公开(公告)号：US20250166665A1

公开(公告)日：2025-05-22

申请号：US18957276

申请日：2024-11-22

Applicant: Meta Platforms, Inc.

Inventor： Alicia Fujun Lew ,  Zachary Ian Howard ,  Sara Mousavicheshmehkaboodi ,  Bina Thakkar ,  Anish Doshi ,  Bo Shuang ,  Wen Wang

IPC: G11B27/031 ,  G06F3/0482 ,  G06F3/0484 ,  G06T11/60

Abstract: A disclosed computer-implemented method may include presenting, within a video creation interface, a list of video styles, each video style within the list of video styles representative of a trained model, the trained model trained to apply different aesthetic attributes to video content in accordance with a different video style. The method may also include receiving, via user input to the video creation interface, a selection of a particular video style from the list of video styles and, in response to receiving the selection, applying, to video content received via the video creation interface, a video editing technique corresponding to the particular video style. Various other methods, systems, and devices are also disclosed.

公开(公告)号：US20250158947A1

公开(公告)日：2025-05-15

申请号：US18946365

申请日：2024-11-13

Applicant: META PLATFORMS, INC.

Inventor： Vincent Charles Cheung ,  Hadi Michel Salem ,  Kaolin Imago Fire ,  Catherine Suzanne Trono ,  Yipin Zhou ,  Marc David ,  Aran Mun ,  Gaurav Pankaj Sharma

IPC: H04L51/10 ,  G06T5/50 ,  G06T13/40 ,  H04L51/04

Abstract: Methods and systems are described for an intelligent messaging platform between users to foster more an immersive and creative messaging environment. In various examples, systems and methods may receive, via a device associated with a user, a media input. Context associated with the media input may be determined. The creation of a media item may be based on the media input and context associated with the media input. The creation of a media item may be based on the use of a machine learning model. The media may be provided to a user or group of users via one or more user devices associated with the users.

公开(公告)号：US20250157106A1

公开(公告)日：2025-05-15

申请号：US18942011

申请日：2024-11-08

Applicant: META PLATFORMS, INC.

Inventor： Arantxa Casanova Paga ,  Bo Sun ,  Anmol Kalia ,  Amy Lawson Bearman ,  Dhruv Kumar Mahajan ,  Animesh Sinha

IPC: G06T11/60 ,  G06F3/04845

Abstract: Aspects of the present disclosure may include systems and methods generating visual content. The system may detect input of descriptive text associated with text content or audio content. The system may generate, based on the descriptive text, an initial latent representation by using a finetuned latent diffusion model. The system may apply a denoising process to the initial latent representation to produce a refined latent representation. The system may sample data points from a content distribution associated with prior timesteps and from a style distribution associated with subsequent timesteps, thereby generating a final image latent. The system may decode the final image latent to obtain a visually aligned image(s) corresponding to the descriptive text. The system may output the visually aligned image(s) on a user interface or a display.

公开(公告)号：US20250141751A1

公开(公告)日：2025-05-01

申请号：US18384278

申请日：2023-10-26

Applicant: Meta Platforms, Inc.

Inventor： YuLing Chen ,  Matthew Calder ,  Ayush Jain ,  Supratim Deb ,  Lee Mark Hetherington ,  Huapeng Zhou ,  Benjamin Vallis ,  Wen Liu

IPC: H04L41/122 ,  H04L43/0864

Abstract: In some embodiments, a computer-implemented method includes ascertaining a multitier topology representation of an edge cloud network; generating a pseudo node topology representation of the edge cloud network from the multitier topology representation; and utilizing the pseudo node topology representation of the edge cloud network to ascertain minimum-latency pseudo-node-based edge cloud clusters (ECCs), the minimum-latency pseudo-node-based ECCs being utilized to minimize a latency of user requests routed through the edge cloud network from a user of the edge cloud network. In some embodiments of the computer-implemented method, the minimum-latency pseudo-node-based ECCs are ascertained based upon a pseudo-node-based round-trip-times (RTTs) assessment from the user of the edge cloud network, the user requests being routed to the minimum-latency pseudo-node-based ECCs ascertained using the pseudo node topology representation.

公开(公告)号：US12249014B1

公开(公告)日：2025-03-11

申请号：US17877595

申请日：2022-07-29

Applicant: Meta Platforms, Inc.

Inventor： Mokhtar Mohamed Khorshid ,  Trang Tran ,  Beau Dunn ,  Erica Feld

IPC: G06T13/40 ,  G06T15/00 ,  G06T19/00

Abstract: In one embodiment, a method includes rendering a first output image of an XR assistant avatar within a first environment associated with a first XR application for displays of a first extended-reality (XR) display device, wherein the XR assistant avatar has a first form according to a first rendering specification associated with the first XR application and the XR assistant avatar is interactable by a first user to access an assistant system, receiving an indication that the first user is switching from the first XR application to a second XR application, accessing a second rendering specification associated with the second XR application, and rendering a second output image of the XR assistant avatar within a second environment associated with the second XR application for displays of a second XR display device, wherein the XR assistant avatar is rendered to have a second form according to the second rendering specification.

