Outlier data point detection
    23.
    发明授权
    Outlier data point detection 有权
    异常数据点检测

    公开(公告)号:US09195713B2

    公开(公告)日:2015-11-24

    申请号:US12614432

    申请日:2009-11-08

    IPC分类号: G06F7/00 G06F17/00 G06F17/30

    CPC分类号: G06F17/30516

    摘要: New data points are added to a streaming window of data points and existing data points are removed from the window over time. Each data point has a value for each of one or more dimensions. Each time a given new data point is added to the window or a given existing data point is removed from the window, one or more outlier detection data structures are updated. Each outlier detection data structure encompasses the data points within the streaming window for a corresponding dimension. The outlier detection data structures are used to detect outlier data points within the window over selected one or more dimensions.

    摘要翻译: 新的数据点被添加到数据点的流窗口中,并且现有的数据点随着时间从窗口中移除。 每个数据点具有一个或多个维度中的每一个的值。 每当将给定的新数据点添加到窗口或者从窗口中移除给定的现有数据点时,将更新一个或多个异常值检测数据结构。 每个异常值检测数据结构包含用于相应维度的流窗口内的数据点。 异常值检测数据结构用于在所选择的一个或多个维度上检测窗口内的异常值数据点。

    System and method for modifying scheduling of queries in response to the balancing average stretch and maximum stretch of scheduled queries
    24.
    发明授权
    System and method for modifying scheduling of queries in response to the balancing average stretch and maximum stretch of scheduled queries 有权
    响应于平均平均拉伸和调度查询的最大拉伸来修改查询调度的系统和方法

    公开(公告)号:US08365174B2

    公开(公告)日:2013-01-29

    申请号:US12251272

    申请日:2008-10-14

    IPC分类号: G06F9/46 G06F17/30

    摘要: A mixed workload scheduler and operating method efficiently handle diverse queries ranging from short less-intensive queries to long resource-intensive queries. A scheduler is configured for scheduling mixed workloads and comprises an analyzer and a schedule controller. The analyzer detects execution time and wait time of a plurality of queries and balances average stretch and maximum stretch of scheduled queries wherein query stretch is defined as a ratio of a sum of wait time and execution time to execution time of a query. The schedule controller modifies scheduling of queries according to service level differentiation.

    摘要翻译: 混合的工作负载调度程序和操作方法可以有效地处理从较少密集型查询到长资源密集型查询的各种查询。 调度器被配置用于调度混合工作负载并且包括分析器和调度控制器。 分析器检测多个查询的执行时间和等待时间,并且将查询延伸定义为等待时间和执行时间之和与查询的执行时间的比率的预定查询的平均拉伸和最大拉伸。 调度控制器根据服务水平差异来修改查询的调度。

    Event prediction
    25.
    发明申请
    Event prediction 有权
    事件预测

    公开(公告)号:US20120226652A1

    公开(公告)日:2012-09-06

    申请号:US13040171

    申请日:2011-03-03

    IPC分类号: G06N5/04

    CPC分类号: G06N7/005

    摘要: A selected set of one or more first events that have occurred within current data is received. An episode set of which the selected set is a subset, the episode set including one or more second events that have occurred within historical data related to the current data is identified. One or more third events that occurred within the historical data within a predetermined time horizon after the one or more second events of the episode set occurred within the historical data are identified. The one or more third events are predicted to likely occur within the current data as a result of the one or more first events having occurred within the current data.

    摘要翻译: 接收在当前数据内发生的所选择的一个或多个第一事件集合。 识别所选集合是其子集的集集,包括在与当前数据相关的历史数据内发生的一个或多个第二事件的剧集集。 识别发生在历史数据中的发生集合的一个或多个第二事件之后的预定时间范围内在历史数据内发生的一个或多个第三事件。 由于一个或多个第一事件已经在当前数据内发生,所以一个或多个第三事件被预测可能发生在当前数据内。

    DETERMINING WHETHER A POINT IN A DATA STREAM IS AN OUTLIER USING HIERARCHICAL TREES
    26.
    发明申请
    DETERMINING WHETHER A POINT IN A DATA STREAM IS AN OUTLIER USING HIERARCHICAL TREES 有权
    确定数据流中的一个点是使用分层条件的出处

    公开(公告)号:US20120072390A1

    公开(公告)日:2012-03-22

    申请号:US12887965

    申请日:2010-09-22

    IPC分类号: G06N5/02

    CPC分类号: G06N5/02

    摘要: A technique that includes receiving a data stream that is indicative of a plurality of multi-dimensional points in a processor-based machine and for each dimension, organizing data indicative of values of the points in the dimension in an associated hierarchical tree. The technique includes using the processor-based machine to determine whether a given point of the plurality of points is an outlier based on a combination of the trees.

