-
1.发明申请公开(公告)号：US20170053013A1
公开(公告)日：2017-02-23
申请号：US14829522
申请日：2015-08-18
Applicant: Facebook, Inc.
Inventor： Ehud Weinsberg , Bogdan State , Amaç Herdagdelen , Thomas Frederick Dimson , Bai Xiao , Danilo Torres de Sa Resende
IPC: G06F17/30
CPC classification number: G06F17/30598
Abstract: Systems, methods, and non-transitory computer-readable media can acquire a set of labels associated with a set of content items. Each label in the set of labels can be associated with at least one content item in the set of content items. It can be determined that at least two labels, out of the set of labels, are related. The at least two labels can be determined to be related based on at least one of a co-occurrence metric associated with the at least two labels or a topic similarity metric associated with the at least two labels. One label can be selected, out of the at least two labels, as being representative of the at least two labels.
Abstract translation: 系统，方法和非暂时计算机可读介质可以获取与一组内容项目相关联的一组标签。 该组标签中的每个标签可以与该组内容项中的至少一个内容项相关联。 可以确定在标签组中的至少两个标签是相关的。 可以基于与至少两个标签相关联的同现度量或与至少两个标签相关联的主题相似度度量中的至少一个来确定至少两个标签是相关的。 可以从至少两个标签中选出一个标签作为至少两个标签的代表。
-
公开(公告)号：US20190303391A1
公开(公告)日：2019-10-03
申请号：US16379436
申请日：2019-04-09
Applicant: Facebook, Inc.
Inventor： Ehud Weinsberg , Li Yang , Bogdan State , Amaç Herdagdelen , Thomas Frederick Dimson , Bai Xiao , Danilo Torres de Sa Resende
IPC: G06F16/28
Abstract: Systems, methods, and non-transitory computer-readable media can acquire a set of labels associated with a set of content items. Each label in the set of labels can be associated with at least one content item in the set of content items. It can be determined that at least two labels, out of the set of labels, are related. The at least two labels can be determined to be related based on at least one of a co-occurrence metric associated with the at least two labels or a topic similarity metric associated with the at least two labels. One label can be selected, out of the at least two labels, as being representative of the at least two labels.
-
Patent Agency Ranking
公开(公告)号：US10296634B2
公开(公告)日：2019-05-21
申请号：US14829522
申请日：2015-08-18
Applicant: Facebook, Inc.
Inventor： Ehud Weinsberg , Bogdan State , Amaç Herda{hacek over (g)}delen , Thomas Frederick Dimson , Bai Xiao , Danilo Torres de Sa Resende
IPC: G06F17/30
Abstract: Systems, methods, and non-transitory computer-readable media can acquire a set of labels associated with a set of content items. Each label in the set of labels can be associated with at least one content item in the set of content items. It can be determined that at least two labels, out of the set of labels, are related. The at least two labels can be determined to be related based on at least one of a co-occurrence metric associated with the at least two labels or a topic similarity metric associated with the at least two labels. One label can be selected, out of the at least two labels, as being representative of the at least two labels.
-
公开(公告)号：US10698945B2
公开(公告)日：2020-06-30
申请号：US14829537
申请日：2015-08-18
Applicant: Facebook, Inc.
Inventor： Bogdan State , Amaç Herda{umlaut over (g)}delen , Maxime Boucher , Ehud Weinsberg
IPC: G06F16/48 , G06N20/00 , G06F16/38 , G06F16/438
Abstract: Systems, methods, and non-transitory computer readable media configured to acquire data associated with a content item, the data associated with the content item including contextual information. The data associated with the content item can be provided to a model trained by machine learning. A set of hashtags associated with the content item can be determined based on the model.
-
5.发明申请公开(公告)号：US20180121830A1
公开(公告)日：2018-05-03
申请号：US15342069
申请日：2016-11-02
Applicant: Facebook, Inc.
Inventor： Matthew Logan Schmid , Ehud Weinsberg
Abstract: Systems, methods, and non-transitory computer-readable media according to certain aspects can obtain a comment submitted by a user on a page associated with an entity. A training data set, including a plurality of comments, that indicates whether each of the plurality of comments is actionable can be determined. A machine learning model can be trained based on the training data set. Whether the comment is actionable can be determined based at least in part on the machine learning model.
-
6.发明申请公开(公告)号：US20180012139A1
公开(公告)日：2018-01-11
申请号：US15203493
申请日：2016-07-06
Applicant: Facebook, Inc.
Inventor： Matthew Logan Schmid , Akhil Nambiar , Ehud Weinsberg , Tianyu Xie , Shuyang Lin
CPC classification number: G06N20/00 , G06Q10/00 , G06Q10/10 , G06Q30/02 , G06Q50/01 , H04L51/32 , H04L67/10
Abstract: Systems, methods, and non-transitory computer-readable media according to certain aspects can receive at least one message sent by a user of a social networking system to a page provided by the social networking system, where the page is associated with an entity. A training data set including a plurality of messages can be determined, and the training data set can indicate an intent classification for each of the plurality of messages. The intent classification can be indicative of an intent associated with a particular message. A machine learning model may be trained based at least in part on the training data set. A first intent classification for the at least one message can be determined, based at least in part on the machine learning model.
-
公开(公告)号：US20170052954A1
公开(公告)日：2017-02-23
申请号：US14829537
申请日：2015-08-18
Applicant: Facebook, Inc.
Inventor： Bogdan State , Amaç Herdagdelen , Maxime Boucher , Ehud Weinsberg
CPC classification number: G06F16/48 , G06F16/381 , G06F16/438 , G06N20/00
Abstract: Systems, methods, and non-transitory computer readable media configured to acquire data associated with a content item, the data associated with the content item including contextual information. The data associated with the content item can be provided to a model trained by machine learning. A set of hashtags associated with the content item can be determined based on the model.
Abstract translation: 被配置为获取与内容项相关联的数据的系统，方法和非暂时计算机可读介质，所述数据与所述内容项相关联，包括上下文信息。 可以将与内容项相关联的数据提供给由机器学习训练的模型。 可以基于模型来确定与内容项目相关联的一组主题标签。
-
-
-
-
-
-
Search Results
7
records
(took 0.011 seconds)
