知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

949 records (took 0.03 seconds)

    Utilizing multiple interfaces when sending data and acknowledgement packets
    131.
    发明授权
    Utilizing multiple interfaces when sending data and acknowledgement packets 有权

    公开(公告)号：US09634982B2

    公开(公告)日：2017-04-25

    申请号：US13945886

    申请日：2013-07-18

    Applicant: Cisco Technology, Inc.

    Inventor： Jonathan W. Hui ,  Wei Hong ,  Jean-Philippe Vasseur

    IPC: H04L12/58

    CPC classification number: H04L51/18 ,  H04L51/38

    Abstract: Utilizing multiple network interfaces when sending data and acknowledgement packages comprises, in a low power and lossy network (LLN) or other network, a sender device comprises two or more network interfaces for communicating with one or more recipient devices. The sender device assesses the transmission capabilities of the network interfaces to determine data rates available for each interface. The sender device specifies which network interface will be used to transfer data and which network interface will be used to receive an acknowledgement from the recipient device. The sender device selects the network interface with the larger data capacity for transmitting a data packet and the network interface with the smaller data capacity for receiving an acknowledgement. The data transmission and the acknowledgement transmission may be transmitted simultaneously. The recipient device uses transmission parameters received from the sender device to determine the data rate with which to transmit the acknowledgement.

    DETECTING OSCILLATION ANOMALIES IN A MESH NETWORK USING MACHINE LEARNING
    132.
    发明申请
    DETECTING OSCILLATION ANOMALIES IN A MESH NETWORK USING MACHINE LEARNING 审中-公开
    使用机器学习检测网状网络中的振荡异常

    公开(公告)号：US20170078170A1

    公开(公告)日：2017-03-16

    申请号：US14855492

    申请日：2015-09-16

    Applicant: Cisco Technology, Inc.

    Inventor： Jean-Philippe Vasseur ,  Pascal Thubert ,  Patrick Wetterwald ,  Eric Levy-Abegnoli

    IPC: H04L12/26 ,  G06N99/00 ,  H04L29/06

    CPC classification number: H04L43/08 ,  G06N99/005 ,  H04L41/142 ,  H04L41/16 ,  H04L43/04 ,  H04L67/12 ,  H04L69/22

    Abstract: In one embodiment, a device in a network receives metrics regarding a node in the network. The device uses the metrics as input to a machine learning model. The device determines, using the machine learning model and based on the metrics, an indication of abnormality of the node oscillating between using a plurality of different routing parents in the network. The device provides a results notification based on the indication of abnormality of the node oscillating between using the plurality of different routing parents.

    Abstract translation: 在一个实施例中，网络中的设备接收关于网络中的节点的度量。 该设备使用度量作为机器学习模型的输入。 该设备使用机器学习模型并且基于度量来确定节点在使用网络中的多个不同路由父节点之间振荡的异常的指示。 该设备基于在使用多个不同路由父节点之间振荡的节点的异常的指示来提供结果通知。

    Learning machine based computation of network join times
    134.
    发明授权
    Learning machine based computation of network join times 有权
    基于学习机的网络连接时间计算

    公开(公告)号：US09553773B2

    公开(公告)日：2017-01-24

    申请号：US13948367

    申请日：2013-07-23

    Applicant: Cisco Technology, Inc.

    Inventor： Jean-Philippe Vasseur ,  Grégory Mermoud ,  Sukrit Dasgupta

    IPC: G06F15/173 ,  H04L12/24

    CPC classification number: H04L41/16 ,  H04L41/142

    Abstract: In one embodiment, techniques are shown and described relating to learning machine based computation of network join times. In particular, in one embodiment, a device computes a join time of the device to join a computer network. During joining, the device sends a configuration request to a server, and receives instructions whether to provide the join time. The device may then provide the join time to a collector in response to instructions to provide the join time. In another embodiment, a collector receives a plurality of join times from a respective plurality of nodes having one or more associated node properties. The collector may then estimate a mapping between the join times and the node properties and determines a confidence interval of the mapping. Accordingly, the collector may then determine a rate at which nodes having particular node properties report their join times based on the confidence interval.

    Abstract translation: 在一个实施例中，与基于学习机的网络连接时间的计算相关的技术被示出和描述。 特别地，在一个实施例中，设备计算设备加入计算机网络的加入时间。 在加入过程中，设备向服务器发送配置请求，并接收指令是否提供加入时间。 响应于提供加入时间的指令，设备可以向收集器提供加入时间。 在另一个实施例中，收集器从具有一个或多个关联节点属性的相应多个节点接收多个连接时间。 然后，收集器可以估计连接时间和节点属性之间的映射，并确定映射的置信区间。 因此，收集器然后可以基于置信区间来确定具有特定节点属性的节点报告其连接时间的速率。

    Dynamically determining node locations to apply learning machine based network performance improvement
    135.
    发明授权
    Dynamically determining node locations to apply learning machine based network performance improvement 有权
    动态确定节点位置，以应用基于学习机的网络性能改进

    公开(公告)号：US09553772B2

    公开(公告)日：2017-01-24

    申请号：US13946227

    申请日：2013-07-19

    Applicant: Cisco Technology, Inc.

    Inventor： Sukrit Dasgupta ,  Jean-Philippe Vasseur ,  Grégory Mermoud

    IPC: G06F15/173 ,  H04L12/24 ,  H04L12/26

    CPC classification number: H04L41/16 ,  H04L41/0677 ,  H04L41/12 ,  H04L43/10

    Abstract: In one embodiment, techniques are shown and described relating to dynamically determining node locations to apply learning machine based network performance improvement. In particular, a degree of significance of nodes in a network, respectively, is calculated based on one or more significance factors. One or more significant nodes are then determined based on the calculated degree of significance. Additionally, a nodal region in the network of deteriorated network health is determined, and the nodal region of deteriorated network health is correlated with a significant node of the one or more significant nodes.

