公开(公告)号：US11244115B2

公开(公告)日：2022-02-08

申请号：US16523893

申请日：2019-07-26

Applicant: HRL Laboratories, LLC

Inventor： Jiejun Xu ,  Tsai-Ching Lu ,  Dnyanesh Rajpathak ,  John Anthony Cafeo

IPC: G06F40/30 ,  G06F40/289 ,  G06Q30/02 ,  G07C5/00 ,  G06K9/62

Abstract: Described is a system for identification of correlations in customer observables (COs). The system extracts key phrases representing COs from textual inputs from multiple data sources, wherein the COs are related to a consumer product. A unified hypergraph is constructed that models co-occurrences of COs. The unified hypergraph includes nodes and types of hyperedges connecting the nodes, where COs are represented by nodes and data sources are represented by different types of hyperedges. Each node of the unified hypergraph is embedded into a latent feature space. The unified hypergraph is partitioned into clusters within the latent feature space, where each cluster contains correlated CO data. The correlated CO data from a cluster are used to generate and provide targeted messages specific to the consumer product to a display device.

公开(公告)号：US11200354B1

公开(公告)日：2021-12-14

申请号：US16746436

申请日：2020-01-17

Applicant: HRL Laboratories, LLC

Inventor： Vincent De Sapio ,  Kang-Yu Ni ,  Tsai-Ching Lu

IPC: G06F30/18 ,  G06F17/13 ,  G06F111/10

Abstract: Described is a system for selecting measurement nodes in a distributed physical system of agents. In operation, the distributed physical system is represented as a multi-layer network having a communication layer and an agent layer. The communication layer represents the amount of collective communication activities between any pair of areas and the agent layer represents movement of agents within the distributed physical system such that the communication layer and agent layer collectively generate network dynamics. The network dynamics are modeled as hybrid partial differential equations (PDEs) with measurable interconnected states in the communication layer. Notably, placement of a minimum set of measurement nodes is determined within the distributed physical system to provide full-state observability of the distributed physical system. The system can then track the full system state and apply compensation to one or more agents in the distributed physical system based on tracking the full system state.

公开(公告)号：US20200057809A1

公开(公告)日：2020-02-20

申请号：US16523893

申请日：2019-07-26

Applicant: HRL Laboratories, LLC

Inventor： Jiejun Xu ,  Tsai-Ching Lu ,  Dnyanesh Rajpathak ,  John Anthony Cafeo

IPC: G06F17/27 ,  G06K9/62 ,  G07C5/00 ,  G06Q30/02

Abstract: Described is a system for identification of correlations in customer observables (COs). The system extracts key phrases representing COs from textual inputs from multiple data sources, wherein the COs are related to a consumer product. A unified hypergraph is constructed that models co-occurrences of COs. The unified hypergraph includes nodes and types of hyperedges connecting the nodes, where COs are represented by nodes and data sources are represented by different types of hyperedges. Each node of the unified hypergraph is embedded into a latent feature space. The unified hypergraph is partitioned into clusters within the latent feature space, where each cluster contains correlated CO data. The correlated CO data from a cluster are used to generate and provide targeted messages specific to the consumer product to a display device.

公开(公告)号：US10255352B1

公开(公告)日：2019-04-09

申请号：US14535812

申请日：2014-11-07

Applicant: HRL Laboratories, LLC

Inventor： Jiejun Xu ,  Tsai-Ching Lu ,  Ryan F. Compton ,  David L. Allen

IPC: G06N5/04 ,  G06F17/30

Abstract: Described is a system for early detection of events via social media mining. The system receives, as input, social media blog posts comprising textual data. The system processes the social media blog posts through a cascade of filters. The cascade of filters comprises an event term detection filter, a location term detection filter following the event term detection filter, and a future date detection filter following the location term detection filter. A plurality of candidate social media blog posts describing an event of interest on a future date is output to a user for further analysis.

公开(公告)号：US10178120B1

公开(公告)日：2019-01-08

申请号：US15217393

申请日：2016-07-22

Applicant: HRL Laboratories, LLC

Inventor： Matthew S. Keegan ,  Kang-Yu Ni ,  Tsai-Ching Lu

IPC: H04L29/06

Abstract: Described is a system for predicting temporal evolution of contagions on multilayer networks. The system determines a functional epidemic threshold for disappearance of a contagion on a multilayer network model according to a score value s=λβ/δ, where λ corresponds to an adjacency matrix of the first layer of the multilayer network model, β represents a spread rate of the contagion, and δ represents a recovery rate. A prediction of future behavior of the contagion on the multilayer network model using the functional epidemic threshold is output and utilized to inform decisions regarding connectivity within a multilayer network in order to prevent spread of the contagion on a multilayer network.

公开(公告)号：US09904740B1

公开(公告)日：2018-02-27

申请号：US14472351

申请日：2014-08-28

Applicant: HRL Laboratories, LLC

Inventor： Kang-Yu Ni ,  Tsai-Ching Lu

IPC: G06F17/30

CPC classification number: G06F17/30958

Abstract: Network of networks (NoN) structure reconstruction employs compressed sensing with multivariate time series data and graph partitioning to reconstruct a node-to-node connection structure of an NoN. The NoN structure reconstruction includes determining an adjacency matrix of the NoN from the multivariate time series data using the compressed sensing. Partitioning a graph representing the determined adjacency matrix into subgraphs provides the reconstruction of the node-to-node connection structure.

