公开(公告)号：US20160092563A1

公开(公告)日：2016-03-31

申请号：US14497591

申请日：2014-09-26

Applicant: Yahoo!, Inc.

Inventor： Jie Luo ,  Yi Chang ,  Scott Gaffney

IPC: G06F17/30 ,  G06K9/00 ,  G06F3/048

CPC classification number: G06F17/30864 ,  G06F3/0483 ,  G06F3/0488 ,  G06F17/30554

Abstract: A system and/or technique for graphical interface presentation comprises receiving a search string and presenting a search result series to a user on a client device. Search results of the search result series are presented in the form of cards, where a first card comprises information associated with a first search result of the search result series and a second card comprises information associated with a second search result of the search result series. A user may navigate through the cards to view various search results.

Abstract translation: 用于图形界面呈现的系统和/或技术包括接收搜索字符串并在客户端设备上向用户呈现搜索结果序列。 搜索结果系列的搜索结果以卡的形式呈现，其中第一卡包括与搜索结果系列的第一搜索结果相关联的信息，第二卡包括与搜索结果系列的第二搜索结果相关联的信息。 用户可以浏览卡片以查看各种搜索结果。

公开(公告)号：US20160041983A1

公开(公告)日：2016-02-11

申请号：US14453915

申请日：2014-08-07

Applicant: YAHOO! INC.

Inventor： Hongbo Deng ,  Anlei Dong ,  Shenhong Zhu ,  Jiuhe Gan ,  Yi Chang

IPC: G06F17/30

CPC classification number: G06F16/9537

Abstract: One or more suggested search query completion alternatives are provided to the user and are selectable by the user in completing the user's search query. The suggested search query completion alternatives may comprise local business query completion suggestions, each of which may correspond to a local business, and general query completion suggestions, each of which may correspond to a general query. A ranking of local business query completion suggestions and general query completion suggestions may be used to identify a number of top-ranked query completion suggestions for presentation to the user. The ranking may use a popularity measure associated with each business and a frequency measure associated with each general query. A popularity associated with a local business may be weighted using a granularity weighting, which may be determined using a local query intent confidence level.

Abstract translation: 一个或多个建议的搜索查询完成替代方案被提供给用户，并且可由用户在完成用户的搜索查询时选择。 建议的搜索查询完成替代方案可以包括本地业务查询完成建议，每个建议可以对应于本地业务，以及一般查询完成建议，每个查询完成建议可以对应于一般查询。 可以使用本地业务查询完成建议和一般查询完成建议的排名来识别用于呈现给用户的一些排名最高的查询完成建议。 排名可以使用与每个业务相关联的受欢迎度量和与每个一般查询相关联的频率测量。 可以使用粒度加权来加权与本地业务相关的流行度，其可以使用本地查询意图置信水平来确定。

公开(公告)号：US20180005131A1

公开(公告)日：2018-01-04

申请号：US15200922

申请日：2016-07-01

Applicant: Yahoo! Inc.

Inventor： Dawei Yin ,  Jiliang Tang ,  Yi Chang

IPC: G06N7/00 ,  G06F17/30 ,  G06Q50/00

CPC classification number: G06N7/005 ,  G06F16/9535 ,  G06N20/00 ,  G06Q50/01

Abstract: Disclosed are systems and methods for improving interactions with and between computers in social media content generation and delivery 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 disclosed systems and methods provide systems and methods for automatically method for automatically summarizing social media content using a timeline comprising a set (or chain) of episodes and a summary of each episode. The disclosed systems and methods identify a number of episodes based on analysis of each social media content item of a corpus, identify a number of social content items to summarize each episode, and generate a timeline summarization of the corpus of social media content items.

公开(公告)号：US20170091189A1

公开(公告)日：2017-03-30

申请号：US14868135

申请日：2015-09-28

Applicant: Yahoo! Inc.

Inventor： Changsung Kang ,  Yuening Hu ,  Dawei Yin ,  Yi Chang

IPC: G06F17/30

CPC classification number: G06F16/24578 ,  G06F16/23 ,  G06F16/24575 ,  G06F16/29 ,  G06F16/9535

Abstract: A location prediction framework is described for applying location labels or tags to target documents and/or identifying location-sensitive queries. Terms in content and queries are represented by corresponding term locations vectors (TLVs) in which the term is represented as a weighted distribution across locations. Each element of a TLV represents a probability that the term corresponding to the TLV relates to a particular location. Predicted locations may be introduced as features to a ranking framework to improve the identification and ranking of search results for a given query.

公开(公告)号：US20160189202A1

公开(公告)日：2016-06-30

申请号：US14587328

申请日：2014-12-31

Applicant: Yahoo! Inc.

Inventor： Pengyuan WANG ,  Dawei Yin ,  Yi Chang ,  Jian Yang ,  Wei Sun

IPC: G06Q30/02 ,  G06F17/30 ,  G06Q10/06

CPC classification number: G06Q30/0243 ,  G06Q10/067

Abstract: Systems and methods for are provided for measuring treatment effect of advertisement campaigns. The system includes a processor and a non-transitory storage medium accessible to the processor. The system includes a memory storing a database including historical advertisement data. A computer server is in communication with the memory and the database, the computer server programmed to obtain a tree-based model using the historical advertisement data, where the tree-based model include a plurality of leaf nodes. Within at least one leaf node of the tree-based model, the computer server obtains a number of subjects and estimates a treatment effect for a treatment. The computer server calculates a final treatment effect for the tree-based model using the number of subjects and the treatment effect. The computer server then determines a parameter for future advertising strategy using the final treatment effect.

