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
    • 11. 发明专利
    • Sign recognition device
    • 标志识别装置
    • JP2010282278A
    • 2010-12-16
    • JP2009133115
    • 2009-06-02
    • Mitsubishi Electric Corp三菱電機株式会社
    • YONEYAMA SHOGOHIRANO TAKASHIYAMAZAKI KOMATSUMOTO ATSUSHIKAWAMATA TAKENORI
    • G08G1/09B60R1/00G01C21/00G06T1/00G08G1/16
    • G06K9/00818
    • PROBLEM TO BE SOLVED: To provide a sign recognition device capable of determining correctly an effective range of a recognized roadway sign, and capable of presenting accurately the roadway sign to a driver.
      SOLUTION: The sign recognition device includes a sign effective range data recording unit 7 for prestoring effective range conditions such as the number of effective roadway sections, a distance, and an effective time zone shown by a sign and an auxiliary sign, and a condition of a vehicle state, a sign recognition unit 2 for recognizing a sign and an auxiliary sign by using a captured image of a roadway in front of a vehicle, a vehicle information acquiring unit 4 for acquiring vehicle information indicating a current position, a type, a state and the like of the vehicle, a map information acquiring unit 3 for acquiring map information about a map of an area surrounding the vehicle, and a sign effective range determining unit 5 for determining whether or not the vehicle is staying in the effective range specified with the sign and the auxiliary sign which have been recognized by the sign recognition unit 2 by using the effective range conditions stored in the sign effective range data recording unit 7, the vehicle information, and the map information.
      COPYRIGHT: (C)2011,JPO&INPIT
    • 要解决的问题:提供一种符号识别装置,其能够正确地确定识别的道路标志的有效范围,并且能够将驾驶员的道路标志准确地呈现。

      解决方案:符号识别装置包括用于预先存储有效范围条件的符号有效范围数据记录单元7,例如有效道路段的数量,距离和由符号和辅助符号所示的有效时区,以及 车辆状态,通过使用车辆前方的道路的拍摄图像识别符号的符号识别单元2和用于获取表示当前位置的车辆信息的车辆信息获取单元4, 类型,状态等,用于获取关于车辆周围区域的地图的地图信息的地图信息获取单元3,以及用于判定车辆是否停留在车辆中的车牌的有效范围确定单元5 通过使用存储在符号有效范围d中的有效范围条件,由符号识别单元2识别的符号和辅助符号指定的有效范围 ata记录单元7,车辆信息和地图信息。 版权所有(C)2011,JPO&INPIT

    • 12. 发明专利
    • Navigation apparatus and navigation method
    • 导航装置和导航方法
    • JP2010190773A
    • 2010-09-02
    • JP2009036371
    • 2009-02-19
    • Mitsubishi Electric Corp三菱電機株式会社
    • WATANABE KEISUKEHIRANO TAKASHISENFUKU TAKESHISHIINO TOMOHIRONOMOTO KOHEI
    • G01C21/00
    • PROBLEM TO BE SOLVED: To solve a problem in a navigation apparatus wherein, though display guidance by various pieces of information has been conventionally proposed, these are set by the assumption of a designer of the navigation apparatus and the guidance is not so easy to understand as the guidance by a fellow passenger and that although the guidance display method may be changed based on the history information and the recognition degree of a driver, the criteria of the fellow passenger is not reflected.
      SOLUTION: The navigation method includes: a step of calculating a driving state feature quantity in a guidance by a guidance time driving state feature quantity calculation means from the guidance history in the guidance history storage means, the guidance history being the history of the guidance performed by the passenger to the driver; a step of classifying the guidance in a class by a guidance classification means, in the class the driving state feature quantity to the guidance satisfies the condition; a step of replacing the variable part of the speech content of the driving state feature quantity to a variable part signal, a step of selecting the most frequent speech content in each of the classes by a speech content selection means; and a step of storing in a storage means as a guide rule.
