MULTIPLE IMPUTATION OF MISSING DATA IN MULTI-DIMENSIONAL RETAIL SALES DATA SETS VIA TENSOR FACTORIZATION
    1.
    发明申请
    MULTIPLE IMPUTATION OF MISSING DATA IN MULTI-DIMENSIONAL RETAIL SALES DATA SETS VIA TENSOR FACTORIZATION 有权
    多维零售销售数据丢失数据的多次打印通过传感器制造

    公开(公告)号:US20130036082A1

    公开(公告)日:2013-02-07

    申请号:US13204237

    申请日:2011-08-05

    IPC分类号: G06N5/02

    CPC分类号: G06Q30/00

    摘要: A system, method and computer program product provides for multiple imputation of missing data elements in retail data sets used for modeling and decision-support applications based on the multi-dimensional, tensor structure of the data sets, and a fast, scalable scheme is implemented that is suitable for large data sets. The method generates multiple imputations comprising a set of complete data sets each containing one of a plurality of imputed realizations for the missing data values in the original data set, so that the variability in the magnitudes of these missing data values can be captured for subsequent statistical analysis. The method is based on the multi-dimensional structure of the retail data sets incorporating tensor factorization, that in a preferred embodiment can be implemented using fast, scalable imputation methods suitable for large data sets, to obtain multiple complete data sets in which the original missing values are replaced by various imputed values.

    摘要翻译: 基于数据集的多维,张量结构,系统,方法和计算机程序产品提供了用于建模和决策支持应用的零售数据集中的丢失数据元素的多个插补,并且实现了快速,可扩展的方案 这适用于大型数据集。 该方法生成包括一组完整数据集的多个插补,每组完整数据集包含原始数据集中缺失数据值的多个插补实现之一,从而可以捕获这些丢失数据值的大小的可变性,用于后续统计 分析。 该方法基于包含张量因子分解的零售数据集的多维结构,在优选实施例中可以使用适用于大数据集的快速,可缩放的插补方法来实现,以获得多个完整数据集,其中原始丢失 值被各种估算值取代。

    Multiple imputation of missing data in multi-dimensional retail sales data sets via tensor factorization
    2.
    发明授权
    Multiple imputation of missing data in multi-dimensional retail sales data sets via tensor factorization 有权
    通过张量因子分解对多维零售销售数据集中的数据进行多重插补

    公开(公告)号:US08818919B2

    公开(公告)日:2014-08-26

    申请号:US13204237

    申请日:2011-08-05

    IPC分类号: G06F15/18 G06Q30/00

    CPC分类号: G06Q30/00

    摘要: A system, method and computer program product provides for multiple imputation of missing data elements in retail data sets used for modeling and decision-support applications based on the multi-dimensional, tensor structure of the data sets, and a fast, scalable scheme is implemented that is suitable for large data sets. The method generates multiple imputations comprising a set of complete data sets each containing one of a plurality of imputed realizations for the missing data values in the original data set, so that the variability in the magnitudes of these missing data values can be captured for subsequent statistical analysis. The method is based on the multi-dimensional structure of the retail data sets incorporating tensor factorization, that in a preferred embodiment can be implemented using fast, scalable imputation methods suitable for large data sets, to obtain multiple complete data sets in which the original missing values are replaced by various imputed values.

    摘要翻译: 基于数据集的多维,张量结构,系统,方法和计算机程序产品提供了用于建模和决策支持应用的零售数据集中的丢失数据元素的多个插补,并且实现了快速,可扩展的方案 这适用于大型数据集。 该方法生成包括一组完整数据集的多个插补,每组完整数据集包含原始数据集中的丢失数据值的多个插补实现之一,从而可以捕获这些丢失数据值的幅度的可变性,用于随后的统计 分析。 该方法基于包含张量因子分解的零售数据集的多维结构,在优选实施例中可以使用适用于大数据集的快速,可缩放的插补方法来实现,以获得多个完整数据集,其中原始丢失 值被各种估算值取代。

    INFERRING EMERGING AND EVOLVING TOPICS IN STREAMING TEXT
    3.
    发明申请
    INFERRING EMERGING AND EVOLVING TOPICS IN STREAMING TEXT 审中-公开
    在流动文字中传播新兴和演变主题

