公开(公告)号：US20130006636A1

公开(公告)日：2013-01-03

申请号：US13636061

申请日：2011-03-24

申请人： Hironori Mizuguchi ,  Dai Kusui

发明人： Hironori Mizuguchi ,  Dai Kusui

IPC分类号： G10L15/06

CPC分类号： G06F17/30705 ,  G06F17/30616

摘要： A meaning extraction device includes a clustering unit, an extraction rule generation unit and an extraction rule application unit. The clustering unit acquires feature vectors that transform numerical features representing the features of words having specific meanings and the surrounding words into elements, and clusters the acquired feature vectors into a plurality of clusters on the basis of the degree of similarity between feature vectors. The extraction rule generation unit performs machine learning based on the feature vectors within a cluster for each cluster, and generates extraction rules to extract words having specific meanings. The extraction rule application unit receives feature vectors generated from the words in documents which are subject to meaning extraction, specifies the optimum extraction rules for the feature vectors, and extracts the meanings of the words on the basis of which the feature vectors were generated by applying the specified extraction rules to the feature vectors.

摘要翻译： 意思提取装置包括聚类单元，提取规则生成单元和提取规则应用单元。 聚类单元获取将表示具有特定含义的单词的特征的数字特征和周围单词的数字特征变换为元素的特征向量，并且基于特征向量之间的相似度将所获取的特征向量聚类成多个群集。 提取规则生成单元基于针对每个群集的群集内的特征向量执行机器学习，并且生成提取规则以提取具有特定含义的单词。 提取规则应用单元接收从文本中经过含义提取的单词生成的特征向量，指定特征向量的最优提取规则，并提取基于特征向量生成的单词的含义， 指定的提取规则到特征向量。

公开(公告)号：US20120303611A1

公开(公告)日：2012-11-29

申请号：US13522278

申请日：2010-12-21

申请人： Yukitaka Kusumura ,  Hironori Mizuguchi ,  Dai Kusui

发明人： Yukitaka Kusumura ,  Hironori Mizuguchi ,  Dai Kusui

IPC分类号： G06F17/30

CPC分类号： G06F17/3071

摘要： The information processing device 1 processes document collections having tags permitting semantic class identification appended to each document and comprises a search unit 2, which creates multiple semantic class units containing one, two, or more semantic classes based on a taxonomy that identifies relationships between semantic classes, and a frequency calculation unit 3 which, for each of the semantic class units, identifies documents that match that semantic class unit in the document collections and, for these matching documents, calculates a first frequency that represents the frequency of occurrence in a designated document collection and a second frequency that represents the frequency of occurrence in non-designated document collections. Once the calculations have been performed, the search unit 2 identifies any of the semantic class units based on the first frequency and the second frequency of the matching documents.

摘要翻译： 信息处理装置1处理具有附加到每个文档的允许语义类标识的标签的标签的文档集合，并且包括搜索单元2，其基于识别语义类之间的关系的分类法创建包含一个，两个或更多个语义类的多个语义类单元 以及频率计算单元3，对于每个语义类单元，识别与文档集合中的该语义类单元相匹配的文档，并且对于这些匹配文档，计算表示指定文档中出现频率的第一频率 收集，第二个频率代表非指定文件收集中的发生频率。 一旦执行了计算，搜索单元2基于匹配文档的第一频率和第二频率来识别任何语义类单元。

公开(公告)号：US20120071176A1

公开(公告)日：2012-03-22

申请号：US13375500

申请日：2010-06-03

申请人： Hironori Mizuguchi

发明人： Hironori Mizuguchi

IPC分类号： H04W64/00

CPC分类号： H04W8/005 ,  H04W52/365 ,  H04W60/06

摘要： A base station apparatus that estimates whether or not each terminal device belonging to a communication cell of the present apparatus is present in an end area of the cell. The apparatus includes a reception device that receives from each terminal device, transmission power information which indicates transmission power of the terminal device; a registration device that successively registers the transmission power information with a storage device; a statistical processing device that computes a statistic used for estimating the terminal device present in the end area of the communication cell, with respect to a population which is the transmission power information stored in the storage device; a candidate extraction device that extracts candidates for the terminal device present in the end area of the communication cell, based on the statistic computed by the statistical processing device; and an estimation device that estimates the terminal device present in the end area of the communication cell from among the candidates extracted by the candidate extraction device.

