公开(公告)号：US20140081743A1

公开(公告)日：2014-03-20

申请号：US14078203

申请日：2013-11-12

Applicant: Yahoo! Inc.

Inventor： Amita Gajewar ,  Jian Yang ,  Dongni Chen ,  Peiji Chen

IPC: G06Q30/02

CPC classification number: G06Q30/0247 ,  G06Q10/04

Abstract: A simulation framework for evaluating revenue that may use a pricing engine that runs at least one pricing algorithm with particular configurations and under particular model market conditions to provide revenue projections.

Abstract translation: 用于评估收入的模拟框架，可以使用定价引擎运行至少一种具有特定配置和特定模型市场条件的定价算法，以提供收入预测。

公开(公告)号：US20170039456A1

公开(公告)日：2017-02-09

申请号：US14820972

申请日：2015-08-07

Applicant: Yahoo! Inc.

Inventor： Mohammad Saberian ,  Jia Li ,  Jian Yang

IPC: G06K9/66

CPC classification number: G06N3/08 ,  G06N3/0454 ,  G06N3/084

Abstract: Briefly, embodiments of methods and/or systems of training multiclass convolutional neural networks (CNNs) are disclosed. For one embodiment, as an example, an auxiliary CNN may be utilized to form an ensemble with the collection as a linear combination. The linear combination may be based, at least in part, on boost prediction error encountered during the training process.

Abstract translation: 简单地，公开了训练多级卷积神经网络（CNN）的方法和/或系统的实施例。 对于一个实施例，作为示例，可以使用辅助CNN来形成集合作为线性组合的集合。 线性组合可以至少部分地基于训练过程中遇到的升压预测误差。

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：US20170032424A1

公开(公告)日：2017-02-02

申请号：US14815334

申请日：2015-07-31

Applicant: Yahoo! Inc.

Inventor： Suleyman Cetintas ,  Srinath Ravindran ,  Mohammad Saberian ,  Sandeep Soni ,  Kuang-chih Lee ,  Hong Yao ,  Jian Yang ,  Pradhan Pattanayak

IPC: G06Q30/02

CPC classification number: G06Q30/0269 ,  G06Q30/0277

Abstract: The technologies described herein serve contextually relevant advertisements under a guaranteed advertisement campaign. A publisher retrieves a guaranteed advertisement campaign related to a webpage available for serving an advertisement, and identifies a set of advertisements relating to the guaranteed advertisement campaign. Advertisement selecting circuitry of the publisher determines whether an advertisement that is contextually relevant to content published at the webpage is present in the set of advertisements. If there is no contextually relevant advertisement in the set of advertisements, the advertisement selecting circuitry selects an alternative advertisement from the set of advertisements that minimizes an under-delivery risk related to the guaranteed advertisement campaign. If there is a contextually relevant advertisement in the set of advertisements, the advertisement selecting circuitry selects the contextually relevant advertisement. Then, the publisher provides the selected advertisement to a client device.

Abstract translation: 本文描述的技术在保证的广告活动下提供与内容相关的广告。 发布者检索与可用于服务广告的网页有关的保证广告活动，并且识别与保证广告活动相关的一组广告。 发布者的广告选择电路决定在该广告集中是否存在与在网页上发布的内容上下文相关的广告。 如果广告集合中没有上下文相关的广告，则广告选择电路从该广告集合中选择一个替代的广告，使与保证的广告活动相关的不足的风险最小化。 如果广告集合中存在上下文相关的广告，则广告选择电路选择上下文相关的广告。 然后，发布者将所选择的广告提供给客户端设备。

公开(公告)号：US20160055320A1

公开(公告)日：2016-02-25

申请号：US14466470

申请日：2014-08-22

Applicant: Yahoo! Inc.

Inventor： Pengyuan Wang ,  Jian Yang ,  Marsha Meytlis ,  Fei Yu

IPC: G06F19/00

CPC classification number: G16H15/00 ,  G16H50/70

Abstract: Methods, systems and programming for measuring user treatment effectiveness. First information related to activities of each user in a first user set in response to a first treatment is received. Second information related to activities of each user in a second user set in response to a second treatment is received. A model with respect to features is obtained based on the first and second information. Each user is associated with the features. A weighing factor for each user is estimated based on the model and each user's features. A first success rate is computed based on the first information and the weighting factors for each user in the first user set. A second success rate is computed based on the second information and the weighting factors for each user in the second user set. A metric of effectiveness is measured based on the first and second success rates.

Abstract translation: 测量用户治疗效果的方法，系统和程序。 接收与第一用户响应于第一处理的每个用户的活动有关的第一信息。 接收与第二用户响应于第二处理的每个用户的活动有关的第二信息。 基于第一和第二信息获得关于特征的模型。 每个用户与功能相关联。 根据模型和每个用户的特征估算每个用户的称重系数。 基于第一用户集合中的每个用户的第一信息和加权因子来计算第一成功率。 基于第二用户集合中的每个用户的第二信息和加权因子来计算第二成功率。 有效性的度量是根据第一个和第二个成功率来衡量的。

公开(公告)号：US20140201009A1

公开(公告)日：2014-07-17

申请号：US13739129

申请日：2013-01-11

Applicant: YAHOO! INC.

Inventor： Jian Yang ,  Michael Schwarz ,  Vijay Bharadwaj ,  Peiji Chen

IPC: G06Q30/02

CPC classification number: G06Q30/0273

Abstract: A system and method for dynamic pricing in a guaranteed display market includes: receiving attribute parameters and values for an incoming pricing query for an advertisement; calculating a base price for the advertisement using recent historical information from contracts matching the attribute parameters; calculating a price response by adjusting the base price to reflect market conditions; calculating a non-guaranteed display opportunity cost for the adjusted base price; and calculating a final price as a function of the adjusted base price and the non-guaranteed display opportunity cost, with the non-guaranteed display opportunity cost as a lower bound for the price.

Abstract translation: 用于保证展示市场中的动态定价的系统和方法包括：接收用于广告的进入定价查询的属性参数和值; 使用与属性参数匹配的合同中的近期历史信息计算广告的基价; 通过调整基准价格来反映市场状况来计算价格回应; 计算调整基准价格的无保证显示机会成本; 并计算最终价格作为调整后的基准价格和无保证的显示机会成本的函数，其中无保证的显示机会成本作为价格的下限。