公开(公告)号：US09256657B1

公开(公告)日：2016-02-09

申请号：US13916772

申请日：2013-06-13

Applicant: AMAZON TECHNOLOGIES, INC.

Inventor： Andrew Ross Evenson ,  Masud Ahmed Khan ,  Jeremy David McCarthy ,  Muralidharan Subramani

IPC: G06F17/30

CPC classification number: G06F17/30569

Abstract: Techniques are described for tracking data objects transferred among multiple services in a computing environment. Services that are involved in the transfer of data objects may be instrumented to generate recordings that describe outbound and inbound transfers of data objects. The recordings may be analyzed to identify key-value pairs included in the transferred data objects, where the key corresponds to a data attribute that stores a particular value in a data object. For each pair of keys that are associated with a same or substantially similar value, a correlation metric may be updated for each instance of association. Over time, the correlation metric may indicate a higher degree of correlation for those pairs of keys that frequently share a same value. Pairs of keys exhibiting an above-threshold correlation count may be designated as related in that they are involved in the transfer of data objects.

Abstract translation: 描述了用于跟踪在计算环境中在多个服务之间传送的数据对象的技术。 涉及数据对象传输的服务可能会进行检测，以生成描述数据对象的出站和内向传输的记录。 可以分析记录以识别包括在传送的数据对象中的键值对，其中键对应于在数据对象中存储特定值的数据属性。 对于与相同或基本相似的值相关联的每对密钥对，可以为每个关联实例更新关联度量。 随着时间的推移，相关性度量可以指示经常共享相同值的那些键对更高程度的相关性。 表现出高于阈值的相关计数的键对可以被指定为相关的，因为它们涉及数据对象的传送。