中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

90 records (took 0.025 seconds)

    ADJUSTING TRIGGERS FOR AUTOMATIC SCALING OF VIRTUAL NETWORK FUNCTIONS
    61.
    发明申请
    ADJUSTING TRIGGERS FOR AUTOMATIC SCALING OF VIRTUAL NETWORK FUNCTIONS 有权

    公开(公告)号：US20220303192A1

    公开(公告)日：2022-09-22

    申请号：US17805680

    申请日：2022-06-06

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Raghvendra Savoor ,  Frederick Armanino ,  Cathleen Southwick ,  Robert Roycroft ,  Zhi Li

    IPC: H04L41/00 ,  H04L12/46 ,  G06F9/455 ,  H04L43/16

    Abstract: A method performed by a processor in a network function virtualization infrastructure includes determining an amount of resources consumed by a virtual network function subsequent to a scaling of the amount of resources in response to an occurrence of a predefined trigger event, determining an amount of time elapsed between the predefined trigger event and a completion of the scaling, determining a key performance indicator value for the virtual network function subsequent to completion of the scaling, evaluating an efficiency of the predefined trigger event that triggers the scaling, based on the amount of resources consumed by the virtual network function subsequent to the scaling, the amount of time elapsed between the detection of the predefined trigger event and completion of the scaling, and the key performance indicator for the virtual network function subsequent to completion of the scaling, and adjusting the predefined trigger event based on the evaluating.

    Adjusting triggers for automatic scaling of virtual network functions
    62.
    发明授权
    Adjusting triggers for automatic scaling of virtual network functions 有权

    公开(公告)号：US11356336B2

    公开(公告)日：2022-06-07

    申请号：US17087580

    申请日：2020-11-02

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Raghvendra Savoor ,  Frederick Armanino ,  Cathleen Southwick ,  Robert Roycroft ,  Zhi Li

    IPC: H04L41/00 ,  G06F9/455 ,  H04L12/46 ,  H04L43/16

    Abstract: A method performed by a processor in a network function virtualization infrastructure includes determining an amount of resources consumed by a virtual network function subsequent to a scaling of the amount of resources in response to an occurrence of a predefined trigger event, determining an amount of time elapsed between the predefined trigger event and a completion of the scaling, determining a key performance indicator value for the virtual network function subsequent to completion of the scaling, evaluating an efficiency of the predefined trigger event that triggers the scaling, based on the amount of resources consumed by the virtual network function subsequent to the scaling, the amount of time elapsed between the detection of the predefined trigger event and completion of the scaling, and the key performance indicator for the virtual network function subsequent to completion of the scaling, and adjusting the predefined trigger event based on the evaluating.

    Adjusting triggers for automatic scaling of virtual network functions
    64.
    发明授权
    Adjusting triggers for automatic scaling of virtual network functions 有权

    公开(公告)号：US10826789B2

    公开(公告)日：2020-11-03

    申请号：US16234248

    申请日：2018-12-27

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Raghvendra Savoor ,  Frederick Armanino ,  Cathleen Southwick ,  Robert Roycroft ,  Zhi Li

    IPC: H04L12/24 ,  H04L12/46 ,  H04L12/26 ,  G06F9/455

    Abstract: A method performed by a processor in a network function virtualization infrastructure includes determining an amount of resources consumed by a virtual network function subsequent to a scaling of the amount of resources in response to an occurrence of a predefined trigger event, determining an amount of time elapsed between the predefined trigger event and a completion of the scaling, determining a key performance indicator value for the virtual network function subsequent to completion of the scaling, evaluating an efficiency of the predefined trigger event that triggers the scaling, based on the amount of resources consumed by the virtual network function subsequent to the scaling, the amount of time elapsed between the detection of the predefined trigger event and completion of the scaling, and the key performance indicator for the virtual network function subsequent to completion of the scaling, and adjusting the predefined trigger event based on the evaluating.

    Cloud oversubscription system
    65.
    发明授权
    Cloud oversubscription system 有权

    公开(公告)号：US10795715B2

    公开(公告)日：2020-10-06

    申请号：US16021739

    申请日：2018-06-28

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Imad Ahmad ,  Frederick M. Armanino ,  Raghvendra Savoor