    Abstract translation: 在一个实施例中，显示和描述与动态确定节点位置以应用基于学习机的网络性能改进相关的技术。 特别地，基于一个或多个重要因素来分别计算网络中节点的重要程度。 然后基于所计算的显着程度来确定一个或多个有效节点。 另外，确定网络健康状况恶化的网络中的节点区域，将网络运行恶化的节点区域与一个或多个重要节点的重要节点相关联。

    NETWORK-BASED DYNAMIC DATA MANAGEMENT
    136.
    发明申请
    NETWORK-BASED DYNAMIC DATA MANAGEMENT 审中-公开

    公开(公告)号：US20160381087A1

    公开(公告)日：2016-12-29

    申请号：US15264039

    申请日：2016-09-13

    Applicant: Cisco Technology, Inc.

    Inventor： Sateesh K. Addepalli ,  Raghuram S. Sudhaakar ,  Jean-Philippe Vasseur ,  Flavio Bonomi

    IPC: H04L29/06 ,  H04L29/08

    Abstract: In one embodiment, a router operating in a hierarchically routed computer network may receive collected data from one or more hierarchically lower devices in the network (e.g., hierarchically lower sensors or routers). The collected data may then be converted to aggregated metadata according to a dynamic schema, and the aggregated metadata is stored at the router. The aggregated metadata may also be transmitted to one or more hierarchically higher routers in the network. Queries may then be served by the router based on the aggregated metadata, accordingly.

    Dynamic source route computation to avoid self-interference
    139.
    发明授权
    Dynamic source route computation to avoid self-interference 有权
    动态源路由计算避免自身干扰

    公开(公告)号：US09401863B2

    公开(公告)日：2016-07-26

    申请号：US14136425

    申请日：2013-12-20

    Applicant: Cisco Technology, Inc.

    Inventor： Jonathan W. Hui ,  Jean-Philippe Vasseur ,  Wei Hong

    IPC: H04L12/721 ,  H04W40/16 ,  H04B3/54 ,  H04L12/753

    CPC classification number: H04L45/72 ,  H04B3/54 ,  H04L45/48 ,  H04W40/16 ,  Y02D70/00 ,  Y02D70/142 ,  Y02D70/144 ,  Y02D70/22 ,  Y02D70/34

    Abstract: In a multiple interface, low power and lossy network comprising a plurality of devices, interface options for a source route to minimize self-interferences are desired. The ability to request a interface technology for a device to use with neighboring devices allows multiple transmissions to occur simultaneously without interfering with each other. A root phase device obtains interface option information from the devices. Each device in a network path determines the interface options available, such as powerline communications (“PLC”) and radio frequency (“RF”). The device transmits the interface options to the parent device. The parent device transmits the interface options up the network path toward the root phase device, which collects the interface options and determines transmission routes to any needed endpoint device. The transmission route will comprise the device routes and a interface option for each hop from a parent device to a child device.

    Abstract translation: 在多接口中，包括多个设备的低功率和有损耗的网络是希望用于最小化自干扰的源路由的接口选项。 请求接口技术以使设备与相邻设备一起使用的能力允许多个传输同时发生而不会彼此干扰。 根相设备从设备获取接口选项信息。 网络路径中的每个设备确定可用的接口选项，例如电力线通信（“PLC”）和射频（“RF”）。 设备将接口选项发送到父设备。 父设备将网络路径上的接口选项发送到根相设备，该根相设备收集接口选项并确定到任何所需端点设备的传输路由。 传输路由将包括从父设备到子设备的每一跳的设备路由和接口选项。

    Attack mitigation using learning machines
    140.
    发明授权
    Attack mitigation using learning machines 有权
    攻击缓解使用学习机

    公开(公告)号：US09398035B2

    公开(公告)日：2016-07-19

    申请号：US14165424

    申请日：2014-01-27

    Applicant: Cisco Technology, Inc.

    Inventor： Jean-Philippe Vasseur ,  Javier Cruz Mota ,  Andrea Di Pietro ,  Jonathan W. Hui

    IPC: H04L29/06 ,  H04W12/12 ,  G06N99/00

    CPC classification number: H04L63/1416 ,  G06N99/005 ,  H04K3/226 ,  H04K2203/18 ,  H04L63/1441 ,  H04L63/1458 ,  H04W12/12

    Abstract: In one embodiment, techniques are shown and described relating to attack mitigation using learning machines. A node may receive network traffic data for a computer network, and then predict a probability that one or more nodes are under attack based on the network traffic data. The node may then decide to mitigate a predicted attack by instructing nodes to forward network traffic on an alternative route without altering an existing routing topology of the computer network to reroute network communication around the one or more nodes under attack, and in response, the node may communicate an attack notification message to the one or more nodes under attack.

    Abstract translation: 在一个实施例中，与使用学习机器的攻击缓解有关的技术被示出和描述。 节点可以接收计算机网络的网络流量数据，然后基于网络流量数据预测一个或多个节点受到攻击的概率。 然后，节点可以通过指示节点在替代路由上转发网络流量而不改变计算机网络的现有路由拓扑以重新路由在被攻击的一个或多个节点周围的网络通信，并且响应于节点 可以将攻击通知消息传送给被攻击的一个或多个节点。

Patent Agency Ranking