more errors in dependence on the predicted video image. Where the machine learning model has been trained using training data comprising video images for the video game and associated action inputs.

Claims

1. A data processing apparatus for detecting one or more errors for one or more video images for a video game, the data processing apparatus comprising:receiving circuitry to receive a sequence of video images for the video game and one or more action inputs associated with the sequence of video images;prediction circuitry to generate a predicted video image in dependence on at least one video image of the sequence of video images and an action input associated with the at least one video image, the prediction circuitry comprising a trained machine learning model to generate the predicted video image; anderror detection circuitry to detect, for one or more video images subsequent to the at least one video image, one or more errors in dependence on the predicted video image.

2. The data processing apparatus according to claim 1, wherein the machine learning model has been trained using training data comprising video images for the video game and associated action inputs.

3. The data processing apparatus according to claim 2, wherein the machine learning model has been trained using the training data to learn a function for mapping a video image and an action input associated with the video image to a predicted video image.

4. The data processing apparatus according to claim 3, wherein the machine learning model has been trained using reinforcement learning.

5. The data processing apparatus according to claim 4, wherein the machine learning model is trained to learn a world model for the video game for mapping the video image for the video game and the action input associated with the video image to the predicted video image.

6. The data processing apparatus according to any one of claims 1 to 4, wherein the training data comprises one or more from the list consisting of:video images and action inputs associated with one or more other video games corresponding to a same video game series as the video game; andvideo images and action inputs associated with one or more other video games corresponding to a same video game genre as the video game.

7. The data processing apparatus according to any preceding claim, wherein the error detection circuitry is configured to detect, for a video image subsequent to the at least one videoimage, one or more errors in dependence upon detection of one or more differences between the video image and the predicted video image.

8. The data processing apparatus according to clam 7, wherein the error detection circuitry comprises an image difference detector to generate a difference video image indicative of differences between the video image subsequent to the at least one video image and the predicted video image.

9. The data processing apparatus according to claim 7 or claim 8, wherein the error detection circuitry is configured detect one or more differences between the video image and the predicted video image based on object recognition processing.

10. The data processing apparatus according to any one of claims 7 to 9, wherein the error detection circuitry is configured to detect one or more of the errors in dependence upon whether a difference between the another video image and the predicted video image satisfies a threshold condition.

11. The data processing apparatus according to any preceding claim, wherein the error detection circuitry is configured to detect one or more error regions in one or more video images subsequent to the at least one video image.

12. The data processing apparatus according to any preceding claim, comprising image processing circuitry to generate, in response to detection by the error detection circuitry of one or more errors, one or more visual indicators for one or more of the errors.

13. The data processing apparatus according to claim 12 when dependent on claim 11, wherein the image processing circuitry is configured to generate one or more of the visual indicators to be overlaid on one or more of the error regions in one or more of the video images.

14. A computer-implemented method apparatus for detecting one or more errors for one or more video images for a video game, the method comprising:receiving a sequence of video images for the video game and one or more action inputs associated with the sequence of video images;generating a predicted video image in dependence on at least one video image of the sequence of video images and an action input associated with the at least one video image, the step of generating comprising using a trained machine learning model to generate the predicted video image; anddetecting, for one or more video images subsequent to the at least one video image, one or more errors in dependence on the predicted video image.

15. Computer software which when executed by a computer causes the computer to perform 5 the method according to claim 14.23

Images