公开(公告)号：US20180276561A1

公开(公告)日：2018-09-27

申请号：US15469399

申请日：2017-03-24

Applicant: Facebook, Inc.

Inventor： Jeffrey William Pasternack ,  David Vickrey ,  Justin MacLean Coughlin ,  Prasoon Mishra ,  Austen Norment McDonald ,  Max Christian Eulenstein ,  Jianfu Chen ,  Kritarth Anand ,  Polina Kuznetsova

IPC: G06N99/00 ,  G06N7/00 ,  G06F17/30

CPC classification number: G06N20/00 ,  G06F16/353 ,  G06N5/041 ,  G06N20/20

Abstract: An online system predicts topics for content items. The online system provides one or more topic labels for a user to apply concurrently while a user is composing a post, in response to requests periodically received from the user's device. A request includes information such as content composed by the user and contextual information. The online system employs machine learning techniques to analyze content composed by a user and contextual information thereby to predict topic labels. Different machine learning models for classifying individual topic labels, identifying relevant topic labels, and/or detecting changes in existing topic predictions are developed. Some machine learning models predict topics for full content and some predict topics for partial content. The online system trains the machine learning models to ensure accurate topic predictions are provided timely. The online system employs various machine learning model training methods such as active training and gradient training.

公开(公告)号：US10063513B2

公开(公告)日：2018-08-28

申请号：US14535308

申请日：2014-11-06

Applicant: Facebook, Inc.

Inventor： Erich James Owens ,  David Vickrey

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

CPC classification number: H04L51/32 ,  G06F16/9535 ,  G06Q50/01 ,  H04L67/22

Abstract: A social networking system generates stories based on actions of users in the system and provides a newsfeed to users that contain stories that related to one or more of their friends in the system. Although the story ranking algorithm includes a time decay to penalize older stories, stories may actually become stale at different rates. To measure the staleness of a story, the system computes a ratio of a current engagement rate for the story to an average engagement rate for the story. Based on this ratio, the system may filter out stale stories, includes the ratio as a feature in the scoring model, and/or adjust the decay rate.

公开(公告)号：US09569727B2

公开(公告)日：2017-02-14

申请号：US14587624

申请日：2014-12-31

Applicant: Facebook, Inc.

Inventor： David Vickrey ,  Jeffrey William Pasternack

IPC: G06N5/04 ,  H04L12/58 ,  G06N99/00

CPC classification number: G06N5/048 ,  G06F17/277 ,  G06F17/2785 ,  G06N99/005 ,  H04L51/32

Abstract: A social networking system receives messages from users that include hashtags. The social networking system may use a natural language model to identify terms in the hashtag corresponding to words or phrases of the hashtag. The words or phrases may be used to modify a string of the hashtag. The social networking system may also generate computer models to determine likely membership of a message with various hashtags. Prior to generating the computer models, the social networking system may filter certain hashtags from eligibility for computer modeling, particularly hashtags that are not frequently used or that more typically appear as normal text in a message instead of as a hashtag. The social networking system may also calibrate the computer model outputs by comparing a test message output with outputs of a calibration group that includes positive and negative examples with respect to the computer model output.

Abstract translation: 社交网络系统从包含主题标签的用户接收消息。 社交网络系统可以使用自然语言模型来识别与主题标签的单词或短语相对应的主题标签中的术语。 这些单词或短语可用于修改主题标签的字符串。 社交网络系统还可以生成计算机模型以确定具有各种主题标签的消息的可能成员资格。 在生成计算机模型之前，社交网络系统可以将特定的标签从过滤计算机建模的资格过滤出来，特别是不经常使用的标签，或者通常在消息中更常见地显示为正常文本，而不是主题标签。 社交网络系统还可以通过将测试消息输出与包括关于计算机模型输出的正和负的示例的校准组的输出进行比较来校准计算机模型输出。

公开(公告)号：US20160189045A1

公开(公告)日：2016-06-30

申请号：US14587624

申请日：2014-12-31

Applicant: Facebook, Inc.

