中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

61 records (took 0.021 seconds)

    System for instability detection and structure estimation of complex network dynamics
    31.
    发明授权
    System for instability detection and structure estimation of complex network dynamics 有权
    复杂网络动力学的不稳定性检测和结构估计系统

    公开(公告)号：US09367804B1

    公开(公告)日：2016-06-14

    申请号：US14207269

    申请日：2014-03-12

    Applicant: HRL Laboratories, LLC

    Inventor： Hankyu Moon ,  Tsai-Ching Lu

    IPC: G06N5/04 ,  G06N5/02 ,  G06N5/00

    CPC classification number: G06N7/005 ,  G06N5/00 ,  G06N5/04

    Abstract: Described is a system for predicting system instability. The system can measure the degree of the network's instability due to critical transitions using the leading eigenvalue of the covariance matrix, where the instability measure is invariant to (1) the changes in network structure in terms of addition/removal of nodes and links, and (2) the feedback of the global system stability to the changes in stability. Based on that, the system is operable for providing an estimation of the network's changing connectivity when the network is near critical transitions.

    Abstract translation: 描述了一种预测系统不稳定性的系统。 该系统可以使用协方差矩阵的主要特征值来测量由于关键转换引起的网络不稳定程度，其中不稳定性度量不变（1）网络结构在节点和链路的添加/删除方面的变化，以及 （2）全球系统对稳定性变化的反馈。 基于此，该系统可操作用于在网络接近关键转变时提供网络变化连接的估计。

    Catastrophe prediction via estimated network autocorrelation
    32.
    发明授权
    Catastrophe prediction via estimated network autocorrelation 有权
    通过估计网络自相关的灾难预测

    公开(公告)号：US09020875B1

    公开(公告)日：2015-04-28

    申请号：US13747466

    申请日：2013-01-22

    Applicant: HRL Laboratories, LLC

    Inventor： Ryan Compton ,  Hankyu Moon ,  Tsai-Ching Lu

    IPC: G06N5/04 ,  G06N5/02 ,  G06N7/00

    CPC classification number: G06Q10/00 ,  G06N5/04 ,  G06N7/00 ,  G06Q40/08

    Abstract: Described is a system for catastrophe prediction. The system generates a time series of observables at multiple time steps from data observed from a complex system. A surrogate time series based on the time series of observables is then generated. Inferred network structures for both the time series of observables and the surrogate time series are reconstructed. Next, spatial autocorrelation for each inferred network structure in both the time series of observables and the surrogate time series is computed. A statistical test of a detected trend between the time series of observables and the surrogate time series is computed to determine if the detected trend occurred by chance. Finally, an early warning signal of the detected trend occurring by chance is generated.

    Abstract translation: 描述了一种灾难预测系统。 系统可以从复杂系统观察到的数据的多个时间步长生成可观测时间序列。 然后生成基于可观察时间序列的替代时间序列。 重建了可观察时间序列和替代时间序列的推断网络结构。 接下来，计算观测时间序列中每个推断的网络结构的空间自相关性和替代时间序列。 计算观察时间序列与替代时间序列之间的检测趋势的统计检验，以确定检测到的趋势是否偶然发生。 最后，产生了偶然发生的检测趋势的预警信号。

    State transition network analysis of multiple one-dimensional time series
    33.
    发明授权
    State transition network analysis of multiple one-dimensional time series 有权

    公开(公告)号：US11106989B1

    公开(公告)日：2021-08-31

    申请号：US15912209

    申请日：2018-03-05

    Applicant: HRL Laboratories, LLC

    Inventor： Alex N. Waagen ,  Tsai-Ching Lu ,  Jiejun Xu

    IPC: G06N7/00 ,  G06N5/02 ,  G06N5/04 ,  G06F9/448 ,  G06F16/2458 ,  G06F16/901 ,  G06Q50/00

    Abstract: Described is a system for predicting an occurrence of large-scale events using social media data. A collection of time series is acquired from social media data related to an event of interest. The collection of time series is partitioned into time intervals and semantic features are extracted from the time intervals as a set of semantic intervals. The semantic features are encoded into a multilayer network. Subgraphs of the multilayer network are transformed into a state transition network. A prediction of a future event of interest is generated by analyzing the encoded network using the state transition network. Using the analyzed encoded network, a device is controlled based on the prediction of the future event of interest.

