专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明专利

JP2004301698A On-board information service system 审中-公开
公开(公告)号：JP2004301698A
公开(公告)日：2004-10-28
申请号：JP2003095524
申请日：2003-03-31
申请人： Cyber Creative Institute Co Ltd , Fujitsu Ltd , Hitachi Ltd , Japan Automobile Research Inst Inc , Matsushita Electric Ind Co Ltd , Mitsubishi Electric Corp , Ntt Advanced Technology Corp , Toshiba Corp , Yazaki Corp , エヌ・ティ・ティ・アドバンステクノロジ株式会社 , 三菱電機株式会社 , 富士通株式会社 , 松下電器産業株式会社 , 株式会社サイバー創研 , 株式会社日立製作所 , 株式会社東芝 , 矢崎総業株式会社 , 財団法人日本自動車研究所
发明人： HATAOKA NOBUO , SHIOTANI MAKOTO , ETSUNO NAGAAKI , MORIHIRO YOSHIHARU , MINOWA TOSHIMITSU , TAKAHASHI JUHEI , KANDA MASAE , YOSHIKAWA KENSHO , SATO YAMATO , ODAJIMA TAKASHI , FUJII HARUKI , NISHIMOTO TAKUYA , HIRAI KAZUKO , WATANABE MASARU
IPC分类号： G01C21/00 , B60R16/02
摘要： PROBLEM TO BE SOLVED: To enable to concentrate on a driving under the condition that the driving must be concentrated.
SOLUTION: Firstly, the service system is provided with a dialogue control means for interruption of input/output request with voice when at the condition that the driving load is high, and resumed when the driving load becomes low. Secondly, a means that a driver can freely interrupt/resume the input/output request. Thirdly, a means that the driver can freely control the dialogue with the system by setting up standard commands.
COPYRIGHT: (C)2005,JPO&NCIPI

2. 发明专利

JP2007122735A Pedestrian movement support device 审中-公开
标题翻译： PEDESTRIAN运动支持设备
公开(公告)号：JP2007122735A
公开(公告)日：2007-05-17
申请号：JP2006311275
申请日：2006-11-17
申请人： Hitachi Ltd , 株式会社日立製作所
发明人： HATAKEYAMA TOMOKO , HATAOKA NOBUO , OGAWA YUKIO
IPC分类号： G08B25/04 , A61G12/00 , G01C21/00 , G01C21/26 , G01S5/04 , G08B25/10 , G08G1/0969 , H04W4/02
摘要： PROBLEM TO BE SOLVED: To provide a pedestrian movement support device for regularly detecting the position of a pedestrian with poriomania who is away from home or the like, and reporting it to a traveling vehicle or the like.
SOLUTION: ID information of the pedestrian regularly transmitted from a portable transmitter (100) is received by a relay station (110) provided in a plurality of positions to determine a receiving direction angle, and the ID information and the receiving direction angle are transmitted to a head office (120). The head office (120) analyzes the receiving direction angle to specify the position of the pedestrian. The head office transmits position information of the pedestrian to the circumference through the relay stations. A pedestrian recognition device (150) mounted on a vehicle or the like receives the position information and outputs it in a form of voice or the like to make the driver of the vehicle recognize the pedestrian. The head office also analyzes the safety during movement of the pedestrian such as access to a dangerous spot, and transmits it with the position information.
COPYRIGHT: (C)2007,JPO&INPIT
摘要翻译：要解决的问题：提供一种行人运动支援装置，用于定期检测远离家乡等的眼睛的行人的位置，并将其报告给行驶车辆等。解决方案：从便携式发射机（100）定期发送的行人的ID信息由设置在多个位置的中继站（110）接收，以确定接收方向角度，并且识别信息和接收方向角度被传送到总部（120）。总部（120）分析接收方向角度以指定行人的位置。总部通过中继站将行人的位置信息传送到周围。安装在车辆等上的行人识别装置（150）接收位置信息，并以声音等的形式输出，以使车辆驾驶员识别行人。总行还分析行人运动过程中的安全问题，如进入危险场所，并将其与位置信息一并发送。版权所有（C）2007，JPO＆INPIT

