Back to results
US 12,762,762 B2Granted
Customized digital humans and pets for metaverse
AssigneeSony Interactive Entertainment Inc.
InventorSudha Krishnamurthy
Life of this patent
Estimating the term…
Abstract
Deep learning is used to dynamically adapt virtual humans in metaverse applications. The adaptation can be according to user preferences. In addition or alternatively, virtual humans and pets can be adapted for metaverse applications based on demographics of the user. The user's personal demographics may be used to establish the costume, skin color, emotion, voice, and behavior of the virtual humans. Similar considerations may be used to adapt virtual pets to the user's experience of the metaverse.
Claims19
A device comprising:
- at least one computer storage that is not a transitory signal and that comprises instructions executable by at least one processor to:
- execute A, or B, or both A and B, wherein A comprises:
- receive at least one image of a person;
- input the image to a machine learning (ML) model;
- receive from the ML model first information regarding customization of a virtual being in a metaverse;
- and
- present on a display the virtual being with a customized appearance altered from an original appearance from original game software according to the first information from the ML model;
- and
- wherein B comprises:
- receive at least one recording of speech of the person;
- input the recording to the ML model;
- responsive to inputting the recording to the ML model, receive from the ML model second information regarding customization of the virtual being;
- and
- present the virtual being with a customized voice altered from an original voice from the original game software according to the second information from the ML model;
- and
- send the first information regarding customization to at least one display presenting a metaverse other than the display so that the virtual being appears in customized form on the at least one display presenting the metaverse, the first information regarding customization being sent to the at least one display presenting the metaverse based on a status of the person.
13 more elements
An apparatus comprising:
- at least one processor programmed with executable instructions to:
- customize an appearance of a virtual being presented on a display according to at least one image of a person to render an altered appearance of the virtual being, the altered appearance based at least in part on an original appearance from original game software;
- access at least one recording of speech of the person;
- input the recording to a machine learning (ML) model;
- responsive to inputting the recording to the ML model, receive, from the ML model, information regarding customization of the virtual being;
- and
- present the virtual being with a customized voice altered from an original voice from the original game software according to the information from the ML model.
4 more elements
A method, comprising:
- receiving at least one image of a real world person viewing a virtual person on a display;
- customizing an appearance of the virtual person being presented on the display according to the at least one image to render an altered appearance of the virtual person, the altered appearance being determined at least in part from an original appearance from original game software;
- and
- sending first information regarding customization to at least one display presenting a metaverse other than the display so that a virtual being appears in customized form on the at least one display presenting the metaverse, the first information regarding customization being sent to the at least one display presenting the metaverse based on a status of the real world person.
1 more element
Dependencies are inferred from the claim text.