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
    • 22. 发明申请
    • Information processing apparatus and method
    • 信息处理装置和方法
    • US20050119982A1
    • 2005-06-02
    • US10483149
    • 2003-01-21
    • Masato ItoJun Tani
    • Masato ItoJun Tani
    • G06K9/00G06K9/66G06N3/04G06G7/00G06F15/18H03F1/26G06F15/00H04B15/00G06N5/02G06F17/00
    • G06K9/00536G06N3/049
    • This invention relates to an information processing device and method that enable classification of a new time series pattern. A time series pattern N of a curve L (21) is inputted to an output layer (13) of a recurrent neural network 1. An intermediate layer (12) has already learned a predetermined time series pattern, and a weighting coefficient corresponding to that time series pattern is held in its neurons. The intermediate layer (12) calculates a parameter corresponding to the time series pattern N on the basis of the weighting coefficient and outputs the calculated parameter from parametric bias nodes (11-2). A comparator unit (31) compares a parameter of a learned pattern stored in a storage unit (32) with the parameter of the time series pattern N and thus classifies the time series pattern N. This invention can be applied to a robot.
    • 本发明涉及能够对新的时间序列模式进行分类的信息处理装置和方法。 曲线L(21)的时间序列图案N被输入到经常性神经网络1的输出层(13)。中间层(12)已经学习了预定的时间序列图案,并且与之对应的加权系数 时间序列模式保存在其神经元中。 中间层(12)基于加权系数计算与时间序列图形N对应的参数,并从参数偏差节点(11-2)输出计算出的参数。 比较器单元(31)将存储在存储单元(32)中的学习模式的参数与时间序列模式N的参数进行比较,并且对时间序列模式N进行分类。本发明可以应用于机器人。
    • 23. 发明授权
    • Information processing device, information processing method and program
    • 信息处理装置,信息处理方法和程序
    • US09280709B2
    • 2016-03-08
    • US13814170
    • 2011-08-02
    • Hirotaka SuzukiMasato Ito
    • Hirotaka SuzukiMasato Ito
    • G06F17/24G06K9/00G06K9/18G06F17/30
    • G06K9/00718G06F17/30796G06F17/30843G06F17/30852G06K9/18G06K2209/27
    • The present invention relates to an information processing device, an information processing method, and a program capable of easily adding an annotation to content.A feature amount extracting unit 21 extracts an image feature amount of each frame of an image of learning content and extracts word frequency information regarding frequency of appearance of each word in a description text describing a content of the image of the learning content (for example, a text of a caption) as a text feature amount of the description text. A model learning unit 22 learns an annotation model, which is a multi-stream HMM, by using an annotation sequence for annotation, which is a multi-stream including the image feature amount of each frame and the text feature amount. The present invention may be applied when adding the annotation to the content such as a television broadcast program, for example.
    • 本发明涉及一种信息处理设备,信息处理方法和能够容易地向内容添加注释的程序。 特征量提取单元21提取学习内容的图像的每帧的图像特征量,并且提取关于描述学习内容的图像的内容的描述文本中的每个单词的出现频率的词频信息(例如, 文字的文本)作为描述文本的文本特征量。 模型学习单元22通过使用注释的注释序列来学习作为多流HMM的注释模型,注释序列是包括每个帧的图像特征量和文本特征量的多流。 例如,当将注释添加到诸如电视广播节目的内容时,可以应用本发明。
    • 24. 发明申请
    • CONTROL DEVICE FOR ROTARY MACHINE
    • 旋转机控制装置
    • US20140084822A1
    • 2014-03-27
    • US14117770
    • 2011-06-27
    • Masato ItoToshio Morohoshi
    • Masato ItoToshio Morohoshi
    • H02P21/14
    • H02P21/146H02P6/185H02P6/186H02P21/18H02P21/32H02P2203/03
    • A storage section stores, as stored current values, currents flowing when a voltage application section applies voltage vectors to a three-phase rotary machine. A position estimation section estimates the rotor position of the rotary machine in a stopped state based on the stored current values. An adjustment section adjusts a minimum necessary application time that allows the rotary machine to be magnetically saturated by voltage vector application, to enable rotor position estimation. Further, the adjustment section uses, as an adjustment evaluation value, the magnitude |ΔY| of differential admittance obtained by dividing a summed current value calculated from the stored current values by the voltage amplitude value of the voltage vector instruction when the voltage vector based on the voltage vector instruction is applied with the application time being set at an arbitrary application time, and adjusts the application time based on |ΔY|.