    公开(公告)号:US20130151525A1

    公开(公告)日:2013-06-13

    申请号:US13616403

    申请日:2012-09-14

    IPC分类号: G06F17/30

    CPC分类号: G06F17/2785 G06F16/316

    摘要: A method, system and computer program product for inferring topic evolution and emergence in a set of documents. In one embodiment, the method comprises forming a group of matrices using text in the documents, and analyzing these matrices to identify evolving topics and emerging topics. The matrices includes a matrix X identifying a multitude of words in each of the documents, a matrix W identifying a multitude of topics in each of the documents, and a matrix H identifying a multitude of words for each of the multitude of topics. These matrices are analyzed to identify the evolving and emerging topics. In an embodiment, two forms of temporal regularizers are used to help identify the evolving and emerging topics. In another embodiment, a two stage approach involving detection and clustering is used to help identify the evolving and emerging topics.

    摘要翻译: 一套用于推断主题演变和出现在一组文件中的方法,系统和计算机程序产品。 在一个实施例中,该方法包括使用文档中的文本形成一组矩阵,并且分析这些矩阵以识别演进主题和新兴主题。 矩阵包括识别每个文档中的多个单词的矩阵X,标识每个文档中的众多主题的矩阵W以及为每个主题识别多个单词的矩阵H。 对这些矩阵进行分析,以确定不断发展的新兴主题。 在一个实施例中,使用两种形式的时间正则化器来帮助识别不断发展和新兴的主题。 在另一个实施例中,使用涉及检测和聚类的两阶段方法来帮助识别不断发展和新兴的主题。

    MANAGING BACKUP DEVICE METADATA IN A HIGH AVAILABILITY DISK SUBSYSTEM
    4.
    发明申请
    MANAGING BACKUP DEVICE METADATA IN A HIGH AVAILABILITY DISK SUBSYSTEM 有权
    在高可用性盘库子系统中管理备份设备元数据

    公开(公告)号:US20110016260A1

    公开(公告)日:2011-01-20

    申请号:US12503242

    申请日:2009-07-15

    IPC分类号: G06F12/16 G06F12/00 G06F12/02

    摘要: A system includes a data storage device, a controller coupled with the data storage device, a backup device coupled with the controller for backing up a modified portion of data and volatile memory metadata stored by the controller, and a backup power source for powering the controller. The controller includes a pre-specified region of volatile memory for storing backup device metadata for managing a modified portion of data, the metadata comprising one or more intents corresponding to modified data written back to the data storage device. The controller is configured to invalidate the one or more intents. During a restore operation, the controller is configured to store the backup device metadata in the pre-specified region of volatile memory when a charge on the backup power source is at least a minimum threshold charge and to store the updated backup device metadata in the backup device during an interruption of power.

    摘要翻译: 系统包括数据存储设备,与数据存储设备耦合的控制器,与控制器耦合的备用设备,用于备份由控制器存储的数据的修改部分和易失性存储器元数据;以及用于为控制器供电的备用电源 。 所述控制器包括用于存储用于管理修改的数据部分的备份设备元数据的易失性存储器的预定区域,所述元数据包括对应于被写回数据存储设备的修改数据的一个或多个意图。 控制器被配置为使一个或多个意图无效。 在还原操作期间,当备用电源的费用至少为最小阈值电荷并且将更新的备份设备元数据存储在备份中时,控制器被配置为将备份设备元数据存储在易失性存储器的预定区域内 设备在电源中断期间。

    METHOD AND APPARATUS FOR THE SOLUTION DEPOSITION OF OXIDE
    5.
    发明申请
    METHOD AND APPARATUS FOR THE SOLUTION DEPOSITION OF OXIDE 审中-公开
    用于溶解氧化物沉积的方法和装置

    公开(公告)号:US20100200411A1

    公开(公告)日:2010-08-12

    申请号:US12369022

    申请日:2009-02-11

    IPC分类号: C25D5/10

    摘要: A metal and oxygen material such as a transparent electrically conductive oxide material is electro deposited onto a substrate in a solution deposition process. Process parameters are controlled so as to result in the deposition of a high quality layer of material which is suitable for use in a back reflector structure of a high efficiency photovoltaic device The deposition may be carried out in conjunction with a masking member which operates to restrict the deposition of the metal and oxygen material to specific portions of the substrate. In particular instances the deposition may be implemented in a continuous, roll-to-roll process. Further disclosed are semiconductor devices and components of semiconductor devices made by the present process, as well as apparatus for carrying out the process.

