Hierarchical Sparse Dictionary Learning (HiSDL) for Heterogeneous High-Dimensional Time Series
    1.
    发明申请
    Hierarchical Sparse Dictionary Learning (HiSDL) for Heterogeneous High-Dimensional Time Series 有权
    用于异构高维时间序列的分层稀疏词典学习(HiSDL)

    公开(公告)号:US20160012334A1

    公开(公告)日:2016-01-14

    申请号:US14794487

    申请日:2015-07-08

    Abstract: A system, method and computer program product for hierarchical sparse dictionary learning (“HiSDL”) to construct a learned dictionary regularized by an a priori over-complete dictionary, includes providing at least one a priori over-complete dictionary for regularization, performing sparse coding of the at least one a priori over-complete dictionary to provide a sparse coded dictionary, using a processor, updating the sparse coded dictionary with regularization using at least one auxiliary variable to provide a learned dictionary, determining whether the learned dictionary converges to an input data set, and outputting the learned dictionary regularized by the at least one a priori over-complete dictionary when the learned dictionary converges to the input data set. The system and method includes, when the learned dictionary lacks convergence, repeating the steps of performing sparse coding, updating the sparse coded dictionary, and determining whether the learned dictionary converges to the input data set.

    Abstract translation: 一种用于分层稀疏字典学习(“HiSDL”)的系统,方法和计算机程序产品,用于构建由先验过完整字典正规化的学习字典,包括提供至少一个用于正则化的先验过完整字典,执行稀疏编码 的所述至少一个先验过完整字典以提供稀疏编码字典,使用处理器,使用至少一个辅助变量更新所述稀疏编码字典,以提供学习字典,确定所学习的辞典是否收敛到输入 数据集,并且当学习的词典收敛到输入数据集时,输出由所述至少一个先验过完整词典正规化的学习辞典。 该系统和方法包括:当学习词典缺少收敛时,重复进行稀疏编码,更新稀疏编码词典,确定学习词典是否收敛到输入数据集的步骤。

    HETEROGENEOUS LOG ANALYSIS
    2.
    发明申请
    HETEROGENEOUS LOG ANALYSIS 审中-公开
    异质日志分析

    公开(公告)号:US20150094959A1

    公开(公告)日:2015-04-02

    申请号:US14503549

    申请日:2014-10-01

    CPC classification number: G01V99/005

    Abstract: A method and system are provided for heterogeneous log analysis. The method includes performing hierarchical log clustering on heterogeneous logs to generate a log cluster hierarchy for the heterogeneous logs. The method further includes performing, by a log pattern recognizer device having a processor, log pattern recognition on the log cluster hierarchy to generate log pattern representations. The method also includes performing log field analysis on the log pattern representations to generate log field statistics. The method additionally includes performing log indexing on the log pattern representations to generate log indexes.

    Abstract translation: 提供了一种用于异构对数分析的方法和系统。 该方法包括在异构日志上执行分层日志聚类,以生成异类日志的日志群集层次结构。 该方法还包括通过具有处理器的日志模式识别器装置执行日志簇层级上的日志模式识别以产生日志模式表示。 该方法还包括对日志模式表示执行日志字段分析以生成日志字段统计。 该方法还包括对日志模式表示执行日志索引以生成日志索引。

    SYSTEM AND METHOD FOR PROFILING REQUESTS IN SERVICE SYSTEMS
    4.
    发明申请
    SYSTEM AND METHOD FOR PROFILING REQUESTS IN SERVICE SYSTEMS 有权
    在服务系统中分配要求的系统和方法

    公开(公告)号:US20160063398A1

    公开(公告)日:2016-03-03

    申请号:US14839363

    申请日:2015-08-28

    Abstract: A system and method for profiling a request in a service system with kernel events including a pre-processing module configured to obtain kernel event traces from the service system and determine starting and ending communication pairs of a request path for a request. A learning module is configured to learn pairwise relationships between the starting and ending communication pairs of training traces of sequential requests. A generation module is configured to generate communication paths for the request path from the starting and ending communication pairs of testing traces of concurrent requests using a heuristic procedure that is guided by the learned pairwise relationships and generate the request path for the request from the communication paths. The system and method precisely determine request paths for applications in a distributed system from kernel event traces even when there are numerous concurrent requests.

    Abstract translation: 一种用于在具有内核事件的服务系统中对请求进行分析的系统和方法,所述内核事件包括预处理模块,所述预处理模块被配置为从所述服务系统获取内核事件跟踪并且确定请求的请求路径的起始和结束通信对。 学习模块被配置为学习顺序请求的训练轨迹的开始和结束通信对之间的成对关系。 生成模块被配置为使用由所学习的成对关系指导的启发式过程从并发请求的测试跟踪的起始和结束通信对生成针对请求路径的通信路径,并且从通信路径生成针对请求的请求路径 。 即使有许多并发请求,系统和方法也可以精确地确定来自内核事件跟踪的分布式系统中应用程序的请求路径。

    High-order semi-Restricted Boltzmann Machines and Deep Models for accurate peptide-MHC binding prediction
    6.
    发明申请
    High-order semi-Restricted Boltzmann Machines and Deep Models for accurate peptide-MHC binding prediction 审中-公开
    高阶半限制Boltzmann机器和深度模型用于准确的肽-MHC结合预测

    公开(公告)号:US20150278441A1

    公开(公告)日:2015-10-01

    申请号:US14512332

    申请日:2014-10-10

    CPC classification number: G16B40/00 G06N20/00 G16B20/00

    Abstract: A method for peptide binding prediction includes receiving a peptide sequence descriptor and descriptors of contacting amino acids on major histocompatibility complex (MHC) protein-peptide interaction structure; generating a model with an ensemble of high order neural network; pre-training the model by high order semi-restricted Boltzmann machine (RBM) or high-order denoising autoencoder; and generating a prediction as a binary output or continuous output with initial model parameters pre-trained using binary output data if available. A systematic learning method for leveraging high-order interactions/associations among items for better collaborative filtering and item recommendation.

