利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

1403 条记录 (耗时 0.025 秒)

    Network optimization method, device, and storage medium
    1.
    发明授权
    Network optimization method, device, and storage medium 有权

    公开(公告)号：US12133097B2

    公开(公告)日：2024-10-29

    申请号：US17622513

    申请日：2020-06-22

    申请人： ZTE Corporation

    发明人： Qinzheng Xie

    IPC分类号： H04W24/02 ,  H04L41/046 ,  H04L41/0823 ,  H04L41/14 ,  H04L41/16 ,  H04L43/08 ,  H04W16/18

    CPC分类号： H04W24/02 ,  H04L41/046 ,  H04L41/0823 ,  H04L41/145 ,  H04L41/16 ,  H04L43/08 ,  H04W16/18

    摘要： A network optimization method, a device, and a non-transitory computer-readable storage medium are disclosed. The method may include: modeling problems existing in cells in a first region to obtain N agents, a modeling method and a training method, where a proportion of cells in which existing problems belong to a same problem category among the cells contained in the first region is greater than or equal to a preset threshold, geographic locations of the cells contained are consecutive, and an outline of the first region is an outwardly convex figure, and N is an integer greater than or equal to 1; and for each of the agents, determining an initial model of the agent according to the modeling method and the training method, and training the initial model of the agent using a reinforcement learning method according to the modeling method and the training method.

    MACHINE LEARNING-BASED TARGETING MODEL BASED ON HISTORICAL AND DEVICE TELEMETRY DATA
    2.
    发明公开
    MACHINE LEARNING-BASED TARGETING MODEL BASED ON HISTORICAL AND DEVICE TELEMETRY DATA 审中-公开

    公开(公告)号：US20240330826A1

    公开(公告)日：2024-10-03

    申请号：US18295191

    申请日：2023-04-03

    申请人： Cisco Technology, Inc.

    发明人： Evan K Pease ,  Liz Williams

    IPC分类号： G06Q10/0637 ,  H04L41/0823 ,  H04L41/14 ,  H04L41/16

    CPC分类号： G06Q10/06375 ,  H04L41/0823 ,  H04L41/145 ,  H04L41/16

    摘要： In one aspect, a method includes receiving first data for a plurality of accounts, the first data including information related to feature subscriptions and adoption for each of the plurality of accounts, each account utilizing one or more devices and features of an enterprise network, receiving second data for the plurality of accounts, the second data including telemetry information on network device and feature usage by one or more devices associated with each of the plurality of accounts, and generating, using a trained machine-learning model, an analysis of the plurality of accounts, wherein the machine-learning model receives the first data and the second data as input and provides a likelihood of feature adoption by each of the plurality of accounts.

    Methods And Apparatus For Implementing Reinforcement Learning
    3.
    发明公开
    Methods And Apparatus For Implementing Reinforcement Learning 审中-公开

    公开(公告)号：US20240311687A1

    公开(公告)日：2024-09-19

    申请号：US18272956

    申请日：2021-01-18

    申请人： Telefonaktiebolaget LM Ericsson (publ)

    发明人： Alexandros Nikou ,  Anusha Pradeep Mujumdar

    IPC分类号： G06N20/00 ,  H04L41/0823 ,  H04L41/16

    CPC分类号： G06N20/00 ,  H04L41/0823 ,  H04L41/16

    摘要： Methods and apparatus for implementing reinforcement learning (RL) are provided. A method of operation for a node implementing RL, wherein the node instructs actions in an environment in accordance with a policy generated by a RL agent, wherein the RL agent models the environment and encodes a state of the environment using a set of features, comprises obtaining an intent, wherein the intent specifies one or more criteria to be satisfied by the environment. The method further comprises determining a Companion Markov Decision Process (CMDP) that encodes states of the environment using a subset of the set of features used by the RL agent. The method further comprises generating a finite state automaton that represents the intent as a series of logic states, and computing a product of CMDP output states and logic states, wherein the product contains all of the potential combinations of a CMDP output state and a logic state. The method further comprises selecting an action to be performed on the environment from one or more suggested actions obtained from the policy, the selection being based on the product of CMDP output states and logic state.

    Optimization method and server thereof
    4.
    发明授权
    Optimization method and server thereof 有权

    公开(公告)号：US12095636B2

    公开(公告)日：2024-09-17

    申请号：US17869764

    申请日：2022-07-20

    申请人： Wistron Corporation

    发明人： Chih-Ming Chen

    IPC分类号： G06F15/177 ,  H04L41/0823 ,  H04L43/045

    CPC分类号： H04L43/045 ,  H04L41/0823

    摘要： An optimization method includes generating a constrained causal graph according to an observation data received from a distributed unit, performing a finite domain representation planning using the constrained causal graph to generate an action data about a plurality of radio unit parameters after optimization, and outputting the action data to the distributed unit. A number of a plurality of causal variables of the constrained causal graph and a causal structure of the constrained causal graph are determined at a time.

    Network communications with optimized quality
    8.
    发明授权
    Network communications with optimized quality 有权

    公开(公告)号：US12052159B2

    公开(公告)日：2024-07-30

    申请号：US16021807

    申请日：2018-06-28

    申请人： LiveQoS Inc.

    发明人： Miika Anttoni Klemetti ,  Benjamin Skinner

    IPC分类号： H04L45/02 ,  G06N20/00 ,  H04L41/0813 ,  H04L41/0823 ,  H04L41/5019 ,  H04L65/102 ,  H04L65/80

    CPC分类号： H04L45/08 ,  G06N20/00 ,  H04L41/0813 ,  H04L41/0823 ,  H04L41/5019 ,  H04L65/102 ,  H04L65/80

    摘要： A method for configuring a data path comprising receiving, by a gateway server, a network request from a source to a destination. The network request is associated with a path quality level. A plurality of possible links between the gateway server and a destination server is determined. Each of the plurality of possible links is associated with one of a plurality of predictive models. Each of the plurality of predictive models produces an estimate of a link quality level. Utilizing the plurality of predictive models, a plurality of links between the gateway server and the destination server utilizing the plurality of possible links is selected. The plurality of selected links forms a selected path that satisfies the path quality level. A plurality of routers at both ends of the plurality of selected links are configured to fulfill the network request.

    CHARGING FOR EDGE ENABLING INFRASTRUCTURE RESOURCES
    10.
    发明公开
    CHARGING FOR EDGE ENABLING INFRASTRUCTURE RESOURCES 审中-公开

    公开(公告)号：US20240243936A1

    公开(公告)日：2024-07-18

    申请号：US18558604

    申请日：2022-12-12

    申请人： Intel Corporation

    发明人： Yizhi YAO ,  Joey CHOU

    IPC分类号： H04L12/14 ,  H04L41/0823 ,  H04L43/0876

    CPC分类号： H04L12/1407 ,  H04L41/0823 ,  H04L43/0876

    摘要： Various embodiments herein relate to a logical element configured to consume a management service (MnS). The logical element may further identify, based on consumption of the MnS, a performance measurement related to usage of an edge enabling infrastructure resource for an edge application server (EAS); generate, based on the performance measurement, charging data related to the edge enabling infrastructure; and transmit an indication of the charging data to a second logical clement of the cellular system. The logical element may further identify, based on the transmitted indication of the charging data, a Charging Data Response received from the second logical element. Other embodiments may be described and/or claimed.