公开(公告)号：US20160371731A1

公开(公告)日：2016-12-22

申请号：US15244064

申请日：2016-08-23

Applicant: Google Inc.

Inventor： Ibrahim Elbouchikhi ,  Ficus Kirkpatrick

IPC: G06Q30/02

CPC classification number: G06Q30/0255

Abstract: A developer/requestor may select a subset of users for a promotion by querying a database; however, the developer may not be provided with specific details about each user (e.g., purchase history, browsing history, etc.). The system returns a response to the query that obfuscates a user's data while simultaneously providing the developer with a response to indicate to the developer whether or not a user or group of users is promotion eligible based on the developer's criteria. The developer may dispatch a promotion to the one or more users determined to be promotion eligible.

公开(公告)号：US20150039427A1

公开(公告)日：2015-02-05

申请号：US14299030

申请日：2014-06-09

Applicant: Google Inc.

Inventor： Ibrahim Elbouchikhi ,  Ficus Kirkpatrick

IPC: G06Q30/02

CPC classification number: G06Q30/0255

Abstract: A developer/requestor may select a subset of users for a promotion by querying a database; however, the developer may not be provided with specific details about each user (e.g., purchase history, browsing history, etc.). The system returns a response to the query that obfuscates a user's data while simultaneously providing the developer with a response to indicate to the developer whether or not a user or group of users is promotion eligible based on the developer's criteria. The developer may dispatch a promotion to the one or more users determined to be promotion eligible.

Abstract translation: 开发人员/请求者可以通过查询数据库来选择促销的一部分用户; 然而，可能不会向开发者提供关于每个用户的具体细节（例如，购买历史，浏览历史等）。 系统返回对查询的响应，模糊用户的数据，同时向开发者提供响应，以向开发人员指示用户或用户组是否根据开发人员的标准进行促销。 开发商可能会向一个或多个确定为促销资格的用户发送促销活动。

公开(公告)号：US20160132771A1

公开(公告)日：2016-05-12

申请号：US14539392

申请日：2014-11-12

Applicant: Google Inc.

Inventor： Sanketh Shetty ,  Ibrahim Elbouchikhi

IPC: G06N5/02 ,  H04L29/08 ,  G06N99/00 ,  H04W4/00 ,  G06Q30/06

CPC classification number: H04L67/32 ,  G06Q30/0631 ,  H04W4/60

Abstract: A machine learning technique may be applied to applications hosted by an application store to extract features that can be utilized to train one or more classifiers of the applications based on their relative complexity. A processor may receive pairwise comparisons of relative complexity and feature representations for the applications to be used in training of a classifier. The processor may determine a feature set that is correlated with the pairwise comparison of relative complexity and obtain a classifier based thereupon.

Abstract translation: 机器学习技术可以应用于由应用商店托管的应用，以提取可以用于基于它们的相对复杂度来训练应用的一个或多个分类器的特征。 处理器可以接收用于在分类器的训练中使用的应用的相对复杂性和特征表示的成对比较。 处理器可以确定与相对复杂度的成对比较相关的特征集合，并且基于此获得基于分类器。