-
公开(公告)号：US20160378757A1
公开(公告)日：2016-12-29
申请号：US14747917
申请日：2015-06-23
申请人： Facebook, Inc.
发明人： Amit Bahl
CPC分类号： G06N5/04 , G06N5/022 , G06N20/00 , G06Q10/101 , G06Q30/0282 , G06Q50/01
摘要： Some embodiments include a method of defining a concept taxonomy. The concept taxonomy can be a mechanism to identify user activities that is relevant to a content analysis study. For example, the method can include identify one or more explicit concept identifiers to include in a concept taxonomy on a user interface. The method can include generating a relevant concepts network by identifying one or more potential concept candidates in past user activities within a time window. The relevant concepts network can include the potential concept candidates and the explicit concept identifiers as nodes. A concept taxonomy system can then select at least a subset of the potential concept candidates to present on the user interface as concept recommendations to supplement the concept taxonomy by identifying commonalities between the nodes of the relevant concepts network.
摘要翻译： 一些实施例包括定义概念分类法的方法。 概念分类法可以是识别与内容分析研究相关的用户活动的机制。 例如，该方法可以包括识别一个或多个显式概念标识符以包括在用户界面上的概念分类中。 该方法可以包括通过在时间窗口内识别过去用户活动中的一个或多个潜在概念候选来生成相关概念网络。 相关概念网络可以将潜在的概念候选和显式概念标识符作为节点。 概念分类系统然后可以选择潜在概念候选的至少一个子集，以呈现在用户界面上作为概念建议，以通过识别相关概念网络的节点之间的共同点来补充概念分类。
-
公开(公告)号：US20160358086A1
公开(公告)日：2016-12-08
申请号：US14732534
申请日：2015-06-05
申请人： Facebook, Inc.
发明人： Jason Sundram , Neil A. Kodner , Mui Thu Tran , Guangdeng Liao , Justin Thomas Palumbo , Guven Burc Arpat , Amit Bahl
CPC分类号： H04L67/22 , G06F17/2785 , G06N20/00 , H04L67/303
摘要： Some embodiments include a method of performing a content analysis study around a central theme utilizing a concept study system. The concept study system can generate a classifier machine corresponding to the content analysis study based on a super topic taxonomy including one or more concept identifiers. The concept study system can process a content object, associated with a user activity in a social networking system, through the classifier machine to determine whether to assign the user activity to the content analysis study. The concept study system can aggregate at least an attribute derived from the user activity in a study-specific data container associated with the content analysis study and compute a statistical or analytical insight based on aggregated attributes in the study-specific data container.
摘要翻译： 一些实施例包括利用概念研究系统围绕中心主题执行内容分析研究的方法。 概念研究系统可以基于包含一个或多个概念标识符的超级主题分类法生成与内容分析研究相对应的分类机。 概念研究系统可以通过分类机处理与社交网络系统中的用户活动相关联的内容对象，以确定是否将用户活动分配给内容分析研究。 概念研究系统可以将至少从用户活动导出的属性聚合在与内容分析研究相关联的特定于研究的数据容器中，并基于研究特定数据容器中的聚合属性计算统计或分析洞察。
-
公开(公告)号：US20190205372A1
公开(公告)日：2019-07-04
申请号：US15860362
申请日：2018-01-02
申请人： Facebook, Inc.
发明人： Xian Li , Irina-Elena Veliche , Debnil Sur , Shaomei Wu , Amit Bahl , Juan Miguel Pino
CPC分类号： G06F17/273 , G06F3/0481 , G06F17/24 , G06F17/274 , G06N20/00
摘要： In one embodiment, a method includes identifying a plurality of dyslexic users on an online social network. The plurality of dyslexic users may be identified based on content objects posted by these users over a particular time period, where the content objects may include one or more of word-level errors or sentence-level errors. A machine-learning model may be trained for text correction using a corpus of social network data, which may include at least the content objects with one or more of word-level errors or sentence-level errors, and a corresponding set of corrected content objects. A text string including one or more errors may be received from a client system associated with a first user. The text string may be transformed into a vector representation using an encoder of the machine-learning model. A corrected text string may be generated from the vector representation using a decoder of the machine-learning model.
-
-
搜索结果
3 条记录 (耗时 0.011 秒)
