Apparatus and method to facilitate an iterative, machine learning based traffic classification

    公开(公告)号:US11227488B2

    公开(公告)日:2022-01-18

    申请号:US16535180

    申请日:2019-08-08

    Abstract: Aspects of the subject disclosure may include, for example, applying a model to a first unlabeled traffic item to generate a classification of the first unlabeled traffic item as a first class of traffic items or a second class of traffic items, generating a first score that is representative of a first confidence of the classification, determining that the first score is greater than a first threshold, and responsive to determining that the first score is greater than the first threshold, refining the model in accordance with at least the classification, resulting in a modified model. Other embodiments are disclosed.

    METHODS TO ESTIMATE VIDEO PLAYBACK BUFFER
    25.
    发明申请

    公开(公告)号:US20200213636A1

    公开(公告)日:2020-07-02

    申请号:US16814451

    申请日:2020-03-10

    Abstract: Aspects of the subject disclosure may include, for example, a method including monitoring a video session to determine key performance indicators for cross-layer interactions between a network providing video session video data and user equipment receiving the video session video data, wherein the key performance indicators include a transmission control protocol congestion window size that corresponds to a video chunk requested by the user equipment, and a radio access network throughput of a download of the video chunk requested by the user equipment, and determining a quality of service for the user equipment during the video session according to a residual length of content in a playback buffer for the user equipment based on the transmission control protocol congestion window size, and the radio access network throughput. Other embodiments are disclosed.

    Method to Identify Video Applications from Encrypted Over-the-top (OTT) Data

    公开(公告)号:US20190279113A1

    公开(公告)日:2019-09-12

    申请号:US15914057

    申请日:2018-03-07

    Abstract: Aspects of the subject disclosure may include, for example, a processing system that performs operations including collecting encrypted network traffic flow data from user interaction with an application, deriving a first set of traffic feature vectors from the encrypted network traffic flow data collected, training a machine learning algorithm on the first set of traffic feature vectors to classify each traffic feature vector in the first set of traffic feature vectors as associated with a type of the application or not associated with the type of the application, and classifying whether an encrypted network traffic flow as the type of the application by applying the machine learning algorithm to a traffic feature vector of the encrypted network traffic flow. Other embodiments are disclosed.

    ESTIMATING NETWORK DATA STREAMING RATE
    27.
    发明申请

    公开(公告)号:US20180324234A1

    公开(公告)日:2018-11-08

    申请号:US15587479

    申请日:2017-05-05

    CPC classification number: H04L65/1083 H04L65/607 H04L67/02 H04L67/06

    Abstract: In one example, the present disclosure describes a device, computer-readable medium, and method for estimating the streaming rate at which data is delivered over a network. For instance, in one example, a data packet is intercepted from a data streaming session conducted between a first device and a second device connected over a network. A size of a file segment contained in the data packet is calculated. The file segment corresponds to a portion of an item of multimedia content being delivered via the data streaming session. The encoding rate of the data streaming session is then calculated based at least in part on the size of the file segment.

    METHOD AND APPARATUS FOR MULTI-STAGE DEVICE CLASSIFICATION

    公开(公告)号:US20250053863A1

    公开(公告)日:2025-02-13

    申请号:US18448372

    申请日:2023-08-11

    Abstract: Aspects of the subject disclosure may include determining a local classifier device classification associated with a first device via a local machine learning (ML) device classifier according to basic information data associated with the first device, storing the local classifier device classification at a local device classification database, and storing the local classifier device classification at a device classification for ML training database, receiving a ML model update from a trainer for ML device classifier, the ML model update is generated by the trainer for ML device classifier according to the device classification for ML training database and a remote classifier device classification, and the remote classifier device classification is determined via a remote ML device classifier according to historical network information associated with the first device, and updating the local ML device classifier according to the ML model update. Other embodiments are disclosed.

    Estimation of network latency based on aggregated performance data

    公开(公告)号:US12212479B2

    公开(公告)日:2025-01-28

    申请号:US17957326

    申请日:2022-09-30

    Abstract: Estimation of network latency based on aggregated performance data is disclosed. End-to-end latency between endpoints can comprise protocol-induced latency, access network-induced, core-network latency, and network-distance-based latency. Network latency, e.g., network-distance-based latency, also referred to as topological latency, can correspond to communication path length between endpoints. Crowdsourcing of communication path performance information can enable estimation of topological latency, and derivatives thereof, such as topological distance. Crowdsourcing can be the practice of obtaining information or input into a task or project by enlisting the services of a large number of people, either paid or unpaid, e.g., collection of performance information. The disclosure illustrates estimation of protocol-induced latency, access network-induced, and core-network latency, such that they can be compensated for in end-to-end latency information, thereby enabling estimation of topological latency that can be employed in determining, initiating, etc., a network response operation that can affect change in a network.

Patent Agency Ranking