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

JP2008250385A Information retrieval device, information retrieval method and information retrieval program 有权
标题翻译：信息检索设备，信息检索方法和信息检索程序
公开(公告)号：JP2008250385A
公开(公告)日：2008-10-16
申请号：JP2007087384
申请日：2007-03-29
申请人： Toshiba Corp , 株式会社東芝
发明人： SUZUKI MASARU , ISHITANI YASUTO
IPC分类号： G06F17/30 , G06F3/12
CPC分类号： G06F17/30637
摘要： PROBLEM TO BE SOLVED: To improve usability by automatically setting a retrieval condition.
SOLUTION: The device comprises a co-occurring phrase accumulation part for storing a first phrase in association with a second phrase which is contained in the same document as the first phrase is contained and relates to a plurality of semantic attributes; a condition storage part for storing the semantic attribute of the first phrase in association with a characteristic word extracted from the document and a condition item; an input receiving part for receiving input of a keyword; a semantic attribute acquisition part for acquiring the semantic attribute of the input keyword; a characteristic word extraction part for extracting a characteristic word contained in a document containing the keyword; a condition extraction part for extracting a semantic attribute associated with the acquired semantic attribute and the extracted characteristic word from the co-occurring phrase accumulation part; and a retrieval part for retrieving a document containing the keyword and an additional keyword.
COPYRIGHT: (C)2009,JPO&INPIT
摘要翻译：要解决的问题：通过自动设置检索条件来提高可用性。解决方案：该装置包括一个共同出现的短语累积部分，用于存储与包含在与第一短语相同的文档中的第二短语相关联的第一短语，并且涉及多个语义属性; 条件存储部分，用于存储与从文档提取的特征词和条件项相关联的第一短语的语义属性; 用于接收关键字的输入的输入接收部分; 用于获取输入关键字的语义属性的语义属性获取部分; 特征词提取部分，用于提取包含在包含该关键词的文档中的特征词; 条件提取部分，用于提取与获取的语义属性相关联的语义属性和从共同出现的短语累积部分提取的特征词; 以及用于检索包含关键字的文档和附加关键字的检索部分。版权所有（C）2009，JPO＆INPIT

2. 发明专利

JP2007094855A Document processing device and method 有权
标题翻译：文件处理装置和方法
公开(公告)号：JP2007094855A
公开(公告)日：2007-04-12
申请号：JP2005284885
申请日：2005-09-29
申请人： Toshiba Corp , 株式会社東芝
发明人： NUNOME MITSUO , ISHITANI YASUTO
IPC分类号： G06F17/21 , G06F17/30
摘要： PROBLEM TO BE SOLVED: To provide a document processing device that can assign appropriate semantic tags to various documents. SOLUTION: A general proper expression extraction part 11 and a semantic role word extraction part 12 extract general proper expressions and semantic role words from an input document 100, and a general document structure analysis part 13 computes a basic document structure. A document type identification part 15 selects a document type for the input document by comparing a resultant document model based on the general proper expressions and semantic role words with each of document models based on general proper expressions and semantic role words which are defined for respective document types. A detailed document structure detection part 16 detects substructures of the input document according to information on detailed document structure based on general proper expressions and semantic role words which is defined for the document type. A semantic tag assignment part 17 assigns semantic tags predefined for the detailed document structure to the detected substructures to create an output document 101. COPYRIGHT: (C)2007,JPO&INPIT
摘要翻译：要解决的问题：提供可以为各种文档分配适当的语义标签的文档处理装置。解决方案：一般正则表达式提取部分11和语义角色提取部分12从输入文档100中提取一般的正确表达和语义角色词，并且一般文档结构分析部分13计算基本文档结构。文档类型识别部分15通过将基于一般适当表达和语义角色词的结果文档模型与基于为相应文档定义的一般适当表达和语义角色词的每个文档模型进行比较来选择输入文档的文档类型类型。详细的文档结构检测部分16基于针对文档类型定义的一般适当表达和语义角色词，根据关于详细文档结构的信息来检测输入文档的子结构。语义标签分配部分17将为详细文档结构预定义的语义标签分配给检测到的子结构以创建输出文档101.版权所有（C）2007，JPO＆INPIT

