公开(公告)号：US20160314189A1

公开(公告)日：2016-10-27

申请号：US15199420

申请日：2016-06-30

Applicant: Yahoo! Inc.

Inventor： Mike Wexler ,  Brian Webb

IPC: G06F17/30

CPC classification number: G06F17/30598 ,  G06F17/30321 ,  G06F17/3033 ,  G06F17/30345

Abstract: A content item categorizer system retrieves content items from Internet sources. If a retrieved content item includes sufficient information for traditional categorization methods, then the system assigns one or more categories to the content item using such traditional methods. The system creates a metadata model, based on information about traditionally-categorized content items, that maps at least hashtags from the content items to one or more content categories. When the system retrieves a sparse-info item that does not include sufficient information for traditional categorization, the system applies the metadata model to categorize the content item using at least hashtags in the sparse-info item. The metadata model may also include information indicating mappings between categories and coincidence of hashtags and additional content item attributes. Also, the metadata model may provide information for categorizing sparse-info items based on multiple hashtags in the sparse-info item metadata.

公开(公告)号：US20150220615A1

公开(公告)日：2015-08-06

申请号：US14170952

申请日：2014-02-03

Applicant: Yahoo! Inc.

Inventor： Mike Wexler ,  Brian Webb

IPC: G06F17/30

CPC classification number: G06F17/30598 ,  G06F17/30321 ,  G06F17/3033 ,  G06F17/30345

Abstract: A content item categorizer system retrieves content items from Internet sources. If a retrieved content item includes sufficient information for traditional categorization methods, then the system assigns one or more categories to the content item using such traditional methods. The system creates a metadata model, based on information about traditionally-categorized content items, that maps at least hashtags from the content items to one or more content categories. When the system retrieves a sparse-info item that does not include sufficient information for traditional categorization, the system applies the metadata model to categorize the content item using at least hashtags in the sparse-info item. The metadata model may also include information indicating mappings between categories and coincidence of hashtags and additional content item attributes. Also, the metadata model may provide information for categorizing sparse-info items based on multiple hashtags in the sparse-info item metadata.

Abstract translation: 内容项分类系统从互联网来源检索内容项。 如果检索到的内容项目包含用于传统分类方法的足够信息，则系统使用这种传统方法向内容项目分配一个或多个类别。 该系统基于关于传统分类的内容项目的信息创建元数据模型，其将至少将内容项目的标签图映射到一个或多个内容类别。 当系统检索到不包含传统分类的足够信息的稀疏信息项时，系统应用元数据模型，使用稀疏信息项中的至少一个标签进行内容分类。 元数据模型还可以包括指示类别之间的映射的信息，以及主题标签和附加内容项目属性的一致性。 此外，元数据模型可以提供用于根据稀疏信息项元数据中的多个标签符号对稀疏信息项进行分类的信息。

公开(公告)号：US09384259B2

公开(公告)日：2016-07-05

申请号：US14170952

申请日：2014-02-03

Applicant: Yahoo! Inc.

Inventor： Mike Wexler ,  Brian Webb

IPC: G06F17/30

CPC classification number: G06F17/30598 ,  G06F17/30321 ,  G06F17/3033 ,  G06F17/30345

Abstract: A content item categorizer system retrieves content items from Internet sources. If a retrieved content item includes sufficient information for traditional categorization methods, then the system assigns one or more categories to the content item using such traditional methods. The system creates a metadata model, based on information about traditionally-categorized content items, that maps at least hashtags from the content items to one or more content categories. When the system retrieves a sparse-info item that does not include sufficient information for traditional categorization, the system applies the metadata model to categorize the content item using at least hashtags in the sparse-info item. The metadata model may also include information indicating mappings between categories and coincidence of hashtags and additional content item attributes. Also, the metadata model may provide information for categorizing sparse-info items based on multiple hashtags in the sparse-info item metadata.

Abstract translation: 内容项分类系统从互联网来源检索内容项。 如果检索到的内容项目包含用于传统分类方法的足够信息，则系统使用这种传统方法向内容项目分配一个或多个类别。 该系统基于关于传统分类的内容项目的信息创建元数据模型，其将至少将内容项目的标签图映射到一个或多个内容类别。 当系统检索到不包含传统分类的足够信息的稀疏信息项时，系统应用元数据模型，使用稀疏信息项中的至少一个标签进行内容分类。 元数据模型还可以包括指示类别之间的映射的信息，以及主题标签和附加内容项目属性的一致性。 此外，元数据模型可以提供用于根据稀疏信息项元数据中的多个标签符号对稀疏信息项进行分类的信息。

公开(公告)号：US20160189343A1

公开(公告)日：2016-06-30

申请号：US14588213

申请日：2014-12-31

Applicant: Yahoo! Inc.

Inventor： Daozheng Chen ,  Sally Lee ,  Brian Webb ,  Ralph Rabbat ,  Ali Khodaei ,  Paul Krakow ,  Dave Todd ,  Samantha Giordano ,  Max Chern

IPC: G06T3/40 ,  G06K9/46

CPC classification number: G06K9/46 ,  G06K9/3233 ,  G06K9/6289 ,  G06T3/0012

Abstract: Briefly, embodiments disclosed herein relate to image cropping, such as for digital images, for example.

Abstract translation: 简而言之，本文公开的实施例涉及图像裁剪，例如用于数字图像。

公开(公告)号：US20140280554A1

公开(公告)日：2014-09-18

申请号：US13838046

申请日：2013-03-15

Applicant: YAHOO! INC.

Inventor： Brian Webb ,  Jin C. Lim

IPC: H04L29/08

CPC classification number: H04L67/22 ,  H04L67/02 ,  H04L67/306

Abstract: A method for updating content. The method includes determining at least one indicator with respect to the content, wherein the at least one indicator is at least one of a user engagement indicator, a content popularity indicator, a content quality indicator, and a content update frequency indicator. The method further includes updating the content based on the at least one indicator, wherein the at least one indicator is dynamically updated.

Abstract translation: 一种更新内容的方法。 所述方法包括确定关于所述内容的至少一个指示符，其中所述至少一个指示符是用户参与指示符，内容流行度指示符，内容质量指示符和内容更新频率指示符中的至少一个。 所述方法还包括基于所述至少一个指示符来更新所述内容，其中所述至少一个指示符被动态地更新。

公开(公告)号：US20190197069A1

公开(公告)日：2019-06-27

申请号：US14343931

申请日：2013-03-15

Applicant: Yahoo! Inc.

Inventor： Xin Fan ,  Todd Beaupre ,  Brian Webb

IPC: G06F16/9535 ,  G06Q50/00 ,  G06F16/435

CPC classification number: G06F16/9535 ,  G06F16/437 ,  G06Q50/01

Abstract: A method for content selection. The method comprises identifying a reference to content associated with a social media network user having a ranking above a pre-determined level, identifying one or more occurrences of the reference attributed to at least one additional social media network user, where the one or more occurrences are indicative of popularity of the content, and selecting the reference corresponding to the content based on the popularity.