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
    • 7. 发明授权
    • Method and system for feature interaction detection in a telecommunication network
    • 电信网络中特征交互检测的方法和系统
    • US06185519B2
    • 2001-02-06
    • US09204019
    • 1998-12-01
    • Fuchun Joseph LinAbhrajit GhoshHong Liu
    • Fuchun Joseph LinAbhrajit GhoshHong Liu
    • G06N500
    • H04Q3/0041
    • Methods and systems disclosed efficiently detect potential interactions between features in a telecommunications network. The methods and systems specify AIN (Advanced Intelligent Network) and switch-based features and detect their interactions when present within a feature package provided to a single subscriber. The methodology supports the assumption that each feature is created without the knowledge of other features, and that each feature is specified as a “black box,” i.e., nothing is known about its internal logic except its input/output behaviors. The invention models a call environment, models two or more features, and combines the call variable usage for each feature. Methods then compare the combined call variable usages to detect potential feature interactions. The invention assists a service mediator in the tasks of detecting potential interactions among AIN features provided by different third party service providers, and detecting potential interactions between a third party service provider's AIN features and switch-based features.
    • 公开的方法和系统有效地检测电信网络中的特征之间的潜在交互。 该方法和系统指定AIN(高级智能网络)和基于交换机的功能,并在提供给单个用户的功能包中存在时检测其交互。 该方法支持假设每个特征是在没有其他特征的知识的情况下创建的,并且每个特征被指定为“黑匣子”,即,除了其输入/输出行为之外,其内部逻辑除外。 本发明建模一个呼叫环境,建立两个或多个特征,并组合每个功能的呼叫变量使用。 然后,方法比较组合的调用变量用法以检测潜在的特征相互作用。 本发明有助于服务调解员检测由不同第三方服务提供商提供的AIN特征之间的潜在交互,并检测第三方服务提供商的AIN特征和基于交换机的功能之间的潜在交互。
    • 9. 发明授权
    • System and method for spammer host detection from network flow data profiles
    • 从网络流数据配置文件中检测垃圾邮件主机的系统和方法
    • US08769677B2
    • 2014-07-01
    • US13547174
    • 2012-07-12
    • Akshay VashistYitzchak M. GottliebAbhrajit GhoshYukiko SawayaAyumu Kubota
    • Akshay VashistYitzchak M. GottliebAbhrajit GhoshYukiko SawayaAyumu Kubota
    • G06F11/00
    • H04L63/101H04L51/12H04L63/1425
    • A system and method for spammer host detection from network flow data profiles comprises constructing one or more cluster profiles and detecting spammer hosts. Construction cluster profiles comprises observing network flow data from one or more hosts; for each host, representing the network flow data associated with the host as a multidimensional vector; clustering the vectors of the hosts into the plurality of cluster profiles; annotating each cluster profile using at least one of black lists and white lists; and calculating a confidence in each cluster profile annotation. Detecting spammer hosts comprises observing the network flow data from a new host; representing the network flow data associated with the new host as a multidimensional vector, and placing the new multidimensional vector of the new host into one cluster profile of the one or more cluster profiles.
    • 用于从网络流数据简档发送垃圾邮件主机检测的系统和方法包括构建一个或多个集群简档并检测垃圾邮件发送者主机。 构建集群配置文件包括观察来自一个或多个主机的网络流数据; 对于每个主机,将与主机相关联的网络流数据表示为多维向量; 将主机的向量聚类成多个集群简档; 使用黑名单和白名单中的至少一个来标注每个群集简档; 并计算每个聚类配置文件注释的置信度。 检测垃圾邮件发送者主机包括观察来自新主机的网络流数据; 将与新主机相关联的网络流数据表示为多维向量,以及将新主机的新多维向量放置到一个或多个集群简档的一个集群简档中。