-
公开(公告)号：US09514022B1
公开(公告)日：2016-12-06
申请号：US13275607
申请日：2011-10-18
IPC分类号： G06F11/34
CPC分类号： G06F11/3447 , G06F11/00
摘要： A system and method for creating an accurate black-box model of a live storage system and for predicting performance of the storage system under a given workload is disclosed. An analytics engine determines a subset of counters that are relevant to performance of the storage system with respect to a particular output (e.g., throughput or latency) from performance data in counters of the storage system. Using the subset of counters, the analytics engine creates a workload signature for the storage system by using a recursive partitioning technique, such as a classification and regression tree. The analytics engine then creates the black-box model of the storage system performance by applying uncertainty measurement techniques, such as a Gaussian process, to the workload signature.
摘要翻译： 公开了一种用于创建实时存储系统的精确黑箱模型并用于在给定工作负载下预测存储系统的性能的系统和方法。 分析引擎确定与存储系统的计数器中的性能数据相关的特定输出（例如，吞吐量或延迟）与存储系统的性能相关的计数器的子集。 使用计数器子集，分析引擎通过使用递归分区技术（如分类和回归树）为存储系统创建工作负载签名。 然后，分析引擎通过对工作负载签名应用不确定性测量技术（例如高斯过程）来创建存储系统性能的黑盒模型。
-
公开(公告)号：US08903995B1
公开(公告)日：2014-12-02
申请号：US13553741
申请日：2012-07-19
申请人： Jayanta Basak , Vipul Mathur , Siddhartha Nandi , Srinivasan Narayanamurthy , Kaladhar Voruganti
发明人： Jayanta Basak , Vipul Mathur , Siddhartha Nandi , Srinivasan Narayanamurthy , Kaladhar Voruganti
IPC分类号： G06F15/16
CPC分类号： G06Q10/06 , H04L41/0636 , H04L43/08
摘要： A network server analyzes a change in the network, including performing a machine-learning analysis of an extrapolation space. The server accesses observed data from multiple counters that each record samples for a metric in the network. The server performs a CART (classification and regression tree) analysis of the observed data to select the counters whose metrics affect a target network performance, such as latency. The server estimates an extrapolation space based on the observed data for the selected counters. The server then performs a machine-learning analysis of the extrapolation space based on a kriging model of the selected counters.
摘要翻译： 网络服务器分析网络中的变化，包括执行外推空间的机器学习分析。 服务器访问来自多个计数器的观测数据，每个记录对网络中的度量进行记录采样。 服务器对观察到的数据执行CART（分类和回归树）分析，以选择其度量影响目标网络性能的计数器，例如延迟。 服务器根据所选计数器的观察数据估计外推空间。 然后，服务器基于所选计数器的克里金模型对外推空间进行机器学习分析。
-
公开(公告)号：US08219834B2
公开(公告)日：2012-07-10
申请号：US12539978
申请日：2009-08-12
申请人： Jayanta Basak , Pradip Bose , Alper Buyuktosunoglu , Anita Lungu
发明人： Jayanta Basak , Pradip Bose , Alper Buyuktosunoglu , Anita Lungu
CPC分类号： G06F1/3203
摘要： A mechanism is provided for predictively power gating a set of units within the data processing system. A second-level power gating controller monitors a set of events for each unit in a set of units within the data processing system. The second-level power gating controller identifies idle sequences of a predetermined set of cycles within the events from each unit where the unit is idle. The second-level power gating controller determines preceding sequences of a predetermined length that precede the idle sequences. The second-level power gating controller determines an accuracy of the preceding sequences. Responsive to the accuracy being above a threshold, the second-level power gating controller sends a permit command to a first-level power gating mechanism associated with the unit to permit power gating of the unit.