    SYSTEM AND METHOD FOR HUMAN-MACHINE HYBRID PREDICTION OF EVENTS
    35.
    发明申请
    SYSTEM AND METHOD FOR HUMAN-MACHINE HYBRID PREDICTION OF EVENTS 审中-公开

    公开(公告)号：US20200257943A1

    公开(公告)日：2020-08-13

    申请号：US16708166

    申请日：2019-12-09

    Applicant: HRL LABORATORIES, LLC

    Inventor： David J. Huber ,  Tsai-Ching Lu ,  Nigel D. Stepp ,  Aruna Jammalamadaka ,  Hyun J. Kim ,  Samuel D. Johnson

    IPC: G06K9/62 ,  G06N3/08 ,  G06N20/00 ,  G06F40/205 ,  G06F40/284 ,  G06F16/907

    Abstract: A method for generating human-machine hybrid predictions of answers to forecasting problems includes: parsing text of an individual forecasting problem to identify keywords; generating machine models based on the keywords; scraping data sources based on the keywords to collect scraped data relevant to the individual forecasting problem; providing the scraped data to the machine models; receiving machine predictions of answers to the individual forecasting problem from the machine models based on the scraped data; providing, by the computer system via a user interface, the scraped data to human participants; receiving, by the computer system via the user interface, human predictions of answers to the individual forecasting problem from the human participants; aggregating the machine predictions with the human predictions to generate aggregated predictions; and generating and outputting a hybrid prediction based on the aggregated predictions.

    System and method for using network data to improve event predictions
    36.
    发明授权
    System and method for using network data to improve event predictions 有权

    公开(公告)号：US10452729B1

    公开(公告)日：2019-10-22

    申请号：US14830289

    申请日：2015-08-19

    Applicant: HRL Laboratories, LLC

    Inventor： Matthew S. Keegan ,  Ryan F. Compton ,  Tsai-Ching Lu

    IPC: G06F16/00 ,  G06F16/9535 ,  G06F16/958 ,  G06F16/2457

    Abstract: Described is a system for event prediction on microblogs. In operation, the system receives a social media post stream from a social network to generate and maintain a social network database and an audit trail database. New social media posts are filtered to determine if the new social media posts are related to a possible future event. The new social media posts are compared against the social network database and audit trail database to provide a quality score, the quality score representing a likelihood that at least one of the new social media posts is a true prediction of a future event. If the quality score is determined to be true, the detection is published as a true prediction of a future event.

    Accurate user alignment across online social media platforms
    39.
    发明授权
    Accurate user alignment across online social media platforms 有权

    公开(公告)号：US10305845B1

    公开(公告)日：2019-05-28

    申请号：US14639979

    申请日：2015-03-05

    Applicant: HRL Laboratories, LLC

    Inventor： Alex N. Waagen ,  Jiejun Xu ,  Tsai-Ching Lu

    IPC: H04L12/58 ,  H04L29/08 ,  H04L29/12

    Abstract: Described is system for accurate user alignment across multiple online social media platforms. Out of textual messages from multiple user accounts of a first social media platform, the system identifies a set of textual messages from a first user account and a second user account of the first social media platform, each textual message in the set of textual messages comprising a set of specific character strings. The set of specific character strings represents a link to a post on a second social media platform, resulting in linked messages, the post originating from a linked account of the second social media platform. Either the first user account or the second user account is selected as an associated account by determining which originated the greater number of messages in the set of textual messages. A map component associated with a user identity that includes the associated account and the linked account is generated.

Patent Agency Ranking