利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

36 条记录 (耗时 0.022 秒)

    Calibrated classifiers with threshold comparisons
    21.
    发明授权
    Calibrated classifiers with threshold comparisons 失效
    校准分类器与阈值比较

    公开(公告)号：US07266536B2

    公开(公告)日：2007-09-04

    申请号：US10932386

    申请日：2004-09-02

    申请人： Ira Cohen ,  Moises Goldszmidt

    发明人： Ira Cohen ,  Moises Goldszmidt

    IPC分类号： G06F9/44 ,  G06N7/02 ,  G06N7/06

    CPC分类号： G06K9/6277

    摘要： A classifier is calibrated to produce a calibration map and a threshold is derived from the calibration map. A probability assignment produced by the classifier for input data is then compared to the threshold.

    摘要翻译： 分类器被校准以产生校准图，并且从校准图导出阈值。 然后将用于输入数据的分类器产生的概率分配与阈值进行比较。

    Determining and annotating a signature of a computer resource
    22.
    发明授权
    Determining and annotating a signature of a computer resource 失效
    确定和注释计算机资源的签名

    公开(公告)号：US07184935B1

    公开(公告)日：2007-02-27

    申请号：US11149566

    申请日：2005-06-10

    申请人： Ira Cohen ,  Moises Goldszmidt

    发明人： Ira Cohen ,  Moises Goldszmidt

    IPC分类号： G06F3/01

    CPC分类号： G06F11/3409 ,  G06F11/3452 ,  G06F11/3466 ,  G06F2201/81 ,  G06F2201/875

    摘要： Metrics for a computer resource are collected. A signature representing a state of the computer resource from the metrics are determined by determining raw values for each of the metrics and generating a vector from at least some of the raw values for the metrics, where generating the vector further comprises generating models for possible system states of the computer resource, determining a model that closely matches a state of the computer resource, determining key metrics for the model, and determining a vector of values from the key metrics. An annotation that describes the state of the computer resource is received and associated with the signature. The signature and the associated annotation are stored such that they are searchable.

    摘要翻译： 收集计算机资源的指标。 通过确定每个度量的原始值并从用于度量的至少一些原始值生成向量来确定表示来自度量的计算机资源的状态的签名，其中生成向量还包括为可能的系统生成模型 计算机资源的状态，确定与计算机资源的状态紧密匹配的模型，确定模型的关键度量，以及根据关键度量确定值向量。 描述计算机资源的状态的注释被接收并与签名相关联。 存储签名和相关注释，使其可搜索。

    ESTIMATING AND MANAGING POWER CONSUMPTION OF COMPUTING DEVICES USING POWER MODELS
    23.
    发明申请
    ESTIMATING AND MANAGING POWER CONSUMPTION OF COMPUTING DEVICES USING POWER MODELS 有权
    使用电源模型估算和管理计算设备的功耗

    公开(公告)号：US20130124885A1

    公开(公告)日：2013-05-16

    申请号：US13295112

    申请日：2011-11-14

    申请人： John D. Davis ,  Moises Goldszmidt ,  Suzanne M. Rivoire

    发明人： John D. Davis ,  Moises Goldszmidt ,  Suzanne M. Rivoire

    IPC分类号： G06F1/32

    CPC分类号： G06F1/3206 ,  G06F1/324 ,  G06F1/325 ,  G06F1/3296 ,  Y02D10/126 ,  Y02D10/172

    摘要： Power consumption of computing devices are monitored with performance counters and used to generate a power model for each computing device. The power models are used to estimate the power consumption of each computing device based on the performance counters. Each computing device is assigned a power cap, and a software-based power control at each computing device monitors the performance counters, estimates the power consumption using the performance counters and the model, and compares the estimated power consumption with the power cap. Depending on whether the estimated power consumption violates the power cap, the power control may transition the computing device to a lower power state to prevent a violation of the power cap or a higher power state if the computing device is below the power cap.

