专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

61. 发明申请

US20050033574A1 Method and apparatus handling speech recognition errors in spoken dialogue systems 有权
标题翻译：处理语音对话系统中语音识别错误的方法和设备
公开(公告)号：US20050033574A1
公开(公告)日：2005-02-10
申请号：US10911675
申请日：2004-08-05
申请人： Jung-eun Kim , Jae-won Lee
发明人： Jung-eun Kim , Jae-won Lee
IPC分类号： G10L15/08 , G10L15/18 , G10L15/22 , G10L15/00
CPC分类号： G10L15/22 , G10L15/08 , G10L15/1815
摘要： In order to handle portions of a recognized sentence having an error, a speaker or user is questioned about contents associated with the portions, and according to a user's answer a result is obtained. A speech recognition unit extracts a speech feature of a speech signal inputted from a user and finds a phoneme nearest to the speech feature to recognize a word. A recognition error determination unit finds a sentence confidence based on a confidence of the recognized word, performs examination of a semantic structure of a recognized sentence, and determines whether or not an error exists in the recognized sentence which is subject to speech recognition according to a predetermined criterion based on both the sentence confidence and a result of examining the semantic structure of the recognized sentence. Further, a meta-dialogue generation unit generates a question asking the user for additional information based on a content of a portion where the error exists and a type of the error.
摘要翻译：为了处理具有错误的识别句子的部分，向与该部分相关的内容询问扬声器或用户，并根据用户的答案获得结果。语音识别单元提取从用户输入的语音信号的语音特征，并找到最接近语音特征的音素来识别单词。识别错误确定单元基于所识别的字的置信度来查找句子置信度，对识别的句子的语义结构进行检查，并且根据一个判断单元确定是否存在经过语音识别的识别句子中的错误基于句子置信度和检查识别句子的语义结构的结果的预定标准。此外，元对话生成单元基于存在错误的部分的内容和错误的类型生成询问用户附加信息的问题。

62. 发明授权

US6133824A Method for modeling roadway and method for recognizing lane markers based on the same 失效
标题翻译：巷道建模方法及其识别方法
公开(公告)号：US6133824A
公开(公告)日：2000-10-17
申请号：US379594
申请日：1999-08-24
申请人： Suk-han Lee , Jae-won Lee , Dong-mok Shin , Woong Kwon , Dong-yoon Kim , Kyoung-sig Roh
发明人： Suk-han Lee , Jae-won Lee , Dong-mok Shin , Woong Kwon , Dong-yoon Kim , Kyoung-sig Roh
IPC分类号： G08G1/16 , B60Q1/52 , G01S13/93 , G06K9/46 , B60Q1/00
CPC分类号： G06K9/00798 , B60Q9/008 , G01S13/931 , G06K9/4604 , G01S2013/9353
摘要： A method for modeling a roadway and a method for recognizing lane markers based on the modeling method. The method for recognizing lane markers of roadway for a vehicle by getting image information about the roadway and information about the speed and steering angle using a camera and a sensor attached to the vehicle, includes the steps of modeling the actual roadway on which the vehicle travels, as a structure having a plurality of rectangular plates linked to each other. The modeled plates are overlayed onto the image information about the actual roadway, photographed by the camera, pixels forming the lane markers are extracted, and linear lane marker information is then obtained from the pixels forming the land markers. Then, the linear lane marker information is overlayed onto the modeled plates to recalculate lane marker information using the plates as a frame, and predetermined limitations of the features of the lane markers are applied to the plates onto which the linear lane marker information has been overlayed, to optimize the lane marker information. Then, the roadway on which the vehicle is traveling, is remodeled using the optimized lane marker information, the information about the speed and steering angle of the vehicle measured by the sensor, and the information about the modeled plates, and the position and orientation of the remodeled plates are calculated. Therefore, roadway recognition can be easily achieved using a modeled structure of the roadway, in which a plurality of rectangular plates are linked. Also, the model roadway is repeatedly mapped onto the actual roadway image, so that reliability in recognition of roadway increases.
摘要翻译：基于建模方法的道路建模方法和车道识别识别方法。通过使用摄像机和安装在车辆上的传感器获取关于车道的图像信息和关于速度和转向角的信息来识别车辆道路车道标记的方法包括以下步骤：对车辆行进的实际道路进行建模作为具有彼此连接的多个矩形板的结构。将建模的板叠加在由相机拍摄的关于实际道路的图像信息上，提取形成车道标记的像素，然后从形成陆地标记的像素获得线性车道标记信息。然后，将线性车道标记信息覆盖在建模的板上，以板为框重新计算车道标记信息，并且将车道标记的特征的预定限制应用于已经覆盖线性车道标记信息的板，以优化车道标记信息。然后，使用优化的车道标记信息，由传感器测量的关于车辆的速度和转向角的信息以及关于模型板的信息，以及关于车辆行驶的道路的位置和方位计算出改造后的板材。因此，可以使用多个矩形板连接的道路的建模结构容易地实现道路识别。此外，模型道路被重复地映射到实际的道路图像上，使得道路识别的可靠性增加。