3. 发明专利

JP2006107148A Sound information providing system 审中-公开
标题翻译：声音信息提供系统
公开(公告)号：JP2006107148A
公开(公告)日：2006-04-20
申请号：JP2004293193
申请日：2004-10-06
申请人： Hitachi Ltd , 株式会社日立製作所
发明人： KOKUBO HIROAKI , KUJIRAI TOSHIHIRO , HATAOKA NOBUO
IPC分类号： G08G1/16
摘要： PROBLEM TO BE SOLVED: To solve the problems that the provision of information is possibly delayed in the case of emergency since it is hard to express even the details of a dangerous object only with sound localization information and, in the meantime, a reproduction time is prolonged when even detail information is outputted by sound, concerning a sound information providing system using stereophony.
SOLUTION: A sound output mode is changed in response to an emergency degree. When the emergency degree is high, information is provided by performing localization by stereophony without outputting sound information of position/direction information of an object.
COPYRIGHT: (C)2006,JPO&NCIPI
摘要翻译：要解决的问题：为了解决在紧急情况下提供信息可能延迟的问题，因为即使仅使用声音定位信息，甚至难以表达危险物体的细节，并且同时，关于使用立体声的声音信息提供系统，当通过声音输出甚至细节信息时，再现时间延长。
解决方案：响应于紧急程度改变声音输出模式。当紧急程度高时，通过立体声执行定位而不输出对象的位置/方向信息的声音信息来提供信息。版权所有（C）2006，JPO＆NCIPI

4. 发明专利

JP2006099424A Voice information service system and terminal 审中-公开
标题翻译：语音信息服务系统和终端
公开(公告)号：JP2006099424A
公开(公告)日：2006-04-13
申请号：JP2004284603
申请日：2004-09-29
申请人： Denso Corp , Hitachi Ltd , 株式会社デンソー , 株式会社日立製作所
发明人： HATAOKA NOBUO , AKAHORI ICHIRO , TATEISHI MASAHIKO , MITAMURA TERUKO , NYBERG ERIC
IPC分类号： G06F3/16 , G01C21/00 , G08G1/137 , G10L15/22
CPC分类号： H04M3/4938 , G01C21/3608 , G10L15/26 , H04M1/271
摘要： PROBLEM TO BE SOLVED: To provide a user interface method and a device which permit dialog by voice input freely and efficiently, to provide system configuration capable of handling communication interception with a center, and to provide system configuration permitting access from a terminal to the center not constantly but as required basis, in a vehicle-mounted information service system. SOLUTION: As the configuration of a terminal side, a flexible dialog management part 106 and a task management part 107 for performing application management are separated. Furthermore, the configuration comprises four layers of a user interface, dialog management, task management, and the application. In addition, a means is provided which fetches in application information from the center as required. COPYRIGHT: (C)2006,JPO&NCIPI
摘要翻译：要解决的问题：提供一种通过语音输入自由而高效地进行对话的用户界面方法和装置，以提供能够处理与中心的通信拦截的系统配置，并且提供允许从终端访问的系统配置在车载信息服务系统中，中心不是不断，而是根据需要。解决方案：作为终端侧的配置，分离用于执行应用程序管理的灵活对话管理部分106和任务管理部分107。此外，该配置包括四层用户界面，对话管理，任务管理和应用。另外，提供了一种根据需要从中心获取应用信息的装置。版权所有（C）2006，JPO＆NCIPI

5. 发明专利

JP2006251061A Voice dialog apparatus and voice dialog method 审中-公开
标题翻译：语音对话设备和语音对话方法
公开(公告)号：JP2006251061A
公开(公告)日：2006-09-21
申请号：JP2005064227
申请日：2005-03-08
申请人： Hitachi Ltd , Nissan Motor Co Ltd , Xanavi Informatics Corp , 日産自動車株式会社 , 株式会社ザナヴィ・インフォマティクス , 株式会社日立製作所
发明人： ONO TAKESHI , TOGASHI MINORU , TOMOTA TAKAHISA , HATAOKA NOBUO , KUJIRAI TOSHIHIRO
IPC分类号： G10L15/28 , G10L15/22
摘要： PROBLEM TO BE SOLVED: To provide a voice dialog apparatus for suppressing the occurrence of erroneous recognition by enabling a user to intuitively comprehend to what degree the user may change an utterance method, and also to provide a voice dialog method.
SOLUTION: The voice dialog system recognizes utterance of the user by voice recognition means (11 and 14), analyzes the utterance of the user by an utterance analysis means (14), predicts erroneous recognition factors contributed to erroneous recognition on the basis of an analysis result by the utterance analysis means, and voice-synthesizes responses including a recognition result of the user by responding means (12 and 14) to be output. The responding means responds by performing utterance conversion emphasizing the erroneous recognition factors when predicting the erroneous recognition factors by a predicting means.
COPYRIGHT: (C)2006,JPO&NCIPI
摘要翻译：要解决的问题：提供一种用于通过使用户能够直观地理解用户可以改变话语方法的程度来抑制错误识别的发生的语音对话装置，并且还提供语音对话方法。语音对话系统通过语音识别装置（11和14）识别用户的话语，通过话语分析装置（14）分析用户的话语，预测基于错误识别的错误识别因素通过话音分析装置的分析结果，并且通过响应装置（12和14）语音合成包括用户的识别结果的响应，以输出。当通过预测装置预测错误的识别因子时，响应装置通过执行强调错误识别因子的话语转换来进行响应。版权所有（C）2006，JPO＆NCIPI

