US-12616902-B2 - Method and system for generating an image representing the results of a gaming session

Abstract

A method for generating a moment asset to represent interactive activity that occurred during a session of gameplay includes executing an instance of a game for a user, with the executing generating state data descriptive of interactive activity occurring during the session, and examining the state data by a machine learning process, which extracts features for classification and input to a moment model. The method also includes accessing user profile data, which includes labeled user profile feature data that identifies characteristics of playing the game by the user and is input to the moment model. The method further includes outputting, by the moment model, two or more images and at least one text descriptor of interactive activities that occurred during the session, and inputting the images and text descriptor to an image generation artificial intelligence process with priority data to influence a layout of image content for the moment asset.

Inventors

• Arran Green

Assignees

• SONY INTERACTIVE ENTERTAINMENT INC.

Dates

Publication Date

20260505

Application Date

20230117

Claims (20)

1. 1 . A method for generating a moment asset to represent interactive activity that occurred during a session of gameplay of a game, comprising: executing an instance of the game wherein the executing generates state data descriptive of interactive activity occurring during the session of gameplay of the game; examining the state data by a machine learning process, wherein the machine learning process is configured to extract features from the state data for classification; outputting, by the machine learning process, two or more images and at least one text descriptor of interactive activities that occurred during the session of gameplay of the game; and inputting the two or more images and the at least one text descriptor to an image generation process with priority data to influence a layout of image content for the moment asset, wherein the image content is a selective representation of certain interactive activity of a user that occurred during the session of gameplay of the game, wherein the moment asset comprises a combination of the two or more images of interactive activities that occurred during the session of gameplay output in a hybrid collage format, and wherein a first portion of the moment asset includes a first collage of the two or more images and has a first format, and wherein a second portion of the moment asset includes a second collage of the two or more images and has a second format different from the first format, wherein the first format and the second format each defines an arrangement of the two or more images within the moment asset.
2. 2 . The method of claim 1 , wherein the image generation process comprises an image generation artificial intelligence process.
3. 3 . The method of claim 1 , wherein the first portion of the moment asset is comprised of a structurally-arranged collage in which images of interactive activities that occurred during the session of gameplay of the game are arranged in an order based on priority ranking.
4. 4 . The method of claim 1 , wherein the first portion of the moment asset is comprised of an arbitrarily-blended collage in which images of interactive activities that occurred during the session of gameplay of the game are randomly arranged.
5. 5 . The method of claim 1 , wherein the first format includes a structurally-arranged collage in which images of interactive activities that occurred during the session of gameplay of the game are arranged in an order based on priority ranking and the second format includes an arbitrarily-blended collage in which images of interactive activities that occurred during the session of gameplay of the game are randomly arranged.
6. 6 . The method of claim 1 , wherein the moment asset is certified to be authentic using a non-fungible token (NFT) recorded in a blockchain.
7. 7 . A method for generating a moment asset to represent interactive activity that occurred during a session of gameplay of a game, comprising: executing an instance of the game, wherein the executing generates state data descriptive of interactive activity occurring during the session of gameplay of the game; examining the state data by a machine learning process, wherein the machine learning process is configured to extract features from the state data for classification; outputting, by the machine learning process, two or more images and at least one text descriptor of interactive activities that occurred during the session of gameplay of the game; and inputting the two or more images and the at least one text descriptor to an image generation process with priority data to influence a definition of digital content for the moment asset, wherein the digital content is a selective representation of certain interactive activity of a user that occurred during the session of gameplay of the game, wherein the moment asset comprises a combination of the two or more images that occurred during the session of gameplay output in a hybrid collage format, and wherein a first portion of the moment asset includes a first collage of the two or more images and has a first format, and wherein a second portion of the moment asset includes a second collage of the two or more images and has a second format different from the first format, wherein the first format and the second format each defines an arrangement of the two or more images within the moment asset.
8. 8 . The method of claim 7 , wherein the digital content is usable to construct the hybrid collage format to represent the moment asset, and wherein the image generation process comprises an image generation artificial intelligence process.
9. 9 . The method of claim 7 , wherein the moment asset further comprises a video, and wherein the digital content is usable to construct the video.
10. 10 . The method of claim 7 , wherein the moment asset further comprises a three-dimensional physical asset, and wherein the digital content is usable to construct the three-dimensional physical asset.
11. 11 . The method of claim 10 , wherein the three-dimensional physical asset is a statue, statuette, or figurine.
12. 12 . The method of claim 10 , wherein the three-dimensional physical asset is a medal or token.
13. 13 . The method of claim 10 , wherein the moment asset is certified to be authentic using a non-fungible token (NFT) recorded in a blockchain.
14. 14 . The method of claim 11 , wherein the statue, statuette, or figurine is certified to be authentic using a non-fungible token (NFT) recorded in a blockchain.
15. 15 . The method of claim 12 , wherein the medal or token is certified to be authentic using a non-fungible token (NFT) recorded in a blockchain.
16. 16 . A non-transitory computer readable medium comprising program instructions for generating a moment asset to represent interactive activity that occurred during a session of gameplay of a game, wherein execution of the program instructions by one or more processors of a computer system causes the one or more processors to perform operations comprising: executing an instance of the game, wherein the executing generates state data descriptive of interactive activity occurring during the session of gameplay of the game; examining the state data by a machine learning process, wherein the machine learning process is configured to extract features from the state data for classification; outputting, by the machine learning process, two or more images and at least one text descriptor of interactive activities that occurred during the session of gameplay of the game; and inputting the two or more images and the at least one text descriptor to an image generation process with priority data to influence a layout of image content for the moment asset, wherein the image content is a selective representation of certain interactive activity of a user that occurred during the session of gameplay of the game, wherein the moment asset comprises a combination of the two or more images of interactive activities that occurred during the session of gameplay output in a hybrid collage format, and wherein a first portion of the moment asset includes a first collage of the two or more images and has a first format, and wherein a second portion of the moment asset includes a second collage of the two or more images and has a second format different from the first format, wherein the first format and the second format each defines an arrangement of the two or more images within the moment asset.
17. 17 . The non-transitory computer readable medium of claim 16 , wherein the image generation process comprises an image generation artificial intelligence process.
18. 18 . The non-transitory computer readable medium of claim 16 , wherein the first portion of the moment asset is comprised of a structurally-arranged collage in which images of interactive activities that occurred during the session of gameplay of the game are arranged in an order based on priority ranking.
19. 19 . The non-transitory computer readable medium of claim 16 , wherein the first portion of the moment asset is comprised of an arbitrarily-blended collage in which images of interactive activities that occurred during the session of gameplay of the game are randomly arranged.
20. 20 . The non-transitory computer readable medium of claim 16 , wherein the moment asset is certified to be authentic using a non-fungible token (NFT) recorded in a blockchain.