摘要翻译： 提供了用于在数据处理系统内预测性地选通一组单元的机构。 二级电源门控控制器监视数据处理系统内的一组单元中的每个单元的一组事件。 第二级电力门控控制器从单元空闲的每个单元的事件内识别预定的一组周期的空闲序列。 第二级电源门控控制器确定在空闲序列之前的预定长度的先前序列。 二级电源门控控制器确定前面的序列的精度。 响应于精度高于阈值，二级电源门控控制器向与该单元相关联的一级电源门控机构发送许可命令，以允许该单元的电源门控。
-
4.发明授权Methods, systems, and computer program products for a multi-resolution storage scheme for historical data 失效用于历史数据的多分辨率存储方案的方法，系统和计算机程序产品公开(公告)号：US07986848B2
公开(公告)日：2011-07-26
申请号：US11853063
申请日：2007-09-11
IPC分类号： G06K9/46
摘要： A method, system, and computer program product for a multi-resolution storage scheme for historical data are provided. The method includes dividing the historical data into a plurality of time frames and determining an amount of compression for each of the time frames, where at least two of the time frames have a different amount of compression. The method further includes applying the amount of compression to each of the time frames, resulting in multi-resolution historical data, and storing the multi-resolution historical data.
摘要翻译： 提供了一种用于历史数据的多分辨率存储方案的方法，系统和计算机程序产品。 该方法包括将历史数据划分为多个时间帧，并确定每个时间帧的压缩量，其中至少两个时间帧具有不同的压缩量。 该方法还包括将压缩量应用于每个时间帧，导致多分辨率历史数据，以及存储多分辨率历史数据。
-
公开(公告)号：US20090287509A1
公开(公告)日：2009-11-19
申请号：US12122142
申请日：2008-05-16
申请人： Jayanta Basak , Desmond Lim , Rashmi Singh
发明人： Jayanta Basak , Desmond Lim , Rashmi Singh
IPC分类号： G06Q40/00
摘要： Techniques for automating insurance claim processing are provided. The techniques include obtaining at least one rule from historical data, using the at least one rule to segment a dataset, wherein segmenting the dataset comprises using an iterative process involving a pattern classification technique, using the segmented dataset to determine if a claim can be automatically settled, and automatically settling a claim if it is determined that the claim can be automatically settled.
摘要翻译： 提供自动保险索赔处理的技术。 所述技术包括使用至少一个规则来从历史数据获得至少一个规则来分割数据集，其中分割数据集包括使用涉及模式分类技术的迭代过程，使用分割数据集来确定权利要求是否可以自动 如果确定声明可以自动结算，并自动结算索赔。
-
公开(公告)号：US07529720B2
公开(公告)日：2009-05-05
申请号：US10811275
申请日：2004-03-26
申请人： Jayanta Basak , Ravi Kothari
发明人： Jayanta Basak , Ravi Kothari
CPC分类号： G06K9/6293
摘要： Each individual classifier is based on the partial view of the data that is locally available. For the decision made by the classifiers to be consistent, the data sets available to the classifiers are sampled from the same (fixed though unknown) distribution. A test pattern is assumed to be observable across the classifiers. A combined classification is achieved based upon the posterior probabilities computed by, the individual classifiers. The posterior is computed for a test sample based on the posteriors provided by a subset of consistent classifiers.
摘要翻译： 每个单独的分类器都是基于本地可用数据的部分视图。 为了使分类器做出的决策一致，分类器可用的数据集从相同的（固定的但未知的）分布中进行采样。 假设测试模式在分类器之间是可观察的。 基于由单个分类器计算的后验概率来实现组合分类。 基于由一致分类器的子集提供的后验，针对测试样本计算后验。
-
公开(公告)号：US20080167837A1
公开(公告)日：2008-07-10
申请号：US11970003
申请日：2008-01-07
IPC分类号： G06F17/18
CPC分类号： G06K9/00503
摘要： A window size for outlier detection in a time series of a database system is determined. Strength values are calculated for data points using a set of window sizes, resulting at least in one set of strength values for each window size. The strength values increase as a distance between a value of a respective data point and a local mean value increases. For each set of strength values, a weighted sum is calculated based on the respective set of strength values. A weighting function is used to suppress the effect of largest strength values and a window size is selected based on the weighted sums.
