公开(公告)号：US20150081420A1

公开(公告)日：2015-03-19

申请号：US14030431

申请日：2013-09-18

Applicant: GOOGLE INC.

Inventor： Jianyuan Min ,  Wenjun Lu ,  Stephen Leung ,  Xuefu Wang ,  Li Zou

IPC: G06Q30/02 ,  G06F17/30

CPC classification number: G06Q30/0244 ,  G06F16/951

Abstract: A computer-implemented method for identifying relationships between online content items uses a computing device including a processor and a memory. The method includes identifying a first content item and identifying a plurality of occurrence results for the first content item. Each occurrence result of the plurality of occurrence results includes an indicator that the first content item was retrieved along with a list of other content items based on an online activity of at least one user device. The method also includes computing a number of co-occurrence events involving the first content item and a second content item from the plurality of occurrence results. Each co-occurrence event includes an indicator that both first content item and second content item were retrieved together in an occurrence result. The method further includes computing a relationship value between first content item and second content item using at least the number of co-occurrence events.

Abstract translation: 用于识别在线内容项之间的关系的计算机实现的方法使用包括处理器和存储器的计算设备。 该方法包括识别第一内容项目并识别第一内容项目的多个出现结果。 多个发生结果的每个出现结果包括基于至少一个用户设备的在线活动的第一内容项目与其他内容项目的列表一起被检索的指示符。 该方法还包括从多个发生结果计算涉及第一内容项目和第二内容项目的多个同现事件。 每个同现事件包括在发生结果中一起检索第一内容项和第二内容项的指示符。 所述方法还包括使用至少所述同现事件的数量来计算第一内容项和第二内容项之间的关系值。