公开(公告)号：US12236011B2

公开(公告)日：2025-02-25

申请号：US18147547

申请日：2022-12-28

Applicant: Meta Platforms, Inc.

Inventor： Mark Terrano ,  Ian Erkelens ,  Kevin James MacKenzie

IPC: G06T19/00 ,  G02B27/01 ,  G06F3/01 ,  G06F3/04812 ,  G06N20/00

Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for selectively rendering augmented reality content based on predictions regarding a user's ability to visually process the augmented reality content. For instance, the disclosed systems can identify eye tracking information for a user at an initial time. Moreover, the disclosed systems can predict a change in an ability of the user to visually process an augmented reality element at a future time based on the eye tracking information. Additionally, the disclosed systems can selectively render the augmented reality element at the future time based on the predicted change in the ability of the user to visually process the augmented reality element.

公开(公告)号：US12229321B1

公开(公告)日：2025-02-18

申请号：US18154106

申请日：2023-01-13

Applicant: META PLATFORMS, INC.

Inventor： Michael Kounavis

IPC: G06F21/64 ,  G06F16/22 ,  G06F21/60

Abstract: Methods, systems, and apparatuses for disguising or otherwise hiding big data access patterns and frequencies may include a replica being directly obtained from a key and a replica index, based on applying a pseudorandom permutation or pseudorandom function. Data object access frequencies may be quantized so that the ratios of quantized data object access frequencies are rational numbers of integers, which may allow for a uniform distribution of data object accesses. Fake accesses may be implemented by simulating an access schedule produced by a cryptographic primitive and by performing a greedy mapping between the real data object accesses and simulated data object accesses.

公开(公告)号：US20250037462A1

公开(公告)日：2025-01-30

申请号：US18829705

申请日：2024-09-10

Applicant: Meta Platforms, Inc.

Inventor： Emily Wang ,  Yilei Li ,  Amy Lawson Bearman ,  Alireza Dirafzoon ,  Ruchir Srivastava

IPC: G06V20/40 ,  G06N20/00 ,  H04N23/60 ,  H04N23/61

Abstract: In one embodiment, a method includes accessing from a client system associated with a first user sensor signals captured by sensors of the client system, wherein the client system comprises a plurality of sensors, and wherein the sensors signals are accessed from the sensors based on cascading model policies, wherein each cascading model policy utilizes one or more of a respective cost or relevance associated with each sensor, detecting a change in a context of the first user associated with an activity of the first user based on machine-learning models and the sensor signals, wherein the change in the context of the first user satisfies a trigger condition associated with the activity, and responsive to the detected change in the context of the first user automatically capturing visual data by cameras of the client system.

公开(公告)号：US20250021941A1

公开(公告)日：2025-01-16

申请号：US18145153

申请日：2022-12-22

Applicant: Meta Platforms, Inc.

Inventor： Yang Liu

IPC: G06Q10/1093

Abstract: A system for determining personalized execution times for delivery of optimized content is disclosed. The system may evaluate activities of a user, occurring within a network, during hours of days. The system may determine, based on the evaluated activities, optimal time periods during a time interval in which to schedule provision of content items to a communication device(s) associated with the user. The system may determine a best time period among the optimal time periods. The system may generate, in advance of the optimal time periods, content items tailored to the user. The system may determine, in advance of the best time period, a highest ranked generated content item, among the generated content items, for delivery to the communication device(s) associated with the user during the best time period. The system may enable provision, to the communication device(s), of the highest ranked generated content item during the best time period.

公开(公告)号：US20250021791A1

公开(公告)日：2025-01-16

申请号：US17953836

申请日：2022-09-27

Applicant: Meta Platforms, Inc.

Inventor： Andrew Donald Yates ,  Kurt Dodge Runke ,  Gunjit Singh

IPC: G06N3/04 ,  G06Q30/02 ,  G06Q50/00

Abstract: An online system receives explicit user data and explicit event data, and implicit user data and implicit event data from a third party system. The online system generates an implicit users/implicit events data feature, an explicit users/explicit events data feature, and an explicit users/implicit events data feature. The online system generates a prediction of the counterfactual rate based on the implicit users/implicit events data feature, the explicit users/explicit events data feature, and the explicit users/explicit events data feature, the counterfactual rate indicating the likelihood that target users matching certain characteristics caused an event to occur when the target are not been presented with content by the online system, the content configured to induce users to cause the event to occur. A combined prediction rate is presented to the third party system based on the counterfactual rate.