公开(公告)号：US10915509B2

公开(公告)日：2021-02-09

申请号：US15968161

申请日：2018-05-01

Applicant: Facebook, Inc.

Inventor： Hongzhao Huang ,  Peng-Jen Chen ,  Justin Moore ,  Yaniv Shmueli

IPC: G06F16/215 ,  H04L12/58 ,  G06F16/29 ,  G06F16/28 ,  G06F16/951 ,  G06F16/901 ,  H04L29/08 ,  H04W4/80 ,  H04W4/02 ,  G06Q50/00 ,  H04W4/029

Abstract: In one embodiment, a method includes identifying one or more place-entity nodes in a heterogeneous graph, wherein the heterogenous graph comprises place-entity nodes, user nodes, and n-gram nodes, and wherein each place-entity node corresponds to a place-entity associated with a particular geographic location, assigning, for each identified place-entity node, an initial quality-score for the place-entity node, and calculating, for each identified place-entity node, a final quality-score for the identified place-entity node, wherein each final quality-score is calculated by iteratively propagating the initial quality-scores corresponding to the identified place-entity nodes, respectively, through the place-entity nodes, n-gram nodes, and user nodes of the heterogeneous graph until the quality-scores associated with the place-entity nodes, n-gram nodes, and user nodes reach convergence.

公开(公告)号：US10019466B2

公开(公告)日：2018-07-10

申请号：US15192750

申请日：2016-06-24

Applicant: Facebook, Inc.

Inventor： Hongzhao Huang ,  Peng-Jen Chen ,  Justin Moore ,  Yaniv Shmueli

IPC: G06F15/173 ,  G06F17/30 ,  H04L12/58 ,  H04L29/08 ,  H04W4/00 ,  H04W4/02 ,  G06Q50/00

CPC classification number: G06F16/215 ,  G06F16/285 ,  G06F16/29 ,  G06F16/9024 ,  G06F16/951 ,  G06Q50/01 ,  H04L51/20 ,  H04L51/32 ,  H04L67/02 ,  H04L67/2814 ,  H04L67/306 ,  H04W4/02 ,  H04W4/029 ,  H04W4/80

Abstract: In one embodiment, an online social network accesses a social graph that includes a number of place-entity nodes each corresponding to a place-entity, and a number of user nodes each corresponding to a user. A heterogeneous graph is generated based on the place-entity nodes, user nodes, and n-gram nodes, each n-gram node corresponding to an n-gram in the name of at least one place-entity. Each n-gram node is connected to corresponding place-entity nodes containing the n-gram, and user nodes with a social networking interaction with the corresponding place-entity nodes. Each place-entity node is assigned an initial quality-score. The quality-scores are propagated through the redirection graph based on the connections between the place-entity nodes, the n-gram nodes, and the user nodes. A final quality-score is assigned to each place-entity node when the propagation of the quality-scores through the redirection graph reaches convergence.

公开(公告)号：US20170201851A1

公开(公告)日：2017-07-13

申请号：US15192750

申请日：2016-06-24

Applicant: Facebook, Inc.

Inventor： Hongzhao Huang ,  Peng-Jen Chen ,  Justin Moore ,  Yaniv Shmueli

IPC: H04W4/00 ,  H04W4/02 ,  H04L12/58 ,  H04L29/08

CPC classification number: G06F17/30303 ,  G06F17/30241 ,  G06F17/30598 ,  G06F17/30864 ,  G06F17/30958 ,  G06Q50/01 ,  H04L51/20 ,  H04L51/32 ,  H04L67/02 ,  H04L67/2814 ,  H04L67/306 ,  H04W4/02 ,  H04W4/80

Abstract: In one embodiment, an online social network accesses a social graph that includes a number of place-entity nodes each corresponding to a place-entity, and a number of user nodes each corresponding to a user. A heterogeneous graph is generated based on the place-entity nodes, user nodes, and n-gram nodes, each n-gram node corresponding to an n-gram in the name of at least one place-entity. Each n-gram node is connected to corresponding place-entity nodes containing the n-gram, and user nodes with a social networking interaction with the corresponding place-entity nodes. Each place-entity node is assigned an initial quality-score. The quality-scores are propagated through the redirection graph based on the connections between the place-entity nodes, the n-gram nodes, and the user nodes. A final quality-score is assigned to each place-entity node when the propagation of the quality-scores through the redirection graph reaches convergence.

公开(公告)号：US20190180171A1

公开(公告)日：2019-06-13

申请号：US15838287

申请日：2017-12-11

Applicant: Facebook, Inc.

Inventor： Myle Arif Ott ,  Aaron Bryan Adcock ,  Yaniv Shmueli ,  Peng-Jen Chen ,  Wenbo Yuan ,  Junfei Wang

IPC: G06N3/04 ,  G06N3/08 ,  G06F7/08

Abstract: In one embodiment, a method includes receiving, from a client system associated with a user of an online social network, data indicating that the user is located at a first geographic location at a first time; accessing a first embedding representing a first place-entity corresponding to the first geographic location; accessing multiple second embeddings representing multiple respective second place-entities each corresponding to a second geographic location; calculating, a similarity metric between the embedding representing the first place-entity and each of the embeddings representing the second place-entities; ranking each of the second place-entities based on their calculated similarity metrics; and sending, to the client system, information associated with one or more second geographic locations corresponding to one or more second place-entities having a ranking greater than a threshold ranking.

公开(公告)号：US20180246913A1

公开(公告)日：2018-08-30

申请号：US15968161

申请日：2018-05-01

Applicant: Facebook, Inc.

Inventor： Hongzhao Huang ,  Peng-Jen Chen ,  Justin Moore ,  Yaniv Shmueli

IPC: G06F17/30 ,  H04W4/02 ,  H04L29/08 ,  H04L12/58 ,  H04W4/80 ,  G06Q50/00

CPC classification number: G06F16/215 ,  G06F16/285 ,  G06F16/29 ,  G06F16/9024 ,  G06F16/951 ,  G06Q50/01 ,  H04L51/20 ,  H04L51/32 ,  H04L67/02 ,  H04L67/2814 ,  H04L67/306 ,  H04W4/02 ,  H04W4/029 ,  H04W4/80

Abstract: In one embodiment, a method includes identifying one or more place-entity nodes in a heterogeneous graph, wherein the heterogenous graph comprises place-entity nodes, user nodes, and n-gram nodes, and wherein each place-entity node corresponds to a place-entity associated with a particular geographic location, assigning, for each identified place-entity node, an initial quality-score for the place-entity node, and calculating, for each identified place-entity node, a final quality-score for the identified place-entity node, wherein each final quality-score is calculated by iteratively propagating the initial quality-scores corresponding to the identified place-entity nodes, respectively, through the place-entity nodes, n-gram nodes, and user nodes of the heterogeneous graph until the quality-scores associated with the place-entity nodes, n-gram nodes, and user nodes reach convergence.