Back to results
US 2025/0148734 A1Published application
Scene creation using language models
AssigneeRoblox Corporation
InventorsBehzad Haghgoo, Vinith Misra, Maxwell Wen Xiong
Life of this patent
Estimating the term…
Loading patent…
Loading patent…
AssigneeRoblox Corporation
InventorsBehzad Haghgoo, Vinith Misra, Maxwell Wen Xiong
Estimating the term…
A user prompt, such as a user prompt received by a client device and sent to an online game system, is provided into a trained large language model. The large language model identifies keywords corresponding to the user prompt. These keywords may be provided to a search engine that identifies corresponding object(s) to place in a virtual experience. The large language model further processes the user prompt to determine spatial placement information for the objects and places the objects accordingly. Subsequently, the system may iteratively receive more prompts and update the virtual experience based on the additional prompts. The placement may be facilitated using macros. The prompts may also affect other attributes of the objects. The knowledge built-into the LLM allows it to suggest which objects are relevant and what quantity and arrangements of these objects is consistent with a scene requested in the user prompt.
A computer-implemented method, the method comprising:
A non-transitory computer-readable medium comprising instructions that, responsive to execution by a processing device, causes the processing device to perform operations comprising:
A system comprising:
Dependencies are inferred from the claim text.