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
    • Cost evaluation and prediction
    • 成本评估与预测
    • US08682633B2
    • 2014-03-25
    • US13516884
    • 2010-11-17
    • Tsuyoshi IdeHiroki Yanagisawa
    • Tsuyoshi IdeHiroki Yanagisawa
    • G06F17/50
    • G01C21/3469
    • A mechanism is provided for enabling prediction of a cost between an origin and a destination even in the case of insufficient past route information. Data D, which includes an origin, a destination, and information on cost between these points, is prepared as well as a subroutine for calculating cost ce along an arbitrary link e on the basis of the set along with a variable denoted by fe. In the first step, the minimum cost route is found from the current {fe} with respect to all pairs of the origin and the destination included in the data D, thereby forming transformed data D′. {fe} is recalculated by using the above subroutine from D′ by computer processing and then compared with {fe} calculated last time. If a change is equal to or greater than a threshold, control returns to finding the minimum cost route. Otherwise, {fe} is fixed.
    • 提供了一种用于能够预测原始和目的地之间的成本的机制,即使在过去的路线信息不足的情况下也是如此。 准备包括原点,目的地和这些点之间的成本的信息的数据D以及用于根据该集合以及由fe表示的变量来计算任意链路e的成本ce的子程序。 在第一步骤中,从包含在数据D中的原始对象和目的地的所有目标对{fe}找到最小成本路线,从而形成变换数据D'。 通过计算机处理使用D'的上述子程序重新计算{fe},然后与上次计算的{fe}进行比较。 如果更改等于或大于阈值,则控制返回找到最小成本路线。 否则,{fe}是固定的。
    • 5. 发明授权
    • Method and system for detecting difference between plural observed results
    • 检测多个观察结果差异的方法和系统
    • US07849124B2
    • 2010-12-07
    • US12264556
    • 2008-11-04
    • Tsuyoshi Ide
    • Tsuyoshi Ide
    • G06F17/15
    • G05B23/024
    • A method and system for analyzing time series data. In an embodiment, a loop is executed and terminated upon a specified maximum number of iterations of the loop being performed or upon a difference between scores in successive iterations of the loop not being greater than a specified tolerance, wherein the score in each iteration is calculated as function of an absolute value of a difference between respective cumulative probability values of first and second cumulative probability distributions which are generated from respectively first and second time series data sets. In an embodiment, time series data is processed in a sequence of time periods, wherein a combined cumulative probability distribution is generated in each time period by combining a cumulative probability distribution of new time series data with previously combined cumulative probability distribution data according to a ratio of the number of new to previous observed values.
    • 一种用于分析时间序列数据的方法和系统。 在一个实施例中,循环被执行并且在所执行的循环的指定最大迭代次数或循环的连续迭代中的得分之间的差不大于指定的公差的情况下终止,其中计算每次迭代中的得分 作为从分别的第一和第二时间序列数据集生成的第一和第二累积概率分布的各个累积概率值之间的差的绝对值的函数。 在一个实施例中,以时间序列的顺序对时间序列数据进行处理,其中通过将新的时间序列数据的累积概率分布与先前组合的累积概率分布数据相结合,在每个时间周期内产生组合累积概率分布 的新到先前观察值的数量。
    • 6. 发明授权
    • Information providing method, information providing system, and information server apparatus
    • 信息提供方法,信息提供系统和信息服务器装置
    • US07752257B2
    • 2010-07-06
    • US10477970
    • 2002-05-09
    • Tsuyoshi IdeHiroshi UdagawaChizuru MakitaIchiro UjiieMasato Nakamura
    • Tsuyoshi IdeHiroshi UdagawaChizuru MakitaIchiro UjiieMasato Nakamura
    • G06F15/16G06F17/30
    • G06F17/30867
    • An information serving system that includes an information device capable of setting a user identifier carrying a medium type indicating an information type the information device is compatible with and identifying an information-provided user and also capable of connection to a network. An information serving device to which the information device is connected via the network, the information serving device includes databases having recorded therein, in association with each other, user profile data indicating information to be provided correspondingly to a user identifier, and content data associated with a medium type and information genre, respectively, and a request handling computer which searches, upon request from the information device, the database for content data to acquire the content data and supplies the information device with the content data as a one of the medium type the information device is compatible with.