    IPC: G06F9/455 ,  G06F9/48 ,  G06F9/50 ,  G06F11/00 ,  G06F11/07 ,  G06F11/30 ,  G06N7/08 ,  G06F17/18 ,  H04L12/24

    Abstract: A cloud oversubscription system comprising an overload detector configured to model a time series of data of at least one virtual machine on a host as a vector-valued stochastic process including at least one model parameter, the overload detector communicating with an inventory database, the overload detector configured to obtain an availability requirement for each of the at least one virtual machine; a model parameter estimator communicating with the overload detector, the model parameter estimator communicating with a database containing resource measurement data for at least one virtual machine on a host at a selected time interval, the model parameter estimator is configured to estimate the at least one model parameter from the resource measurement data; a loading assessment module communicating with the model parameter module to obtain the at least one model parameter for each of the at least one host running at least one virtual machine and determine a probability of overload based on the at least one model parameter, wherein the loading assessment module communicates the probability of overload to the overload detector; wherein the overload detector compares the probability of overload to the availability requirement to identify a probable overload condition value; and wherein the overload detector communicates the probable overload condition value to a recommender, wherein the recommender generates an alert when the overload condition value exceeds the service level agreement requirements for any of the at least one virtual machine.

    SYSTEM AND METHOD OF INTERACTING WITH DATA AT A WIRELESS COMMUNICATION DEVICE
    68.
    发明申请
    SYSTEM AND METHOD OF INTERACTING WITH DATA AT A WIRELESS COMMUNICATION DEVICE 审中-公开
    在无线通信设备上与数据交互的系统和方法

    公开(公告)号：US20150220560A1

    公开(公告)日：2015-08-06

    申请号：US14687531

    申请日：2015-04-15

    Applicant: AT&T INTELLECTUAL PROPERTY I, L.P.

    Inventor： Zhi Li ,  Raghvendra Savoor

    IPC: G06F17/30 ,  H04W4/00

    CPC classification number: G06F17/30194 ,  G06F3/0481 ,  G06F13/385 ,  G06F2213/3814 ,  G06Q50/06 ,  H04M1/72522 ,  H04M1/72552 ,  H04W4/70 ,  H04W88/02

    Abstract: A wireless communication device includes a processor and a memory coupled to the processor. The memory includes instructions executable by the processor to perform operations. The operations include receiving a communication request input corresponding to an action to be executed with respect to a data file. The action is executable by the processor when the processor is connected to an external resource. The operations include automatically determining, in response to receiving the communication request input, whether the processor is connected to the external resource. The external resource enables the processor to communication via a wireless wide area network. The method also includes generating delayed action metadata in response to determining that the processor is not connected to the external resource. The delayed action metadata indicates that the requested action is to be executed by the processor when the processor is subsequently coupled to the external resource.

    Abstract translation: 无线通信设备包括处理器和耦合到处理器的存储器。 存储器包括可由处理器执行以执行操作的指令。 这些操作包括接收与要针对数据文件执行的动作相对应的通信请求输入。 当处理器连接到外部资源时，该操作可由处理器执行。 这些操作包括响应于接收到通信请求输入而自动确定处理器是否连接到外部资源。 外部资源使处理器能够通过无线广域网进行通信。 该方法还包括响应于确定处理器未连接到外部资源而产生延迟动作元数据。 延迟动作元数据指示当处理器随后耦合到外部资源时，由处理器执行所请求的动作。

    IMPLEMENTING NETWORK SECURITY RULES IN HOME ROUTERS
    69.
    发明申请
    IMPLEMENTING NETWORK SECURITY RULES IN HOME ROUTERS 有权

    公开(公告)号：US20250088525A1

    公开(公告)日：2025-03-13

    申请号：US18951519

    申请日：2024-11-18

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Yaron Kanza ,  Raghvendra Savoor

    IPC: H04L9/40 ,  H04L43/062

    Abstract: In one example, the present disclosure describes a device, computer-readable medium, and method for implementing programmable security specifications in home routers. For instance, in one example, a method performed by a processing system including at least one processor includes monitoring network traffic flowing into and out of a home network that is connected to a core network via a gateway device, constructing a model of network traffic flowing into and out of the home network, based on the monitoring, detecting an anomaly in the model of the network traffic, generating a rule based on the anomaly, where the rule specifies an action to be taken when a match condition related to the anomaly is detected, and deploying the rule on the gateway device.

    METHOD AND APPARATUS FOR MULTI-STAGE DEVICE CLASSIFICATION
    70.
    发明申请
    METHOD AND APPARATUS FOR MULTI-STAGE DEVICE CLASSIFICATION 有权

    公开(公告)号：US20250053863A1

    公开(公告)日：2025-02-13

    申请号：US18448372

    申请日：2023-08-11

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Sangho Oh ,  Vanessa Tan ,  Yali Liu ,  Raghvendra Savoor

    IPC: G06N20/00

    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.

Patent Agency Ranking