公开(公告)号：US20150339590A1

公开(公告)日：2015-11-26

申请号：US14284180

申请日：2014-05-21

Applicant: Yahoo! Inc.

Inventor： Yoelle Maarek ,  Avihai Mejer ,  Idan Szpektor ,  Dan Pelleg

IPC: G06N99/00 ,  H04L29/08 ,  G06F17/30

CPC classification number: G06N99/005 ,  G06F17/30477 ,  G06F17/30634 ,  G06F17/30637 ,  G06F17/30643 ,  G06F17/30864 ,  H04L67/02

Abstract: Briefly, embodiments disclosed herein may relate to formulating synthetic questions, such as in response to a search query, for example. Candidate synthetic questions may be presented to a user who may initiate a search at least in part by selecting one or more candidate synthetic questions, for example, in an embodiment.

Abstract translation: 简而言之，本文公开的实施例可以涉及例如响应于搜索查询来制定综合问题。 候选合成问题可以呈现给可以至少部分地通过选择一个或多个候选综合问题来发起搜索的用户，例如在一个实施例中。

公开(公告)号：US20180219814A1

公开(公告)日：2018-08-02

申请号：US15421033

申请日：2017-01-31

Applicant: Yahoo! Inc.

Inventor： Yoelle Maarek ,  Ido Guy ,  Dan Pelleg ,  Idan Szpektor ,  Alexander Nus ,  Jeffrey Bonforte

IPC: H04L12/58 ,  G06F17/30 ,  G06T7/90 ,  G06K9/62 ,  G06K9/46

CPC classification number: H04L51/08 ,  G06F16/583 ,  G06K9/00677 ,  G06Q50/01 ,  H04L51/10

Abstract: Disclosed are systems and methods for improving interactions with and between computers in content searching, generating, hosting and/or providing systems supported by or configured with personal computing devices, servers and/or platforms. The systems interact to identify and retrieve data within or across platforms, which can be used to improve the quality of data used in processing interactions between or among processors in such systems. The disclosure provides a novel, computerized framework for automatically identifying and recommending socially-engaging photos to their creators for sharing. Execution of the disclosed systems and methods turns a tedious manual chore into an automated, software-driven process. The disclosed systems and methods utilizes a novel, computerized learn-to-rank (LTR) algorithm for identifying the most engaging, socially driven photos by: (a) grouping near-duplicate photos; (b) selecting a representative photo for sharing per group; and (c) ranking of the groups by their likelihood to contain a “shareable” photo.

公开(公告)号：US20170161395A1

公开(公告)日：2017-06-08

申请号：US15436507

申请日：2017-02-17

Applicant: Yahoo!, Inc.

Inventor： Shirin Oskooi ,  Dan Pelleg ,  Yoelle Maarek ,  Samiksha Harish Kothari

IPC: G06F17/30 ,  G06F3/0482 ,  G06F3/0484

CPC classification number: G06F17/30867 ,  G06F3/011 ,  G06F3/023 ,  G06F3/0482 ,  G06F3/04842 ,  G06F17/30056 ,  G06F2203/011 ,  H04L67/10 ,  H04N21/25891 ,  H04N21/458 ,  H04N21/4755 ,  H04W4/20

Abstract: Users may engage with content that may invoke various emotions. For example, a user may find an image as inspirational, a social network post as funny, etc. Accordingly, content may be labeled with user emotion labels, specified by users that engaged with the content, to create labeled content (e.g., the image may be labeled as inspirational). Emotional transition triggers may be defined for users (e.g., 30 minutes of a user writing a school report using a word processing application). Responsive to a triggering of an emotional transition trigger, labeled content may be provided to a user (e.g., the image may be provided to the user as an inspirational break from writing the school report). In this way, content may be labeled based upon emotions that the content invokes in users, and such labeled content may be provided to users in a contextually relevant manner (e.g., a study break).

公开(公告)号：US20200090062A1

公开(公告)日：2020-03-19

申请号：US16693825

申请日：2019-11-25

Applicant: Yahoo! Inc.

Inventor： Dan Pelleg ,  Oleg Rokhlenko ,  Idan Szpektor ,  Yuval David Pinter ,  David Carmel ,  Shirin Oskooi ,  Somesh Jain ,  Archit Shrivastava

IPC: G06N5/04

Abstract: Methods and devices for assessing the quality of user-generated content are described. In one embodiment, a method is disclosed for measuring the quality of a user-generated answer to a question by combining various factors, including question-answer surface word vector similarity, question-answer explicit semantic analysis vector similarity, answer-answer explicit sematic analysis vector similarity, query performance predictor, sentiment analysis, textual analysis of the answer, and reputation of the answerer. The method uses a learning procedure to determine the best algorithm for measuring the overall quality of the answer based on these factors.

公开(公告)号：US09613033B2

公开(公告)日：2017-04-04

申请号：US14472430

申请日：2014-08-29

Applicant: Yahoo!, Inc.

