知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

949 records (took 0.035 seconds)

    NEGOTIATING MACHINE LEARNING MODEL INPUT FEATURES BASED ON COST IN CONSTRAINED NETWORKS
    51.
    发明申请
    NEGOTIATING MACHINE LEARNING MODEL INPUT FEATURES BASED ON COST IN CONSTRAINED NETWORKS 有权

    公开(公告)号：US20210176146A1

    公开(公告)日：2021-06-10

    申请号：US16709235

    申请日：2019-12-10

    Applicant: Cisco Technology, Inc.

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

    IPC: H04L12/26 ,  G06N20/00 ,  G06N5/04

    Abstract: In one embodiment, a service receives a feature availability report indicative of which telemetry variables are available at a device in a network and resource costs associated with data features that the device could compute from the telemetry variables. The service selects at least a subset of the data features for input to a machine learning model, based on their associated resource costs and on their respective impacts on one or more performance metrics for the machine learning model. The service trains the machine learning model to evaluate the selected data features. The service sends the trained machine learning model to the device. The device computes the selected data features from the telemetry variables available at the device and uses the computed data features as input to the machine learning model.

    Cascade-based classification of network devices using multi-scale bags of network words
    53.
    发明授权
    Cascade-based classification of network devices using multi-scale bags of network words 有权

    公开(公告)号：US11025486B2

    公开(公告)日：2021-06-01

    申请号：US16164882

    申请日：2018-10-19

    Applicant: Cisco Technology, Inc.

    Inventor： Pierre-André Savalle ,  Jean-Philippe Vasseur ,  Grégory Mermoud

    IPC: G06F15/177 ,  H04L12/24 ,  H04L29/08 ,  G06K9/62

    Abstract: In one embodiment, a device classification service extracts, for each of a plurality of time windows, one or more sets of traffic features of network traffic in a network from traffic telemetry data captured by the network. The service represents, for the time windows, the extracted one or more sets of traffic features as feature vectors. A feature vector for a time window indicates whether each of the traffic features was present in the network traffic during that window. The service trains, using a training dataset based on the feature vectors, a cascade of machine learning classifiers to label devices with device types. The service uses the classifiers to label a particular device in the network with a device type based on the traffic features of network traffic associated with that device. The service initiates enforcement of a network policy regarding the device based on its device type.

    Detecting network entity groups with abnormal time evolving behavior
    55.
    发明授权
    Detecting network entity groups with abnormal time evolving behavior 有权

    公开(公告)号：US10938664B2

    公开(公告)日：2021-03-02

    申请号：US16132933

    申请日：2018-09-17

    Applicant: Cisco Technology, Inc.

    Inventor： Vikram Kumaran ,  Santosh Ghanshyam Pandey ,  Jean-Philippe Vasseur

    IPC: G06F15/16 ,  H04L12/24 ,  H04B17/345 ,  H04B17/318 ,  H04B17/336 ,  H04L12/733

    Abstract: In one embodiment, a network assurance service that monitors a network calculates network frequency distributions of a performance measurement from the network over a plurality of different time periods. The service calculates entity frequency distributions of the performance measurement for a plurality of different groupings of one or more network entities in the network over the plurality of different time periods. The service determines distance measurements between the network frequency distributions and the entity frequency distributions. The service identifies a particular one of the grouping of one or more networking entities as an outlier, based on a change in distance measurements between the network frequency distributions and the entity frequency distributions for the particular grouping. The service provides an indication of the identified outlier grouping to a user interface.

    Threshold selection for KPI candidacy in root cause analysis of network issues
    56.
    发明授权
    Threshold selection for KPI candidacy in root cause analysis of network issues 有权

    公开(公告)号：US10897389B2

    公开(公告)日：2021-01-19

    申请号：US16131143

    申请日：2018-09-14

    Applicant: Cisco Technology, Inc.

    Inventor： Sajjit Thampy ,  Santosh Ghanshyam Pandey ,  Jean-Philippe Vasseur

    IPC: H04L12/24 ,  H04L12/26 ,  H04W24/04 ,  H04B17/309 ,  H04W28/04

    Abstract: In one embodiment, a network assurance service that monitors a network maps time series of values of key performance indicator (KPIs) measured from the network to lists of unique values from the time series. The service sets a target alarm rate for anomaly detection alarms raised by the network assurance service. The service uses an optimization function to identify a set of thresholds for the KPIs. The optimization function is based on: a comparison between the target alarm rate and a fraction of network issues flagged by the service as outliers, KPI thresholds selected based on the lists of unique values from the time series, and a number of thresholds that the KPIs must cross for the service to raise an alarm. The service raises an anomaly detection alarm for the monitored network based on the identified set of thresholds for the KPIs.

    Propagation of routing information in RSVP-TE for inter-domain TE-LSPS
    57.
    发明授权
    Propagation of routing information in RSVP-TE for inter-domain TE-LSPS 有权

    公开(公告)号：US10826824B2

    公开(公告)日：2020-11-03

    申请号：US15662117

    申请日：2017-07-27

    Applicant: Cisco Technology, Inc.

    Inventor： Jean-Philippe Vasseur ,  Stefano B. Previdi

    IPC: H04L12/723 ,  H04L12/701 ,  H04L12/715

    Abstract: In one embodiment, a traffic engineering (TE) label switched path (LSP) is established between a head-end node in a local domain and a tail-end node in a remote domain. The TE-LSP spans one or more intervening domains located between the local domain and the remote domain. The head-end node sends a routing information request over the TE-LSP to a target node on the TE-LSP that is in the remote domain. The head end node receives routing information from the target node. The received routing information includes a list of address prefixes reachable by the target node. The head end node uses the received routing information to calculate routes reachable via the TE-LSP to the target node. The calculated routes have a next-hop interface set to be the TE-LSP. The calculated routes are inserted into a routing table of the head-end node.

    Jitter elimination and latency compensation at DetNet transport egress
    59.
    发明授权
    Jitter elimination and latency compensation at DetNet transport egress 有权

    公开(公告)号：US10798012B2

    公开(公告)日：2020-10-06

    申请号：US16136947

    申请日：2018-09-20

    Applicant: Cisco Technology, Inc.

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

    IPC: H04L12/841 ,  H04L12/801 ,  H04L12/851 ,  H04L12/875 ,  H04L12/861 ,  H04L12/727

    Abstract: In one embodiment, a method comprises receiving, by a transport layer executed by a processor circuit in an apparatus, an identifiable grouping of data; storing, by the transport layer, the data as transport layer packets in a buffer circuit in the apparatus, the storing including inserting into each transport layer packet a grouping identifier that identifies the transport layer packets as belonging to the identifiable grouping; and causing, by the transport layer, a plurality of transmitting deterministic network interface circuits to deterministically retrieve the transport layer packets from the buffer circuit for deterministic transmission across respective deterministic links, the grouping identifier enabling receiving deterministic network interface circuits to group the received transport layer packets, regardless of deterministic link, into a single processing group for a next receiving transport layer.

Patent Agency Ranking