中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

61 records (took 0.022 seconds)

    System and methods for automated community discovery in networks with multiple relational types
    21.
    发明授权
    System and methods for automated community discovery in networks with multiple relational types 有权

    公开(公告)号：US09749406B1

    公开(公告)日：2017-08-29

    申请号：US14207205

    申请日：2014-03-12

    Applicant: HRL Laboratories, LLC

    Inventor： David A. Jurgens ,  Tsai-Ching Lu

    IPC: G06F15/173 ,  H04L29/08 ,  H04L12/44

    CPC classification number: H04L67/1061 ,  H04L12/44

    Abstract: Described is a system for automated community discovery in networks with multiple relational types. The system receives a network as input. The network comprises neighbors, edges connecting the neighbors, and vertices, where edges between two vertices represent a relation. A set of pair-wise similarity comparisons is computed for all pairs of relations. Two relations are considered similar if vertices connected to the two relations share similar relations to the same set of neighbors. A relation dendrogram is created based on the set of pair-wise similarity comparisons. Then, a cut in the relation dendrogram is selected to compute a community solution, resulting in a plurality of relation dendrogram partitions. Each relation dendrogram partition represents a community. A community density criterion is computed based on a density of each community calculated with respect to edge types contained within each community. Finally, a community solution is generated that maximizes the community density criterion.

    System and method for event prediction using online social media
    23.
    发明授权
    System and method for event prediction using online social media 有权

    公开(公告)号：US11475334B1

    公开(公告)日：2022-10-18

    申请号：US15847866

    申请日：2017-12-19

    Applicant: HRL Laboratories, LLC

    Inventor： Krishna Bathina ,  Aruna Jammalamadaka ,  Jiejun Xu ,  Tsai-Ching Lu

    IPC: G06N5/04 ,  G06N7/00

    Abstract: Described is a system for large-scale event prediction and a corresponding response. The system, using an agent-based model, predicts how many users (agent accounts) on a social media platform will become activists related to a large-scale event. This process is accomplished using both Before and During models. Before the large-scale event, the system operates to generate agent attributes and a posting network based on posts on the social media platform. During the large-scale event and based on the agent attributes and posting network, the system determines if a social media user (agent account) will become an activist of the large-scale event and a corresponding magnitude of the large-scale event. Depending on the magnitude, the system can implement a responsive measure and control a device based on the prediction of the activists.

    SYSTEMS AND METHODS FOR FORECAST ALERTS WITH PROGRAMMABLE HUMAN-MACHINE HYBRID ENSEMBLE LEARNING
    25.
    发明申请
    SYSTEMS AND METHODS FOR FORECAST ALERTS WITH PROGRAMMABLE HUMAN-MACHINE HYBRID ENSEMBLE LEARNING 审中-公开

    公开(公告)号：US20200311615A1

    公开(公告)日：2020-10-01

    申请号：US16714068

    申请日：2019-12-13

    Applicant: HRL LABORATORIES, LLC

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

    IPC: G06N20/20 ,  G06N7/00 ,  G06F40/205 ,  G06K9/62

    Abstract: A method for computing a human-machine hybrid ensemble prediction includes: receiving an individual forecasting question (IFP); classifying the IFP into one of a plurality of canonical question topics; identifying machine models associated with the canonical question topic; for each of the machine models: receiving, from one of a plurality of human participants: a first task input including a selection of sets of training data; a second task input including selections of portions of the selected sets of training data; and a third task input including model parameters to configure the machine model; training the machine model in accordance with the first, second, and third task inputs; and computing a machine model forecast based on the trained machine model; computing an aggregated forecast from machine model forecasts computed by the machine models; and sending an alert in response to determining that the aggregated forecast satisfies a threshold condition.

