公开(公告)号：US20130227054A1

公开(公告)日：2013-08-29

申请号：US13393310

申请日：2011-11-10

申请人： Xu Zhang ,  Louhua Zhu ,  Haijie Gu ,  Duoquan Li

发明人： Xu Zhang ,  Louhua Zhu ,  Haijie Gu ,  Duoquan Li

IPC分类号： H04L29/08

CPC分类号： H04L67/32 ,  G06Q30/0241 ,  G06Q30/0269 ,  G06Q30/06 ,  G06Q30/0631

摘要： The present disclosure provides a method and device for transmitting recommended product information. In one embodiment, a system retrieves product evaluation records given by one or more users. Each of the product evaluation records includes an identification of the user (user ID), an identification of the product (product ID), and evaluation information. The system uses the user ID and the product ID as a primary key, and then, based on intervals of the primary key, divides the product evaluation records into several subsets of records, and assigns these subsets of records into multiple calculation nodes. The system retrieves such SVD calculation results of the multiple subsets of records from the multiple calculation nodes. The recommended product information is sent to a client terminal based on the SVD calculation results. The present disclosure implements the distribution processing of SVD calculation, reduces the calculation complexity, and saves the calculation time.

摘要翻译： 本公开提供了用于传送推荐产品信息的方法和装置。 在一个实施例中，系统检索由一个或多个用户给出的产品评估记录。 每个产品评估记录包括用户（用户ID）的标识，产品的标识（产品ID）和评估信息。 系统使用用户ID和产品ID作为主键，然后根据主键的间隔将产品评估记录划分为多个记录子集，并将这些记录子集分配到多个计算节点中。 系统从多个计算节点检索多个记录子集的SVD计算结果。 根据SVD计算结果将推荐的产品信息发送到客户终端。 本公开实现了SVD计算的分布处理，降低了计算复杂度，节省了计算时间。

公开(公告)号：US09160808B2

公开(公告)日：2015-10-13

申请号：US13393310

申请日：2011-11-10

申请人： Xu Zhang ,  Louhua Zhu ,  Haijie Gu ,  Duoquan Li

发明人： Xu Zhang ,  Louhua Zhu ,  Haijie Gu ,  Duoquan Li

IPC分类号： G06F15/16 ,  H04L29/08 ,  G06Q30/06

CPC分类号： H04L67/32 ,  G06Q30/0241 ,  G06Q30/0269 ,  G06Q30/06 ,  G06Q30/0631

摘要： The present disclosure provides a method and device for transmitting recommended product information. In one embodiment, a system retrieves product evaluation records given by one or more users. Each of the product evaluation records includes an identification of the user (user ID), an identification of the product (product ID), and evaluation information. The system uses the user ID and the product ID as a primary key, and then, based on intervals of the primary key, divides the product evaluation records into several subsets of records, and assigns these subsets of records into multiple calculation nodes. The system retrieves such SVD calculation results of the multiple subsets of records from the multiple calculation nodes. The recommended product information is sent to a client terminal based on the SVD calculation results. The present disclosure implements the distribution processing of SVD calculation, reduces the calculation complexity, and saves the calculation time.

摘要翻译： 本公开提供了用于传送推荐产品信息的方法和装置。 在一个实施例中，系统检索由一个或多个用户给出的产品评估记录。 每个产品评估记录包括用户（用户ID）的标识，产品的标识（产品ID）和评估信息。 系统使用用户ID和产品ID作为主键，然后根据主键的间隔将产品评估记录划分为多个记录子集，并将这些记录子集分配到多个计算节点中。 系统从多个计算节点检索多个记录子集的SVD计算结果。 根据SVD计算结果将推荐的产品信息发送到客户终端。 本公开实现了SVD计算的分布处理，降低了计算复杂度，节省了计算时间。

公开(公告)号：US20120059735A1

公开(公告)日：2012-03-08

申请号：US13199574

申请日：2011-09-01

申请人： Ningjun Su ,  Zhixiong Yang ,  Haijie Gu ,  Louhua Zhu

发明人： Ningjun Su ,  Zhixiong Yang ,  Haijie Gu ,  Louhua Zhu

IPC分类号： G06Q30/00

CPC分类号： G06Q30/0631

摘要： A technique of product recommendations is disclosed, including: determining user characteristic information and product characteristic information for a user; determining at least one of a basic recommended product set and an auxiliary recommended product set for the user; receiving an indication associated with a type of the user's network operation; generating product recommendations based at least in part on type of the user's network operation and at least one of the basic recommended product set and the auxiliary recommended product set for the user; and presenting the generated product recommendations.

摘要翻译： 公开了一种产品推荐技术，包括：确定用户的用户特征信息和产品特征信息; 确定用户的基本推荐产品组和辅助推荐产品组中的至少一个; 接收与所述用户的网络操作的类型相关联的指示; 至少部分地基于用户的网络操作的类型和用户的至少一个基本推荐的产品集合和辅助推荐的产品集合来生成产品建议; 并介绍生成的产品建议。