    • 一种信息服务系统,包括能够设置携带介质类型的用户标识符的信息装置,所述媒体类型指示信息装置兼容的信息类型,并且识别信息提供的用户并且还能够连接到网络。 信息服务装置,通过网络与信息装置连接的信息服务装置,所述信息服务装置包括记录在其中的数据库,所述信息服务装置彼此相关联地指示要对应于用户标识符提供的信息的用户简档数据,以及与 媒体类型和信息类型,以及请求处理计算机,其根据来自信息装置的请求,搜索用于获取内容数据的内容数据的数据库,并且向信息装置提供内容数据作为媒体类型之一 信息设备兼容。
    • 7. 发明授权
    • Pairwise symmetry decomposition method for generalized covariance analysis
    • 用于广义协方差分析的成对对称分解法
    • US07702714B2
    • 2010-04-20
    • US11548278
    • 2006-10-10
    • Tsuyoshi Ide
    • Tsuyoshi Ide
    • G06F17/15
    • G06F17/18
    • The present invention provides a system for evaluating a correlation between a plurality of time-series data. The system includes a calculating section which calculates characteristic quantities indicating symmetry of a diagram drawn by a graph, on which data values included in the plurality of time-series data are plotted in a multidimensional space in which each coordinate axis represents the data value of each time-series data; and an evaluating section which evaluates the correlation between the plurality of time-series data, based on the calculated characteristic quantities.
    • 本发明提供一种用于评估多个时间序列数据之间的相关性的系统。 该系统包括计算部分,其计算指示由图形绘制的图形的对称性的特征量,其中包括在多个时间序列数据中的数据值被绘制在多维空间中,其中每个坐标轴表示每个坐标轴的数据值 时间序列数据; 以及评价部,其基于计算出的特征量来评价所述多个时间序列数据之间的相关性。
    • 8. 发明申请
    • METHOD AND SYSTEM FOR DETECTING DIFFERENCE BETWEEN PLURAL OBSERVED RESULTS
    • 用于检测多个观察结果之间的差异的方法和系统
    • US20090132626A1
    • 2009-05-21
    • US12264556
    • 2008-11-04
    • TSUYOSHI IDE
    • TSUYOSHI IDE
    • G06F7/64
    • G05B23/024
    • A method and system for analyzing time series data. In an embodiment, a loop is executed and terminated upon a specified maximum number of iterations of the loop being performed or upon a difference between scores in successive iterations of the loop not being greater than a specified tolerance, wherein the score in each iteration is calculated as function of an absolute value of a difference between respective cumulative probability values of first and second cumulative probability distributions which are generated from respectively first and second time series data sets. In an embodiment, time series data is processed in a sequence of time periods, wherein a combined cumulative probability distribution is generated in each time period by combining a cumulative probability distribution of new time series data with previously combined cumulative probability distribution data according to a ratio of the number of new to previous observed values.
    • 一种用于分析时间序列数据的方法和系统。 在一个实施例中,循环被执行并且在所执行的循环的指定最大迭代次数或循环的连续迭代中的得分之间的差不大于指定的公差的情况下终止,其中计算每次迭代中的得分 作为从分别的第一和第二时间序列数据集生成的第一和第二累积概率分布的各个累积概率值之间的差的绝对值的函数。 在一个实施例中,以时间序列的顺序对时间序列数据进行处理,其中通过将新的时间序列数据的累积概率分布与先前组合的累积概率分布数据相结合,在每个时间周期内产生组合累积概率分布 的新到先前观察值的数量。
    • 9. 发明授权
    • Scoring method for correlation anomalies
    • 相关异常评分方法
    • US07529991B2
    • 2009-05-05
    • US11668745
    • 2007-01-30
    • Tsuyoshi IdeShoko Suzuki
    • Tsuyoshi IdeShoko Suzuki
    • G01R31/28
    • G06K9/6253
    • Within aspects of the present invention, correlation anomalies are calculated in four stages for a reference data set, and a target data set, respectively, the four stages are: Initially, a similarity matrix K of the variables to be diagnosed is calculated. This similarity matrix is embedded in a low-dimensional vector space in order to calculate and obtain the coordinates {z1, . . . zp} for each variable. Next, an energy value {e1, . . . ep} is calculated per variable from calculated coordinates. Lastly, a comparison is made of the energy values that have been calculated for the target data set with the energy values of that have been calculated for the reference data set in order to determine the degree of correlation anomalies that has occurred between the two data sets.
    • 在本发明的方面中,针对参考数据集的四个阶段计算相关异常,并且四个阶段的目标数据集分别是:首先,计算待诊断的变量的相似度矩阵K. 该相似性矩阵嵌入在低维向量空间中,以便计算和获得坐标{z1,...。 。 。 zp}为每个变量。 接下来,能量值{e1,... 。 。 每个变量从计算坐标计算ep}。 最后,比较已针对目标数据集计算出的能量值,其能量值已针对参考数据集计算,以便确定两个数据集之间发生的相关异常程度 。