会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 2. 发明授权
    • System for internet scale visualization and detection of performance events
    • 用于互联网规模可视化和性能事件检测的系统
    • US08671183B2
    • 2014-03-11
    • US12967869
    • 2010-12-14
    • Shobha VenkataramanJeffrey PangSubhabrata SenOliver Spatscheck
    • Shobha VenkataramanJeffrey PangSubhabrata SenOliver Spatscheck
    • H04L12/26
    • H04L43/045H04L43/0852
    • A system for visualization of performance measurements is disclosed. The system may include an electronic data processor configured to receive a stream of the performance measurements and select a maximum number of leaf nodes of a plurality of nodes for use in an adaptive decision tree. Additionally, the electronic processor may be configured to determine a depth of each branch in the adaptive decision tree needed to differentiate performance among internet protocol addresses in an internet protocol prefix of each node. Each of the plurality of nodes may be annotated with a predicted latency category and the processor may be configured to generate the adaptive decision tree based on the maximum number of leaf nodes selected, the depth of each branch determined, the predicted latency category, and on the stream of performance measurements associated with the network. Moreover, the processor may display the adaptive decision tree.
    • 公开了用于可视化性能测量的系统。 该系统可以包括电子数据处理器,其被配置为接收性能测量的流并且选择用于自适应决策树中的多个节点的最大数量的叶节点。 此外,电子处理器可以被配置为确定在每个节点的因特网协议前缀中的互联网协议地址之间区分性能所需的自适应决策树中的每个分支的深度。 可以利用预测的等待时间类别对多个节点中的每一个进行注释,并且处理器可以被配置为基于所选择的叶节点的最大数目,所确定的每个分支的深度,预测的等待时间类别和开启来生成自适应决策树 与网络相关的性能测量流。 此外,处理器可以显示自适应决策树。
    • 3. 发明授权
    • Methods and apparatus to implement scalable routing in network communication systems
    • 在网络通信系统中实现可扩展路由的方法和装置
    • US08670351B2
    • 2014-03-11
    • US13531018
    • 2012-06-22
    • Mohammad HajiaghayiMohammad Hossein BateniAlexandre GerberSubhabrata Sen
    • Mohammad HajiaghayiMohammad Hossein BateniAlexandre GerberSubhabrata Sen
    • H04L12/46
    • H04L45/00H04L45/123H04L45/125
    • An example method involves for a first virtual private network (VPN) installed on a candidate hub router, selecting a first spoke-to-hub assignment solution having a first least memory utilization cost to assign the candidate hub router a quantity of first virtual private edge (VPE) routers serving the first VPN; for a second VPN installed on the candidate hub router, selecting a second spoke-to-hub assignment solution having a second least memory utilization cost to assign the candidate hub router a quantity of second VPE routers serving the second VPN; determining third least memory utilization costs to assign the candidate hub router to a quantity of the first VPE routers, and fourth least memory utilization costs to assign the candidate hub router to a quantity of the second VPE routers; and selecting the first or second spoke-to-hub assignment solution for the candidate hub router based on the least memory utilization costs.
    • 示例性方法涉及安装在候选集线器路由器上的第一虚拟专用网络(VPN),选择具有第一最小存储器利用成本的第一分散对集线器分配解决方案以分配候选集线器路由器数量的第一虚拟私有边缘 (VPE)路由器服务第一个VPN; 对于安装在所述候选集线器路由器上的第二VPN,选择具有第二最小存储器利用成本的第二辐射对集线器分配解决方案来为所述候选集线器路由器分配服务于所述第二VPN的第二VPE路由器的数量; 确定将所述候选集线器路由器分配给所述第一VPE路由器的数量的第三最小存储器利用成本以及将所述候选集线器路由器分配给所述第二VPE路由器的数量的第四最小存储器利用成本; 以及基于所述最小存储器利用成本为所述候选集线器路由器选择所述第一或第二辐条对集线器分配解决方案。
    • 7. 发明授权
    • Scalable traffic classifier and classifier training system
    • 可扩展流量分类器和分类器训练系统
    • US08311956B2
    • 2012-11-13
    • US12539430
    • 2009-08-11
    • Subhabrata SenNicholas DuffieldPatrick HaffnerJeffrey ErmanYu Jin
    • Subhabrata SenNicholas DuffieldPatrick HaffnerJeffrey ErmanYu Jin
    • G06F15/18
    • G06N99/005
    • A traffic classifier has a plurality of binary classifiers, each associated with one of a plurality of calibrators. Each calibrator trained to translate an output score of the associated binary classifier into an estimated class probability value using a fitted logistic curve, each estimated class probability value indicating a probability that the packet flow on which the output score is based belongs to the traffic class associated with the binary classifier associated with the calibrator. The classifier training system configured to generate a training data based on network information gained using flow and packet sampling methods. In some embodiments, the classifier training system configured to generate reduced training data sets, one for each traffic class, reducing the training data related to traffic not associated with the traffic class.
    • 流量分类器具有多个二进制分类器,每个二进制分类器与多个校准器之一相关联。 每个校准器被训练成使用拟合的逻辑曲线将相关联的二进制分类器的输出得分转换成估计的类概率值,每个估计的类概率值指示输出得分所基于的分组流的概率属于相关联的流量类别 与校准器相关联的二进制分类器。 分类器训练系统被配置为基于使用流和分组采样方法获得的网络信息生成训练数据。 在一些实施例中,分类器训练系统被配置为生成减少的训练数据集,每个业务类别一个,减少与业务类别不相关的业务相关的训练数据。