US 12,141,905 B2
Content generation system and method
Calum Armstrong, London (GB); Nicholas Anthony Edward Ryan, London (GB); Marina Villanueva-Barreiro, Acoruňa (ES); and Mark Anthony, London (GB)
Assigned to Sony Interactive Entertainment Inc., Tokyo (JP)
Filed by Sony Interactive Entertainment Inc., Tokyo (JP)
Filed on Oct. 10, 2022, as Appl. No. 17/962,568.
Claims priority of application No. 2114675 (GB), filed on Oct. 14, 2021.
Prior Publication US 2023/0117530 A1, Apr. 20, 2023
Int. Cl. G06T 13/40 (2011.01); A63F 13/55 (2014.01); G06T 17/10 (2006.01)
CPC G06T 13/40 (2013.01) [A63F 13/55 (2014.09); G06T 17/10 (2013.01); A63F 2300/6607 (2013.01)] 13 Claims
OG exemplary drawing
 
1. A content generation system operable to generate one or more actions to be performed by an agent, the system comprising:
an input receiving unit operable to receive two or more actions for the agent;
a model generation unit operable to input the actions to a machine learning model so as to generate a trained machine learning model; and
an action generation unit operable to generate an action to be performed by the agent, wherein the generation comprises selection of a latent space interpolation state associated with the trained machine learning model,
wherein the selection of a latent space interpolation state is performed in dependence upon one or more constraints upon a desired action to be generated.