利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

20 条记录 (耗时 0.016 秒)

    ONTOLOGICAL CATEGORIZATION OF QUESTION CONCEPTS FROM DOCUMENT SUMMARIES
    2.
    发明申请
    ONTOLOGICAL CATEGORIZATION OF QUESTION CONCEPTS FROM DOCUMENT SUMMARIES 有权
    文献概要中的问题概念的本体分类

    公开(公告)号：US20110218947A1

    公开(公告)日：2011-09-08

    申请号：US12719600

    申请日：2010-03-08

    申请人： VISWANATH VADLAMANI ,  ABHINAI SRIVASTAVA ,  TAREK NAJM ,  MUNIRATHNAM SRIKANTH ,  PHANI VADDADI ,  ARUNGUNRAM CHANDRASEKARAN SURENDRAN

    发明人： VISWANATH VADLAMANI ,  ABHINAI SRIVASTAVA ,  TAREK NAJM ,  MUNIRATHNAM SRIKANTH ,  PHANI VADDADI ,  ARUNGUNRAM CHANDRASEKARAN SURENDRAN

    IPC分类号： G06F17/30 ,  G06F15/18

    CPC分类号： G06F15/18 ,  G06F17/30

    摘要： Electronic documents are analyzed to identify assertions, which are inverted to generate questions that may be answered by the assertions. A document or a corpus of electronic documents may be analyzed to identify entities and relationships among entities within the text of the document(s). Assertions are identified based on the entities and relationships among the entities. Each assertion represents a fact about an entity, and a group of assertions represents a summary of the document or document corpus. The assertions are inverted to generate questions that may be answered by the assertions. The questions may be further analyzed to identify relevant concepts and topics and to cluster the questions around the concepts and topics. A combined graph may also be generated that facilitates traversal among topics, concepts, questions, assertions, document summaries, and documents.

    摘要翻译： 分析电子文档以识别断言，这些断言被反转，以产生可能由断言回答的问题。 可以分析电子文档的文档或语料库以识别文档文本内的实体和实体之间的关系。 断言是根据实体和实体之间的关系来确定的。 每个断言表示一个关于实体的事实，一组断言表示文档或文档语料库的摘要。 断言被反转，以产生可以由断言回答的问题。 可以进一步分析这些问题，以确定相关概念和主题，并围绕概念和主题聚集问题。 还可以生成组合图，其有助于在主题，概念，问题，断言，文档摘要和文档之间进行遍历。

    Inferring procedural knowledge from data sources
    4.
    发明授权
    Inferring procedural knowledge from data sources 有权
    从数据源中推断程序知识

    公开(公告)号：US09135561B2

    公开(公告)日：2015-09-15

    申请号：US13291126

    申请日：2011-11-08

    申请人： Viswanath Vadlamani ,  Arungunram Surendran ,  Prasanth Pulavarthi ,  Phani Vaddadi ,  Munirathnam Srikanth ,  Tarek Najm

    发明人： Viswanath Vadlamani ,  Arungunram Surendran ,  Prasanth Pulavarthi ,  Phani Vaddadi ,  Munirathnam Srikanth ,  Tarek Najm

    IPC分类号： G06F15/18 ,  G06N5/04 ,  G06N5/02 ,  G06N99/00

    CPC分类号： G06N5/022 ,  G06N5/04 ,  G06N99/005

    摘要： A procedural inference system is described herein that infers procedural knowledge from various data sources to help a user complete one or more tasks for which the data sources provide information. The system understands users' queries, identifies a task at hand, provides recommendations on the steps to take and the agents to use based on a knowledge base of tasks and agents, and provides the fabric to determine which different agents can work together to help the user accomplish a task. Tasks can be started on one device and completed on another seamlessly. Users are able to finish complex, multi-step tasks efficiently, without trial and error or data reentry. Thus, the procedural inference system provides a generalized framework that helps users to complete tasks using already available data and does not ask each data provider to invest in infrastructure to build dedicated task information systems.

    摘要翻译： 本文描述了一种程序性推理系统，其推导来自各种数据源的程序性知识，以帮助用户完成数据源为其提供信息的一个或多个任务。 系统了解用户的查询，识别手头的任务，根据任务和代理的知识库提供有关采取的步骤和代理使用的建议，并提供结构以确定哪些不同的代理可以协同工作 用户完成任务。 任务可以在一个设备上启动，另一个无缝完成。 用户能够有效地完成复杂的多步骤任务，无需进行试错和数据重入。 因此，程序推理系统提供了一个通用框架，可帮助用户使用已有的数据完成任务，并且不要求每个数据提供商投资于基础架构来构建专用的任务信息系统。

    FEDERATING COMPUTING RESOURCES ACROSS THE WEB
    5.
    发明申请
    FEDERATING COMPUTING RESOURCES ACROSS THE WEB 有权
    联网计算资源