63. 发明申请

US20130124733A1 SERVER AND METHOD FOR PROVIDING MOBILE WEB SERVICE 审中-公开
标题翻译：提供移动WEB服务的服务器和方法
公开(公告)号：US20130124733A1
公开(公告)日：2013-05-16
申请号：US13735706
申请日：2013-01-07
申请人： Jae-won Lee , Joon-sung Hong
发明人： Jae-won Lee , Joon-sung Hong
IPC分类号： H04L12/56
CPC分类号： H04L47/70 , H04L67/02 , H04L67/2861
摘要： A server for a mobile web service and a method for providing a web service are provided. The wired server stores an IP address of at least one mobile web server. When a request for access to a mobile web server is received, the wired server delivers the access request to the mobile web server or provides a service in place of the mobile web server, using a URL included in the access request.
摘要翻译：提供了用于移动Web服务的服务器和用于提供web服务的方法。有线服务器存储至少一个移动Web服务器的IP地址。当接收到访问移动Web服务器的请求时，有线服务器使用访问请求中包含的URL将访问请求传送到移动Web服务器或者提供代替移动web服务器的服务。

64. 发明授权

US08301450B2 Apparatus, method, and medium for dialogue speech recognition using topic domain detection 有权
标题翻译：使用主题域检测的对话语音识别的装置，方法和介质
公开(公告)号：US08301450B2
公开(公告)日：2012-10-30
申请号：US11589165
申请日：2006-10-30
申请人： Jae-won Lee , In-jeong Choi
发明人： Jae-won Lee , In-jeong Choi
IPC分类号： G06F17/27 , G10L15/00 , G10L15/04 , G10L17/00 , G10L15/18
CPC分类号： G10L15/1822 , G10L15/1815
摘要： An apparatus, method, and medium for dialogue speech recognition using topic domain detection are disclosed. An apparatus includes a forward search module performing a forward search in order to create a word lattice similar to a feature vector, which is extracted from an input voice signal, with reference to a global language model database, a pronunciation dictionary database and an acoustic model database, which have been previously established, a topic-domain-detection module detecting a topic domain by inferring a topic based on meanings of vocabularies contained in the word lattice using information of the word lattice created as a result of the forward search, and a backward-decoding module performing a backward decoding of the detected topic domain with reference to a specific topic domain language model database, which has been previously established, thereby outputting a speech recognition result for an input voice signal in text form. Accuracy and efficiency for a dialogue sentence are improved.
摘要翻译：公开了一种使用主题域检测进行对话语音识别的装置，方法和介质。一种装置，包括执行前向搜索的前向搜索模块，以便参考全局语言模型数据库，发音词典数据库和声学模型来创建类似于从输入语音信号提取的特征向量的单词格数据库，其已经建立，主题域检测模块通过使用由作为前向搜索的结果创建的单词格点的信息，基于包含在单词格中的词汇的含义来推断主题来检测主题领域，以及后向解码模块参照已经建立的特定主题域语言模型数据库执行所检测到的主题域的反向解码，从而以文本形式输出用于输入语音信号的语音识别结果。提高对话句子的准确性和效率。

