Incremental context accumulating systems with information co-location for high performance and real-time decisioning systems
    1.
    发明授权
    Incremental context accumulating systems with information co-location for high performance and real-time decisioning systems 有权
    增量上下文积累系统,具有高性能和实时决策系统的信息共存

    公开(公告)号:US08775342B2

    公开(公告)日:2014-07-08

    申请号:US13614541

    申请日:2012-09-13

    IPC分类号: G06F15/18

    CPC分类号: G06F17/30345

    摘要: Provided are techniques for incrementally integrating and persisting context over an available observational space. At least one feature associated with a new observation is used to create at least one index key. The at least one index key is used to query one or more reverse lookup tables to locate at least one previously persisted candidate observation. The new observation is evaluated against the at least one previously persisted candidate observation to determine at least one relationship. In response to determining the at least one relationship, a threshold is used to make a new assertion about the at least one relationship. The new observation is used to review previous assertions to determine whether a previous assertion is to be reversed. In response to reversing the previous assertion, the new observation, the new assertion, and the reversed assertion are incrementally integrated into persistent context.

    摘要翻译: 提供了用于在可用观测空间上逐渐整合和持续上下文的技术。 使用与新观察相关联的至少一个特征来创建至少一个索引关键字。 所述至少一个索引关键字用于查询一个或多个反向查找表以定位至少一个先前持续的候选观察。 针对至少一个以前持续的候选观察评估新观察值以确定至少一个关系。 响应于确定至少一个关系,使用阈值来形成关于至少一个关系的新的断言。 新的观察结果用于回顾以前的断言,以确定先前的断言是否被反转。 为了回应以前的断言,新的观察,新的断言和反向的断言被递增地整合到持续的上下文中。

    INCREMENTAL CONTEXT ACCUMULATING SYSTEMS WITH INFORMATION CO-LOCATION FOR HIGH PERFORMANCE AND REAL-TIME DECISIONING SYSTEMS
    2.
    发明申请
    INCREMENTAL CONTEXT ACCUMULATING SYSTEMS WITH INFORMATION CO-LOCATION FOR HIGH PERFORMANCE AND REAL-TIME DECISIONING SYSTEMS 有权
    具有高性能和实时决策系统信息协同的增量上下文统计系统

    公开(公告)号:US20130132400A1

    公开(公告)日:2013-05-23

    申请号:US13614541

    申请日:2012-09-13

    IPC分类号: G06F17/30

    CPC分类号: G06F17/30345

    摘要: Provided are techniques for incrementally integrating and persisting context over an available observational space. At least one feature associated with a new observation is used to create at least one index key. The at least one index key is used to query one or more reverse lookup tables to locate at least one previously persisted candidate observation. The new observation is evaluated against the at least one previously persisted candidate observation to determine at least one relationship. In response to determining the at least one relationship, a threshold is used to make a new assertion about the at least one relationship. The new observation is used to review previous assertions to determine whether a previous assertion is to be reversed. In response to reversing the previous assertion, the new observation, the new assertion, and the reversed assertion are incrementally integrated into persistent context.

    摘要翻译: 提供了用于在可用观测空间上逐渐整合和持续上下文的技术。 使用与新观察相关联的至少一个特征来创建至少一个索引关键字。 所述至少一个索引关键字用于查询一个或多个反向查找表以定位至少一个先前持续的候选观察。 针对至少一个以前持续的候选观察评估新观察值以确定至少一个关系。 响应于确定至少一个关系,使用阈值来形成关于至少一个关系的新的断言。 新的观察结果用于回顾以前的断言,以确定先前的断言是否被反转。 为了回应以前的断言,新的观察,新的断言和反向的断言被递增地整合到持续的上下文中。

    INCREMENTAL CONTEXT ACCUMULATING SYSTEMS WITH INFORMATION CO-LOCATION FOR HIGH PERFORMANCE AND REAL-TIME DECISIONING SYSTEMS

    公开(公告)号:US20130132399A1

    公开(公告)日:2013-05-23

    申请号:US13302900

    申请日:2011-11-22

    IPC分类号: G06F17/30

    CPC分类号: G06F17/30345

    摘要: Provided are techniques for incrementally integrating and persisting context over an available observational space. At least one feature associated with a new observation is used to create at least one index key. The at least one index key is used to query one or more reverse lookup tables to locate at least one previously persisted candidate observation. The new observation is evaluated against the at least one previously persisted candidate observation to determine at least one relationship. In response to determining the at least one relationship, a threshold is used to make a new assertion about the at least one relationship. The new observation is used to review previous assertions to determine whether a previous assertion is to be reversed. In response to reversing the previous assertion, the new observation, the new assertion, and the reversed assertion are incrementally integrated into persistent context.

    Context Accumulation Based on Properties of Entity Features
    4.
    发明申请
    Context Accumulation Based on Properties of Entity Features 审中-公开
    基于实体特征的背景累积

    公开(公告)号:US20140052685A1

    公开(公告)日:2014-02-20

    申请号:US13585066

    申请日:2012-08-14

    IPC分类号: G06N5/02

    CPC分类号: G06N5/02

    摘要: According to one embodiment of the present invention, a system for determining related entities includes at least one processor. The system identifies one or more candidate entities for a data object associated with an entity based on one or more features. The entity and candidate entities are each associated with one or more features and each feature is associated with one or more behaviors. The identified candidate entities related to the entity are determined based on the associated behaviors of the features of the identified candidate entities and the entity. Embodiments of the present invention further include a method and computer program product for determining related entities in substantially the same manner described above.

    摘要翻译: 根据本发明的一个实施例,用于确定相关实体的系统包括至少一个处理器。 该系统基于一个或多个特征来识别与实体相关联的数据对象的一个​​或多个候选实体。 实体和候选实体各自与一个或多个特征相关联,并且每个特征与一个或多个行为相关联。 基于所识别的候选实体和实体的特征的相关行为来确定与该实体相关的所识别的候选实体。 本发明的实施例还包括用于基本上相同的方式确定相关实体的方法和计算机程序产品。

    Incremental context accumulating systems with information co-location for high performance and real-time decisioning systems

    公开(公告)号:US08688605B2

    公开(公告)日:2014-04-01

    申请号:US13302900

    申请日:2011-11-22

    IPC分类号: G06F15/18

    CPC分类号: G06F17/30345

    摘要: Provided are techniques for incrementally integrating and persisting context over an available observational space. At least one feature associated with a new observation is used to create at least one index key. The at least one index key is used to query one or more reverse lookup tables to locate at least one previously persisted candidate observation. The new observation is evaluated against the at least one previously persisted candidate observation to determine at least one relationship. In response to determining the at least one relationship, a threshold is used to make a new assertion about the at least one relationship. The new observation is used to review previous assertions to determine whether a previous assertion is to be reversed. In response to reversing the previous assertion, the new observation, the new assertion, and the reversed assertion are incrementally integrated into persistent context.

    Context accumulation based on properties of entity features

    公开(公告)号:US10387780B2

    公开(公告)日:2019-08-20

    申请号:US13585066

    申请日:2012-08-14

    IPC分类号: G06N5/02

    摘要: According to one embodiment of the present invention, a system for determining related entities includes at least one processor. The system identifies one or more candidate entities for a data object associated with an entity based on one or more features. The entity and candidate entities are each associated with one or more features and each feature is associated with one or more behaviors. The identified candidate entities related to the entity are determined based on the associated behaviors of the features of the identified candidate entities and the entity. Embodiments of the present invention further include a method and computer program product for determining related entities in substantially the same manner described above.