公开(公告)号：US20150046260A1

公开(公告)日：2015-02-12

申请号：US14361671

申请日：2013-07-22

Applicant: Google Inc.

Inventor： Lars Engebretsen ,  Jennifer J. Huang ,  Thomas Hofmann

IPC: G06Q30/02

CPC classification number: G06Q30/0256

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer-readable storage medium, for comparing a request entity to a campaign entity. A method includes: identifying a campaign associated with a content sponsor, the campaign having an associated creative for presentation to users and selection criteria for use in evaluating when to present the creative in response to received requests for content; receiving at least one keyword from the content sponsor to be used as selection criteria; identifying an entity from a plurality of entities to associate with the keyword; storing the identified entity along with the keyword in association with the campaign; and using the keyword and the identified entity when evaluating the received requests for content.

Abstract translation: 方法，系统和装置，包括在计算机可读存储介质上编码的计算机程序，用于将请求实体与活动实体进行比较。 一种方法包括：识别与内容赞助商相关联的活动，所述活动具有用于呈现给用户的相关联的广告素材和用于评估何时呈现所述广告素材以响应于所接收到的内容请求的选择标准; 从内容赞助商接收至少一个关键字以用作选择标准; 从多个实体识别实体以与所述关键字相关联; 与所述活动相关联地存储所述识别的实体以及所述关键字; 以及在评估接收到的内容请求时使用关键字和所识别的实体。

公开(公告)号：US09881077B1

公开(公告)日：2018-01-30

申请号：US13962705

申请日：2013-08-08

Applicant: Google Inc.

Inventor： Enrique Alfonseca ,  Yasemin Altun ,  Massimiliano Ciaramita ,  Jean-Yves Delort ,  Ekaterina Filippova ,  Thomas Hofmann ,  Evangelos Kanoulas ,  Ioannis Tsochantaridis

IPC: G06F17/30

CPC classification number: G06F17/30705 ,  G06F17/3089

Abstract: News documents from one or more sources are aggregated. The news documents are grouped into a plurality of news collections. Each of the news collections includes a sub-set of the news documents having related content. Objects described by the news collections are determined. The objects collectively form a set of objects. A relevance of each of the news collections is measured with respect to the objects respectively described by the news collections and one or more news collections are determined from the plurality of news collections to be associated with a first object included in the set of objects based on the relevance of the one or more news collections to the first object.

公开(公告)号：US09317564B1

公开(公告)日：2016-04-19

申请号：US14518891

申请日：2014-10-20

Applicant: Google Inc.

Inventor： Dmity Korolev ,  Hartmut Maennel ,  Matthias Heiler ,  Michael Schaer ,  Thomas Hofmann ,  Wojciech Gajewski ,  Justyna Sidorska

IPC: G06F17/30

CPC classification number: G06F17/30 ,  G06F15/00 ,  G06F17/2785 ,  G06F17/30707 ,  G06K9/726

Abstract: Methods, systems, and apparatus, including computer program products, for constructing text classifiers. The method includes receiving a collection of candidate phrases for a given topic; filtering the received candidate phrases to remove erroneously included candidate phrases; assigning weights to the candidate phrases including scoring each candidate phrase using an initial classifier and assigning weights to the candidate phrases based on the scores; and generating a linear classifier using the filtered and weighted candidate phrases, where the linear classifier varies the weights for each phrase candidate depending on the length of the document being classified.

Abstract translation: 用于构建文本分类器的方法，系统和装置，包括计算机程序产品。 该方法包括接收给定主题的候选短语集合; 过滤所接收的候选短语以去除错误地包括的候选短语; 向所述候选短语分配权重，包括使用初始分类器对每个候选短语进行评分，并且基于所述分数向所述候选短语分配权重; 以及使用经滤波和加权的候选短语生成线性分类器，其中线性分类器根据被分类的文档的长度来改变每个短语候选的权重。