    公开(公告)号：US20130198386A1

    公开(公告)日：2013-08-01

    申请号：US13454764

    申请日：2012-04-24

    申请人： Munirathnam Srikanth ,  Steve Jamieson

    发明人： Munirathnam Srikanth ,  Steve Jamieson

    IPC分类号： G06F15/173

    CPC分类号： G06F9/5061

    摘要： Hardware and software are configured to select and provision computing resources from heterogeneous on-demand computing environments through the framework of a layered, federated on-demand computing ecology of computing resource providers, users, and federation servers. These pieces of hardware and software include a mechanism for defining and managing the life cycle of different resource types; a mechanism for extending document-centric protocols to support computing resources as first order objects; a mechanism for routing messages to computing resources; federation topologies; and a mechanism for federation servers to access and use computing resources from providers controlled by other federation servers.

    摘要翻译： 硬件和软件被配置为通过计算资源提供者，用户和联合服务器的分层的联合按需计算生态学的框架，从异构的按需计算环境中选择和提供计算资源。 这些硬件和软件包括用于定义和管理不同资源类型的生命周期的机制; 一种扩展以文档为中心的协议以支持计算资源作为一级对象的机制; 用于将消息路由到计算资源的机制; 联合拓扑 以及联合服务器访问和使用由其他联合服务器控制的提供商的计算资源的机制。

    Ontological categorization of question concepts from document summaries
    6.
    发明授权
    Ontological categorization of question concepts from document summaries 有权
    文献摘要中问题概念的本体论分类

    公开(公告)号：US08370278B2

    公开(公告)日：2013-02-05

    申请号：US12719600

    申请日：2010-03-08

    申请人： Viswanath Vadlamani ,  Abhinai Srivastava ,  Tarek Najm ,  Munirathnam Srikanth ,  Phani Vaddadi ,  Arungunram Chandrasekaran Surendran

    发明人： Viswanath Vadlamani ,  Abhinai Srivastava ,  Tarek Najm ,  Munirathnam Srikanth ,  Phani Vaddadi ,  Arungunram Chandrasekaran Surendran

    IPC分类号： G06F15/18

    CPC分类号： G06F15/18 ,  G06F17/30

    摘要： Electronic documents are analyzed to identify assertions, which are inverted to generate questions that may be answered by the assertions. A document or a corpus of electronic documents may be analyzed to identify entities and relationships among entities within the text of the document(s). Assertions are identified based on the entities and relationships among the entities. Each assertion represents a fact about an entity, and a group of assertions represents a summary of the document or document corpus. The assertions are inverted to generate questions that may be answered by the assertions. The questions may be further analyzed to identify relevant concepts and topics and to cluster the questions around the concepts and topics. A combined graph may also be generated that facilitates traversal among topics, concepts, questions, assertions, document summaries, and documents.

    摘要翻译： 分析电子文档以识别断言，这些断言被反转，以产生可能由断言回答的问题。 可以分析电子文档的文档或语料库以识别文档文本内的实体和实体之间的关系。 断言是根据实体和实体之间的关系来确定的。 每个断言表示一个关于实体的事实，一组断言表示文档或文档语料库的摘要。 断言被反转，以产生可以由断言回答的问题。 可以进一步分析这些问题，以确定相关概念和主题，并围绕概念和主题聚集问题。 还可以生成组合图，其有助于在主题，概念，问题，断言，文档摘要和文档之间进行遍历。

    IDENTIFYING DOMINANT CONCEPTS ACROSS MULTIPLE SOURCES
    7.
    发明申请
    IDENTIFYING DOMINANT CONCEPTS ACROSS MULTIPLE SOURCES 审中-公开
    识别多个来源的主要概念

    公开(公告)号：US20110302149A1

    公开(公告)日：2011-12-08

    申请号：US12795238

    申请日：2010-06-07

    申请人： VISWANATH VADLAMANI ,  TAREK NAJM ,  ABHINAI SRIVASTAVA ,  MUNIRATHNAM SRIKANTH ,  ARUNGUNRAM CHANDRASEKARAN SURENDRAN ,  RAJEEV PRASAD

    发明人： VISWANATH VADLAMANI ,  TAREK NAJM ,  ABHINAI SRIVASTAVA ,  MUNIRATHNAM SRIKANTH ,  ARUNGUNRAM CHANDRASEKARAN SURENDRAN ,  RAJEEV PRASAD

    IPC分类号： G06F17/30

    CPC分类号： G06F16/24578 ,  G06F16/24575

    摘要： Systems, methods, and computer-storage media for identifying dominant concepts are provided. The system includes a search engine connected to various sources, an entity extraction component, a metabase, and a ranking component. The search engine receives a contextual query and provides results in response to the contextual query. The entity extraction component parses the results and identifies entities included in the results. The metabase provides a distance between the entities included in the results and the query terms included in the contextual query. The ranking component ranks the entities based on the provided distance and selects dominant concepts within the results based on the ranks assigned to entities.

