利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

79 条记录 (耗时 0.041 秒)

    Method for a natural language question-answering system to complement decision-support in a real-time command center
    7.
    发明授权
    Method for a natural language question-answering system to complement decision-support in a real-time command center 有权
    一种用于补充实时指挥中心决策支持的自然语言问答系统的方法

    公开(公告)号：US08601030B2

    公开(公告)日：2013-12-03

    申请号：US13228709

    申请日：2011-09-09

    申请人： Sugato Bagchi ,  Laura Wynter

    发明人： Sugato Bagchi ,  Laura Wynter

    IPC分类号： G06F7/00 ,  G06F9/44

    CPC分类号： G06F17/30654

    摘要： System and methods provide decision support by receiving suggested actions from a decision support system and automatically determining parameters of the suggested actions to serve as input to a question-answering system. System and methods also automatically generate questions based on the parameters, automatically search a corpus of unstructured data to retrieve answers to the questions, and automatically provide impact confidence values for each answer indicating the degree of impact the answers have on the suggested actions. The systems and methods can then output the questions, answers, and impact confidence values.

    摘要翻译： 系统和方法通过从决策支持系统接收建议的操作并自动确定建议的操作的参数来提供决策支持，以作为问答系统的输入。 系统和方法还会根据参数自动生成问题，自动搜索非结构化数据的语料库以检索问题的答案，并自动提供每个答案的影响置信度值，以表明答案对建议操作的影响程度。 系统和方法可以输出问题，答案和影响置信度值。

    DECISION SUPPORT SYSTEM OPTIMIZER FOR A REAL-TIME COMMAND CENTER
    8.
    发明申请
    DECISION SUPPORT SYSTEM OPTIMIZER FOR A REAL-TIME COMMAND CENTER 失效
    用于实时指令中心的决策支持系统优化器

    公开(公告)号：US20120203724A1

    公开(公告)日：2012-08-09

    申请号：US13022369

    申请日：2011-02-07

    申请人： So Yeon Chun ,  Laura Wynter

    发明人： So Yeon Chun ,  Laura Wynter

    IPC分类号： G06N5/02

    CPC分类号： G06N99/005

    摘要： A decision support for real time command center, in one aspect, classifies, using a decision tree, an observed network state of a network into at least one category. A meta-model associated with the classified at least one category may be selected from a plurality of meta-models, the plurality of meta-models having been calibrated using results of simulations of a plurality of scenarios occurring in the network. One or more action plans may be evaluated by running the selected meta-model with data of the observed network state. One or more recommended action plans may be generated for the real time command center, based on the evaluation. Actual network state data resulting from having applied the one or more recommended action plans may be evaluated and used to recalibrate the meta-model and/or the decision tree.

    摘要翻译： 对于实时指挥中心的决策支持，在一个方面，使用决策树将网络的观察网络状态分类为至少一个类别。 可以从多个元模型中选择与分类的至少一个类别相关联的元模型，所述多个元模型已经使用在网络中发生的多个场景的模拟的结果来校准。 可以通过使用观察到的网络状态的数据运行所选择的元模型来评估一个或多个动作计划。 基于评估，可以为实时指挥中心生成一个或多个推荐的行动计划。 可以评估由应用了一个或多个推荐的行动计划而产生的实际网络状态数据，并用于重新校准元模型和/或决策树。

    Multiple resource control-advisor for management of distributed or web-based systems
    9.
    发明授权
    Multiple resource control-advisor for management of distributed or web-based systems 失效
    用于管理分布式或基于Web的系统的多个资源控制顾问

    公开(公告)号：US07953856B2

    公开(公告)日：2011-05-31

    申请号：US12167183

    申请日：2008-07-02

    申请人： Dimitrios Pendarakis ,  Jeremy I. Silber ,  Laura Wynter

    发明人： Dimitrios Pendarakis ,  Jeremy I. Silber ,  Laura Wynter

    IPC分类号： G06F15/173

    CPC分类号： H04L12/66

    摘要： A system and method are provided for autonomic system management in a computing system containing system resources including network resources and multiple resource demands, or processes. The computing system may be a stream-processing system or other real-time computer management system, such as workload management, or a virtualization engine. The system and method enables achieving a better level of performance than would occur in the computing system using only existing mechanism. It permits, with very low computational overhead, achieving or driving the system closer to a user-defined system performance objective. To do so, a system performance equation is defined to determine a level of performance of the system as a function of the allocation of two or more system resources among a plurality of system resource demands or processes. From this system performance equation, a plurality of resource-specific change equations is derived. Each resource-specific change equation is capable of calculating changes in the level of performance of the system attributable to changes in the allocation of one of the system resources. The resource-specific change equation yielding the greatest change in the level of system performance at a given allocation of all of the system resources and the system resource associated with the identified resource-specific change equation are identified. The allocation of the identified associated system resource to at least one system resource demand to provide the largest increase in the level of performance of the system, and allocations for all system resources are adjusted in accordance with the modified allocation of the identified associated system resource.

    摘要翻译： 提供了一种系统和方法，用于包含系统资源，包括网络资源和多个资源需求或过程的计算系统中的自主系统管理。 计算系统可以是流处理系统或其他实时计算机管理系统，例如工作负载管理或虚拟化引擎。 该系统和方法能够实现比仅使用现有机制的计算系统中发生的更好的性能水平。 它以非常低的计算开销允许更接近用户定义的系统性能目标来实现或驱动系统。 为此，定义系统性能方程式以根据在多个系统资源需求或过程中的两个或多个系统资源的分配来确定系统的性能水平。 从该系统性能方程式，导出多个资源特定变化方程。 每个资源特定的变化方程能够计算由于系统资源之一的分配变化引起的系统性能水平的变化。 识别在给定分配所有系统资源和与所识别的资源特定变化方程相关联的系统资源的系统性能水平上产生最大变化的资源特定变化方程。 将所识别的相关联的系统资源分配给至少一个系统资源需求以提供系统性能水平的最大增加，以及针对所有系统资源的分配，根据所识别的相关系统资源的修改分配进行调整。

    Method and apparatus for predicting future travel times over a transportation network
    10.
    发明授权
    Method and apparatus for predicting future travel times over a transportation network 有权
    用于预测运输网络未来旅行时间的方法和装置

    公开(公告)号：US07920960B2

    公开(公告)日：2011-04-05

    申请号：US12038559

    申请日：2008-02-27

    申请人： Zhen Liu ,  Laura Wynter ,  Li Zhang

    发明人： Zhen Liu ,  Laura Wynter ,  Li Zhang

    IPC分类号： G06F19/00

    CPC分类号： G08G1/123

    摘要： The present invention is a method and an apparatus for predicting future travel times over a transportation network. In one embodiment, a method for predicting future travel times over a transportation network includes receiving a data point indicating a real-time volume of traffic on the link at a given time and updating a template representative of an observed traffic pattern on the link in accordance with the received data point. A future travel time over the link can then be estimated in accordance with the updated template. Thus, the template is able to adapt to dynamically changing traffic patterns, taking these changing traffic patterns into account when making predictions of future traffic patterns.

    摘要翻译： 本发明是用于预测运输网络上的未来旅行时间的方法和装置。 在一个实施例中，用于预测运输网络上的未来旅行时间的方法包括在给定时间接收指示链路上的实时流量的数据点，并且根据链路更新表示链路上观察到的业务模式的模板 与收到的数据点。 然后可以根据更新的模板来估计链接上的未来旅行时间。 因此，模板能够适应动态变化的流量模式，在对未来流量模式进行预测时考虑到这些变化的流量模式。