Abstract translation: 提供用于衡量广告活动的治疗效果的系统和方法。 该系统包括可处理器可访问的处理器和非暂时性存储介质。 该系统包括存储包含历史广告数据的数据库的存储器。 计算机服务器与存储器和数据库通信，计算机服务器被编程为使用历史广告数据获得基于树的模型，其中基于树的模型包括多个叶节点。 在基于树的模型的至少一个叶节点中，计算机服务器获得多个受试者并估计治疗的治疗效果。 计算机服务器使用受试者数量和治疗效果计算基于树型模型的最终治疗效果。 然后，计算机服务器使用最终处理效果确定用于将来广告策略的参数。

公开(公告)号：US20160140451A1

公开(公告)日：2016-05-19

申请号：US14543133

申请日：2014-11-17

Applicant: YAHOO! INC.

Inventor： Jia Li ,  Yi Chang ,  Xiangnan Kong

IPC: G06N99/00 ,  G06N5/02

CPC classification number: G06N99/005

Abstract: At least one label prediction model is trained, or learned, using training data that may comprise training instances that may be missing one or more labels. The at least one label prediction model may be used in identifying a content item's ground-truth label set comprising an indicator for each label in the label set indicating whether or not the label is applicable to the content item.

Abstract translation: 使用可能包含可能缺少一个或多个标签的训练实例的训练数据来训练或学习至少一个标签预测模型。 所述至少一个标签预测模型可以用于识别内容项目的地面真相标签集合，其中包括标签组中的每个标签的指示符，指示标签是否适用于内容项目。

公开(公告)号：US20160140125A1

公开(公告)日：2016-05-19

申请号：US14546635

申请日：2014-11-18

Applicant: Yahoo! Inc.

Inventor： Amit Goyal ,  Lizi Zhang ,  Weize Kong ,  Hongbo Deng ,  Anlei Dong ,  Yi Chang

IPC: G06F17/30 ,  G06N99/00

Abstract: Methods, systems and programming for providing query suggestions based on user feedback. In one example, a prefix of a query is first received. An input including a prefix of a query is received from a user in a search session. A plurality of query suggestions are fetched based on the prefix of the query. Rankings of the plurality of query suggestions are determined based, at least in part, on the user's previous interactions in the search session with respect to at least one of the plurality of query suggestions. The at least one of the plurality of query suggestions has been previously provided to the user in the search session. The plurality of query suggestions are provided in the search session based on their rankings as a response to the input.

Abstract translation: 基于用户反馈提供查询建议的方法，系统和程序。 在一个示例中，首先接收查询的前缀。 在搜索会话中从用户接收包括查询的前缀的输入。 基于查询的前缀获取多个查询建议。 至少部分地基于所述搜索会话中关于所述多个查询建议中的至少一个的所述用户先前的交互来确定所述多个查询建议的排名。 多个查询建议中的至少一个先前已经在搜索会话中提供给用户。 基于它们的排名作为对输入的响应，在搜索会话中提供多个查询建议。

公开(公告)号：US20160110656A1

公开(公告)日：2016-04-21

申请号：US14516471

申请日：2014-10-16

Applicant: Yahoo! Inc.

Inventor： Makoto Yamada ,  Hua Ouyang ,  Yi Chang ,  Avishek Saha

IPC: G06N99/00

CPC classification number: G06N99/005 ,  G06N5/003

Abstract: A novel method and/or system of feature selection is described.

Abstract translation: 描述了一种新颖的方法和/或特征选择系统。

公开(公告)号：US20150317317A1

公开(公告)日：2015-11-05

申请号：US14265900

申请日：2014-04-30

Applicant: Yahoo! Inc.

Inventor： Hongbo Deng ,  Anlei Dong ,  Shenhong Zhu ,  Jiuhe Gan ,  Sudarshan Lamkhede ,  Yi Chang

IPC: G06F17/30

CPC classification number: G06F17/3097 ,  G06F17/3053 ,  G06F17/3064 ,  G06F17/30864

Abstract: Methods, systems and programming for providing query suggestions including entities. In one example, a prefix of a query is first received. A plurality of query suggestions are then identified based on the prefix of the query. The plurality of query suggestions include at least one entity. Scores of each of the plurality of query suggestions are computed using a first model. The first model includes an adjustable parameter used for computing the score of the at least one entity. The plurality of question suggestions are ranked based, at least in part, on the scores.

Abstract translation: 提供包括实体在内的查询建议的方法，系统和程序。 在一个示例中，首先接收查询的前缀。 然后，基于查询的前缀来识别多个查询建议。 多个查询建议包括至少一个实体。 使用第一模型来计算多个查询建议中的每一个的分数。 第一模型包括用于计算至少一个实体的分数的可调参数。 多个问题建议至少部分地基于得分进行排名。

公开(公告)号：US09836554B2

公开(公告)日：2017-12-05

申请号：US14265900

申请日：2014-04-30

Applicant: Yahoo! Inc.

Inventor： Hongbo Deng ,  Anlei Dong ,  Shenhong Zhu ,  Jiuhe Gan ,  Sudarshan Lamkhede ,  Yi Chang

IPC: G06F7/02 ,  G06F17/30

CPC classification number: G06F17/3097 ,  G06F17/3053 ,  G06F17/3064 ,  G06F17/30864

Abstract: Methods, systems and programming for providing query suggestions including entities. In one example, a prefix of a query is first received. A plurality of query suggestions are then identified based on the prefix of the query. The plurality of query suggestions include at least one entity. Scores of each of the plurality of query suggestions are computed using a first model. The first model includes an adjustable parameter used for computing the score of the at least one entity. The plurality of question suggestions are ranked based, at least in part, on the scores.