    摘要翻译: 一种技术,包括接收指示基于处理器的机器中的多个多维点的数据流,并且针对每个维度,组织指示相关层级树中维度中的点的值的数据。 该技术包括使用基于处理器的机器来确定多个点的给定点是否是基于树的组合的异常值。

    Compression of non-dyadic sensor data organized within a non-dyadic hierarchy
    27.
    发明申请
    Compression of non-dyadic sensor data organized within a non-dyadic hierarchy 有权
    压缩在非二元层次结构中组织的非二元传感器数据

    公开(公告)号:US20110010405A1

    公开(公告)日:2011-01-13

    申请号:US12501446

    申请日:2009-07-12

    IPC分类号: G06F17/14 G06F7/552

    CPC分类号: G06F17/148

    摘要: Sensor data is received from one or more sensors. The sensor data is organized within a hierarchy. The sensor data is organized within a hierarchy that is non-dyadic. A processor of a computing device generates a discrete wavelet transform, based on the sensor data and based on the hierarchy of the sensor data, to compress the sensor data. The sensor data, as has been compressed via generation of the discrete wavelet transform, is processed.

    摘要翻译: 从一个或多个传感器接收传感器数据。 传感器数据组织在层次结构中。 传感器数据被组织在非二进制的层次结构中。 计算设备的处理器基于传感器数据并基于传感器数据的层级来生成离散小波变换,以压缩传感器数据。 已经通过生成离散小波变换压缩的传感器数据被处理。

    Sentiment cube
    28.
    发明授权
    Sentiment cube 有权
    情感立方体

    公开(公告)号:US08725781B2

    公开(公告)日:2014-05-13

    申请号:US13017013

    申请日:2011-01-30

    IPC分类号: G06F17/30

    CPC分类号: G06Q30/02

    摘要: A sentiment cube system is disclosed. In one example, the system discloses a sentiment storage, including a sentiment cube data structure having a set of cells arranged by a set of dimensions. The system includes a computer programmed with executable instructions which operate a set of modules, wherein the modules comprise: a sentiment storage module which receives sentiment values associated with a set of entity features, and then populates a hierarchy of the cells in the sentiment cube with the sentiment values. A sentiment analysis module effecting a set of operations on the sentiment cube.

    摘要翻译: 披露情感立方体系。 在一个示例中,系统公开了情绪存储,其包括具有由一组维度排列的一组单元的情感立方体数据结构。 该系统包括用可操作的指令编程的计算机,该可执行指令操作一组模块,其中模块包括:情绪存储模块,其接收与一组实体特征相关联的情绪值,然后在情绪立方体中填充情绪立方体中的细胞层级, 情绪价值观。 情绪分析模块对情绪立方体执行一组操作。

    SENTIMENT CUBE
    29.
    发明申请
    SENTIMENT CUBE 有权
    感应杯

    公开(公告)号:US20120197950A1

    公开(公告)日:2012-08-02

    申请号:US13017013

    申请日:2011-01-30

    IPC分类号: G06F17/30

    CPC分类号: G06Q30/02

    摘要: A sentiment cube system is disclosed. In one example, the system discloses a sentiment storage, including a sentiment cube data structure having a set of cells arranged by a set of dimensions. The system includes a computer programmed with executable instructions which operate a set of modules, wherein the modules comprise: a sentiment storage module which receives sentiment values associated with a set of entity features, and then populates a hierarchy of the cells in the sentiment cube with the sentiment values. A sentiment analysis module effecting a set of operations on the sentiment cube.

    摘要翻译: 披露情感立方体系。 在一个示例中,系统公开了情绪存储,其包括具有由一组维度排列的一组单元的情感立方体数据结构。 该系统包括用可操作的指令编程的计算机,该可执行指令操作一组模块,其中模块包括:情绪存储模块,其接收与一组实体特征相关联的情绪值,然后在情绪立方体中填充情绪立方体中的细胞层级, 情绪价值观。 情绪分析模块对情绪立方体执行一组操作。

    DETERMINING CORRELATIONS BETWEEN SLOW STREAM AND FAST STREAM INFORMATION
    30.
    发明申请
    DETERMINING CORRELATIONS BETWEEN SLOW STREAM AND FAST STREAM INFORMATION 审中-公开
    确定慢流与快速流动信息之间的相关性

    公开(公告)号:US20120076416A1

    公开(公告)日:2012-03-29

    申请号:US12889805

    申请日:2010-09-24

    IPC分类号: G06K9/46

    摘要: A collection of documents are correlated with information items in a fast stream of information using categorical hierarchical neighborhood trees (C-HNTs). First data entities extracted from the documents are inserted into corresponding C-HNTs. The first data entities that are neighbors in the C-HNTs of second data entities extracted from the fast stream items are identified. Similarities between the documents and the fast stream items are determined based on the location at which the neighbors are located.

    摘要翻译: 使用分类分层邻域树(C-HNT),文档的集合与快速信息流中的信息项相关。 从文档中提取的第一个数据实体插入相应的C-HNT。 识别从快速流项目提取的第二数据实体的C-HNT中的邻居的第一数据实体。 基于邻居位置确定文件和快速流项目之间的相似性。