    • 作为存储电流值,存储部存储当电压施加部向三相旋转机施加电压矢量时流动的电流。 位置估计部基于所存储的当前值来估计旋转机器处于停止状态的转子位置。 调整部分调整允许旋转机器通过电压矢量施加磁饱和的最小必要的施加时间,以实现转子位置估计。 此外,调整部使用幅度|&Dgr; Y |作为调整评估值 通过将应用时间设定为任意的施加时间,将施加了基于电压矢量指令的电压矢量时,根据所存储的电流值计算的求和电流值除以电压矢量指令的电压振幅值而得到的微分导纳, 并根据|&Dgr; Y |调整应用时间。
    • 25. 发明申请
    • MOTOR CONTROL DEVICE
    • 电机控制装置
    • US20130285588A1
    • 2013-10-31
    • US13978562
    • 2011-01-25
    • Masato ItoYoshihiko Kinpara
    • Masato ItoYoshihiko Kinpara
    • H02P31/00
    • H02P31/00H02P23/14H02P23/22H02P27/085
    • A motor control device includes: a frequency instruction setting section for outputting a plurality of frequency instructions; an AC voltage instruction generation section for generating and outputting an AC voltage instruction based on each of the frequency instructions; a voltage application section for applying voltage to a motor based on the AC voltage instruction; a current detection section for detecting motor current flowing in the motor; and a type determination section for determining the type of the motor based on a transfer characteristic of the motor calculated from the motor current, the AC voltage instruction, and the frequency instruction.
    • 电动机控制装置包括:频率指令设定部分,用于输出多个频率指令; 交流电压指令生成部分,用于基于每个频率指令产生和输出交流电压指令; 电压施加部,其基于所述交流电压指令向电动机施加电压; 用于检测在电动机中流动的电动机电流的电流检测部分; 以及类型确定部分,用于基于从电动机电流,AC电压指令和频率指令计算出的电动机的传递特性来确定电动机的类型。
    • 26. 发明申请
    • CONTROLLER FOR AC ROTARY MACHINE
    • 交流电机控制器
    • US20120001573A1
    • 2012-01-05
    • US13255738
    • 2009-03-26
    • Yoshihiko KimparaMasato ItoMasanori Tanimoto
    • Yoshihiko KimparaMasato ItoMasanori Tanimoto
    • H02P21/14
    • H02P21/0003H02P29/032
    • A controller for an AC rotary machine which performs a smooth drive from a low-speed region including zero speed to a high-speed region, and which can attain, even if an initial value error is present in an estimated phase, desired characteristics by promptly converging the error. An adaptive observation mechanism outputs an estimated magnetic flux phase, an estimated current vector, an estimated magnetic flux vector, and an estimated speed, based on a voltage instruction vector, a current deviation vector, and an amplified deviation vector; a deviation vector calculator calculates the current deviation vector between the estimated current vector and a detected current vector from a current vector detector, and a magnetic flux deviation vector between the estimated magnetic flux vector and a detected magnetic flux vector from a magnetic flux vector detector; and a deviation amplifier amplifies the current deviation vector and the magnetic flux deviation vector, and outputs the result as the amplified deviation vector.