      COPYRIGHT: (C)2010,JPO&INPIT
    • 要解决的问题为了解决导航装置中的问题,其中虽然传统上提出了各种信息的显示引导,但是这些是通过导航装置的设计者的假定来设定的,并且引导不是这样 容易理解为乘客的指导,尽管可以根据驾驶员的历史信息和识别度来改变指导显示方法,但是乘客的标准没有被反映出来。 导航方法包括:从引导历史存储装置中的指导历史计算由引导时间驱动状态特征量计算装置引导的驾驶状态特征量的步骤,作为历史的指导历史 乘客对司机的指导; 通过指导分类手段对课堂上的引导进行分类的步骤,在该类中,引导的驾驶状态特征量满足条件; 将驱动状态特征量的语音内容的可变部分替换为可变部分信号的步骤,通过语音内容选择装置选择每个类中最频繁的语音内容的步骤; 以及作为引导规则存储在存储装置中的步骤。 版权所有(C)2010,JPO&INPIT
    • 13. 发明专利
    • Information retrieval support device
    • 信息搜索支持设备
    • JP2009157620A
    • 2009-07-16
    • JP2007334585
    • 2007-12-26
    • Mitsubishi Electric Corp三菱電機株式会社
    • WATANABE KEISUKEHIRANO TAKASHI
    • G06F17/30G06F12/00
    • PROBLEM TO BE SOLVED: To provide an information search support device, for enhancing the efficiency of information search by reducing user's trial and error. SOLUTION: A search condition series extraction part 2 collates an input search condition series with past search condition series held in a search history storage part 1 and extracts a search condition series corresponding to the input search condition series from the past search condition series. A search condition candidate evaluation part 3 calculates an evaluation value for each search condition in the search condition series extracted by the extraction part 2. A search condition input part 4 presents, as search condition candidates corresponding to the input search condition series, search conditions output from the evaluation part 3 based on the evaluation value, and receives selection from the user for the presented search condition candidates. COPYRIGHT: (C)2009,JPO&INPIT
    • 要解决的问题:提供信息搜索支持设备,用于通过减少用户的尝试和错误来提高信息搜索的效率。 搜索条件序列提取部分2将输入搜索条件序列与保存在搜索历史存储部分1中的过去搜索条件序列进行比较,并从先前搜索条件序列提取与输入搜索条件序列相对应的搜索条件序列 。 搜索条件候选评价部3计算由提取部2提取的搜索条件序列中的每个搜索条件的评估值。搜索条件输入部4将与输入搜索条件序列对应的搜索条件候选作为搜索条件输出, 基于评估值从评估部分3获得,并且从用户接收针对所呈现的搜索条件候选者的选择。 版权所有(C)2009,JPO&INPIT
    • 14. 发明专利
    • Device for detecting symbol in drawing
    • 检测图形符号的装置
    • JP2007241436A
    • 2007-09-20
    • JP2006059812
    • 2006-03-06
    • Mitsubishi Electric Corp三菱電機株式会社
    • YONEYAMA SHOGOHIRANO TAKASHIOKADA YASUHIRO
    • G06T7/00
    • PROBLEM TO BE SOLVED: To detect a symbol image in drawing with high precision and at high speed.
      SOLUTION: A direction of a normal θ of an edge at a target pixel in a drawing image is calculated. When the direction of the normal θ
      i of a feature point F
      i matches the direction of the normal θ is stored in a feature quantity table of the feature quantity storage part 15, the feature point F
      i , having the direction of the normal θ
      i , arranges a feature point candidate selection part 22 for acquiring a polar coordinate R
      j of other feature points of the symbol image existing in contour from the feature quantity table. When a luminance value of the pixel for the drawing image, corresponding to the polar coordinate R
      j of other feature points acquired by the feature point candidate selection part 22, is below the threshold value, existence of the symbol image is detected.