    摘要翻译: 在溶液沉积工艺中,将诸如透明导电氧化物材料的金属和氧材料电沉积到衬底上。 控制工艺参数以便导致适合用于高效光伏器件的后反射器结构的高质量材料层的沉积。沉积可以与操作以限制的掩模构件一起进行 金属和氧气材料沉积到衬底的特定部分。 在特定情况下,沉积可以以连续的卷对卷方式实施。 还公开了通过本方法制造的半导体器件和半导体器件的部件以及用于执行该过程的装置。

    METHOD AND SYSTEM FOR FIRMWARE UPGRADE OF A STORAGE SUBSYSTEM HOSTED IN A STORAGE VIRTUALIZATION ENVIRONMENT
    7.
    发明申请
    METHOD AND SYSTEM FOR FIRMWARE UPGRADE OF A STORAGE SUBSYSTEM HOSTED IN A STORAGE VIRTUALIZATION ENVIRONMENT 有权
    在存储虚拟化环境中存储的存储子系统的固件升级方法和系统

    公开(公告)号:US20120291021A1

    公开(公告)日:2012-11-15

    申请号:US13107157

    申请日:2011-05-13

    IPC分类号: G06F9/44

    摘要: A method and controller device for upgrading firmware in a virtualized storage environment having a virtual machine manager, guest virtual machines and a storage device. The method includes downloading a new firmware solution bundle to a first logical area of the storage device, and installing the new firmware containing the virtual machine manager and guest virtual machines. The installation includes moving the solution bundle to a scratch area carved out of a P-cache area in the storage device, extracting the new firmware, copying the new firmware to the first logical area, marking the first logical area as the Active area, and marking the second logical area as the Staging area. The method also includes rebooting the virtualized storage environment with the installed new firmware, committing to the new firmware if the installation is successful, and rolling back the firmware version from the new firmware to the current firmware if the installation is not successful.

    摘要翻译: 一种用于在具有虚拟机管理器,来宾虚拟机和存储设备的虚拟化存储环境中升级固件的方法和控制器设备。 该方法包括将新的固件解决方案包下载到存储设备的第一逻辑区域,以及安装包含虚拟机管理器和来宾虚拟机的新固件。 所述安装包括将所述解决方案束移动到从所述存储设备中的P-缓存区域雕刻的划痕区域,提取所述新固件,将所述新固件复制到所述第一逻辑区域,将所述第一逻辑区域标记为所述活动区域,以及 将第二个逻辑区域标记为分段区域。 该方法还包括使用已安装的新固件重新启动虚拟化存储环境,如果安装成功,则提交新固件,如果安装不成功,则将固件版本从新固件回滚到当前固件。

    Managing backup device metadata in a high availability disk subsystem
    8.
    发明授权
    Managing backup device metadata in a high availability disk subsystem 有权
    在高可用性磁盘子系统中管理备份设备元数据

    公开(公告)号:US08214610B2

    公开(公告)日:2012-07-03

    申请号:US12503242

    申请日:2009-07-15

    IPC分类号: G06F12/00 G06F13/00

    摘要: A system includes a data storage device, a controller coupled with the data storage device, a backup device coupled with the controller for backing up a modified portion of data and volatile memory metadata stored by the controller, and a backup power source for powering the controller. The controller includes a pre-specified region of volatile memory for storing backup device metadata for managing a modified portion of data, the metadata comprising one or more intents corresponding to modified data written back to the data storage device. The controller is configured to invalidate the one or more intents. During a restore operation, the controller is configured to store the backup device metadata in the pre-specified region of volatile memory when a charge on the backup power source is at least a minimum threshold charge and to store the updated backup device metadata in the backup device during an interruption of power.

    摘要翻译: 系统包括数据存储设备,与数据存储设备耦合的控制器,与控制器耦合的备用设备,用于备份由控制器存储的数据的修改部分和易失性存储器元数据;以及用于为控制器供电的备用电源 。 所述控制器包括用于存储用于管理修改的数据部分的备份设备元数据的易失性存储器的预定区域,所述元数据包括对应于被写回数据存储设备的修改数据的一个或多个意图。 控制器被配置为使一个或多个意图无效。 在还原操作期间,当备用电源的费用至少为最小阈值电荷并且将更新的备份设备元数据存储在备份中时,控制器被配置为将备份设备元数据存储在易失性存储器的预定区域内 设备在电源中断期间。