65. 发明授权

US07949750B2 Apparatus and method for controlling access in P2P network 有权
标题翻译：控制P2P网络接入的装置和方法
公开(公告)号：US07949750B2
公开(公告)日：2011-05-24
申请号：US12349091
申请日：2009-01-06
申请人： Jae-won Lee , Hee-ycul Kim
发明人： Jae-won Lee , Hee-ycul Kim
IPC分类号： G06F13/00
CPC分类号： H04L63/10
摘要： An apparatus and method to control access in a P2P (peer-to-peer) network. The apparatus for controlling access in a P2P network includes an attribute processing module to obtain an attribute of a service requestor and to determine an access control policy for the service requestor based on the obtained attribute; and an access control module to control the provision of a service to the service requester according to the access control policy. If a service provider is unable to obtain the attribute of the service requester, the service provider obtains the attribute of the service requester from at least one peer in the network.
摘要翻译：控制P2P（对等）网络中的接入的装置和方法。用于控制P2P网络中的访问的装置包括：属性处理模块，用于获取服务请求者的属性，并根据所获得的属性确定服务请求者的访问控制策略; 以及访问控制模块，用于根据访问控制策略来控制向服务请求者提供服务。如果服务提供商不能获得服务请求者的属性，则服务提供商从网络中的至少一个对等体获得服务请求者的属性。

66. 发明授权

US07734468B2 Method of and apparatus for managing dialog between user and agent 有权
标题翻译：用户和代理之间管理对话的方法和设备
公开(公告)号：US07734468B2
公开(公告)日：2010-06-08
申请号：US10732235
申请日：2003-12-11
申请人： Joon-ah Park , Young-jin Hong , Jae-won Lee
发明人： Joon-ah Park , Young-jin Hong , Jae-won Lee
IPC分类号： G10L21/00 , G06K9/00
CPC分类号： G10L15/24 , G10L15/22
摘要： A method of rapidly and precisely managing a dialog turn between a user and an agent by using speech information, facial expression information, and delay time information includes generating first dialog turn information using dialog information analyzed from a speech uttered by the user, generating second dialog turn information using facial expression information analyzed from a face image of the user, and determining a final dialog turn using the first and second dialog turn information, information on a status of the spoken dialog system, information on whether the user speech is input, and information on a no-answer time of the user.
摘要翻译：通过使用语音信息，面部表情信息和延迟时间信息快速且精确地管理用户和代理之间的对话转弯的方法包括使用从用户发出的语音分析的对话信息产生第一对话转弯信息，产生第二对话使用从用户的脸部图像分析的面部表情信息来转动信息，并使用第一和第二对话转弯信息，关于口语对话系统的状态的信息，关于用户语音是否被输入的信息来确定最终的对话转弯;以及关于用户的无应答时间的信息。