    Abstract translation: 肽结合预测的方法包括接收肽序列描述符和在主要组织相容性复合体(MHC)蛋白 - 肽相互作用结构上接触氨基酸的描述符; 产生具有高阶神经网络集合的模型; 使用高阶半限制玻尔兹曼(RBM)或高阶去噪自动编码器对该模型进行预训练; 并且如果可用,则使用二进制输出数据预训练的初始模型参数生成作为二进制输出或连续输出的预测。 一种系统的学习方法,用于利用项目之间的高阶交互/关联,以实现更好的协同过滤和项目推荐。

    ONLINE SPARSE REGULARIZED JOINT ANALYSIS FOR HETEROGENEOUS DATA
    7.
    发明申请
    ONLINE SPARSE REGULARIZED JOINT ANALYSIS FOR HETEROGENEOUS DATA 审中-公开
    在异常数据的在线小数定期联合分析

    公开(公告)号:US20150095490A1

    公开(公告)日:2015-04-02

    申请号:US14503562

    申请日:2014-10-01

    CPC classification number: H04L41/145 H04L41/064

    Abstract: A method and system are provided for online sparse regularized joint analysis for heterogeneous data. The method generates a latent space model modeling a latent space in which correlation information is encoded for a plurality of heterogeneous data points at respective time instants, responsive to respective energy-preserving projections and structure-preserving projections of the data points in the latent space. The method performs online anomaly detection on a current one of the data points responsive to the encoded correlation information for respective ones of the energy-preserving projections and structure-preserving projections for a previous one of the data points without anomaly. The method generates an alarm responsive to a detection of an anomaly for the current one of the data points. The method updates the latent space model for the current one of the data points, by a processor-based online model updater, responsive to a lack of the detection of the anomaly.

    Abstract translation: 提供了异构数据的在线稀疏正则化联合分析的方法和系统。 该方法响应于相应的能量保留投影和潜在空间中的数据点的结构保留投影,产生潜在空间模型,潜在空间模型对潜在空间建模,其中相应信息针对各个时刻的多个异质数据点进行编码。 该方法响应于编码的相关信息,对于没有异常的前一个数据点的能量保留投影和结构保留投影,对当前一个数据点进行在线异常检测。 该方法响应于对当前数据点的异常的检测而产生报警。 该方法通过基于处理器的在线模型更新器来更新当前一个数据点的潜在空间模型,响应于缺少异常检测。

    Heterogeneous log analysis
    8.
    发明授权

    公开(公告)号:US10114148B2

    公开(公告)日:2018-10-30

    申请号:US14503549

    申请日:2014-10-01

    Abstract: A method and system are provided for heterogeneous log analysis. The method includes performing hierarchical log clustering on heterogeneous logs to generate a log cluster hierarchy for the heterogeneous logs. The method further includes performing, by a log pattern recognizer device having a processor, log pattern recognition on the log cluster hierarchy to generate log pattern representations. The method also includes performing log field analysis on the log pattern representations to generate log field statistics. The method additionally includes performing log indexing on the log pattern representations to generate log indexes.

    System and method for profiling requests in service systems
    10.
    发明授权
    System and method for profiling requests in service systems 有权
    在服务系统中分析请求的系统和方法

    公开(公告)号:US09367821B2

    公开(公告)日:2016-06-14

    申请号:US14839363

    申请日:2015-08-28

    Abstract: A system and method for profiling a request in a service system with kernel events including a pre-processing module configured to obtain kernel event traces from the service system and determine starting and ending communication pairs of a request path for a request. A learning module is configured to learn pairwise relationships between the starting and ending communication pairs of training traces of sequential requests. A generation module is configured to generate communication paths for the request path from the starting and ending communication pairs of testing traces of concurrent requests using a heuristic procedure that is guided by the learned pairwise relationships and generate the request path for the request from the communication paths. The system and method precisely determine request paths for applications in a distributed system from kernel event traces even when there are numerous concurrent requests.

    Abstract translation: 一种用于在具有内核事件的服务系统中对请求进行分析的系统和方法,所述内核事件包括预处理模块,所述预处理模块被配置为从所述服务系统获取内核事件跟踪并且确定请求的请求路径的起始和结束通信对。 学习模块被配置为学习顺序请求的训练轨迹的开始和结束通信对之间的成对关系。 生成模块被配置为使用由所学习的成对关系指导的启发式过程从并发请求的测试跟踪的起始和结束通信对生成针对请求路径的通信路径,并且从通信路径生成针对请求的请求路径 。 即使有许多并发请求,系统和方法也可以精确地确定来自内核事件跟踪的分布式系统中应用程序的请求路径。

Patent Agency Ranking