      COPYRIGHT: (C)2007,JPO&INPIT
    • 要解决的问题:以高精度和高速检测图形中的符号图像。 解决方案:计算绘图图像中目标像素处的边缘的正常θ的方向。 当在特征量存储部15的特征量表中存储特征点F i 的正常θ i 的方向与法线θ的方向一致时, 具有正常θ i 的方向的特征点F i 布置用于获取极坐标R j 的特征点候选选择部22 >来自特征量表的轮廓中存在的符号图像的其他特征点。 当与由特征点候选选择部22获取的其他特征点的极坐标R j 相对应的绘制图像的像素的亮度值低于阈值时,符号的存在 检测到图像。 版权所有(C)2007,JPO&INPIT
    • 15. 发明专利
    • Guidance information presentation system, document/drawing preparation terminal, and knowledge server
    • 指导信息介绍系统,文件/绘图准备终端和知识服务器
    • JP2007048148A
    • 2007-02-22
    • JP2005233497
    • 2005-08-11
    • Mitsubishi Electric Corp三菱電機株式会社
    • HIRANO TAKASHIKAMESHIRO TAIZOUTANIGAKI KOICHIOKANO YUICHI
    • G06F17/21
    • PROBLEM TO BE SOLVED: To present guidance information based on common knowledge data to many types of document/drawing preparation terminals. SOLUTION: The terminal is provided with: a document/drawing preparing part for preparing documents and drawings; a state detecting part for generating inherent edit information dependent on the type and version of the preparing part; and an inherent instruction execution part for presenting guidance onto the document/drawing preparation part according to an inherent instruction returned from a knowledge server. The knowledge server is provided with: a standard edit information generation part for converting document/inherent edit information into standard edit information in a unified format on the basis of edit information conversion data; a guidance information generation part for referring to knowledge data on the basis of the standard edit information to generate standard guidance information in a unified format; and an inherent instruction generation part for converting the standard guidance information into an inherent instruction corresponding to a transmission source of the inherent edit information on the basis of guidance information/inherent instruction conversion data and returning the inherent instruction. COPYRIGHT: (C)2007,JPO&INPIT
    • 要解决的问题:向许多类型的文件/绘图准备终端呈现基于常见知识数据的引导信息。

      解决方案:终端设有:文件/图纸准备部分,用于准备文件和图纸; 状态检测部分,用于根据准备部件的类型和版本产生固有的编辑信息; 以及根据从知识服务器返回的固有指令,向文件/绘图准备部件呈现引导的固有指令执行部分。 知识服务器具有:标准编辑信息生成部,其基于编辑信息转换数据,将文档/固有编辑信息以统一格式转换为标准编辑信息; 指导信息生成部,用于基于标准编辑信息参考知识数据,以统一格式生成标准指导信息; 以及固有指令生成部件,用于根据引导信息/固有指令转换数据将标准引导信息转换成与固有编辑信息的发送源相对应的固有指令,并返回固有指令。 版权所有(C)2007,JPO&INPIT

    • 16. 发明专利
    • Document creation support device
    • 文件创建支持设备
    • JP2007026418A
    • 2007-02-01
    • JP2006000201
    • 2006-01-04
    • Mitsubishi Electric Corp三菱電機株式会社
    • TANIGAKI KOICHIHIRANO TAKASHIKAMESHIRO TAIZOUOKADA YASUHIRO
    • G06F17/21
    • PROBLEM TO BE SOLVED: To obtain a document creation support device capable of presenting appropriate guidance when a document is created by a natural language. SOLUTION: The document creation support device is provided with a conformity judgment part 14 for judging conformity of between the guidance stored in a support rule storage part 13 and the document acquired by a document structure analysis part 11, when the conformity judged by the conformity judgment part 14 is higher than a preset threshold, presents the guidance stored in the support rule storage part 13. Thus, when the document is created by the natural language, the appropriate guidance is presented. COPYRIGHT: (C)2007,JPO&INPIT
    • 要解决的问题:获得当通过自然语言创建文档时能够呈现适当指导的文档创建支持设备。 解决方案:文档创建支持设备设有一致性判断部分14,用于判断存储在支持规则存储部分13中的指导与文档结构分析部分11获取的文档之间的一致性,当由 合格判断部分14高于预设阈值,呈现存储在支持规则存储部分13中的指导。因此,当用自然语言创建文档时,呈现适当的指导。 版权所有(C)2007,JPO&INPIT
    • 17. 发明专利
    • Document creation support system, and document creation support program
    • 文件创建支持系统和文件创建支持计划
    • JP2006330840A
    • 2006-12-07
    • JP2005149773
    • 2005-05-23
    • Mitsubishi Electric Corp三菱電機株式会社
    • KAMESHIRO TAIZOUHIRANO TAKASHI
    • G06F17/21