6. 发明专利

JP2006251059A Voice dialog system and the voice dialog method 有权
标题翻译：语音对话系统和语音对话方法
公开(公告)号：JP2006251059A
公开(公告)日：2006-09-21
申请号：JP2005064223
申请日：2005-03-08
申请人： Hitachi Ltd , Nissan Motor Co Ltd , Xanavi Informatics Corp , 日産自動車株式会社 , 株式会社ザナヴィ・インフォマティクス , 株式会社日立製作所
发明人： ONO TAKESHI , TOGASHI MINORU , TOMOTA TAKAHISA , HATAOKA NOBUO , KUJIRAI TOSHIHIRO
IPC分类号： G10L15/28 , G06F3/16 , G10L15/00 , G10L15/22
摘要： PROBLEM TO BE SOLVED: To provide a voice dialog system for reducing insecurity of a user by intelligibly presenting what role a topic of a current dialog is playing from the point of the whole dialog, and also to provide a voice dialog method. SOLUTION: The voice dialog system comprises: the presentation means (display 5) for promoting utterance of the user by presenting topic information; and the voice recognition means 11 and 14 for recognizing the inputted voice of the user, wherein the dialog with the user is completed after presentation on a plurality of topics by presentation means and voice recognition by voice recognition means. The current topic information is presented on the display 5 as a topic transition process together with connection relationship of the topic information before and after the current topic by a presentation control means 14. COPYRIGHT: (C)2006,JPO&NCIPI
摘要翻译：要解决的问题：提供一种语音对话系统，用于通过从整个对话的角度智能地呈现当前对话的主题的角色来减少用户的不安全性，并且还提供语音对话方法。语音对话系统包括：呈现装置（显示器5），用于通过呈现主题信息来促进用户的话语; 以及用于识别用户的输入语音的语音识别装置11和14，其中在通过呈现装置呈现多个主题并通过语音识别装置的语音识别之后完成与用户的对话。当前主题信息通过呈现控制装置14作为主题转换过程与当前主题之前和之后的主题信息的连接关系呈现在显示器5上。版权所有（C）2006，JPO＆NCIPI

7. 发明专利

JP2003316385A Voice interaction system and voice interaction method 有权
标题翻译：语音交互系统和语音交互方法
公开(公告)号：JP2003316385A
公开(公告)日：2003-11-07
申请号：JP2002122491
申请日：2002-04-24
申请人： Denso Corp , Hitachi Ltd , 株式会社デンソー , 株式会社日立製作所
发明人： HATAOKA NOBUO , WATANABE JUNICHIRO , KUJIRAI TOSHIHIRO , AKAHORI ICHIRO , TATEISHI MASAHIKO , MITAMURA TERUKO , NYBERG ERIC , UENO YOSHIKI
IPC分类号： G01C21/00 , G08G1/137 , G10L15/00 , G10L15/14 , G10L15/22 , G10L15/28
摘要： PROBLEM TO BE SOLVED: To realize inexpensive, efficient, and convenient use of various kinds of on-vehicle information service by realizing free and efficient voice-inputting interaction.
SOLUTION: A task controller 802 generates concretely essential expressions of interaction sequence using, as data, a task document 801 concerning the task of various information to be served. Based on this interaction sequence, concrete interaction dialogs appearing in each task such as a response dialog 806, a time dialog 807, place dialog 808, event site dialog 809 are generated in the form of more detailed interaction dialogs by using an actual time dictionary 8010, a place name dictionary 8011, an event site name dictionary 8012, etc. And, the flow of interaction essential to voice recognition is expressed in a VoiceXML description language or the like to carry out actual interaction services.
COPYRIGHT: (C)2004,JPO
摘要翻译：要解决的问题：通过实现免费高效的语音输入交互，实现廉价，高效，方便地使用各种车载信息服务。解决方案：任务控制器802使用关于要服务的各种信息的任务的任务文档801作为数据来生成具体的交互序列的基本表达。基于该交互序列，通过使用实际时间字典8010，以更详细的交互对话框的形式生成出现在每个任务中的具体交互对话框，诸如响应对话框806，时间对话框807，地方对话框808，事件站点对话框809 ，地名字典8011，事件站点名称字典8012等。此外，语音识别必需的交互流以VoiceXML描述语言等表示，以进行实际的交互服务。版权所有（C）2004，JPO