    摘要翻译： 使用性能计数器监视计算设备的功耗，并用于为每个计算设备生成电源模型。 功率模型用于基于性能计数器来估计每个计算设备的功耗。 每个计算设备被分配一个电源帽，并且每个计算设备的基于软件的功率控制监视性能计数器，使用性能计数器和模型估计功耗，并将估计的功耗与功率上限进行比较。 根据估计的功率消耗是否违反功率上限，功率控制可以将计算设备转换到较低功率状态，以防止在计算设备低于功率上限的情况下违反功率上限或较高功率状态。

    REPAIR-POLICY REFINEMENT IN DISTRIBUTED SYSTEMS
    24.
    发明申请
    REPAIR-POLICY REFINEMENT IN DISTRIBUTED SYSTEMS 有权
    分布式系统修理政策修订

    公开(公告)号：US20120072769A1

    公开(公告)日：2012-03-22

    申请号：US12886566

    申请日：2010-09-21

    申请人： Moises Goldszmidt ,  Mihai Budiu ,  Yue Zhang ,  Michael Pechuk

    发明人： Moises Goldszmidt ,  Mihai Budiu ,  Yue Zhang ,  Michael Pechuk

    IPC分类号： G06F11/28 ,  G06F11/14

    CPC分类号： G06F11/0793 ,  G06F11/3006 ,  G06F11/3055

    摘要： In a distributed system a plurality of devices (including computing units, storage and communication units) are monitored by an automated repair service that uses sensors and performs one or more repair actions on computing devices that are found to fail according to repair policies. The repair actions include automated repair actions and non-automated repair actions. The health of the computing devices is recorded in the form of states along with the repair actions that were performed on the computing devices and the times at which the repair actions were performed, and events generated by both sensors and the devices themselves. After some period of the time, the history of states of each device, the events, and the repair actions performed on the computing devices are analyzed to determine the effectiveness of the repair actions. A statistical analysis is performed based on the cost of each repair action and the determined effectiveness of each repair action, and one or more of the policies may be adjusted, as well as determining from the signals and events from the sensors whether the sensors themselves require adjustment

    摘要翻译： 在分布式系统中，多个设备（包括计算单元，存储和通信单元）由使用传感器的自动修复服务来监视，并且对根据修复策略发现失败的计算设备执行一个或多个修复动作。 修复操作包括自动修复操作和非自动修复操作。 以状态的形式记录计算设备的健康状况以及在计算设备上执行的修复动作以及执行修复动作的时间以及由传感器和设备本身产生的事件。 在一段时间之后，分析每个设备的状态历史，事件和在计算设备上执行的修复动作，以确定修复动作的有效性。 基于每个修复动作的成本和确定的每个修复动作的有效性进行统计分析，并且可以调整一个或多个策略，以及根据来自传感器的信号和事件确定传感器本身是否需要 调整

    Adding prototype information into probabilistic models
    25.
    发明授权
    Adding prototype information into probabilistic models 有权
    将原型信息添加到概率模型中

    公开(公告)号：US08010341B2

    公开(公告)日：2011-08-30

    申请号：US11855099

    申请日：2007-09-13

    申请人： Kannan Achan ,  Moises Goldszmidt ,  Lev Ratinov

    发明人： Kannan Achan ,  Moises Goldszmidt ,  Lev Ratinov

    IPC分类号： G06F17/27 ,  G06F17/20 ,  G06F15/18 ,  G10L15/06 ,  G10L15/14

    CPC分类号： G10L15/142 ,  G06F17/2715 ,  G06K9/6297

    摘要： Mechanisms are disclosed for incorporating prototype information into probabilistic models for automated information processing, mining, and knowledge discovery. Examples of these models include Hidden Markov Models (HMMs), Latent Dirichlet Allocation (LDA) models, and the like. The prototype information injects prior knowledge to such models, thereby rendering them more accurate, effective, and efficient. For instance, in the context of automated word labeling, additional knowledge is encoded into the models by providing a small set of prototypical words for each possible label. The net result is that words in a given corpus are labeled and are therefore in condition to be summarized, identified, classified, clustered, and the like.

