公开(公告)号：US20190327331A1

公开(公告)日：2019-10-24

申请号：US15967342

申请日：2018-04-30

Applicant: Facebook, Inc.

Inventor： Vivek Natarajan ,  Baiyang Liu ,  Xiaohu Liu ,  Ahmed Aly

IPC: H04L29/08 ,  G06F17/30 ,  G06Q50/00 ,  G06F15/18

Abstract: In one embodiment, a method includes receiving a user input by the first user from a client system associated with a first user, parsing the user input to identify one or more n-grams associated with the user input, accessing a user profile associated with the first user, wherein the user profile is stored in a first data store, accessing ontology data based on the one or more identified n-grams from one or more information graphs, wherein the one or more information graphs are stored in one or more second data stores, respectively, determining contextual information associated with the user input, generating semantic information by aggregating the user profile, ontology data, and contextual information, generating a feature representation for the identified one or more n-grams based on the semantic information, and resolving one or more entities associated with the one or more n-grams based on the feature representation.

公开(公告)号：US11010179B2

公开(公告)日：2021-05-18

申请号：US15967342

申请日：2018-04-30

Applicant: Facebook, Inc.

Inventor： Vivek Natarajan ,  Baiyang Liu ,  Xiaohu Liu ,  Ahmed Aly

IPC: G06F16/00 ,  G06F9/451 ,  G10L15/18 ,  G10L15/183 ,  G10L15/22 ,  G06F16/338 ,  G06F16/332 ,  G06F16/33 ,  G06N20/00 ,  G06F16/9535 ,  G06Q50/00 ,  H04L29/08 ,  G06F16/176 ,  G10L15/06 ,  G10L15/16 ,  G06F3/01 ,  G06F16/9032 ,  G06F16/2457 ,  H04L12/58 ,  G06F3/16 ,  G06K9/00 ,  G06K9/62 ,  G06N3/08 ,  G10L15/26 ,  G06F16/9038 ,  G06F16/904 ,  G06F40/30 ,  G06F40/40 ,  G06F16/22 ,  G06F16/23 ,  G06F7/14 ,  H04L12/26 ,  H04L12/28 ,  H04L12/24 ,  H04W12/08 ,  G10L15/07 ,  G10L17/22 ,  G10L13/00 ,  G10L13/04

Abstract: In one embodiment, a method includes receiving a user input by the first user from a client system associated with a first user, parsing the user input to identify one or more n-grams associated with the user input, accessing a user profile associated with the first user, wherein the user profile is stored in a first data store, accessing ontology data based on the one or more identified n-grams from one or more information graphs, wherein the one or more information graphs are stored in one or more second data stores, respectively, determining contextual information associated with the user input, generating semantic information by aggregating the user profile, ontology data, and contextual information, generating a feature representation for the identified one or more n-grams based on the semantic information, and resolving one or more entities associated with the one or more n-grams based on the feature representation.