    摘要翻译： 提供了用于识别主要概念的系统，方法和计算机存储介质。 该系统包括连接到各种源的搜索引擎，实体提取组件，元数据库和排名组件。 搜索引擎接收上下文查询，并提供响应于上下文查询的结果。 实体提取组件解析结果并识别结果中包含的实体。 元数据库提供结果中包含的实体与包含在上下文查询中的查询项之间的距离。 排名组件根据提供的距离对实体进行排名，并根据分配给实体的排名选择结果中的主要概念。

    CONTEXTUAL QUERIES
    8.
    发明申请
    CONTEXTUAL QUERIES 有权
    背景疑问

    公开(公告)号：US20110196852A1

    公开(公告)日：2011-08-11

    申请号：US12700985

    申请日：2010-02-05

    申请人： MUNIRATHNAM SRIKANTH ,  PHANI VADDADI ,  TAREK NAJM

    发明人： MUNIRATHNAM SRIKANTH ,  PHANI VADDADI ,  TAREK NAJM

    IPC分类号： G06F17/30

    CPC分类号： G06F17/3066 ,  G06F17/30731 ,  G06F17/30864

    摘要： Systems, methods, and computer-storage media for generating contextual queries are provided. The system includes a search engine to receive user queries and contexts, a query understanding component to generate a semantic representation of the query, and a data source command generator to transform the semantic representation into commands for multiple data sources. The data source command generator is connected to the query understanding component. The data source command generator selects data source commands based on lexical information associated with each data source.

    摘要翻译： 提供了用于生成语境查询的系统，方法和计算机存储介质。 该系统包括用于接收用户查询和上下文的搜索引擎，用于生成查询的语义表示的查询理解组件，以及用于将语义表示转换为多个数据源的命令的数据源命令生成器。 数据源命令生成器连接到查询理解组件。 数据源命令生成器根据与每个数据源相关联的词汇信息来选择数据源命令。

    Federating computing resources across the web
    9.
    发明授权
    Federating computing resources across the web 有权
    在网络上联合计算资源

    公开(公告)号：US09489243B2

    公开(公告)日：2016-11-08

    申请号：US13454764

    申请日：2012-04-24

    申请人： Munirathnam Srikanth ,  Steve Jamieson

    发明人： Munirathnam Srikanth ,  Steve Jamieson

    IPC分类号： G06F15/173 ,  G06F9/50 ,  G06F15/16

    CPC分类号： G06F9/5061

    摘要： Hardware and software are configured to select and provision computing resources from heterogeneous on-demand computing environments through the framework of a layered, federated on-demand computing ecology of computing resource providers, users, and federation servers. These pieces of hardware and software include a mechanism for defining and managing the life cycle of different resource types; a mechanism for extending document-centric protocols to support computing resources as first order objects; a mechanism for routing messages to computing resources; federation topologies; and a mechanism for federation servers to access and use computing resources from providers controlled by other federation servers.

    摘要翻译： 硬件和软件被配置为通过计算资源提供者，用户和联合服务器的分层的联合按需计算生态学的框架，从异构的按需计算环境中选择和提供计算资源。 这些硬件和软件包括用于定义和管理不同资源类型的生命周期的机制; 一种扩展以文档为中心的协议以支持计算资源作为一级对象的机制; 用于将消息路由到计算资源的机制; 联合拓扑 以及联合服务器访问和使用由其他联合服务器控制的提供商的计算资源的机制。

    Contextual queries
    10.
    发明授权
    Contextual queries 有权
    上下文查询

    公开(公告)号：US08983989B2

    公开(公告)日：2015-03-17

    申请号：US12700985

    申请日：2010-02-05

    申请人： Munirathnam Srikanth ,  Phani Vaddadi ,  Tarek Najm

    发明人： Munirathnam Srikanth ,  Phani Vaddadi ,  Tarek Najm

    IPC分类号： G06F17/30 ,  G06F7/00

    CPC分类号： G06F17/3066 ,  G06F17/30731 ,  G06F17/30864

    摘要： Systems, methods, and computer-storage media for generating contextual queries are provided. The system includes a search engine to receive user queries and contexts, a query understanding component to generate a semantic representation of the query, and a data source command generator to transform the semantic representation into commands for multiple data sources. The data source command generator is connected to the query understanding component. The data source command generator selects data source commands based on lexical information associated with each data source.

    摘要翻译： 提供了用于生成上下文查询的系统，方法和计算机存储介质。 该系统包括用于接收用户查询和上下文的搜索引擎，用于生成查询的语义表示的查询理解组件，以及用于将语义表示转换为多个数据源的命令的数据源命令生成器。 数据源命令生成器连接到查询理解组件。 数据源命令生成器根据与每个数据源相关联的词汇信息来选择数据源命令。