3. 发明专利

JP2006053612A Document conversion device and method, and document conversion program 有权
标题翻译：文件转换装置和方法以及文件转换程序
公开(公告)号：JP2006053612A
公开(公告)日：2006-02-23
申请号：JP2004232785
申请日：2004-08-09
申请人： Toshiba Corp , 株式会社東芝
发明人： NUNOME MITSUO , ISHITANI YASUTO
IPC分类号： G06F17/21
摘要： PROBLEM TO BE SOLVED: To provide a document processor capable of properly extracting a table structure or a portion of a structure similar to a table in a document, and generating an output document wherein the extracted table structure or protion of the structure similar to the table can be used as a structured document. SOLUTION: This document processor 1 has: a knowledge dictionary part 7 defining attribute impartment information; a conversion rule part 9 defining output restriction information; an attribute impartment part 3 deciding presence/absence of a predetermined character string to a character string appearing in a specified conversion target part, and imparting attribute information corresponding to the predetermined character string on the basis of the attribute impartment information of the knowledge dictionary part; a conversion mapping generation part 4 determining regularity of appearance of the predetermined attribute information defined in the output restriction information from the attribute information imparted by the attribute impartment part, and generating conversion mapping of the output restriction information; and an output document generation part 5 generating and outputting the output document from information about the generated conversion mapping in a form according with the output restriction information. COPYRIGHT: (C)2006,JPO&NCIPI
摘要翻译：要解决的问题：提供能够正确地提取与文档中的表类似的表结构或部分结构的文档处理器，并且生成输出文档，其中所提取的表结构或结构类似到表可以用作结构化文档。解决方案：该文档处理器1具有：定义属性分段信息的知识字典部分7; 定义输出限制信息的转换规则部分9; 属性公开部分3，判定出现在指定转换目标部分中的字符串的预定字符串的存在/不存在，并且基于知识字典部分的属性分段信息来赋予与预定字符串相对应的属性信息; 转换映射生成部分4，根据由属性公开部分赋予的属性信息，确定在输出限制信息中定义的预定属性信息的外观的规则性，并生成输出限制信息的转换映射; 以及输出文档生成部5，根据与输出限制信息对应的形式，生成并输出关于生成的转换映射的信息的输出文档。版权所有（C）2006，JPO＆NCIPI

4. 发明专利

JP2004178011A Document conversion device and documents conversion method 审中-公开
公开(公告)号：JP2004178011A
公开(公告)日：2004-06-24
申请号：JP2002340000
申请日：2002-11-22
申请人： Toshiba Corp , 株式会社東芝
发明人： NUNOME MITSUO , ISHITANI YASUTO , SUZUKI MASARU , KANEWA TAKUYA , ISOBE SHOZO , ONO KENJI
IPC分类号： G06F17/21
摘要： PROBLEM TO BE SOLVED: To reduce burden of a user in refinement of a structured document and to obtain a proper structured document output satisfying target document type restriction. SOLUTION: The document structure including a tree structure is obtained by analyzing an input document having an optional structure. As to this input document, a surface expression appearing in the input document is extracted by referring to a predetermined knowledge dictionary. The document structure is refined by applying a predetermined structure refining rule to the extracted surface expression. The refined document structure is compared with a predetermined target document type restriction to verify and correct it. COPYRIGHT: (C)2004,JPO