摘要翻译： 确定数据库系统的时间序列中异常值检测的窗口大小。 使用一组窗口大小计算数据点的强度值，从而至少得到每个窗口大小的一组强度值。 随着各数据点的值和局部平均值之间的距离增加，强度值增加。 对于每组强度值，基于强度值的相应集合来计算加权和。 加权函数用于抑制最大强度值的影响，并且基于加权和选择窗口大小。
-
8.发明授权Dynamically compiling a list of solution documents for information technology queries 有权动态编译信息技术查询的解决方案文档列表公开(公告)号：US08983969B2
公开(公告)日：2015-03-17
申请号：US12504091
申请日：2009-07-16
申请人： Jayanta Basak , Dinesh Garg
发明人： Jayanta Basak , Dinesh Garg
CPC分类号： G06F17/30424
摘要： Techniques for dynamically compiling a list of one or more solution documents are provided. The techniques include receiving one or more questions, forming one or more of the one or more questions into one or more lists, wherein forming one or more questions into one or more lists comprises expressing each question in a compressed manner using one or more sets of one or more keywords, receiving input from a solution database, and using the one or more lists and input from a solution database to dynamically compile a list of one or more solution documents in connection with the one or more questions.
摘要翻译： 提供了用于动态编译一个或多个解决方案文档的列表的技术。 这些技术包括接收一个或多个问题，将一个或多个问题形成一个或多个问题到一个或多个列表中，其中将一个或多个问题形成到一个或多个列表中包括使用一组或多组列表以压缩方式表达每个问题 一个或多个关键字，从解决方案数据库接收输入，以及使用所述一个或多个列表和来自解决方案数据库的输入来动态地编译与所述一个或多个问题有关的一个或多个解决方案文档的列表。
-
公开(公告)号：US08681155B2
公开(公告)日：2014-03-25
申请号：US13584259
申请日：2012-08-13
申请人： Jayanta Basak
发明人： Jayanta Basak
IPC分类号： G06T11/20
CPC分类号： G06T11/20
摘要： Techniques for ranking nodes in a graph are provided. The techniques include computing resultant path strength between each pair of nodes in a polynomial time, determining a first node based on resultant path strength such that total path strength to the first node is a maximum value, iteratively determining a next node from the first node to which the resultant path strength is a maximum value and the node is not visited, and providing each determined node a unique rank value, and ranking the nodes in an order determined by the unique rank value of each node.
摘要翻译： 提供了用于对图中的节点进行排序的技术。 所述技术包括在多项式时间内计算每对节点之间的合成路径强度，基于所得到的路径强度来确定第一节点，使得到第一节点的总路径强度为最大值，迭代地确定从第一节点到下一个节点到 其中所得到的路径强度是最大值，并且节点不被访问，并且为每个确定的节点提供唯一的等级值，并且以由每个节点的唯一等级值确定的顺序对节点进行排序。
-
公开(公告)号：US08219833B2
公开(公告)日：2012-07-10
申请号：US12539941
申请日：2009-08-12
申请人： Jayanta Basak , Pradip Bose , Alper Buyuktosunoglu , Anita Lungu
发明人： Jayanta Basak , Pradip Bose , Alper Buyuktosunoglu , Anita Lungu
CPC分类号： G06F1/3203 , G06F11/3466 , Y02D10/34
摘要： A mechanism is provided for two-level guarded predictive power gating of a set of units within the data processing system. A success determines whether a unit within the set of units is power gated during a monitoring interval. If the unit is power gated, the success monitor determines whether a count of idle cycles for the unit is below a breakeven point. If the count is above the breakeven point, the success monitor increments a success efficiency counter. If the count is below the breakeven point, the success monitor determines whether the unit needs to be woke up. If the unit needs to be woke up, the success monitor increments a harmful efficiency counter. If the value of the harmful efficiency counter is less than the value from the success efficiency counter, the success monitor enables power gating for the unit via a first-level power-gating mechanism.
摘要翻译： 提供了一种用于数据处理系统内的一组单元的两级保护预测能力门控的机制。 一个成功的确定在一个监视间隔期间该单元组内的一个单元是否电源门控。 如果该单元是电源门控，则成功监视器确定该单元的空闲周期计数是否低于盈亏平衡点。 如果计数高于盈亏平衡点，则成功监视器会增加成功效率计数器。 如果计数低于盈亏平衡点，则成功监视器确定该单元是否需要醒来。 如果单位需要醒来，成功监测器会增加一个有害的效率计数器。 如果有害效率计数器的值小于成功效率计数器的值，则成功监视器可通过一级电源门控机构对单元进行功率门控。
-
-
-
-
-
-
-
-
-
搜索结果
41 条记录 (耗时 0.02 秒)