摘要翻译： 一种基站装置，其估计属于本装置的通信小区的各终端装置是否存在于小区的终端区域。 该装置包括从各终端装置接收表示终端装置的发送功率的发送功率信息的接收装置; 登记装置，其将发送功率信息连续登记到存储装置; 相对于存储在存储装置中的发送功率信息的总体，计算用于估计存在于通信小区的终端区域中的终端装置的统计量的统计处理装置; 候选提取装置，基于由统计处理装置计算出的统计量，提取存在于通信小区的终端区域中的终端装置的候选; 以及估计装置，其从候选提取装置提取的候选中估计存在于通信小区的结束区域中的终端装置。

公开(公告)号：US20110153615A1

公开(公告)日：2011-06-23

申请号：US13056030

申请日：2009-07-29

申请人： Hironori Mizuguchi ,  Kenji Tateishi ,  Itaru Hosomi ,  Dai Kusui

发明人： Hironori Mizuguchi ,  Kenji Tateishi ,  Itaru Hosomi ,  Dai Kusui

IPC分类号： G06F17/30

CPC分类号： G06F17/30705 ,  G06F17/30707

摘要： A data classifier system of the present invention selects a plurality of classifications correlated to data groups so as to output classification axes based on hierarchical classifications and data groups. The data classifier system includes a basic category accumulation means, a classification axis candidate reduction means and a priority calculation means. The basic category accumulation means accumulates classifications serving as basic categories used for desired classifications in advance. The classification axis candidate reduction means selects a plurality of classifications from among classifications descendant from each basic category so as to create classification axis candidates, thus reducing classification axis candidates subjected to calculations based on data quantity of classifications and hierarchical distances of classifications. The priority calculation means calculates priority in displaying classification axis candidates, the number of which is reduced by the classification axis candidate reduction means.

摘要翻译： 本发明的数据分类器系统选择与数据组相关的多个分类，以便基于分级分类和数据组来输出分类轴。 数据分类器系统包括基本类别累积装置，分类轴候选减少装置和优先级计算装置。 基本类别积累意味着预先分类用作所需分类的基本类别。 分类轴候选减少装置从每个基本类别的分类中选择多个分类，以便创建分类轴候选，从而基于分类的数据量和分类距离来减少经受计算的分类轴候选。 优先级计算装置计算显示分类轴候选的优先级，分类轴候选减少装置减少其数量。

公开(公告)号：US20060211439A1

公开(公告)日：2006-09-21

申请号：US10548674

申请日：2004-03-09

申请人： Hironori Mizuguchi

发明人： Hironori Mizuguchi

IPC分类号： H04B7/00

CPC分类号： H04W52/42

摘要： Changes in instructions for increasing/decreasing transmission power that have been decoded from TPC bits are monitored, and when the increase/decrease instructions in a prescribed time interval are biased toward instructions for increasing the transmission power, the peak direction or main lobe width of the transmission beam is changed by regulating the transmission power or transmission antenna weights that correspond to each of a plurality of antenna devices. These processes are repeated until the bias toward instructions for increasing the transmission power in the instructions for increasing/decreasing transmission power is eliminated or until the number of changes of the transmission beam reaches a maximum value that has been set in advance.

摘要翻译： 监视从TPC位解码的增加/减少发送功率的指令的改变，并且当规定时间间隔中的增减指令偏向用于增加发送功率的指令时，峰值方向或主波瓣宽度 通过调节与多个天线装置中的每一个相对应的发送功率或发送天线权重来改变发送波束。 重复这些处理，直到消除了用于增加/减少发送功率的指令中用于增加发送功率的指令的偏移，或者直到发送波束的变化数量达到预先设置的最大值。

公开(公告)号：US20050245284A1

公开(公告)日：2005-11-03

申请号：US10515318

申请日：2003-05-22

申请人： Hironori Mizuguchi

发明人： Hironori Mizuguchi

IPC分类号： H01Q3/26 ,  H04B1/69 ,  H04B1/7103 ,  H04B7/04 ,  H04B7/06 ,  H04B7/08 ,  H04B7/26 ,  H04W16/28 ,  H04W88/02 ,  H04M1/00

CPC分类号： H04B7/0842 ,  H04B7/0615

摘要： Reception quality measuring circuit (107) measures the reception quality of received data delivered from adder (103). When the reception quality measured by reception quality measuring circuit (107) is less than a certain threshold value, transmission antenna weight control circuit (108) applies multipliers (1061-196N) with stored transmission antenna weights, that is, transmission antenna weight W″ stored therein when the reception quality exceeded the threshold value at the last time, instead of transmission antenna weights W′ generated by antenna weight converting circuit (105).

摘要翻译： 接收质量测量电路（107）测量从加法器（103）发送的接收数据的接收质量。 当由接收质量测量电路（107）测量的接收质量小于某个阈值时，发射天线权重控制电路（108）应用乘法器（106） >），而不是由天线权重转换电路（105）产生的发送天线权重W'，当接收质量超过上次的阈值时，存储发送天线权重即发送天线权重W“。