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
    • 1. 发明专利
    • Voice translation device, method and program
    • 语音翻译设备,方法和程序
    • JP2012073941A
    • 2012-04-12
    • JP2010219778
    • 2010-09-29
    • Toshiba Corp株式会社東芝
    • SUMITA KAZUO
    • G06F17/28G10L13/02G10L13/08G10L15/00G10L15/10
    • G06F17/2795G06F17/2854G06F17/289G10L17/26
    • PROBLEM TO BE SOLVED: To realize smooth communication.SOLUTION: A voice translation device comprises an input part, a voice recognition part, a feeling recognition part, a calm sentence generation part, a translation part, a supplementary sentence generation part, and a voice synthesis part. The input part converts voice of a first language into a voice signal. The voice recognition part performs a voice recognition process of the voice signal and generates a character string. The emotional identification part acquires emotional identification information including one or more emotion types by identifying what emotion type the character string has. If the character string includes a non calm phrase of the first language, the calm sentence generation part converts the non calm phrase of the first language into a corresponding calm phrase of the first language and generates a calm sentence using a model which associates non calm phrases changed with emotion with calm phrases corresponding to the non calm phrases not changed with emotion. The translation part generates a translation of the calm sentence translated into a second language. The supplementary sentence generation part generates a supplementary sentence illustrating the emotion types of the emotion identification information in the second language. The voice synthesis part converts the translation and the supplementary sentence into a voice signal.
    • 要解决的问题:实现顺畅的沟通。 解决方案:语音翻译装置包括输入部分,语音识别部分,感觉识别部分,平静句子生成部分,翻译部分,补充句子生成部分和语音合成部分。 输入部分将第一语言的语音转换成语音信号。 语音识别部执行语音信号的语音识别处理,生成字符串。 情感识别部通过识别字符串具有的情感类型来获取包括一种或多种情感类型的情感识别信息。 如果字符串包括第一语言的非平静短语,则平静句子生成部分将第一语言的非平静短语转换为第一语言的对应平静短语,并使用将非平静短语相关联的模型生成平静句子 情绪变化与平静的短语相对应的非平静的短语没有改变与情绪。 翻译部分产生翻译成第二语言的平静句子的翻译。 补充句生成部生成表示第二语言的情感识别信息的情感类型的补充句子。 语音合成部分将翻译和补充句子转换成语音信号。 版权所有(C)2012,JPO&INPIT
    • 2. 发明专利
    • Speech translation device and program
    • 语音翻译设备和程序
    • JP2009205579A
    • 2009-09-10
    • JP2008049211
    • 2008-02-29
    • Toshiba Corp株式会社東芝
    • SUMITA KAZUOCHINO TETSUROKAMAYA SATOSHIUENO AKITSUGU
    • G06F17/28G06F3/16G06F17/30G10L13/00G10L15/00G10L15/10
    • G06F17/289G10L15/26
    • PROBLEM TO BE SOLVED: To provide a speech translation device and program, which can achieve smooth communication. SOLUTION: A character string which is obtained by speech recognition and is to be translated is displayed in an area 205 of a display part 3, and a translated character string is displayed in an area 206. A key word for retrieving a document is extracted from a character string to be translated or a translated character string. If the language of a document which is retrieved by using the key word that has been retrieved is the one to be translated, translation is performed. If the language of the retrieved document is a translated language, then translation into an original language is performed. The retrieved document is displayed in an area 207 while a translated document is displayed in an area 208. By this, sharing of information is supported by the presented document. By pressing down a translation switching button 203, a language to be translated and a translated language can be specified for either of two languages, for supporting dialogue in two directions. COPYRIGHT: (C)2009,JPO&INPIT
    • 要解决的问题:提供可以实现平滑通信的语音翻译装置和程序。 解决方案:通过语音识别获得并被翻译的字符串被显示在显示部分3的区域205中,并且翻译的字符串被显示在区域206中。用于检索文档的关键字 从要翻译的字符串或翻译的字符串中提取。 如果通过使用已被检索的关键词检索的文档的语言是要翻译的文本的语言,则执行翻译。 如果检索到的文档的语言是翻译语言,则执行翻译成原始语言。 检索到的文档显示在区域207中,而在区域208中显示翻译的文档。由此,所呈现的文档支持信息共享。 通过按下翻译切换按钮203,可以为两种语言中的任一种指定要翻译的语言和翻译语言,以支持在两个方向上的对话。 版权所有(C)2009,JPO&INPIT
    • 3. 发明专利
    • Device, method and program for selecting proper candidate from language processing result
    • 用于从语言处理结果中选择适当候选人的设备,方法和程序
    • JP2008242607A
    • 2008-10-09
    • JP2007079381
    • 2007-03-26
    • Toshiba Corp株式会社東芝
    • SUMITA KAZUOMASUKO TAKASHI
    • G06F17/27G06F17/28G10L15/18