5. 发明专利

JPH0877294A IMAGE PROCESSOR FOR DOCUMENT 失效
公开(公告)号：JPH0877294A
公开(公告)日：1996-03-22
申请号：JP21295194
申请日：1994-09-06
申请人： TOSHIBA CORP
发明人： ISHITANI YASUTO
IPC分类号： G06K9/20 , G06K9/46 , G06K9/62
摘要： PURPOSE: To provide the document image processor which can accurately specify the document format of a document, etc., and efficiently extract and read a character string. CONSTITUTION: Figure feature quantities extracted by a feature extraction part 12 from an input image of the document generated by an image input part 11 are grouped by a feature structuring part 13, and the relation of the respective features is extracted and managed. The kind of the format structure of the input document is estimated by using the structured features and information (format structure model) regarding the format structure of a document to be processed which is previously registered in a format structure kind identification part 15. A format structure information collation part 16 extracts detailed correspondence relation between the format structure model corresponding to the estimated kind of the format structure and the structured features of the input document. After noncorrespondence and contradict correspondence finding and correction part 18 obtains the matching of the correspondence relation, a document structure acquisition part 19 copies information regarding the previously registered document structure model to the input document on the basis of the correspondence relation to acquire the structure and relative knowledge of the input document.

6. 发明专利

JPH04352295A SYSTEM AND DEVICE FOR IDENTIFING CHARACTER STRING DIRECTION 失效
公开(公告)号：JPH04352295A
公开(公告)日：1992-12-07
申请号：JP12713191
申请日：1991-05-30
申请人： TOSHIBA CORP
发明人： ISHITANI YASUTO , ARIYOSHI SHUNJI
IPC分类号： G06K9/20
摘要： PURPOSE:To correctly identify the direction of a character string on various documents including a document whose character spacing is larger than its line spacing since the direction of the character string is identified by detecting the state of blank lines (or blank column) obtained from image data of an input document. CONSTITUTION:The device consists of a means 6 which extracts the extent of horizontal character arrangement from the inputted image data, a means which extracts the extent of vertical character arrangement, and a means 5 which compares the extents of horizontal character arrangement and vertical character arrangement with each other to identify the character string direction in the image.

7. 发明专利

JP2007095102A Document processor and document processing method 有权
标题翻译：文件处理器和文件处理方法
公开(公告)号：JP2007095102A
公开(公告)日：2007-04-12
申请号：JP2006348367
申请日：2006-12-25
申请人： Toshiba Corp , 株式会社東芝
发明人： ISHITANI YASUTO
IPC分类号： G06F17/21 , G06K9/20
摘要： PROBLEM TO BE SOLVED: To perform automatic input to a computer by extracting and structuring contents written in printed documents. SOLUTION: The document processor comprises: a means 1 for extracting a layout object and a structure from a document image; a means 3 for extracting logical objects, such as a paragraph, a list, a numerical expression, a program, and an annotation, from an area of a text extracted from the document image on the basis of typography; a means 5 for extracting a plurality of possible orders of reading among the objects; and a means 4 for extracting a logical structure by applying a predefined model to the logical objects. By extracting primary information and secondary information even from various documents of a plurality of pages comprising characters, photographs, figures, and tables, automatic establishment of a document management system and a variety of computer application can be used effectively. COPYRIGHT: (C)2007,JPO&INPIT
摘要翻译：要解决的问题：通过提取和构建写入打印文档的内容来执行对计算机的自动输入。解决方案：文档处理器包括：用于从文档图像中提取布局对象和结构的装置1; 用于从基于排版的文档图像提取的文本的区域中提取诸如段落，列表，数字表达式，程序和注释的逻辑对象的装置3; 用于提取多个可能的读取顺序的装置5; 以及用于通过将预定模型应用于逻辑对象来提取逻辑结构的装置4。通过从包括字符，照片，图形和表格的多个页面的各种文档中提取主信息和次要信息，可以有效地使用文档管理系统的自动建立和各种计算机应用。版权所有（C）2007，JPO＆INPIT