Inventor： Shirin Oskooi ,  Dan Pelleg ,  Yoelle Maarek ,  Samiksha Harish Kothari

IPC: G06F17/00 ,  G06F17/30 ,  H04L29/08 ,  G06F3/01 ,  H04N21/458 ,  H04N21/258 ,  H04N21/475 ,  G06F3/023 ,  H04W4/20

CPC classification number: G06F17/30867 ,  G06F3/011 ,  G06F3/023 ,  G06F3/0482 ,  G06F3/04842 ,  G06F17/30056 ,  G06F2203/011 ,  H04L67/10 ,  H04N21/25891 ,  H04N21/458 ,  H04N21/4755 ,  H04W4/20

Abstract: Users may engage with content that may invoke various emotions. For example, a user may find an image as inspirational, a social network post as funny, etc. Accordingly, content may be labeled with user emotion labels, specified by users that engaged with the content, to create labeled content (e.g., the image may be labeled as inspirational). Emotional transition triggers may be defined for users (e.g., 30 minutes of a user writing a school report using a word processing application). Responsive to a triggering of an emotional transition trigger, labeled content may be provided to a user (e.g., the image may be provided to the user as an inspirational break from writing the school report). In this way, content may be labeled based upon emotions that the content invokes in users, and such labeled content may be provided to users in a contextually relevant manner (e.g., a study break).

公开(公告)号：US20160063004A1

公开(公告)日：2016-03-03

申请号：US14472430

申请日：2014-08-29

Applicant: Yahoo!, Inc.

Inventor： Shirin Oskooi ,  Dan Pelleg ,  Yoelle Maarek ,  Samiksha Harish Kothari

IPC: G06F17/30 ,  G06F3/0484 ,  H04L29/08

CPC classification number: G06F17/30867 ,  G06F3/011 ,  G06F3/023 ,  G06F3/0482 ,  G06F3/04842 ,  G06F17/30056 ,  G06F2203/011 ,  H04L67/10 ,  H04N21/25891 ,  H04N21/458 ,  H04N21/4755 ,  H04W4/20

Abstract: Users may engage with content that may invoke various emotions. For example, a user may find an image as inspirational, a social network post as funny, etc. Accordingly, content may be labeled with user emotion labels, specified by users that engaged with the content, to create labeled content (e.g., the image may be labeled as inspirational). Emotional transition triggers may be defined for users (e.g., 30 minutes of a user writing a school report using a word processing application). Responsive to a triggering of an emotional transition trigger, labeled content may be provided to a user (e.g., the image may be provided to the user as an inspirational break from writing the school report). In this way, content may be labeled based upon emotions that the content invokes in users, and such labeled content may be provided to users in a contextually relevant manner (e.g., a study break).

Abstract translation: 用户可以参与可能引起各种情绪的内容。 例如，用户可以将图像发现为鼓舞人心的，社交网络帖子等等。因此，内容可以用用户内容的用户指定的用户情绪标签来标记，以创建标记的内容（例如，图像 可能被标注为鼓舞人心）。 可以为用户定义情绪转换触发器（例如，用户使用文字处理应用程序编写学校报告的30分钟）。 响应于触发情绪转换触发器，可以向用户提供标记的内容（例如，图像可以作为激励性的休息从写入学校报告提供给用户）。 以这种方式，可以基于内容在用户中调用的情绪来标记内容，并且可以以内容相关的方式（例如，研究休息）向用户提供这样的标记的内容。

公开(公告)号：US20180129732A1

公开(公告)日：2018-05-10

申请号：US15344869

申请日：2016-11-07

Applicant: Yahoo!, Inc.

Inventor： Dan Pelleg ,  Alexander Nus ,  Fiana Raiber ,  Ido Guy ,  Avihai Mejer

IPC: G06F17/30

CPC classification number: G06F16/3344 ,  G06F16/355 ,  G06F17/277 ,  G06N20/00

Abstract: One or more computing devices, systems, and/or methods for generating a set of tips for an entity are provided. For example, users may create user generated content describing an entity, such as a user review for a consumer good, a location, an event, etc. Because a user may be unable to read and digest all of the user reviews for the entity, the user may merely read a few user reviews, and thus miss out on useful information. Accordingly, tip templates, indicative of how tips are linguistically/grammatically constructed, are applied to the user reviews to automatically extract a set of tips for the entity (e.g., “make sure to bring a rain jacket”). The set of tips may be filtered to remove undesirable tips, ranked based upon usefulness, and/or diversified to remove redundant tips. In this way, a set of useful tips may be provided to the user.

公开(公告)号：US20170249311A1

公开(公告)日：2017-08-31

申请号：US15055220

申请日：2016-02-26

Applicant: Yahoo! Inc.

Inventor： Dan Pelleg ,  Oleg Rokhlenko ,  Idan Szpektor ,  Yuval David Pinter ,  David Carmel ,  Shirin Oskooi ,  Somesh Jain ,  Archit Shrivastava

IPC: G06F17/30 ,  G06N5/02

CPC classification number: G06N5/04

Abstract: Methods and devices for assessing the quality of user-generated content are described. In one embodiment, a method is disclosed for measuring the quality of a user-generated answer to a question by combining various factors, including question-answer surface word vector similarity, question-answer explicit semantic analysis vector similarity, answer-answer explicit sematic analysis vector similarity, query performance predictor, sentiment analysis, textual analysis of the answer, and reputation of the answerer. The method uses a learning procedure to determine the best algorithm for measuring the overall quality of the answer based on these factors.