    • PROBLEM TO BE SOLVED: To provide a language processor for selecting proper processing results from candidates of processing results. SOLUTION: This language processor is provided with a first storage part 121 for storing constitutional units and a generation probability of a sentence; a second storage part 122 for storing a dependency relation expressed by the constitutional units of a dependency destination and a dependency origin and a conditional probability of the appearance of the constitutional units of the dependency origin with respect to the dependency destination; an input accepting part 101 for accepting the candidate of the processing result; an analyzing part 103 for analyzing the dependency structure of the candidate of the processing result; a calculation part 103a for acquiring the generation probability corresponding to the constitutional units of a sentence end from the first storage part 121 about each of the candidates of the dependency structure, and for acquiring the conditional probability corresponding to the dependency relation from the second storage part 122, and for calculating the generation probability of the candidate of the dependency structure as a product of all the conditional probabilities and a product of the generation probabilities; and a selection part 104 for searching the candidates of the dependency structure maximizing the calculated generation probability, and for selecting the candidates of the processing result corresponding to the searched candidate. COPYRIGHT: (C)2009,JPO&INPIT
    • 要解决的问题:提供一种用于从处理结果候选中选择适当的处理结果的语言处理器。 解决方案:该语言处理器设置有用于存储宪法单位的第一存储部分121和句子的发生概率; 第二存储部122,用于存储由依赖目的地的构成单元表示的依赖关系和依赖起点以及依赖起点相对于依赖目的地的结构单位出现的条件概率; 用于接受处理结果的候选者的输入接受部分101; 用于分析处理结果的候选者的依赖关系结构的分析部分103; 计算部分103a,用于从第一存储部分121获取关于从第一存储部分121的每个句子结尾的结构单位的生成概率,并且从第二存储部分获取与依赖关系对应的条件概率 122,并且用于计算依赖结构的候选者作为所有条件概率的乘积和生成概率的乘积的生成概率; 以及选择部分104,用于搜索最大化所计算的生成概率的依赖关系结构的候选,并且用于选择与所搜索的候选对应的处理结果的候选。 版权所有(C)2009,JPO&INPIT
    • 4. 发明专利
    • Device, method and program of example translation
    • 设备,示例翻译的方法和程序
    • JP2007141133A
    • 2007-06-07
    • JP2005336931
    • 2005-11-22
    • Toshiba Corp株式会社東芝
    • SUMITA KAZUO
    • G06F17/28G10L15/00
    • G06F17/2827
    • PROBLEM TO BE SOLVED: To provide an example translation device by which an appropriate example is easily selected. SOLUTION: The example translation device has: a bilingual example storage part 111 which stores an example in a first language and an example in a second language by associating them with each other; an input acceptance part 101 which accepts a sentence in the first language; an example retrieval part 102 which retrieves the example in the first language and at least one example in the second language associated with the example in the first language from the bilingual example storage part 111 based on the accepted sentence in the first language; an ambiguity detection part 103 which detects whether or not a plurality of examples in the second language exist; an option generation part 104 which acquires the example in the first language associated with the example in the second language, acquires the example in the second language associated with the acquired example in the first language and generates the example in the first language with the least number of acquired examples in the second language as an option for the example to be output when a plurality of examples in the second language exist; and an output control part 105 which outputs the options for the generated example. COPYRIGHT: (C)2007,JPO&INPIT
    • 要解决的问题:提供容易选择适当示例的示例翻译装置。 解决方案:示例翻译装置具有:双语样本存储部分111,其通过将彼此关联来存储第一语言的示例和第二语言的示例; 接受第一语言的句子的输入接受部分101; 基于第一语言的接受句子,从双语示例存储部分111检索第一语言中的示例和与第一语言的示例相关联的至少一个第二语言示例的示例检索部分102; 模糊检测部103,其检测是否存在第二语言的多个例子; 获取与第二语言中的示例相关联的第一语言的示例的选项生成部分104以与第一语言获取的示例相关联的第二语言获取示例,并以最小数量生成具有第一语言的示例 作为在第二语言中存在多个示例的情况下输出该示例的选项的第二语言中的获取的示例; 以及输出控制部105,其输出所生成的例子的选项。 版权所有(C)2007,JPO&INPIT
    • 7. 发明专利
    • Information sharing system and information sharing method
    • 信息共享系统和信息共享方法
    • JP2003288357A
    • 2003-10-10
    • JP2002092924
    • 2002-03-28
    • Toshiba Corp株式会社東芝
    • SUMITA KAZUO
    • G06F17/30G06F13/00G06F15/00
    • PROBLEM TO BE SOLVED: To enable the retrieval and providing of information according to position information and also the exchange of information depending on place or time.
