专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

41. 发明授权

US07606700B2 Adaptive task framework 有权
标题翻译：自适应任务框架
公开(公告)号：US07606700B2
公开(公告)日：2009-10-20
申请号：US11270393
申请日：2005-11-09
申请人： William D. Ramsey , Jonas Barklund , Sanjeev Katariya
发明人： William D. Ramsey , Jonas Barklund , Sanjeev Katariya
IPC分类号： G06F17/27
CPC分类号： G06F17/279 , G06F17/278 , G10L2015/223
摘要： The subject disclosure pertains to systems and methods for performing natural language processing in which natural language input is mapped to a task. The system includes a task interface for defining a task, the associated data and the manner in which the task data is interpreted. Furthermore, the system provides a framework that manages the tasks to facilitate natural language processing. The task interface and framework can be used to provide natural language processing capabilities to third party applications. Additionally, the task framework can learn or be trained based upon feedback received from the third party applications.
摘要翻译：本发明涉及用于执行自然语言处理的系统和方法，其中自然语言输入被映射到任务。该系统包括用于定义任务的任务界面，相关联的数据以及解释任务数据的方式。此外，系统提供了一个管理任务以促进自然语言处理的框架。任务界面和框架可用于向第三方应用程序提供自然语言处理功能。此外，任务框架可以基于从第三方应用程序接收的反馈来学习或接受培训。

42. 发明授权

US07328199B2 Componentized slot-filling architecture 有权
标题翻译：组件化插槽填充架构
公开(公告)号：US07328199B2
公开(公告)日：2008-02-05
申请号：US11246847
申请日：2005-10-07
申请人： William D. Ramsey , Jianfeng Gao , Sanjeev Katariya
发明人： William D. Ramsey , Jianfeng Gao , Sanjeev Katariya
IPC分类号： G06N5/00
CPC分类号： G06F17/2785
摘要： The subject disclosure pertains to systems and methods for performing natural language processing in which tokens are mapped to task slots. The system includes a mapper component that generates a lattice representing possible interpretations of the tokens, a decoder component that creates a ranked list of paths traversing the lattice, a scorer component that generates scores used to rank paths and post-processing components that format the paths for use by other software. Each of these components may be independent, such that the component may be modified or replaced without affecting the remaining components. This allows a variety of different mathematical models and algorithms to be tested or deployed without requiring changes to the remainder of the system.
摘要翻译：本发明涉及用于执行令牌被映射到任务时隙的自然语言处理的系统和方法。该系统包括生成表示可能的令牌解释的格的映射器组件，创建遍历格子的路径的排序列表的解码器组件，产生用于对路径进行排序的得分器组件，以及后处理格式化路径的组件供其他软件使用。这些组件中的每一个可以是独立的，使得可以修改或替换组件而不影响剩余的组件。这允许测试或部署各种不同的数学模型和算法，而不需要更改系统的其余部分。

43. 发明申请

US20070088677A1 Client-server word-breaking framework 有权
标题翻译：客户端 - 服务器破解框架
公开(公告)号：US20070088677A1
公开(公告)日：2007-04-19
申请号：US11249623
申请日：2005-10-13
申请人： Sanjeev Katariya , William Ramsey
发明人： Sanjeev Katariya , William Ramsey
IPC分类号： G06F17/30
CPC分类号： G06F17/30666 , G06F17/278 , G06F17/30616 , Y10S707/99933 , Y10S707/99934
摘要： Word-breaking of a query from a client machine in a client-server environment includes determining whether to use a first word breaking module operable with a client machine in the client-server environment and/or a second word breaking module operable with a server in the client-server environment.
摘要翻译：在客户机 - 服务器环境中从客户端机器断开查询包括确定是否使用可与客户机 - 服务器环境中的客户端机器一起操作的第一单词断开模块和/或可与服务器一起操作的第二单词断开模块客户端 - 服务器环境。