Inventor： David Vickrey ,  Jeffrey William Pasternack

IPC: G06N5/04 ,  G06N99/00 ,  H04L12/58

CPC classification number: G06N5/048 ,  G06F17/277 ,  G06F17/2785 ,  G06N99/005 ,  H04L51/32

Abstract: A social networking system receives messages from users that include hashtags. The social networking system may use a natural language model to identify terms in the hashtag corresponding to words or phrases of the hashtag. The words or phrases may be used to modify a string of the hashtag. The social networking system may also generate computer models to determine likely membership of a message with various hashtags. Prior to generating the computer models, the social networking system may filter certain hashtags from eligibility for computer modeling, particularly hashtags that are not frequently used or that more typically appear as normal text in a message instead of as a hashtag. The social networking system may also calibrate the computer model outputs by comparing a test message output with outputs of a calibration group that includes positive and negative examples with respect to the computer model output.

Abstract translation: 社交网络系统从包含主题标签的用户接收消息。 社交网络系统可以使用自然语言模型来识别与主题标签的单词或短语相对应的主题标签中的术语。 这些单词或短语可用于修改主题标签的字符串。 社交网络系统还可以生成计算机模型以确定具有各种主题标签的消息的可能成员资格。 在生成计算机模型之前，社交网络系统可以将特定的标签从过滤计算机建模的资格过滤出来，特别是不经常使用的标签，或者通常在消息中更常见地显示为正常文本，而不是主题标签。 社交网络系统还可以通过将测试消息输出与包括关于计算机模型输出的正和负的示例的校准组的输出进行比较来校准计算机模型输出。

公开(公告)号：US20160162487A1

公开(公告)日：2016-06-09

申请号：US14564832

申请日：2014-12-09

Applicant: Facebook, Inc.

Inventor： Christopher Shahin Moghbel ,  Varun Kacholia ,  Yuanxuan Wang ,  Deepa Diwakar ,  David Vickrey ,  Cameron Alexander Marlow

IPC: G06F17/30 ,  H04L29/06 ,  H04L29/08

CPC classification number: G06F16/24578 ,  G06F16/24575 ,  G06F16/9535 ,  H04L67/02 ,  H04L67/10 ,  H04L67/22 ,  H04L67/306

Abstract: Systems, methods, and non-transitory computer-readable media can identify a source content item for which related content is to be provided. A set of candidate content items associated with the source content item can be selected. The set of candidate content items can be ranked based, at least in part, on a set of engagement signals associated with the set of candidate content items. A subset of highest ranked candidate content items out of the set of candidate content items can be provided as the related content for the source content item.

Abstract translation: 系统，方法和非暂时计算机可读介质可以标识要提供相关内容的源内容项。 可以选择与源内容项相关联的一组候选内容项。 可以至少部分地基于与该组候选内容项相关联的一组参与信号对候选内容项集合进行排名。 可以提供候选内容项集合中的最高排名的候选内容项目的子集作为源内容项目的相关内容。

公开(公告)号：US10740690B2

公开(公告)日：2020-08-11

申请号：US15469399

申请日：2017-03-24

Applicant: Facebook, Inc.

Inventor： Jeffrey William Pasternack ,  David Vickrey ,  Justin MacLean Coughlin ,  Prasoon Mishra ,  Austen Norment McDonald ,  Max Christian Eulenstein ,  Jianfu Chen ,  Kritarth Anand ,  Polina Kuznetsova

IPC: G06N20/00 ,  G06F16/35 ,  G06N5/04 ,  G06N20/20

Abstract: An online system predicts topics for content items. The online system provides one or more topic labels for a user to apply concurrently while a user is composing a post, in response to requests periodically received from the user's device. A request includes information such as content composed by the user and contextual information. The online system employs machine learning techniques to analyze content composed by a user and contextual information thereby to predict topic labels. Different machine learning models for classifying individual topic labels, identifying relevant topic labels, and/or detecting changes in existing topic predictions are developed. Some machine learning models predict topics for full content and some predict topics for partial content. The online system trains the machine learning models to ensure accurate topic predictions are provided timely. The online system employs various machine learning model training methods such as active training and gradient training.

公开(公告)号：US10311525B1

公开(公告)日：2019-06-04

申请号：US15912479

申请日：2018-03-05

Applicant: Facebook, Inc.