    SYSTEM AND METHOD OF STRUCTURING RATIONALES FOR COLLABORATIVE FORECASTING
    26.
    发明申请
    SYSTEM AND METHOD OF STRUCTURING RATIONALES FOR COLLABORATIVE FORECASTING 审中-公开

    公开(公告)号：US20200219020A1

    公开(公告)日：2020-07-09

    申请号：US16591397

    申请日：2019-10-02

    Applicant: HRL Laboratories, LLC

    Inventor： Robert Giaquinto ,  Tsai-Ching Lu ,  Aruna Jammalamadaka ,  Ryan M. Uhlenbrock

    IPC: G06Q10/04 ,  G06F17/18 ,  G06N7/00 ,  H04L12/58

    Abstract: Described is a system for structuring rationales for collaborative forecasting between users of a crowdsourcing platform. For a given forecasting question, the system produces a forecasting rationale model from a combination of variables related to users and topics in a discussion of the users' forecasting rationale for making an initial forecast of an event. A relationship between the variables is determined, and based on the relationship between the variables, a prediction of each user's performance in making the initial forecast. Based on the predictions, top performing users and their forecasting rationales are selected, and the forecasting rationales of the top performing users are shared with other users of the crowdsourcing platform, allowing the other users to revise their initial forecasts in response to the shared forecasting rationales, resulting in revised forecasts. A forecast of the event that combines the revised forecasts is then output.

    System and method for assessing spatiotemporal impact of emergency events based on social media posting behavior
    27.
    发明授权
    System and method for assessing spatiotemporal impact of emergency events based on social media posting behavior 有权

    公开(公告)号：US10326847B1

    公开(公告)日：2019-06-18

    申请号：US15870531

    申请日：2018-01-12

    Applicant: HRL LABORATORIES, LLC

    Inventor： Aruna Jammalamadaka ,  Jiejun Xu ,  Tsai-Ching Lu

    IPC: H04L29/08 ,  H04W4/021 ,  G06Q50/00

    Abstract: A method for estimating the impact of an event includes: receiving social media posts, each of the social media posts including content, a timestamp, and a geolocation; grouping the social media posts by geographic region in accordance with the geolocation associated with the social media post and by time window in accordance with the timestamp associated with the social media post; extracting feature vectors from the social media posts, each of the feature vectors corresponding to one group of social media posts; supplying the feature vectors to one or more models of events to generate one or more classifications of the groups of social media posts, each of the models of events corresponding to a different kind of event, and the classifications of the groups indicating the level of impact of the different kinds of events; and operating a device based on the classifications of the groups of social media posts.

    Strategic network formation involving information sources, aggregators, and consumers
    28.
    发明授权
    Strategic network formation involving information sources, aggregators, and consumers 有权

    公开(公告)号：US10129093B1

    公开(公告)日：2018-11-13

    申请号：US14670811

    申请日：2015-03-27

    Applicant: HRL Laboratories, LLC

    Inventor： Samuel Johnson ,  Tsai-Ching Lu

    IPC: H04L12/24

    Abstract: Described is a system for modeling strategic network formation. A network formation model is generated using a concatenation of joint strategies s of a set of N agents, such that s=sSsAsC. The N agents include a group of source agents NS, a group of aggregator agents NA, and a group of consumer agents NC, each group of agents having a distinct joint strategy for accessing a set of information. sS represents a joint strategy of the group of source agents, sA represents a joint strategy of the group of aggregator agents, and sC represents a joint strategy of the group of consumer agents. The network formation model is operated according to the joint strategies of the set of N agents. Data relating to the set of N agents of the network formation model is output for the investigation of the formation of information diffusion networks.

    Method for gauging public interest in a topic using network analysis of online discussions
    30.
    发明授权
    Method for gauging public interest in a topic using network analysis of online discussions 有权

    公开(公告)号：US09639610B1

    公开(公告)日：2017-05-02

    申请号：US14452129

    申请日：2014-08-05

    Applicant: HRL Laboratories, LLC

    Inventor： David A. Jurgens ,  Tsai-Ching Lu ,  Veronika Stmadova

    IPC: G06F17/30 ,  H04L12/58

    CPC classification number: H04L51/32 ,  G06Q30/00

    Abstract: Described is system and method for gauging public interest in a topic using network analysis of online discussions. A message from an online discussion related to a specific topic is received as input. The message is analyzed for information related to the message, and a graph comprised of nodes is generated where each node represents information related to the message, such as user name, location, hyperlinks, and annotations. The graph is updated over time as additional messages from the online discussion are received. Additional nodes are generated and linked with at least one of the existing nodes in the graph to form at least one connected component. A normalized diameter of the largest connected component in the graph is determined, and a level of collective focus in the online discussion related to the topic based on the normalized diameter is output to a user.

Patent Agency Ranking