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. 发明授权

US10609455B2 Information processing apparatus, information processing method, and computer program product 有权
公开(公告)号：US10609455B2
公开(公告)日：2020-03-31
申请号：US15683543
申请日：2017-08-22
申请人： Kabushiki Kaisha Toshiba
发明人： Nayuko Watanabe , Kosei Fume , Hiroshi Fujimura
IPC分类号： G10L15/00 , H04N21/488 , G10L15/26 , G06F17/24 , G10L21/10 , G10L15/22 , G10L15/19 , G10L15/187
摘要： According to an embodiment, an information processing apparatus includes one or more processors. The one or more processors are configured to acquire target sentence data including a plurality of morphemes obtained by speech recognition and speech generation time of each morpheme from the plurality of morphemes; and assign display time according to a difference between a confirmed sentence of which a user's correction for the target sentence data is confirmed and a second confirmed sentence of a previous speech generation time.

2. 发明授权

US09304987B2 Content creation support apparatus, method and program 有权
标题翻译：内容创建支持设备，方法和程序
公开(公告)号：US09304987B2
公开(公告)日：2016-04-05
申请号：US14301378
申请日：2014-06-11
申请人： KABUSHIKI KAISHA TOSHIBA
发明人： Kosei Fume , Masahiro Morita
IPC分类号： G10L15/00 , G06F17/27 , G10L13/08 , G10L15/26 , G10L13/033
CPC分类号： G06F17/2755 , G10L13/033 , G10L13/08 , G10L15/26
摘要： According to one embodiment, a content creation support apparatus includes a speech synthesis unit, a speech recognition unit, an extraction unit, a detection unit, a presentation unit and a selection unit. The speech synthesis unit performs a speech synthesis on a first text. The speech recognition unit performs a speech recognition on the synthesized speech to obtain a second text. The extraction unit extracts feature values by performing a morphological analysis on each of the first and second texts. The detection unit compares a first feature value of a first difference string and a second feature value of a second difference string. The presentation unit presents correction candidate(s) according to the second feature value. The selection unit selects one of the correction candidates in accordance with an instruction from a user.
摘要翻译：根据一个实施例，内容创建支持设备包括语音合成单元，语音识别单元，提取单元，检测单元，呈现单元和选择单元。语音合成单元对第一文本执行语音合成。语音识别单元对合成语音执行语音识别以获得第二文本。提取单元通过对第一和第二文本中的每一个执行形态分析来提取特征值。检测单元将第一差分字符串的第一特征值与第二差分字符串的第二特征值进行比较。呈现单元根据第二特征值呈现校正候选。选择单元根据来自用户的指令来选择一个校正候选。

3. 发明授权

US10606875B2 Search support apparatus and method 有权
公开(公告)号：US10606875B2
公开(公告)日：2020-03-31
申请号：US14847961
申请日：2015-09-08
申请人： KABUSHIKI KAISHA TOSHIBA
发明人： Kosei Fume , Masayuki Okamoto
IPC分类号： G06F16/338 , G06F16/951
摘要： According to one embodiment, a search support apparatus includes a first analyzer, a first acquirer, a measurement unit, a first extractor, a second extractor and a storage. The first analyzer analyzes a clipped document. The first acquirer acquires an updated document by referring to the location information if an original document has been updated. The measurement unit measures a first update frequency of the original document. The first extractor extracts one or more first keywords from the clipped document. The second extractor extracts one or more second keywords from the updated document using a first keyword extraction scheme set in accordance with the first update frequency. The storage stores the one or more first keywords, the one or more second keywords and the update document each associated with the clipped document.

4. 发明授权

US10102859B2 Conference support apparatus, conference support method, and computer program product 有权
公开(公告)号：US10102859B2
公开(公告)日：2018-10-16
申请号：US15387335
申请日：2016-12-21
申请人： Kabushiki Kaisha Toshiba
发明人： Taira Ashikawa , Kosei Fume , Masayuki Ashikawa
IPC分类号： G10L15/26 , G06F3/0481 , G06F3/0482 , G06F17/21 , G10L15/08 , G10L21/10 , G06F17/30 , G06F17/24 , G10L21/06 , G06F17/27
摘要： According to an embodiment, a conference support apparatus includes a recognizer, a detector, a summarizer, and a subtitle generator. The recognizer is configured to recognize speech in speech data and generate text data. The detector is configured to detect a correction operation on the text data, the correction operation being an operation of correcting character data that has been incorrectly converted. The summarizer is configured to generate a summary relating to the text data subsequent to a part to which the correction operation is being performed, among the text data, when the correction operation is being detected. The subtitle generator is configured to generate subtitle information corresponding to the summary when the correction operation is being detected, and configured to generate subtitle information corresponding to the text data except when the correction operation is being detected.