Inventor： Erich James Owens ,  David Vickrey

IPC: G06F17/30 ,  G06Q50/00 ,  G06Q30/02

Abstract: A social networking system classifies content items according to their qualities for ranking and selection of content items to present to users within, for example, a newsfeed. Low-quality content items that are unlikely to be interesting or relevant to a user may be distinguished though they may appear to be popular among users in the social networking system. The social networking system identifies within the content items one or more features that are indicators of the quality of the content items. The social networking system can use one or more classifiers to evaluate the content items based on the features, and it can compute a quality metric indicating the quality of a content item based on the result obtained from the classifiers. The quality metric can be used in the ranking and selection of a set of content items to provide to the user.

公开(公告)号：US20170295249A1

公开(公告)日：2017-10-12

申请号：US15095007

申请日：2016-04-08

Applicant: Facebook, Inc.

Inventor： David Vickrey ,  Khalid Bakry El-Arini

IPC: H04L29/08 ,  G06F17/30 ,  H04L29/06

CPC classification number: H04L67/22 ,  G06F17/3053 ,  G06F17/3089 ,  H04L65/403

Abstract: An online system receives a posted content item from a posting user. The online system labels the posted content item with an audience, the audience being a subset of a group of users having an affinity to a topic of the online system, the subset of the group of users sharing a particular treatment regarding the topic. After identifying an opportunity to present content to a viewing user, the online system selects candidate content items, and scores each candidate content item by determining whether the candidate content item is associated with an audience that includes the viewing user, and if so, modifying the score of the candidate content item to be higher. The online system ranks the candidate content items based on the associated score, selects a subset of the candidate content items based on the associated ranking, and presents the selected subset to the viewing user.

公开(公告)号：US20160188739A1

公开(公告)日：2016-06-30

申请号：US14584087

申请日：2014-12-29

Applicant: Facebook, Inc.

Inventor： Joyce Tang ,  Khalid Bakry El-Arini ,  David Vickrey

IPC: G06F17/30

CPC classification number: G06F17/3089 ,  G06F17/30864

Abstract: Systems, methods, and non-transitory computer readable media configured to determine a value of a utility factor associated with a content item corresponding to a link. An optimized utility value relating to an interaction type of an outbound click is determined based on the value of the utility factor. An expected utility score associated with the content item is generated based on the optimized utility value to determine potential presentation of the content item to a user.

Abstract translation: 配置为确定与链接对应的内容项相关联的效用因子的值的系统，方法和非暂时计算机可读介质。 基于效用因子的值确定与出站点击的交互类型相关的优化效用值。 基于优化的效用值生成与内容项目相关联的期望效用评分，以确定内容项目向用户的潜在呈现。

公开(公告)号：US20160134577A1

公开(公告)日：2016-05-12

申请号：US14535308

申请日：2014-11-06

Applicant: Facebook, Inc.

Inventor： Erich James Owens ,  David Vickrey

IPC: H04L12/58 ,  G06Q50/00

CPC classification number: H04L51/32 ,  G06F17/30867 ,  G06Q50/01 ,  H04L67/22

Abstract: A social networking system generates stories based on actions of users in the system and provides a newsfeed to users that contain stories that related to one or more of their friends in the system. Although the story ranking algorithm includes a time decay to penalize older stories, stories may actually become stale at different rates. To measure the staleness of a story, the system computes a ratio of a current engagement rate for the story to an average engagement rate for the story. Based on this ratio, the system may filter out stale stories, includes the ratio as a feature in the scoring model, and/or adjust the decay rate.

Abstract translation: 社交网络系统基于系统中的用户的动作生成故事，并向包含与系统中的一个或多个朋友相关的故事的用户提供新闻馈送。 虽然故事排序算法包含时间衰减来惩罚旧故事，但故事实际上可能会以不同的速度变得陈旧。 为了衡量故事的平淡度，系统计算出故事的当前参与率与故事的平均参与率的比率。 基于这个比例，系统可以过滤掉陈旧的故事，将比例作为评分模型中的特征，和/或调整衰减率。