      SOLUTION: In this information sharing system for disclosing information to a plurality of users to share it, an information registration part registers the information to be registered in association with the position information specified by a position specification part. An information retrieval part limits the information to be read in retrieval from an information storage part according to the position information specified by the position specification part. When proper information is not registered as the result of retrieval, a question registration part registers the question.
      COPYRIGHT: (C)2004,JPO
    • 要解决的问题:为了能够根据位置信息检索和提供信息,还可以根据地点或时间交换信息。 解决方案:在用于向多个用户公开信息以共享信息的信息共享系统中,信息注册部分将与由位置指定部分指定的位置信息相关联地登记的信息进行登记。 信息检索部根据由位置指定部指定的位置信息,从信息存储部检索出的要读取的信息。 当正确的信息未被注册为检索结果时,问题注册部分注册该问题。 版权所有(C)2004,JPO
    • 9. 发明专利
    • Preparing method of document, information processor and recording medium
    • 文件的编制方法,信息处理程序和记录介质
    • JPH11282844A
    • 1999-10-15
    • JP7934098
    • 1998-03-26
    • Toshiba Corp株式会社東芝
    • SAKAI TETSUYASUMITA KAZUO
    • G06F3/048G06F3/00G06F17/21G06F17/27G06F17/28
    • PROBLEM TO BE SOLVED: To prepare a text document that is suitable to mechanical processing more, by detecting a language error of the text document in the process of corresponding character strings which are extracted from the text document and are grammatically related.
      SOLUTION: A text document inputted through an inputting part 1 is shown on a screen of a displaying part 2. And it is transferred to a text analyzing part 3 by performing a prescribed instruction operation on the screen. The part 3 performs morphological analysis, syntax analysis, etc., of the text document while referring to a text analytical dictionary 7 stored in a prescribed memory and the analytical result is transferred to a correspondence relation extracting part 4. The part 4 extracts character strings that are related to each other based on the analytical result and produces additional information that associates a character string of a reference destination with a character string of a reference source based on a correspondence relation selected by a user. An editing part 5 reedits the text document based on the produced additional information and stores it in a storing part 6.
      COPYRIGHT: (C)1999,JPO
    • 要解决的问题:通过在文本文档中提取的相应字符串的过程中检测文本文档的语言错误,并且与语法相关,来准备更适合于机械处理的文本文档。 解决方案:通过输入部分1输入的文本文档被显示在显示部分2的屏幕上。并且通过在屏幕上执行规定的指令操作将其传送到文本分析部分3。 第3部分参照存储在规定的存储器中的文本分析词典7进行文本文档的形态分析,语法分析等,分析结果被传送到对应关系提取部分4.部分4提取字符串 基于分析结果彼此相关,并且基于由用户选择的对应关系产生将参考目的地的字符串与参考源的字符串相关联的附加信息。 编辑部分5基于产生的附加信息重新编辑文本文档并将其存储在存储部分6中。
    • 10. 发明专利
    • Information presenting method, information processor and storage medium
    • 信息呈现方法,信息处理器和存储介质
    • JPH11272396A
    • 1999-10-08
    • JP7230498
    • 1998-03-20
    • Toshiba Corp株式会社東芝
    • SAKAI TETSUYASUMITA KAZUO
    • G06F3/048G06F3/00
    • PROBLEM TO BE SOLVED: To enable a user to easily and accurately grasp the outline of informa tion contents from the contents of an imaged display without requiring opera tional labor such as scrolling and page feeding by making it possible to simulta neously display much more information as compared with a display consisting of only characters in the case of displaying a text sentence on a display screen of limited dimensions.
      SOLUTION: The information processor is provided with a storage means 7 for storing a character string and an image corresponding to the character string, an extraction means 6 for extracting the character string stored in the means 7 from an inputted text sentence and a display switching means 5 for substituting an image corresponding to the extracted character string for the extracted character string to display the image or displaying the character string itself in accordance with an inputted instruction at the time of displaying the text sentence.
      COPYRIGHT: (C)1999,JPO
    • 要解决的问题:为了使用户能够从成像显示器的内容中容易且准确地掌握信息内容的轮廓,而不需要诸如滚动和页面馈送等手工劳动,使得可以同时显示更多的信息 与在有限尺寸的显示屏上显示文本句子的情况下仅包含字符的显示器相比。 解决方案:信息处理器设置有用于存储字符串和对应于字符串的图像的存储装置7,用于从输入的文本句子中提取存储在装置7中的字符串的提取装置6和显示切换装置 如图5所示,将与提取的字符串相对应的图像替换为提取的字符串,以在显示文本句子时根据输入的指令显示图像或显示字符串本身。