5. 发明授权

US09928828B2 Transliteration work support device, transliteration work support method, and computer program product 有权
公开(公告)号：US09928828B2
公开(公告)日：2018-03-27
申请号：US15090776
申请日：2016-04-05
申请人： KABUSHIKI KAISHA TOSHIBA
发明人： Kosei Fume , Yuka Kuroda , Yoshiaki Mizuoka , Masahiro Morita
IPC分类号： G06F17/28 , G10L13/08 , G10L13/027 , G06F17/22 , G06F17/27
CPC分类号： G10L13/08 , G06F17/2223 , G06F17/2264 , G06F17/273 , G06F17/2755 , G10L13/027
摘要： According to an embodiment, a transliteration work support device includes an analysis unit, a storage unit, an estimation unit, a construction unit, a correction unit, and an update unit. The analysis unit performs language analysis on document data and creates transliteration auxiliary information representing a way of transliteration of a word or a phrase in the document data. The storage unit stores a correction history representing a way of transliteration corrected in the past of the word or the phrase. The estimation unit estimates a correction place and a correction candidate of the document data or the transliteration auxiliary information from the history. The construction unit constructs work list information including work items corresponding to types of corrections according to the correction candidate and progress information. The correction unit corrects the document data or the transliteration auxiliary information. The update unit updates the history and the progress information according to the correction.

6. 发明申请

US20160085844A1 TAG ADDING APPARATUS AND TAG ADDING METHOD 审中-公开
标题翻译：标签添加设备和标签添加方法
公开(公告)号：US20160085844A1
公开(公告)日：2016-03-24
申请号：US14848014
申请日：2015-09-08
申请人： KABUSHIKI KAISHA TOSHIBA
发明人： Masayuki Okamoto , Kosei Fume
IPC分类号： G06F17/30
CPC分类号： G06F16/951 , G06F16/3338 , G06F16/93
摘要： According to one embodiment, a tag adding apparatus includes the following units. The input unit inputs an input tag added to an input content item. The storage unit stores registered content items in association with registered tags. The search unit retrieves a first and a second content aggregate from the storage unit. The analyzer analyzes the number of content items of the first content aggregate, and to analyze an inclusion relationship between the first and the second content aggregate. The determination unit determines an additional tag to be additionally added to the input content item based on a result of analysis. The registration unit registers the input content item in the storage unit in association with the input tag and the additional tag.
摘要翻译：根据一个实施例，标签添加装置包括以下单元。输入单元输入添加到输入内容项目的输入标签。存储单元与登记的标签相关联地存储登记的内容项。搜索单元从存储单元检索第一和第二内容聚合。分析器分析第一内容聚合的内容项的数量，并分析第一和第二内容聚合之间的包含关系。确定单元基于分析结果确定要附加到输入内容项目的附加标签。注册单元将输入内容项目与输入标签和附加标签相关联地登记在存储单元中。

7. 发明申请

US20150095314A1 DOCUMENT SEARCH APPARATUS AND METHOD 审中-公开
标题翻译：文件搜索装置和方法
公开(公告)号：US20150095314A1
公开(公告)日：2015-04-02
申请号：US14500149
申请日：2014-09-29
申请人： KABUSHIKI KAISHA TOSHIBA
发明人： Masayuki Okamoto , Kosei Fume
IPC分类号： G06F17/24 , G06F17/30
CPC分类号： G06F17/241 , G06F16/156 , G06F16/38
摘要： According to one embodiment, a related document search apparatus includes a first acquisition unit, a storage, a search unit, a second acquisition unit, a determination unit and a display. The first acquisition unit acquires a document and first annotation added to the document. The search unit searches for document(s) related to content of a search document from the storage, to acquire searched document(s) as related document(s). The determination unit determines whether the second annotation includes a character. The display displays the search document and the second annotation if the second annotation information includes a character, and to display the search document, the second annotation, and an area of the related document to which the second annotation is added if the second annotation includes no character.
摘要翻译：根据一个实施例，相关文档搜索装置包括第一获取单元，存储器，搜索单元，第二获取单元，确定单元和显示器。第一采集单元获取添加到文档中的文档和第一注释。搜索单元从存储器搜索与搜索文档的内容相关的文档，以获取作为相关文档的搜索文档。确定单元确定第二注释是否包括字符。如果第二注释信息包括字符，则显示器显示搜索文档和第二注释，并且如果第二注释不包括第二注释，则显示搜索文档，第二注释以及添加了第二注释的相关文档的区域字符。