8. 发明专利

JP2006236140A Information managing device, information management method and information management program 审中-公开
标题翻译：信息管理设备，信息管理方法和信息管理程序
公开(公告)号：JP2006236140A
公开(公告)日：2006-09-07
申请号：JP2005051823
申请日：2005-02-25
申请人： Toshiba Corp , 株式会社東芝
发明人： ISHII DAISUKE , SUZUKI MASARU , ISHITANI YASUTO
IPC分类号： G06F17/30 , G06F12/00
CPC分类号： G06F17/30064
摘要： PROBLEM TO BE SOLVED: To easily obtain necessary information on the basis of event information display by collectively managing information about past work and meta information of work by using the event information.
SOLUTION: A plurality of events are generated which include: information about work, representing at least any of a retrieval query for retrieving a document, the place of a retrieval result document, the place of a display document, a component document composed of a portion of the document and a scrap sheet constituted of the component document; at least time information for time at which the work is performed; and work type information. The plurality of generated events are stored in an event storing means. The plurality of stored events are arranged according to time information for time at which the work is performed and displayed in different display forms in accordance with the work type information. When any event is selected from among the plurality of displayed events, information about work belonging to the selected event is displayed.
COPYRIGHT: (C)2006,JPO&NCIPI
摘要翻译：要解决的问题：通过使用事件信息集体管理关于过去工作的信息和工作的元信息，基于事件信息显示容易地获得必要的信息。
解决方案：生成多个事件，其包括：关于工作的信息，至少表示用于检索文档的检索查询，检索结果文档的位置，显示文档的位置，组成的组件文档的一部分文件和由组件文件构成的废纸; 至少要进行工作时间的时间信息; 和工作类型信息。多个生成的事件被存储在事件存储装置中。根据工作类型信息，根据时间信息对多个存储的事件进行排列，以便以不同的显示形式执行工作并显示工作。当从多个显示的事件中选择任何事件时，显示关于属于所选事件的工作的信息。版权所有（C）2006，JPO＆NCIPI

9. 发明专利

JP2002108940A METHOD AND DEVICE FOR RETRIEVING INFORMATION 失效
公开(公告)号：JP2002108940A
公开(公告)日：2002-04-12
申请号：JP2000298282
申请日：2000-09-29
申请人： TOSHIBA CORP
发明人： UDA AKIHIRO , ISHITANI YASUTO , KUBOTA HIROAKI
IPC分类号： G06F17/30 , G06F3/00 , G06F3/048
摘要： PROBLEM TO BE SOLVED: To solve the problem that extremely much labor is required for narrowing down target information since it is necessary to find out the target information while displaying information extracted by primary retrieval and watching contents in a conventional information retrieving method. SOLUTION: When retrieving a desired document image from a storage means storing plural document images to become a retrieval target, a document image containing a retrieval word inputted from an operator is retrieved from the storage means. When displaying this retrieved document image, a position, where the retrieval word exists, in the retrieved document image is extracted and the retrieval word is displayed on the central part of a display area on a display means.

10. 发明专利

JP2000181995A CHARACTER RECOGNIZING DEVICE 失效
公开(公告)号：JP2000181995A
公开(公告)日：2000-06-30
申请号：JP35915798
申请日：1998-12-17
申请人： TOSHIBA CORP
发明人： UDA AKIHIRO , ISHITANI YASUTO
IPC分类号： G06K9/62 , G06K9/68
摘要： PROBLEM TO BE SOLVED: To enable the recognition of high accuracy with a suitable calculation quantity to the state of a document by measuring the suitability of respective dictionaries based on reliability in any one of the plural dictionaries and the character recognized result and performing the character recognition while using the dictionary selected out of the respective dictionaries corresponding to the measured suitability. SOLUTION: A suitability measuring part 13 holds correlative information defined between the state of the document and an output from a similarity calculating part 11 and estimates the scratch, crush or unknown font of a certain document at the time of operating. The estimated information is held as a data base, this data base is collated after pattern recognition and quality or suitability between a recognition object character and a dictionary is discriminated. Corresponding to this suitability, a dictionary selecting part 14 selects a dictionary 12, the character recognition is performed while using the selected dictionary 12, and the result is synthesized with the similarity calculating part 11. Thus, recognizing processing can be highly accurately performed.

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