公开(公告)号：US20170316099A1

公开(公告)日：2017-11-02

申请号：US15231346

申请日：2016-08-08

Applicant: HRL Laboratories, LLC

Inventor： Jiejun Xu ,  Tsai-Ching Lu

IPC: G06F17/30 ,  G06Q50/00 ,  G06Q30/02

CPC classification number: G06F16/9535 ,  G06Q30/02 ,  G06Q30/0255 ,  G06Q50/01

Abstract: Described is a system for discovering user interests through online social media, and more specifically, to a way of doing so by means of a bi-directional graph model. During operation, the system generates a confidence matrix F based on user interactions and co-occurring tags on a social media platform. The confidence matrix F indicates a likelihood of the users in the social media platform as being interested in a particular topic. Based on such likelihoods, an action can be initiated regarding a particular topic for those users whose likelihood of being interested in the particular topic exceeds a predetermined threshold. For example, the system generates and presents an online advertisement to users regarding a particular topic to those users whose likelihood of being interested in the particular topic exceeds a predetermined threshold.

公开(公告)号：US09465504B1

公开(公告)日：2016-10-11

申请号：US13888178

申请日：2013-05-06

Applicant: HRL Laboratories, LLC

Inventor： David A. Jurgens ,  Tsai-Ching Lu

IPC: G06N5/00 ,  G06F1/00 ,  G06F3/048

CPC classification number: G06F3/048 ,  G06Q10/103

Abstract: Described is a system for automated collaborative behavior analysis using temporal motifs. The system receives an input documents and change log files of a collaborative media, where the documents are continuously edited by multiple authors and where edits are recorded in the change log files, such as Wikipedia. A type of editing behavior by the authors of a given document is identified, and the edits made to the document are analyzed. The system reports how the authors interacted in a collaboration process, resulting in a set of reported author interactions. From the set of reported author interactions, a set of author interactions that are most and least significant in the collaboration process are identified. Then, based on the set of identified author interactions, future effects on documents of the collaborative media are estimated.

Abstract translation: 描述了使用时间图案进行自动协同行为分析的系统。 系统接收输入文档和更改协作媒体的日志文件，其中文档由多个作者连续编辑，并且编辑记录在更改日志文件（如维基百科）中。 识别给定文档的作者的一种编辑行为，并对文档进行的编辑进行分析。 系统报告作者如何在协作过程中进行交互，从而产生一组报告的作者交互。 从报告的作者交互集中，确定了协作过程中最重要和最不重要的一组作者交互。 然后，根据确定的作者相互作用的集合，估计未来对合作媒体文档的影响。

公开(公告)号：US09317567B1

公开(公告)日：2016-04-19

申请号：US13747312

申请日：2013-01-22

Applicant: HRL Laboratories, LLC

Inventor： Tsai-Ching Lu ,  David L. Allen ,  Hankyu Moon

IPC: G06F17/30

CPC classification number: G06T11/206 ,  G06N5/022

Abstract: Described is a system for supporting human intelligence analysis. The system detects changes in social relations among users within a dynamic information network and enables understanding of a current social situation in the dynamic information network through multiple integrated modules. An active network mining module identifies incomplete data that is related to at least one change in the social relations and resolves conflicting and missing data in the dynamic information network. A relevant network discovery module constructs a relevant network from hidden relations within the dynamic information network. An information-aware social network module constructs an information-aware social network using the relevant network, then classifies and prioritizes items of interest to provide an assessment of a current social situation to a user.

Abstract translation: 描述了一种支持人类智力分析的系统。 系统检测动态信息网络中用户之间的社会关系变化，并通过多个集成模块了解动态信息网络中的当前社会情况。 活动的网络挖掘模块识别与社会关系中至少一个变化相关的不完整数据，并解决动态信息网络中冲突和丢失的数据。 相关网络发现模块从动态信息网络中的隐藏关系构建相关网络。 信息感知社交网络模块使用相关网络构建信息感知社交网络，然后对感兴趣的项目进行分类和优先级，以向用户提供对当前社交情况的评估。

公开(公告)号：US11671436B1

公开(公告)日：2023-06-06

申请号：US17021542

申请日：2020-09-15

Applicant: HRL Laboratories, LLC

Inventor： Jiejun Xu ,  Kang-Yu Ni ,  Alexei Kopylov ,  Shane M. Roach ,  Tsai-Ching Lu

IPC: H04L9/40 ,  G06F16/2457

CPC classification number: H04L63/1425 ,  G06F16/24578

Abstract: Described is a system for producing indicators and warnings of adversarial activities. The system receives multiple networks of transactional data from different sources. Each node of a network of transactional data represents an entity, and each edge represents a relation between entities. A worldview graph is generated by merging the multiple networks of transactional data. Suspicious subgraph regions related to an adversarial activity are identified in the worldview graph through activity detection. The suspicious subgraph regions are used to generate and transmit an alert of the adversarial activity.