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
    • 1. 发明授权
    • Processing overlapping continuous queries
    • 处理重复的连续查询
    • US08055653B2
    • 2011-11-08
    • US11836567
    • 2007-08-09
    • Zhen LiuSrinivasan ParthasarathyAnand RanganathanHao Yang
    • Zhen LiuSrinivasan ParthasarathyAnand RanganathanHao Yang
    • G06F17/20G06F15/16
    • G06F17/30463G06F17/3046
    • An edge-covering based greedy method for shared filter ordering includes receiving a plurality of queries, wherein each query is a conjunction of filters, and each filter is shared across multiple queries of the plurality of queries, evaluating a unit price of each filter, evaluating, sequentially, each filter in order of a lowest to a highest unit price, to determine a value for each filter, and changing an ordering of the filters according to the values. An edge-covering based harmonic method for shared filter ordering includes receiving a plurality of queries, wherein each query is a conjunction of filters, and each filter is shared across multiple queries of the plurality of queries, evaluating a weight of each filter, evaluating, randomly, each filter having a probability inversely proportionally to its weight, to determine a value, and changing an ordering of the filters according to the values.
    • 用于共享过滤器排序的基于边缘覆盖的贪婪方法包括接收多个查询,其中每个查询是过滤器的结合,并且每个过滤器在多个查询的多个查询之间共享,评估每个过滤器的单价,评估 顺序地按每个过滤器按最低到最高单价的顺序,确定每个过滤器的值,并根据该值改变过滤器的排序。 用于共享过滤器排序的基于边缘覆盖的谐波方法包括接收多个查询,其中每个查询是过滤器的结合,并且每个过滤器在多个查询的多个查询之间共享,评估每个过滤器的权重, 随机地,每个滤波器具有与其权重成反比的概率,以确定值,并根据该值改变滤波器的排序。
    • 2. 发明申请
    • Processing Overlapping Continuous Queries
    • 处理重叠的连续查询
    • US20090043729A1
    • 2009-02-12
    • US11836567
    • 2007-08-09
    • Zhen LiuSrinivasan ParthasarathyAnand RanganathanHao Yang
    • Zhen LiuSrinivasan ParthasarathyAnand RanganathanHao Yang
    • G06F17/30
    • G06F17/30463G06F17/3046
    • An edge-covering based greedy method for shared filter ordering includes receiving a plurality of queries, wherein each query is a conjunction of filters, and each filter is shared across multiple queries of the plurality of queries, evaluating a unit price of each filter, evaluating, sequentially, each filter in order of a lowest to a highest unit price, to determine a value for each filter, and changing an ordering of the filters according to the values.An edge-covering based harmonic method for shared filter ordering includes receiving a plurality of queries, wherein each query is a conjunction of filters, and each filter is shared across multiple queries of the plurality of queries, evaluating a weight of each filter, evaluating, randomly, each filter having a probability inversely proportionally to its weight, to determine a value, and changing an ordering of the filters according to the values.
    • 用于共享过滤器排序的基于边缘覆盖的贪婪方法包括接收多个查询,其中每个查询是过滤器的结合,并且每个过滤器在多个查询的多个查询之间共享,评估每个过滤器的单价,评估 顺序地按每个过滤器按最低到最高单价的顺序,确定每个过滤器的值,并根据该值改变过滤器的排序。 用于共享过滤器排序的基于边缘覆盖的谐波方法包括接收多个查询,其中每个查询是过滤器的结合,并且每个过滤器在多个查询的多个查询之间共享,评估每个过滤器的权重, 随机地,每个滤波器具有与其权重成反比的概率,以确定值,并根据该值改变滤波器的排序。
    • 7. 发明授权
    • Configuring classifier trees and classifying data
    • 配置分类树和数据分类
    • US08666988B2
    • 2014-03-04
    • US12466101
    • 2009-05-14
    • Srinivasan ParthasarathyDeepak S. TuragaOlivier Verscheure
    • Srinivasan ParthasarathyDeepak S. TuragaOlivier Verscheure
    • G06F7/00G06F17/30
    • H04L51/12
    • According to an exemplary embodiment of the present invention, a method to configure a network of classifiers includes configuring a plurality of classifiers in a network of classifiers, such that the configuring associates a plurality of operating points with each output branch, associating a different quality profile with each output point for each output branch in the plurality of classifiers, and storing the configured network of classifiers and quality profile associations in the computer system to be used for classifying future input data according to the network configuration and quality profile association. Each classifier comprises executable code that classifies the data. Each of said classifiers has a plurality of the output branches that each output the data to another classifier. Each operating point comprises a probability of determining that a data item input to the classifier has a particular characteristic and a probability that said determination falsely detected the characteristic.
    • 根据本发明的示例性实施例,一种配置分类器网络的方法包括在分类器网络中配置多个分类器,使得所述配置将多个操作点与每个输出分支相关联,将不同质量分布 将多个分类器中的每个输出分支的每个输出点用于计算机系统中的分类器和质量配置文件关联的配置网络,以便根据网络配置和质量配置文件关联对未来的输入数据进行分类。 每个分类器包括对数据进行分类的可执行代码。 每个所述分类器具有多个输出分支,每个输出分支将数据输出到另一个分类器。 每个操作点包括确定输入到分类器的数据项具有特定特性的概率,以及所述确定错误地检测到该特性的概率。