-
公开(公告)号：US20220188361A1
公开(公告)日：2022-06-16
申请号：US17120013
申请日：2020-12-11
Applicant: Meta Platforms, Inc.
Inventor： Fadi Botros , Nanshu Wang , Fan Wang , Meryem Pinar Donmez Ediz , Omer Muzaffar , Kshitiz Malik , Vikas Seshagiri Rao Bhardwaj , Anuj Kumar , Shreyan Bakshi
IPC: G06F16/9032 , G10L15/16 , G10L15/06 , H04L12/58 , G02B27/01
Abstract: In one embodiment, a method includes receiving a first input by a user from a client system associated with the user, wherein the first input is in a voice modality, analyzing the first input to generate one or more candidate hypotheses, determining one or more modalities for presenting output generated by the one or more computing systems to the user at the client system, and sending instructions to the client system for presenting one or more suggested auto-completions corresponding to one or more of the candidate hypotheses, respectively, wherein each suggested auto-completion comprises the corresponding candidate hypothesis, and wherein the one or more suggested auto-completions are presented in the one or more determined modalities.
-
公开(公告)号：US11501081B1
公开(公告)日：2022-11-15
申请号：US16731304
申请日：2019-12-31
Applicant: META PLATFORMS, INC.
Inventor： Prince Gill , Honglei Liu , Wenhai Yang , Kshitiz Malik , Nanshu Wang , David Reiss
Abstract: Exemplary embodiments relate to methods, mediums, and systems for moving language models from a server to the client device. Such embodiments may be deployed in an environment where the server is not able to provide modeling services to the clients, such as an end-to-end encrypted (E2EE) environment. Several different techniques are described to address issues of size and complexity reduction, model architecture optimization, model training, battery power reduction, and latency reduction.
-
公开(公告)号：US11455555B1
公开(公告)日：2022-09-27
申请号：US16731321
申请日：2019-12-31
Applicant: META PLATFORMS, INC.
Inventor： Prince Gill , Honglei Liu , Wenhai Yang , Kshitiz Malik , Nanshu Wang , David Reiss
Abstract: Exemplary embodiments relate to methods, mediums, and systems for moving language models from a server to the client device. Such embodiments may be deployed in an environment where the server is not able to provide modeling services to the clients, such as an end-to-end encrypted (E2EE) environment. Several different techniques are described to address issues of size and complexity reduction, model architecture optimization, model training, battery power reduction, and latency reduction.
-
-
Search Results
3
records
(took 0.013 seconds)