    • PROBLEM TO BE SOLVED: To provide a document creation support system and a document creation support program for automatically collating an automatic execution check list of a knowledge DB to check a failure content of a a creation document and displays the check result, only by inputting the creation document by a user. SOLUTION: A character/line segment extraction means extracts characters, position information of the characters and position information of line segments from an input document from an input means, a document structuring means structures the document with reference to structure information of an attribute DB by using the position information of the characters and line segments, a knowledge DB collating means checks the presence or absence of a defect in the structured document in accordance with an automatic check list in the knowledge DB, and a document correction support means searches the knowledge DB from the checked result to create correction information to display the knowledge DB checked result and correction information on a display means. COPYRIGHT: (C)2007,JPO&INPIT
    • 要解决的问题:提供文档创建支持系统和文档创建支持程序,用于自动整理知识数据库的自动执行检查列表以检查创建文档的故障内容并显示检查结果,仅通过 用户输入创建文档。 解决方案:字符/线段提取装置从输入装置从输入文档中提取字符的字符,位置信息和行段的位置信息,文档结构化装置参考属性的结构信息构建文档 DB通过使用字符和线段的位置信息,知识DB对照装置根据知识DB中的自动检查列表来检查结构化文档中是否存在缺陷,并且文档校正支持装置搜索 知识DB从检查结果创建校正信息以在显示装置上显示知识DB检查结果和校正信息。 版权所有(C)2007,JPO&INPIT
    • 18. 发明专利
    • Attribute extraction method, its device and attribute extraction program
    • 属性提取方法,其设备和属性提取程序
    • JP2004178044A
    • 2004-06-24
    • JP2002340348
    • 2002-11-25
    • Mitsubishi Electric Corp三菱電機株式会社
    • KAMESHIRO TAIZOUHIRANO TAKASHI
    • G06F17/21G06F17/30G06K9/20G06K9/72
    • PROBLEM TO BE SOLVED: To provide a means for precisely extracting document attributes from a document. SOLUTION: This attribute extraction method comprises a morphemic analysis step for carrying out the morphemic analysis of the character fields of an inputted document and for outputting the morphemic analysis results for each character field, and a part of speech pattern collation step for collating the character fields with document attribute part of speech patterns in which the structures of document attributes to be extracted are expressed in morphemic levels and for extracting the character field whose appearing position in the document is within a predetermined range among the matched character fields as document attributes. COPYRIGHT: (C)2004,JPO
    • 要解决的问题:提供从文档中精确提取文档属性的手段。 解决方案:该属性提取方法包括用于对输入文档的字符字段进行语素分析并输出每个字符字段的语素分析结果的语素分析步骤,以及用于整理的一部分语音模式对照步骤 具有文档属性的语言模式的字符域,其中要提取的文档属性的结构以语素级别表示,并且用于提取文档中出现位置在匹配字符字段之间的预定范围内的字符字段作为文档属性 。 版权所有(C)2004,JPO
    • 19. 发明专利
    • Business form character recognition device
    • 业务表格字符识别设备
    • JP2012185713A
    • 2012-09-27
    • JP2011048983
    • 2011-03-07
    • Mitsubishi Electric Corp三菱電機株式会社
    • HIRANO TAKASHI
    • G06K9/03
    • PROBLEM TO BE SOLVED: To provide a business form character recognition device whose processing cost is small and which can inhibit error recognition.SOLUTION: A rejection determination part 107 by score performs a rejection determination of a recognition result on the basis of a value of the reliability of a recognition result obtained by a character pattern recognition part 106. A character and closing line contact number detecting part 110 extracts a non-character frame image for one character from an image in a character entry column and measures the number of character closing lines coming into contact with the non-character frame image. A ruled line contact rejection determination part 111 rejects a recognition result of a character corresponding to a character closing line when the number of character closing lines coming into contact with the non-character frame image exceeds a predetermined threshold. A rejection process integration part 108 performs a rejection determination of a character recognition result to be finally outputted on the basis of both a result of the rejection determination part 107 by score and a result of the ruled line contact rejection determination part 111.
