公开(公告)号：US11314941B2

公开(公告)日：2022-04-26

申请号：US16703700

申请日：2019-12-04

申请人： Facebook Technologies, LLC

发明人： Ahmed Aly ,  Arun Babu ,  Armen Aghajanyan

IPC分类号： G06F40/30 ,  G06F9/54 ,  G06F40/205 ,  G06F40/242 ,  G06N3/04 ,  G06N3/08 ,  H04L12/58 ,  G06F16/9536 ,  G10L15/18 ,  G10L15/22 ,  G10L15/30 ,  G10L15/32 ,  G06F40/253 ,  G06K9/00 ,  H04L29/08 ,  G06N20/00 ,  G06F3/01 ,  G06K9/32 ,  G06Q50/00 ,  G06F16/9032 ,  H04L51/52 ,  H04L51/00 ,  H04L67/75 ,  G06F9/48 ,  G10L15/08 ,  H04N7/14 ,  H04L67/306 ,  G06F3/16

摘要： In one embodiment, a method includes receiving a user input comprising one or more words at a client system, wherein each word comprises one or more characters, inputting the words to a convolutional neural network (CNN) model stored on the client system, accessing a plurality of character-embeddings for a plurality of characters, respectively, from a data store of the client system, generating one or more word-embeddings for the one or more words, respectively, based on the accessed character-embeddings by processing the accessed character-embeddings with one or more convolutional layers and one or more gated linear units of the CNN model, determining one or more tasks corresponding to the user input for execution based on an analysis of the one or more word-embeddings by the CNN model, and providing an output responsive to the user input based on the execution of the one or more tasks at the client system.

公开(公告)号：US20210117623A1

公开(公告)日：2021-04-22

申请号：US16703700

申请日：2019-12-04

申请人： Facebook Technologies, LLC

发明人： Ahmed Aly ,  Arun Babu ,  Armen Aghajanyan

IPC分类号： G06F40/30 ,  G06F40/242 ,  G06F40/205 ,  H04L12/58 ,  G06N3/04 ,  G06N3/08

摘要： In one embodiment, a method includes receiving a user input comprising one or more words at a client system, wherein each word comprises one or more characters, inputting the words to a convolutional neural network (CNN) model stored on the client system, accessing a plurality of character-embeddings for a plurality of characters, respectively, from a data store of the client system, generating one or more word-embeddings for the one or more words, respectively, based on the accessed character-embeddings by processing the accessed character-embeddings with one or more convolutional layers and one or more gated linear units of the CNN model, determining one or more tasks corresponding to the user input for execution based on an analysis of the one or more word-embeddings by the CNN model, and providing an output responsive to the user input based on the execution of the one or more tasks at the client system.