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
    • 85. 发明授权
    • Vision-based document segmentation
    • 基于视觉的文档分割
    • US07428700B2
    • 2008-09-23
    • US10628766
    • 2003-07-28
    • Ji-Rong WenShipeng YuDeng CaiWei-Ying Ma
    • Ji-Rong WenShipeng YuDeng CaiWei-Ying Ma
    • G06F17/00
    • G06F17/30716G06F17/218G06F17/2247
    • Vision-based document segmentation identifies one or more portions of semantic content of a document. The one or more portions are identified by identifying a plurality of visual blocks in the document, and detecting one or more separators between the visual blocks of the plurality of visual blocks. A content structure for the document is constructed based at least in part on the plurality of visual blocks and the one or more separators, and the content structure identifies the one or more portions of semantic content of the document. The content structure obtained using the vision-based document segmentation can optionally be used during document retrieval.
    • 基于视觉的文档分割识别文档的语义内容的一个或多个部分。 通过识别文档中的多个可视块并且检测多个视觉块中的可视块之间的一个或多个分隔符来识别一个或多个部分。 至少部分地基于多个可视块和一个或多个分隔符来构建文档的内容结构,并且内容结构标识文档的语义内容的一个或多个部分。 使用基于视觉的文档分割获得的内容结构可以可选地在文档检索期间使用。
    • 86. 发明授权
    • Semi-automatic construction method for knowledge base of encyclopedia question answering system
    • 百科全书问答系统知识库半自动施工方法
    • US07428487B2
    • 2008-09-23
    • US10828281
    • 2004-04-21
    • Ji Hyun WangEui Sok ChungMyung Gil Jang
    • Ji Hyun WangEui Sok ChungMyung Gil Jang
    • G06F17/21G06F17/28
    • G06F17/30716
    • In a semi-automatic construction method for knowledge base of an encyclopedia question answering system, concept-oriented systematic templates are designed and important fact information related to entries is automatically extracted from summary information and body of the encyclopedia to semi-automatically construct the knowledge base of the encyclopedia question answering system. The method includes the steps of: (a) designing structure of the knowledge base with a plurality of templates for each entry and a plurality attributes related to each of the templates; (b) extracting structured information including the entry, an attribute name and attribute values from summary information of the encyclopedia; (c) extracting unstructured information including an attribute name and attribute values of the entry from a body of the encyclopedia; and (d) storing the structured information and the unstructured information in corresponding template and attribute of the knowledge base according to the entry.
    • 在百科全书问答系统知识库的半自动构建方法中,设计概念导向的系统模板,从摘要信息和百科全书自动提取与条目相关的重要事实信息,以半自动构建知识库 的百科全书问答系统。 该方法包括以下步骤:(a)利用用于每个条目的多个模板和与每个模板相关的多个属性来设计知识库的结构; (b)从百科全书的摘要信息中提取包括条目,属性名称和属性值的结构化信息; (c)从百科全书的主体中提取非结构化信息,包括该条目的属性名称和属性值; 以及(d)根据该条目将结构化信息和非结构化信息存储在知识库的相应模板和属性中。
    • 87. 发明申请
    • System, and method for interactive browsing
    • 系统和方法进行交互式浏览
    • US20080222103A1
    • 2008-09-11
    • US11715090
    • 2007-03-07
    • Li ZhangTao LiuJian Min JianZhong SuYue Pan
    • Li ZhangTao LiuJian Min JianZhong SuYue Pan
    • G06F17/30
    • G06F17/30899G06F17/30716Y10S707/99931Y10S707/99933Y10S707/99934
    • The present invention provides a system and method for achieving interactive browsing. Said system is coupled to a knowledge base and a document database, said knowledge base stores a plurality of terms and information relating to each term, and said document database stores a plurality of documents. Said system comprises term acquiring means, for acquiring terms in which a user has much interest; first extracting means, for extracting information relating to the terms in which the user has much interest, from the knowledge base; second extracting means, for extracting documents containing the terms in which the user has much interest, from the document database; a first display part in a user interface, for displaying information extracted by the first extracting means; and a second display part in the user interface, for displaying a list of the documents extracted by the second extracting means. With the present invention, one can browse both documents and information on terms in the documents in a single interface.
    • 本发明提供了一种用于实现交互式浏览的系统和方法。 所述系统耦合到知识库和文档数据库,所述知识库存储与每个术语相关的多个术语和信息,并且所述文档数据库存储多个文档。 所述系统包括术语获取装置,用于获取用户感兴趣的术语; 第一提取装置,用于从知识库中提取与用户有兴趣的术语有关的信息; 第二提取装置,用于从文档数据库提取包含用户有兴趣的术语的文档; 用于显示由第一提取装置提取的信息的用户界面中的第一显示部分; 以及用户界面中的第二显示部分,用于显示由第二提取装置提取的文档的列表。 利用本发明,可以在单个界面中浏览文档中的文档和文档中的术语信息。
    • 88. 发明申请
    • NAVIGATION OF THE CONTENT SPACE OF A DOCUMENT SET
    • 文件集的内容空间导航
    • US20080140700A1
    • 2008-06-12
    • US11838170
    • 2007-08-13
    • Paul R.M. CarpentierMaarten J.P.A. WillemsJoris Winters
    • Paul R.M. CarpentierMaarten J.P.A. WillemsJoris Winters
    • G06F17/30
    • G06F17/30716
    • Content-based addressing is used to navigate forward, backward and in a circular fashion through documents in a content space. To enable backward navigation, a descriptor file is created for a new version that contains not only a message digest for the new version, but also a message digest of the older document. A message digest is created for the descriptor file. A user navigates backward starting with the message digest of the descriptor file. To enable forward navigation, a mapping table maps a message digest of an older document into the message digest of the new version. A high-level descriptor file contains the message digest of the original document and the message digest of the mapping table. The message digest of the high-level descriptor file is returned to the user. A user navigates forward starting with the high-level descriptor file message digest. To enable circular navigation, a mapping table maps a message digest of a second document into a message digest of a version of the second document containing a message digest of a first document. The techniques are combined to allow navigation through a complex content space.
    • 基于内容的寻址用于通过内容空间中的文档向前,向后和循环地导航。 要启用向后导航,将为新版本创建描述符文件,该新版本不仅包含新版本的消息摘要,还包含较旧文档的消息摘要。 为描述符文件创建消息摘要。 用户从描述符文件的消息摘要开始向后导航。 为了启用前向导航,映射表将较旧文档的消息摘要映射到新版本的消息摘要中。 高级描述符文件包含原始文档的消息摘要和映射表的消息摘要。 高级描述符文件的消息摘要返回给用户。 用户从高级描述符文件消息摘要开始向前导航。 为了启用循环导航,映射表将第二文档的消息摘要映射到包含第一文档的消息摘要的第二文档的版本的消息摘要中。 这些技术被组合以允许通过复杂的内容空间进行导航。