    • 要解决的问题:提供一种处理成本小且可以抑制错误识别的业务形式字符识别装置。 解决方案:通过得分的拒绝判定部分107基于由字符模式识别部分106获得的识别结果的可靠性的值执行识别结果的拒绝确定。字符和闭合线路接触号检测 部分110从字符输入列中的图像中提取一个字符的非字符帧图像,并测量与非字符帧图像接触的字符关闭行的数量。 当与非字符帧图像接触的字符闭合线的数量超过预定阈值时,格线接触拒绝判定部分111拒绝与字符闭合线相对应的字符的识别结果。 拒绝处理整合部108基于拒绝判定部107的结果和得分的结果以及划线接触拒绝判定部111的结果,进行最终输出的字符识别结果的拒绝判定。 版权所有(C)2012,JPO&INPIT
    • 20. 发明专利
    • Vehicle peripheral obstacle monitoring device
    • 车辆外围障碍物监测装置
    • JP2012018613A
    • 2012-01-26
    • JP2010156832
    • 2010-07-09
    • Mitsubishi Electric Corp三菱電機株式会社
    • NIIYAMA MARIKAYONEYAMA SHOGOMIYAHARA HIROYASUHIRANO TAKASHIINOUE SATORUKAWAMATA TAKENORI
    • G08G1/16B60R21/00G01S7/524G01S15/93
    • PROBLEM TO BE SOLVED: To provide a vehicle peripheral obstacle monitoring device capable of improving a detection rate while suppressing a harmful influence on the obstacle detection performance of an ultrasonic sensor.SOLUTION: An image processing section 4 measures a position of an obstacle viewed from a vehicle based on image information of the periphery of the vehicle and recognizes a type of the obstacle. An ultrasonic sensor control section 3 controls a timing of transmitting ultrasonic waves transmitted from the ultrasonic sensor 1 based on a reflected wave selection threshold parameter and an ultrasonic wave transmission interval parameter, detects the obstacle at the periphery of the vehicle from information of the intensity of the received reflected wave, and measures a distance between the vehicle and the obstacle. A parameter adjusting section 5 adjusts a control parameter of the ultrasonic sensor control section 3 based on the processing result of the image processing section 4.
    • 解决的问题:提供一种能够在抑制对超声波传感器的障碍物检测性能的有害影响的同时提高检测率的车辆周边障碍物监视装置。 解决方案:图像处理部分4基于车辆周边的图像信息测量从车辆观察的障碍物的位置,并识别障碍物的类型。 超声波传感器控制部3基于反射波选择阈值参数和超声波发送间隔参数,控制从超声波传感器1发送的超声波的发送定时,根据来自超声波传感器1的强度的信息,检测车辆周边的障碍物 接收到的反射波,并测量车辆与障碍物之间的距离。 参数调整部5基于图像处理部4的处理结果来调整超声波传感器控制部3的控制参数。(C)2012,JPO&INPIT