8. 发明专利

JP2000322088A SPEECH RECOGNITION MICROPHONE AND SPEECH RECOGNITION SYSTEM AND SPEECH RECOGNITION METHOD 失效
公开(公告)号：JP2000322088A
公开(公告)日：2000-11-24
申请号：JP13365999
申请日：1999-05-14
申请人： HITACHI LTD
发明人： WAKIZAKA SHINJI , KONDO KAZUO , KOKUBO HIROAKI , HATAOKA NOBUO
IPC分类号： G10L15/28 , G06F3/16 , G06F17/30 , G10L15/06
摘要： PROBLEM TO BE SOLVED: To provide an easy-to-use speech recognition interface in regard to a speech recognition system used in car navigation systems, compact information appliances, games, or the like. SOLUTION: A speech recognition microphone 1 having a function to execute a speech recognition process and a system main body 5 are connected by a communication means 4, and a recognition result recognized by a speech recognition part 13 is transferred to the system main body 5 for operating a system. The speech recognition microphone 1 has the speech recognition part 13 having an acoustic model 135 and a speech recognition processing part 134, a command dictionary 151, a recognition target dictionary 152, a user registration dictionary 154, and a data communication part 17, registers necessary words from the recognition target dictionary 152 transferred from the system main body 5 to the user registration dictionary 154, and performs speech recognition normally using the command dictionary 151 and the user registration dictionary 154.

9. 发明专利

JPH08336095A INTERACTIVE TELEVISION RECEIVER 失效
公开(公告)号：JPH08336095A
公开(公告)日：1996-12-17
申请号：JP14306095
申请日：1995-06-09
申请人： HITACHI LTD
发明人： HATAOKA NOBUO , ARITSUKA TOSHIYUKI
IPC分类号： H04N5/44 , H04N5/765 , H04N19/00 , H04N19/42 , H04N19/423 , H04N19/503 , H04N19/59 , H04N19/61 , H04N19/625 , H04N19/70 , H04N19/85 , H04N19/91 , H04N7/24
摘要： PURPOSE: To attain stop, fast forward, slow forward and extended edit display of a video being projected in response to the operation of the user by using a video processing technology such as a video compression storage means and a video stop/display means. CONSTITUTION: An operation signal 101 outputted from a remote controller is discriminated by a signal discrimination section 200. As a result, various functions designated are in operation and internal processing in interlocking with it is executed. As the various functions, temporary start stop/release, fast forward/fast rewinding start/release, slow forward slow rewinding start/release, zoom up start/release, and speech speed conversion start/release are provided. For example, when a temporary stop operation signal is sent from the user, a temporary stop is started by a temporary stop part 201 via the signal discrimination section 200. Then a video display section 212 stops tentatively the display of a video image and the succeeding video image s fed from a video image reception section 211 to a recording medium 213 via a video coder 207 and recorded.

10. 发明专利

JPH08166866A EDITING SUPPORT SYSTEM EQUIPPED WITH INTERACTIVE INTERFACE 失效
公开(公告)号：JPH08166866A
公开(公告)日：1996-06-25
申请号：JP26515895
申请日：1995-10-13
申请人： HITACHI LTD
发明人： ANDOU HARU , HATAOKA NOBUO
IPC分类号： G06F3/16 , G06F3/048 , G06F3/14 , G10L13/00 , G10L21/06 , G10L3/00
摘要： PURPOSE: To prepare a document and edit graphics with good operability by inputting a speech, etc., and displaying it at part of a screen, and then sending an indication from a system side for user's operation. CONSTITUTION: When a user inputs a process instruction through a microphone 5-2 by voice and inputs a pointing gesture on a touch panel 5-1 at the same time. The inputted speech is recognized to specify the meaning as a command, which is stored in a memory Com. Then position information inputted by the pointing gesture is stored in a memory. When the process instruction inputted by the user is different from the process result of the system, the user vocalizes a speech negating the process after a series of processes and then the speech is recognized and the meaning is decided, so that the process is corrected. Thus, the contents of the process instruction are made evident and the contents are combined by an information integrating program to perform the actual process.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式