44. 发明授权

US06789230B2 Creating a summary having sentences with the highest weight, and lowest length 有权
标题翻译：创建具有最高权重和最小长度的句子的摘要
公开(公告)号：US06789230B2
公开(公告)日：2004-09-07
申请号：US09216097
申请日：1998-12-18
申请人： Sanjeev Katariya , William P. Jones
发明人： Sanjeev Katariya , William P. Jones
IPC分类号： G06F700
CPC分类号： G06F17/27
摘要： A method and system for generating a summary of a document. The summary generating system generates the summary from the sentences that form the document. The summary generating system calculates a weight for each of the sentences in the document. The weight indicates the importance of the sentence to the document. The summary generating system then selects sentences based on their calculated weights. The summary generating system creates a summary of the selected sentences such that selected sentences are ordered in the created summary in the same relative order as in the document. In one embodiment, the summary generating system identifies sets of sentences whose total length of the sentences in the set is less than a maximum length. The summary generating system then selects an identified set of sentences whose total of the calculated weights of the sentences is greatest as the generated summary. The length of a sentence may be measured in characters or words. In an alternate embodiment, the summary generating system selects the sentences with the highest calculated weights whose total length of the selected sentences is less than a maximum length as the summary.
摘要翻译：一种用于生成文档摘要的方法和系统。摘要生成系统从形成文档的句子中生成摘要。汇总生成系统计算文档中每个句子的权重。权重表示句子对文档的重要性。总结生成系统然后根据它们的计算权重选择句子。摘要生成系统创建所选句子的摘要，使得所选择的句子以与文档中相同的相对顺序在创建的摘要中排序。在一个实施例中，汇总生成系统识别集合中的句子的总长度小于最大长度的句子集合。总结生成系统然后选择所确定的一组句子，其中所计算的句子的总重量最大，作为生成的摘要。句子的长度可以用字母或单词来衡量。在替代实施例中，摘要生成系统选择具有最高计算权重的句子，其总选择句子的总长度小于最大长度作为总结。

45. 发明授权

US06564251B2 Scalable computing system for presenting customized aggregation of information 有权
标题翻译：可扩展的计算系统，用于呈现定制的信息聚合
公开(公告)号：US06564251B2
公开(公告)日：2003-05-13
申请号：US09204592
申请日：1998-12-03
申请人： Sanjeev Katariya , Alok K. Sinha
发明人： Sanjeev Katariya , Alok K. Sinha
IPC分类号： G06F15167
CPC分类号： G06F17/3089
摘要： A method and computing system for providing a highly reliable web site that is capable of handling millions of Internet users per day. The computing system is customizable on a per user basis yet seamlessly aggregates data from a number of information providers, such as news services, weather services, stock services, personal email, and even a community specific service. The computing system includes a plurality of personalization stores that maintain personalization data for a corresponding Internet user. The computing system is based on a federated model in which a single entry point spans to a plurality of web servers. Each web server has an aggregation module, such as an Internet Server API (ISAPI) filter, that retrieves user-specific data “clips” from the personalization store and passes the data to one or more provider objects. The provider objects receive data from the information providers and render the data to form the data clips according to the personalization data retrieved from the personalization store.
摘要翻译：一种用于提供能够每天处理数百万互联网用户的高可靠性网站的方法和计算系统。计算系统是可以根据每个用户进行定制的，但无缝地汇集来自多个信息提供者的数据，例如新闻服务，气象服务，股票服务，个人电子邮件，甚至社区特定的服务。计算系统包括维护相应互联网用户的个性化数据的多个个性化商店。计算系统基于联合模型，其中单个入口点跨越多个web服务器。每个Web服务器都有一个聚合模块，例如Internet Server API（ISAPI）过滤器，可以从个性化存储中检索用户特定的数据“剪辑”，并将数据传递给一个或多个提供者对象。提供者对象从信息提供者接收数据，并根据从个性化商店检索的个性化数据，呈现数据以形成数据剪辑。

46. 发明授权

US06226635B1 Layered query management 有权
标题翻译：分层查询管理
公开(公告)号：US06226635B1
公开(公告)日：2001-05-01
申请号：US09133976
申请日：1998-08-14
申请人： Sanjeev Katariya
发明人： Sanjeev Katariya
IPC分类号： G06F1730
CPC分类号： G06F17/30522 , G06F17/30448 , Y10S707/99934
摘要： The present invention provides a distributed software facility for tailoring an information retrieval query issued by a user based upon the position of that user within an organization of users. In a query client, the facility generates an information retrieval query on behalf of an identified user. The identified user is a member both of first logical subset of the organization and of a second logical subset of the organization. In a first proxy server corresponding to the first logical subset of the organization, the facility modifies the generated query based upon query modification criteria specified for members of the first logical subset. In a second proxy server corresponding to a second logical subset of the organization, the facility modifies the generated query based upon query modification criteria specified for members of the second logical subset. The facility then processes the query as modified by the first and second proxy servers to retrieve information responsive to the modified query.
摘要翻译：本发明提供了一种分布式软件设施，用于根据该用户在用户组织中的位置来定制由用户发出的信息检索查询。在查询客户端中，设备代表识别的用户生成信息检索查询。所识别的用户是组织的第一逻辑子集和组织的第二逻辑子集的成员。在对应于组织的第一逻辑子集的第一代理服务器中，设施基于为第一逻辑子集的成员指定的查询修改标准来修改生成的查询。在对应于组织的第二逻辑子集的第二代理服务器中，设施基于为第二逻辑子集的成员指定的查询修改标准来修改生成的查询。该设备然后处理由第一和第二代理服务器修改的查询以检索响应于修改的查询的信息。

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