公开(公告)号：US20240242442A1

公开(公告)日：2024-07-18

申请号：US18097040

申请日：2023-01-13

Applicant: Meta Platforms, Inc.

Inventor： Fan ZHANG ,  William WONG ,  Anoop Kumar SINHA ,  Timothy ROSENBERG ,  Chen SUN ,  Gary Vu NGUYEN ,  Sofia GALLO PAVAJEAU ,  Agustya MEHTA ,  Johana Gabriela COYOC ESCUDERO ,  Leonid VLADIMIROV ,  James SCHULTZ

IPC: G06T19/00 ,  G02B27/01 ,  G06V10/82 ,  G06V10/84

CPC classification number: G06T19/006 ,  G02B27/0172 ,  G06V10/82 ,  G06V10/84 ,  G02B2027/0178

Abstract: According to examples, a system for supplementing user perception and experience via augmented reality (AR), artificial intelligence (AI), and machine-learning (ML) techniques is described. The system may include a processor and a memory storing instructions. The processor, when executing the instructions, may cause the system to receive data associated with at least one of a location, context, or setting and determine, using at least one artificial intelligence (AI) model and at least one machine learning (ML) model, relationships between objects in the at least one of the location, context, or setting. The processor, when executing the instructions, may then apply an artificial intelligence (AI) agent to analyze the relationships and generate a three-dimensional (3D) mapping of the at least one of the location, context, or setting and provide an output to aid a user's perception and experience.

公开(公告)号：US20240176603A1

公开(公告)日：2024-05-30

申请号：US18059613

申请日：2022-11-29

Applicant: Meta Platforms, Inc.

Inventor： Roman Georg RAEDLE ,  Christopher Robert Harper KLAIBER ,  Yinglao LIU ,  Shiyong FANG ,  Pranav DESHPANDE ,  Hung Shek NGAN ,  Anoop Kumar SINHA

IPC: G06F8/51 ,  G06F8/36

CPC classification number: G06F8/51 ,  G06F8/36

Abstract: Aspects of the present disclosure are directed to translating application calls for on-device machine learning execution. A translation layer supports on-device machine learning execution by translating JavaScript software application call data to achieve interoperability with on-device machine learning models. For example, JavaScript software applications interact with data, such as images, audio, video, and/or text, in a format or data type that is compatible with the application. On the other hand, machine learning models interact with data in a form conducive to mathematical operations, such as a data structure representation (e.g., tensor representation). Implementations translate data types and/or data files to provide compatible data to each of a native JavaScript software application and on-device machine learning models. The translation layer can translate JavaScript application calls to provide compatible data to the machine learning model(s), and output from the machine learning model(s) to provide compatible data to the JavaScript application.