公开(公告)号：US20160210321A1

公开(公告)日：2016-07-21

申请号：US14599026

申请日：2015-01-16

Applicant: Google Inc.

Inventor： Xiaohong Gong ,  Wei Zhang ,  Nima Asgharbeygi

IPC: G06F17/30 ,  H04L29/08

CPC classification number: G06F17/30345 ,  G06F17/30386 ,  G06F17/30867 ,  G06Q30/0631 ,  H04L67/30 ,  H04L67/306 ,  H04N21/4668

Abstract: System and methods of this disclosure are directed to recommending content in real-time or near real-time. The system comprises a number of pipelines updated a different frequencies that process temporally different sets of web property visit data. Within each pipeline, the system can employ different number of algorithms to process visit data to generate content recommendations. One algorithm is a content filter that filters from the visit data those determined to be unsuitable as recommendations. Another is a content analyzer that analyzes the content of each URL in the visit data by topic category and attribute. Another is an item-to-item collaborative filter that determines a correlation score for each URL based on those in the visit data in a single session Another is a device-to-item matrix factorization that determines an affinity score for each URL based on visit data, context information, and topic category.

Abstract translation: 本公开的系统和方法旨在实时或接近实时地推荐内容。 该系统包括多个管道更新处理时间上不同的web属性访问数据集合的不同频率。 在每个流水线中，系统可以使用不同数量的算法来处理访问数据以生成内容建议。 一种算法是从确定为不适合作为推荐的访问数据过滤的内容过滤器。 另一个是内容分析器，按照主题类别和属性分析访问数据中每个URL的内容。 另一个是项目到项目协作过滤器，其基于单个会话中的访问数据中的那些确定每个URL的相关性得分另一个是设备到项目矩阵因式分解，其基于访问确定每个URL的亲和度分数 数据，上下文信息和主题类别。

公开(公告)号：US20150363859A1

公开(公告)日：2015-12-17

申请号：US14162266

申请日：2014-01-23

Applicant: Google Inc.

Inventor： Wei Zhang ,  Jia Zhao ,  Duangmanee Putthividhya ,  Ismail Oner Sebe ,  Nima Asgharbeygi

IPC: G06Q30/06

CPC classification number: G06Q30/0631

Abstract: Systems and methods for determining correlation scores for product pairs are provided. Contextual user behavior indicator data relating to a plurality of user behavior indicator types is received. A correlation score is computed for a first product and a second product for each user behavior indicator type from the plurality of user behavior indicator types. A final correlation score is computed for the first product and the second product by combining the computed correlation scores for each user behavior indicator type. The computed final correlation score for the first product and the second product is stored into a first data storage.

Abstract translation: 提供了用于确定产品对的相关性得分的系统和方法。 接收与多个用户行为指示符类型相关的上下文用户行为指示符数据。 针对来自多个用户行为指示符类型的每个用户行为指示符类型的第一乘积和第二乘积计算相关得分。 通过组合每个用户行为指示符类型的计算的相关性分数来计算第一乘积和第二乘积的最终相关分数。 所计算的第一产品和第二产品的最终相关性得分被存储在第一数据存储器中。

公开(公告)号：US10977573B1

公开(公告)日：2021-04-13

申请号：US15130089

申请日：2016-04-15

Applicant: Google Inc.

Inventor： Jeffrey Dalton ,  Karthik Raman ,  Evgeniy Gabrilovich ,  Kevin Patrick Murphy ,  Wei Zhang

IPC: G06N20/00 ,  G06F16/80 ,  G06F40/169

Abstract: Systems and methods provide distantly supervised wrapper induction for semi-structured documents, including automatically generating and annotating training documents for the wrapper. Training of the wrapper may occur in two phases using the training documents. An example method includes identifying a training set of semi-structured web pages having a subject entity that exists in a knowledge base and, for each training page, identifying target objects, identifying predicates in the knowledge base that connect the subject entity to a target objects identified in the training page, and annotating the training page. Annotating a training page includes generating a feature set for a mention of the target object, generating predicate-target object pairs for the mention, and labeling each predicate-target object pair with a corresponding example type and weight. The annotated training pages are used to train the wrapper to extract new subject entities and new facts from the set of semi-structured web pages.

公开(公告)号：US09858308B2

公开(公告)日：2018-01-02

申请号：US14599026

申请日：2015-01-16

Applicant: Google Inc.

Inventor： Xiaohong Gong ,  Wei Zhang ,  Nima Asgharbeygi

IPC: G06F7/00 ,  G06F17/30 ,  H04L29/08 ,  G06Q30/06 ,  H04N21/466

CPC classification number: G06F17/30345 ,  G06F17/30386 ,  G06F17/30867 ,  G06Q30/0631 ,  H04L67/30 ,  H04L67/306 ,  H04N21/4668

Abstract: System and methods of this disclosure are directed to recommending content in real-time or near real-time. The system comprises a number of pipelines updated a different frequencies that process temporally different sets of web property visit data. Within each pipeline, the system can employ different number of algorithms to process visit data to generate content recommendations. One algorithm is a content filter that filters from the visit data those determined to be unsuitable as recommendations. Another is a content analyzer that analyzes the content of each URL in the visit data by topic category and attribute. Another is an item-to-item collaborative filter that determines a correlation score for each URL based on those in the visit data in a single session Another is a device-to-item matrix factorization that determines an affinity score for each URL based on visit data, context information, and topic category.

公开(公告)号：US20160313876A1

公开(公告)日：2016-10-27

申请号：US15136657

申请日：2016-04-22

Applicant: Google Inc.

Inventor： Xin Dong ,  Christopher Tim Althoff ,  Kevin Patrick Murphy ,  Safa Alai ,  Van Dang ,  Wei Zhang

IPC: G06F3/0482 ,  G06F17/30 ,  G06T11/20 ,  G06F3/0484 ,  G06F3/0481

CPC classification number: G06F3/0482 ,  G06F3/04817 ,  G06F3/04842 ,  G06F3/04845 ,  G06F16/248 ,  G06F16/435 ,  G06F2203/04806 ,  G06T11/206

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for combining authentication and application shortcut. An example method includes responsive to a user request identifying an entity: identifying a first time period associated with the entity based at least on a type of the entity; determining, within the first time period, a plurality of first candidate entities associated with the first entity; selecting first entities in the plurality of first candidate entities according to one or more selection criteria; and providing, for presentation to the user, first user-selectable graphical elements on a first graphical user-interactive timeline. Each first user-selectable graphical element identifies a corresponding first entity in the first entities.

Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于组合认证和应用程序快捷方式。 一个示例性方法包括响应于识别实体的用户请求：至少基于所述实体的类型来识别与所述实体相关联的第一时间段; 在所述第一时间段内确定与所述第一实体相关联的多个第一候选实体; 根据一个或多个选择标准来选择所述多个第一候选实体中的第一实体; 以及在第一图形用户交互时间线上为用户呈现第一用户可选图形元素。 每个第一用户可选图形元素标识第一实体中的对应的第一实体。