8. 发明申请

US20140304118A1 PRODUCT COMPARISON APPARATUS AND METHOD 审中-公开
标题翻译：产品比较装置和方法
公开(公告)号：US20140304118A1
公开(公告)日：2014-10-09
申请号：US14195741
申请日：2014-03-03
申请人： KABUSHIKI KAISHA TOSHIBA
发明人： Kenta Cho , Masayuki Okamoto , Kosei Fume , Masaru Suzuki
IPC分类号： G06Q30/06
CPC分类号： G06Q30/0629
摘要： According to an embodiment, a product comparison apparatus for comparing a plurality of products includes an operation acceptance unit, a comparison table generator, and a display unit. The operation acceptance unit is configured to accept a user operation for selecting a plurality of annotated documents which include specification information items related to the products and annotations appended by a user. The comparison table generator is configured to generate a comparison table comprising the specification information items related to the products, in accordance with the user operation. The display unit is configured to display the comparison table.
摘要翻译：根据实施例，用于比较多个产品的产品比较装置包括操作接受单元，比较表生成器和显示单元。操作接受单元被配置为接受用于选择包括与用户附加的产品和注释相关的指定信息项目的多个注释文档的用户操作。比较表生成器被配置为根据用户操作生成包括与产品相关的规格信息项的比较表。显示单元被配置为显示比较表。

9. 发明申请

US20140289247A1 ANNOTATION SEARCH APPARATUS AND METHOD 审中-公开
标题翻译：新闻搜索设备和方法
公开(公告)号：US20140289247A1
公开(公告)日：2014-09-25
申请号：US14195705
申请日：2014-03-03
申请人： KABUSHIKI KAISHA TOSHIBA
发明人： Masayuki Okamoto , Masaru Suzuki , Kosei Fume , Kenta Cho
IPC分类号： G06F17/30
CPC分类号： G06F16/9535
摘要： According to an embodiment, an annotation search apparatus includes a feature extractor and an annotation search unit. The feature extractor is configured to extract an annotation feature from an input document and an annotation appended by a user to the input document. The annotation search unit is configured to search annotation information items to retrieve at least one of the annotation information items according to an intended purpose of the user, one of the annotation information items corresponding to the input document and including the annotation feature.
摘要翻译：根据实施例，注释搜索装置包括特征提取器和注释搜索单元。特征提取器被配置为从输入文档和用户附加到输入文档的注释提取注释特征。注释搜索单元被配置为搜索注释信息项以根据用户的预期目的来检索注释信息项中的至少一个，与输入文档相对应的注释信息项之一并且包括注释特征。

10. 发明授权

US11429786B2 Document analysis device, learning device, document analysis method, and learning method 有权
公开(公告)号：US11429786B2
公开(公告)日：2022-08-30
申请号：US16801326
申请日：2020-02-26
申请人： KABUSHIKI KAISHA TOSHIBA
发明人： Kosei Fume
IPC分类号： G06F40/268 , G06N3/08 , G06K9/62 , G06V10/44 , G06V30/413
摘要： According to an embodiment, a document analysis device includes one or more hardware processors configured to function as a sentence extraction unit, an analysis unit, a neural network unit. The analysis unit generates, for each of sentences, initial element information representing an initial value of relevance to each of predetermined attribute items. The neural network unit receives sentence information and outputs execution result of a main task on the target document, for each of the sentences. The neural network unit includes an attention unit and a main task execution. The attention receives the sentence information and the initial element information, calculates an attention weight and outputs attention information according to the attention weight, for each of the sentences. The main task execution unit executes the main task based on the attention information for each of the sentences.

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