公开(公告)号：US20150363502A1

公开(公告)日：2015-12-17

申请号：US14305607

申请日：2014-06-16

Applicant: Google Inc.

Inventor： Aiyou Chen ,  James Robert Koehler ,  Nicolas Remy ,  Makoto Uchida

IPC: G06F17/30

CPC classification number: G06F16/9535

Abstract: Systems and techniques are provided for optimizing personalized recommendations with longitudinal data and a future objective. An identifier may be received for content items. A user content item history including a list identifying a previously acquired content item may be received. Content item metadata may be received including a correlation between the previously acquired content item and a content item for which an identifier was received, and a correlation between a content item for which an identifier was received and fulfillment of a future objective. A joint probability may be determined for each content item based on the user content item history and the content item metadata, including the probability that the content item will be acquired by the user after being recommended to the user and that a future objective will be fulfilled after the content item is acquired by the user.

Abstract translation: 提供系统和技术，用于通过纵向数据和未来目标优化个性化建议。 可以为内容项目接收标识符。 可以接收包括标识先前获取的内容项的列表的用户内容项历史。 可以接收包括先前获取的内容项目和接收到标识符的内容项目之间的相关性的内容项目元数据，以及接收到标识符的内容项目与未来目标的实现之间的相关性。 可以基于用户内容项目历史和内容项目元数据确定每个内容项目的联合概率，包括用户在被推荐给用户之后将获取内容项目并且将来将满足目标的概率 在用户获取内容项目之后。

公开(公告)号：US09075506B1

公开(公告)日：2015-07-07

申请号：US13653338

申请日：2012-10-16

Applicant: Google Inc.

Inventor： Makoto Uchida ,  David Andrew Huffaker ,  Abhijit Bose

IPC: G06F17/50 ,  G06F3/0482 ,  G06F11/34 ,  G06F21/12

CPC classification number: G06F3/0482 ,  G06F11/34 ,  G06F21/128 ,  H04L12/6418

Abstract: Systems and methods for providing real-time analysis of feature relationships are provided. In some aspects, a method includes receiving user activity data and user status data for users in the interactive network, the interactive network comprising at least two user features; generating a user dataset by associating, for each user, the user's activity data with the user's status data using a unique identification of the user and a timestamp; analyzing the user dataset using a statistical model; and providing, for display, an output of the analysis by the statistical model, the output including an indicator of a relationship between a use of one of the two user features with a use of the other of the two user features.

Abstract translation: 提供了提供功能关系实时分析的系统和方法。 在一些方面，一种方法包括：接收交互式网络中的用户的用户活动数据和用户状态数据，所述交互式网络包括至少两个用户特征; 通过使用用户的唯一标识和时间戳将针对每个用户的用户的活动数据与用户的状态数据相关联来生成用户数据集; 使用统计模型分析用户数据集; 以及通过所述统计模型提供用于显示所述分析的输出，所述输出包括使用所述两个用户特征中的一个的两个用户特征中的另一个之间的关系的指示符。