    摘要翻译： 公开了将原型信息并入用于自动化信息处理，挖掘和知识发现的概率模型中的机制。 这些模型的示例包括隐马尔可夫模型（HMM），潜在狄利克雷分配（LDA）模型等。 原型信息将先前的知识注入到这些模型中，从而使它们更准确，有效和高效。 例如，在自动化字标识的上下文中，通过为每个可能的标签提供一小组原型字来将附加知识编码到模型中。 最终的结果是，给定语料库中的单词被标记，因此在其中被概括，识别，分类，聚类等等。

    Method of predicting response time for storage request
    26.
    发明授权
    Method of predicting response time for storage request 失效
    预测存储请求的响应时间的方法

    公开(公告)号：US07721061B1

    公开(公告)日：2010-05-18

    申请号：US11159441

    申请日：2005-06-22

    申请人： Terence P. Kelly ,  Ira Cohen ,  Moises Goldszmidt ,  Kimberly K. Keeton

    发明人： Terence P. Kelly ,  Ira Cohen ,  Moises Goldszmidt ,  Kimberly K. Keeton

    IPC分类号： G06F13/00

    CPC分类号： G06F11/3419 ,  G06F11/3447 ,  G06F11/3452 ,  G06F2201/87 ,  G06F2201/885

    摘要： An embodiment of a method of predicting response time for a storage request begins with a first step of a computing entity storing a training data set. The training data set comprises past performance observations for past storage requests of a storage array. Each past performance observation comprises an observed response time and a feature vector for a particular past storage request. The feature vector includes characteristics that are available external to the storage array. In a second step, the computing entity forms a response time forecaster from the training data set. In the third step, the computing entity applies the response time forecaster to a pending feature vector for a pending storage request to obtain a predicted response time for the pending storage request.

    摘要翻译： 预测存储请求的响应时间的方法的实施例开始于存储训练数据集的计算实体的第一步骤。 训练数据集包括对存储阵列的过去存储请求的过去的性能观察。 每个过去的表现观察包括观察到的响应时间和特定过去存储请求的特征向量。 特征向量包括在存储阵列外部可用的特征。 在第二步中，计算实体从训练数据集中形成响应时间预测器。 在第三步骤中，计算实体将响应时间预测器应用于未决存储器请求的未决特征向量，以获得待决存储请求的预测响应时间。

    Automated diagnosis and forecasting of service level objective states
    27.
    发明授权
    Automated diagnosis and forecasting of service level objective states 失效
    服务水平目标状态的自动诊断和预测

    公开(公告)号：US07693982B2

    公开(公告)日：2010-04-06

    申请号：US10987611

    申请日：2004-11-12

    申请人： Moises Goldszmidt ,  Ira Cohen ,  Terence Patrick Kelly ,  Julie Anna Symons

    发明人： Moises Goldszmidt ,  Ira Cohen ,  Terence Patrick Kelly ,  Julie Anna Symons

    IPC分类号： G06F15/173 ,  G06F7/60 ,  G06F17/10 ,  G06F15/18 ,  G06F11/00 ,  G06E1/00 ,  G06E3/00 ,  G06G7/00

    CPC分类号： G06Q10/04

    摘要： Systems, methods, and software used in performing automated diagnosis and identification of or forecasting service level object states. Some embodiments include building classifier models based on collected metric data to detect and forecast service level objective (SLO) violations. Some such systems, methods, and software further include automated detecting and forecasting of SLO violations along with providing alarms, messages, or commands to administrators or system components. Some such messages include diagnostic information with regard to a cause of a SLO violation. Some embodiments further include storing data representative of system performance and detected and forecast system SLO states. This data can then be used to generate reports of system performance including representations of system SLO states.