Description

BACKGROUND Video game players often share memorable achievements from their gaming sessions with their friends via social media platforms, e.g., Discord, Twitch, YouTube, Twitter, etc. In some instances, the memorable achievements are captured in video clips or screenshots taken from a gaming session. The generation of such video clips or screenshots can be time-consuming and burdensome for the player because the player not only has to search through a recording of the gaming session to find the memorable achievements, but also typically must use specialized software to generate the video clips or screenshots. Further, from a network standpoint, this process of generating the video clips or screenshots is relatively inefficient and consequently consumes a significant amount of computing resources. It is in this context that embodiments arise. SUMMARY In an example embodiment, a method for generating a moment asset to represent interactive activity that occurred during a session of gameplay of a game is provided. The method includes executing an instance of the game for a user, with the executing generating state data descriptive of interactive activity occurring during the session. The method also includes examining the state data by a machine learning process, where the machine learning process is configured to extract features from the state data for classification and input to a moment model. The method further includes accessing user profile data of the user, where the user profile data includes labeled user profile feature data that identifies characteristics of playing the game by the user. The labeled user profile feature data is input to the moment model. Still further, the method includes outputting, by the moment model, two or more images and at least one text descriptor of interactive activities that occurred during the session of gameplay of the game, and inputting the two or more images and the at least one text descriptor to an image generation artificial intelligence (IGAI) process with priority data to influence a layout of image content for the moment asset. The image content is a selective representation of certain interactive activity that occurred during the session of gameplay of the game. In one embodiment, the moment asset is comprised of a blend of the two or more images of interactive activities that occurred during the session of gameplay of the game. In one embodiment, the moment asset is comprised of a structurally-arranged collage in which images of interactive activities that occurred during the session of gameplay of the game are arranged in an order based on priority ranking. In one embodiment, the moment asset is comprised of an arbitrarily-blended collage in which images of interactive activities that occurred during the session of gameplay of the game are randomly arranged. In one embodiment, the moment asset is comprised of a hybrid collage in which one portion of the hybrid collage includes a structurally-arranged collage in which images of interactive activities that occurred during the session of gameplay of the game are arranged in an order based on priority ranking and another portion of the hybrid collage includes an arbitrarily-blended collage in which images of interactive activities that occurred during the session of gameplay of the game are randomly arranged. In one embodiment, the moment asset is certified to be authentic using a non-fungible token (NFT) recorded in a blockchain In another example embodiment, another method for generating a moment asset to represent interactive activity that occurred during a session of gameplay of a game is provided. The method includes executing an instance of the game for a user, with the executing generating state data descriptive of interactive activity occurring during the session. The method also includes examining the state data by a machine learning process, where the machine learning process is configured to extract features from the state data for classification and input to a moment model. The method further includes accessing user profile data of the user, where the user profile data includes labeled user profile feature data that identifies characteristics of playing the game by the user. The labeled user profile feature data is input to the moment model. Still further, the method includes outputting, by the moment model, two or more images and at least one text descriptor of interactive activities that occurred during the session of gameplay of the game, and inputting the two or more images and the at least one text descriptor to an image generation artificial intelligence (IGAI) process with priority data to influence a definition of digital content for the moment asset. The digital content is a selective representation of certain interactive activity that occurred during the session of gameplay of the game. In one embodiment, the digital content is usable to construct an image to represent the moment asset. In