67. 发明授权

US07725322B2 Spoken dialogue interface apparatus and method 失效
标题翻译：口语对话界面设备和方法
公开(公告)号：US07725322B2
公开(公告)日：2010-05-25
申请号：US11348301
申请日：2006-02-07
申请人： Byung-kwan Kwak , Jae-won Lee
发明人： Byung-kwan Kwak , Jae-won Lee
IPC分类号： G10L21/00 , G10L13/00
CPC分类号： G10L15/1822
摘要： The spoken dialogue interface apparatus according to an embodiment of the present invention includes a speech recognition module for recognizing a human's speech from a sound signal; a user intention interpretation module for extracting a sentence from the recognized speech and interpreting a user's intention based on the sentence; a user intention selection module for determining user intention using the interpreted user's intention and a predetermined domain action frame; and a system response generation module for generating a system response sentence corresponding to the selected user intention, wherein the domain action frame includes service information which the user requests, and parameter information which is used to perform a service, and the domain action frame is constructed to have a hierarchical tree structure.
摘要翻译：根据本发明的实施例的口语对话界面装置包括：语音识别模块，用于从声音信号识别人的语音; 用户意图解释模块，用于从所识别的语音中提取句子，并且基于所述句子解释用户的意图; 用户意图选择模块，用于使用解释的用户的意图和预定的域动作帧来确定用户意图; 以及系统响应生成模块，用于生成与所选择的用户意图相对应的系统响应语句，其中所述域动作帧包括用户请求的服务信息，以及用于执行服务的参数信息，并且构造域动作帧具有层次树结构。

68. 发明申请

US20090136135A1 Apparatus and method for recognizing characters 有权
标题翻译：用于识别字符的装置和方法
公开(公告)号：US20090136135A1
公开(公告)日：2009-05-28
申请号：US12076280
申请日：2008-03-14
申请人： Ki-wan Eom , Jae-won Lee , Jung-eun Kim
发明人： Ki-wan Eom , Jae-won Lee , Jung-eun Kim
IPC分类号： G06K9/00
CPC分类号： G06K9/2081 , G06K9/325 , G06K2209/01
摘要： Provided is an apparatus and method for recognizing characters. The apparatus includes a display unit to display an image in which a region of interest or an error region is indicated, and a character recognition result, a region-of-interest setting unit to set the region of interest in the image displayed on the display unit, a recognition unit to perform character recognition on the region of interest or the error region and provide the character recognition result to the display unit, and an error correction unit to set the error region in the image displayed on the display region, perform image copying on the set error region according to a user input, and provide a handwriting input using the image copying to the recognition unit.
摘要翻译：提供了一种用于识别字符的装置和方法。该装置包括：显示单元，用于显示其中指示感兴趣区域或错误区域的图像;以及字符识别结果，感兴趣区域设置单元，用于设置显示在显示器上的图像中的感兴趣区域单元，识别单元，用于在感兴趣区域或错误区域上执行字符识别，并将字符识别结果提供给显示单元;以及纠错单元，用于设置在显示区域上显示的图像中的错误区域，执行图像根据用户输入在设置的错误区域上进行复制，并且使用图像复制将手写输入提供给识别单元。

69. 发明授权

US06897854B2 Electronic pen input device and coordinate detecting method therefor 失效
标题翻译：电子笔输入装置及其坐标检测方法
公开(公告)号：US06897854B2
公开(公告)日：2005-05-24
申请号：US10102649
申请日：2002-03-22
申请人： Yong-chul Cho , Suk-han Lee , Kyoung-sig Roh , Jae-won Lee
发明人： Yong-chul Cho , Suk-han Lee , Kyoung-sig Roh , Jae-won Lee
IPC分类号： G01B11/02 , G01B11/26 , G06F3/041 , G08C17/00 , G08C21/00 , G09G5/00
CPC分类号： G06K9/224 , G06F3/03542 , G06F3/03545
摘要： A electronic pen input device and a coordinate determining method are provided. The electronic pen input device includes an optical 3-dimensional detecting device for detecting orientation angles of a centerline of the pen relative to a ground and a height of the pen over a writing surface, a 3-axis accelerometer for detecting a movement of the pen, and a communication means for sending the detected information to a post processing device.
摘要翻译：提供电子笔输入装置和坐标确定方法。电子笔输入装置包括：光学三维检测装置，用于检测笔相对于地面的中心线的方向角度以及笔在书写表面上的高度; 3轴加速度计，用于检测笔的运动以及用于将检测到的信息发送到后处理装置的通信装置。

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