    摘要翻译： 用于执行自动诊断和识别或预测服务级对象状态的系统，方法和软件。 一些实施例包括基于收集的度量数据建立分类器模型以检测和预测服务水平目标（SLO）违规。 一些这样的系统，方法和软件还包括自动检测和预测SLO违规以及向管理员或系统组件提供警报，消息或命令。 一些这样的消息包括关于SLO违规的原因的诊断信息。 一些实施例还包括存储表示系统性能的数据和检测和预测系统SLO状态。 然后，该数据可用于生成系统性能的报告，包括系统SLO状态的表示。

    Determining a recurrent problem of a computer resource using signatures
    29.
    发明申请
    Determining a recurrent problem of a computer resource using signatures 有权
    确定使用签名的计算机资源的经常性问题

    公开(公告)号：US20070083513A1

    公开(公告)日：2007-04-12

    申请号：US11248692

    申请日：2005-10-12

    申请人： Ira Cohen ,  Moises Goldszmidt ,  Julie Symons ,  Terence Kelly ,  Steve Zhang

    发明人： Ira Cohen ,  Moises Goldszmidt ,  Julie Symons ,  Terence Kelly ,  Steve Zhang

    IPC分类号： G06F17/30

    CPC分类号： G06F11/008

    摘要： A computer system includes a signature creation engine operable to determine signatures representing states of a computer resource from metrics for the computer resource. The computer system also includes a database operable to store the signatures along with an annotation for each signature including information relating to a state of the computer resource. The computer system is operable to determine a recurrent problem of the computer resource from stored signatures.

    摘要翻译： 计算机系统包括签名创建引擎，其可操作以根据计算机资源的度量来确定表示计算机资源的状态的签名。 计算机系统还包括可操作以存储签名的数据库以及包括与计算机资源的状态相关的信息的每个签名的注释。 计算机系统可操作以从存储的签名确定计算机资源的经常性问题。

    Estimating and managing power consumption of computing devices using power models
    30.
    发明授权
    Estimating and managing power consumption of computing devices using power models 有权
    使用电力模型估算和管理计算设备的功耗

    公开(公告)号：US08904209B2

    公开(公告)日：2014-12-02

    申请号：US13295112

    申请日：2011-11-14

    申请人： John D. Davis ,  Moises Goldszmidt ,  Suzanne M. Rivoire

    发明人： John D. Davis ,  Moises Goldszmidt ,  Suzanne M. Rivoire

    IPC分类号： G06F1/26 ,  G06F1/28 ,  G06F1/32

    CPC分类号： G06F1/3206 ,  G06F1/324 ,  G06F1/325 ,  G06F1/3296 ,  Y02D10/126 ,  Y02D10/172

    摘要： Power consumption of computing devices are monitored with performance counters and used to generate a power model for each computing device. The power models are used to estimate the power consumption of each computing device based on the performance counters. Each computing device is assigned a power cap, and a software-based power control at each computing device monitors the performance counters, estimates the power consumption using the performance counters and the model, and compares the estimated power consumption with the power cap. Depending on whether the estimated power consumption violates the power cap, the power control may transition the computing device to a lower power state to prevent a violation of the power cap or a higher power state if the computing device is below the power cap.

    摘要翻译： 使用性能计数器监视计算设备的功耗，并用于为每个计算设备生成电源模型。 功率模型用于基于性能计数器来估计每个计算设备的功耗。 每个计算设备被分配一个电源帽，并且每个计算设备的基于软件的功率控制监视性能计数器，使用性能计数器和模型估计功耗，并将估计的功耗与功率上限进行比较。 根据估计的功率消耗是否违反功率上限，功率控制可以将计算设备转换到较低功率状态，以防止在计算设备低于功率上限的情况下违反功率上限或较高功率状态。