    • 一种用于从包括零速度的低速区域到高速区域执行平滑驱动的交流旋转机器的控制器,并且即使在估计阶段中存在初始值误差,也可以及时获得期望的特性 收敛错误。 自适应观察机构基于电压指令矢量,电流偏差矢量和放大偏差矢量,输出估计磁通相位,估计电流矢量,估计磁通矢量和估计速度; 偏差矢量计算器计算来自电流矢量检测器的估计电流矢量和检测电流矢量之间的电流偏差矢量和来自磁通矢量检测器的估计磁通矢量和检测磁通矢量之间的磁通偏差矢量; 并且偏差放大器放大电流偏差矢量和磁通量偏差矢量,并输出该结果作为放大偏差矢量。
    • 28. 发明申请
    • LEARNING APPARATUS, LEARNING METHOD AND PROGRAM
    • 学习设备,学习方法和程序
    • US20110137831A1
    • 2011-06-09
    • US12917853
    • 2010-11-02
    • Naoki IDEMasato ItoKohtaro Sabe
    • Naoki IDEMasato ItoKohtaro Sabe
    • G06F15/18
    • G08G1/0133G06K9/6297G06N20/00G08G1/0112
    • A learning apparatus includes: an interpolating section which interpolates data missing in time series data; an estimating section which estimates a Hidden Markov Model from the time series data; and a likelihood calculating section which calculates the likelihood of the estimated Hidden Markov Model. The likelihood calculating section calculates the likelihood for normal data which does not have missing data and the likelihood for interpolation data which is interpolated data in different conditions and calculates the likelihood of the Hidden Markov Model for the time series data in which the data is interpolated. The estimating section updates the Hidden Markov Model so that the likelihood calculated by the likelihood calculating section becomes high.
    • 学习装置包括:插入时间序列数据中丢失的数据的内插部分; 估计部分,根据时间序列数据估计隐马尔可夫模型; 以及计算估计隐马尔科夫模型的可能性的似然度计算部分。 似然度计算部分计算不具有缺失数据的正常数据的可能性以及在不同条件下被内插数据的内插数据的可能性,并计算隐藏马尔可夫模型对于其中内插数据的时间序列数据的可能性。 估计部分更新隐马尔可夫模型,使得由似然度计算部分计算的似然率变高。
    • 30. 发明申请
    • CONTROLLER OF ROTARY ELECTRIC MACHINE
    • 旋转电机控制器
    • US20100194319A1
    • 2010-08-05
    • US12679326
    • 2008-05-09
    • Masato ItoYoshihiko KimparaTetsuya Kojima
    • Masato ItoYoshihiko KimparaTetsuya Kojima
    • H02P6/16
    • H02P21/14H02P6/183H02P21/24
    • A rotary electric machine controller including a current detector detecting rotary electric machine currents generated in a rotary electric machine, a position estimation mechanism outputting an estimated position in accordance with the rotary electric machine currents; a controller outputting voltage commands in accordance with the estimated position; a pulse-width modulator outputting logic signals which are pulse-width modulated in accordance with the voltage commands and with a switching cycle used for pulse-width modulation control; and a voltage application mechanism applying AC voltages for driving the rotary electric machine in accordance with the logic signals. The voltage commands output by the controller are obtained by superimposing, on fundamental voltages for driving the rotary electric machine, position detection voltages which each have a cycle equal to m times of the switching cycle and which are different in phase among respective phases.
    • 一种旋转电机控制器,包括检测旋转电机中产生的旋转电机的电流检测器,根据旋转电机电流输出估计位置的位置估计机构; 控制器,根据估计位置输出电压指令; 输出根据电压指令进行脉冲宽度调制的脉冲宽度调制器和用于脉冲宽度调制控制的开关周期的脉冲宽度调制器; 以及根据逻辑信号施加用于驱动旋转电机的交流电压的电压施加机构。 由控制器输出的电压指令通过在驱动旋转电机的基波电压上叠加位置检测电压来获得,每个位置检测电压的周期等于开关周期的m倍,并且各相之间的相位不同。