利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

3 条记录 (耗时 0.018 秒)

    SCALABLE TRAFFIC CLASSIFIER AND CLASSIFIER TRAINING SYSTEM
    1.
    发明申请
    SCALABLE TRAFFIC CLASSIFIER AND CLASSIFIER TRAINING SYSTEM 有权
    可扩展的交通分类器和分类器培训系统

    公开(公告)号：US20130013542A1

    公开(公告)日：2013-01-10

    申请号：US13620668

    申请日：2012-09-14

    申请人： SUBHABRATA SEN ,  Nicholas duffield ,  Patrick Haffner ,  Jeffrey Erman ,  Yu Jin

    发明人： SUBHABRATA SEN ,  Nicholas duffield ,  Patrick Haffner ,  Jeffrey Erman ,  Yu Jin

    IPC分类号： G06F15/18 ,  G06N5/02

    CPC分类号： G06N99/005

    摘要： 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.

    摘要翻译： 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。