中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

237 records (took 0.027 seconds)

    Method and apparatus for task scheduling based on deep reinforcement learning, and device
    12.
    发明授权
    Method and apparatus for task scheduling based on deep reinforcement learning, and device 有权

    公开(公告)号：US11886993B2

    公开(公告)日：2024-01-30

    申请号：US17015269

    申请日：2020-09-09

    Applicant: Beijing University of Posts and Telecommunications

    Inventor： Qi Qi ,  Haifeng Sun ,  Jing Wang ,  Lingxin Zhang ,  Jingyu Wang ,  Jianxin Liao

    IPC: G06N3/08 ,  G06N3/047

    CPC classification number: G06N3/08 ,  G06N3/047

    Abstract: Disclosed are a method and apparatus for task scheduling based on deep reinforcement learning and a device. The method comprises: obtaining multiple target subtasks to be scheduled; building target state data corresponding to the multiple target subtasks, wherein the target state data comprises a first set, a second set, a third set, and a fourth set; inputting the target state data into a pre-trained task scheduling model, to obtain a scheduling result of each target subtask; wherein, the scheduling result of each target subtask comprises a probability that the target subtask is scheduled to each target node; for each target subtask, determining a target node to which the target subtask is to be scheduled based on the scheduling result of the target subtask, and scheduling the target subtask to the determined target node.

    FEW-SHOT IMAGE RECOGNITION METHOD AND APPARATUS, DEVICE, AND STORAGE MEDIUM
    13.
    发明公开
    FEW-SHOT IMAGE RECOGNITION METHOD AND APPARATUS, DEVICE, AND STORAGE MEDIUM 审中-公开

    公开(公告)号：US20240029397A1

    公开(公告)日：2024-01-25

    申请号：US18225353

    申请日：2023-07-24

    Applicant: Beijing University of Posts and Telecommunications

    Inventor： Kongming LIANG ,  Zhanyu MA ,  Yurong GUO ,  Ruoyi DU

    IPC: G06V10/74 ,  G06V10/764 ,  G06V10/82

    CPC classification number: G06V10/761 ,  G06V10/764 ,  G06V10/82

    Abstract: The present application discloses a few-shot image recognition method and apparatus, a device, and a storage medium. The method includes: obtaining to-be-recognized images, and constructing an image episode according to the to-be-recognized image, the image episode including a support set and a query set; inputting the image episode into a pre-trained image recognition model, the image recognition model being a few-shot image recognition model based on hard episode training; and calculating a similarity between an image in the query set and each class in the support set according to the image recognition model, and determining the class of to-be-recognized images in the query set according to the similarity. According to the image recognition method provided by the embodiments of the present application, model training and image recognition can be performed by using fewer image samples, and hard episodes are fused into a training process of a few-shot image recognition model, whereby the few-shot image recognition model can be trained more efficiently and quickly, and the trained model is higher in stability and higher in accuracy of image recognition.

    Method and apparatus for classifying mixed signals, and electronic device
    14.
    发明授权
    Method and apparatus for classifying mixed signals, and electronic device 有权

    公开(公告)号：US11816180B2

    公开(公告)日：2023-11-14

    申请号：US17602692

    申请日：2020-03-10

    Applicant: Beijing University of Posts and Telecommunications

    Inventor： Zhiyong Feng ,  Kezhong Zhang ,  Zhiqing Wei ,  Li Xu ,  Che Ji

    IPC: G06K9/00 ,  G06K9/62 ,  G06F18/2135

    CPC classification number: G06F18/2135 ,  G06F2218/12

    Abstract: Disclosed is a method for classifying mixed signals, comprising: receiving mixed signals; performing calculation on a matrix corresponding to the mixed signals by means of a preset Principal Component Analysis method to obtain to-be-classified mixed signals and to determine the number of types of signals contained in the to-be-classified mixed signals; determining a separation matrix based on the number of types of signals contained in the to-be-classified mixed signals; separating individual signals in the to-be-classified mixed signals by means of the separation matrix to obtain to-be-identified signals; calculating a preset number of high-order cumulants corresponding to each to-be-identified signal in the to-be-identified signals respectively; taking the calculated high-order cumulants as characteristics of the to-be-identified signal corresponding to the high-order cumulants respectively; inputting the characteristics of the to-be-identified signal into a preset classification model; and obtaining a modulation mode of the to-be-identified signal. The method according to the embodiment of the present application imposes no requirements on the classification environment, which is different from the prior arts in which the mixed signals can be classified only when certain conditions are met. Therefore, the method has universal applicability.

    Network capability exposure method and device thereof
    17.
    发明授权
    Network capability exposure method and device thereof 有权

    公开(公告)号：US11632713B2

    公开(公告)日：2023-04-18

    申请号：US17330108

    申请日：2021-05-25

    Applicant: Beijing University of Posts and Telecommunications

    Inventor： Luhan Wang ,  Yu Liu ,  Yunan Yan ,  Keliang Du ,  Xiangming Wen ,  Zhaoming Lu

    IPC: H04W48/16 ,  G06N3/08 ,  H04L41/14 ,  H04L41/16 ,  H04W24/02 ,  H04W48/18 ,  G06N3/045

    Abstract: Disclosed is a network capability exposure method, which includes receiving a service request sent by a third-party device; determining a type of a network capability required according to the service request; determining a computing task matching the type of the network capability required; determining computing resources exposed by at least one physical device; obtaining a computing resource exposure result based on the computing task and the computing resources exposed by the at least one physical device; acquiring a network capability corresponding to the type of the network capability and the computing resource exposure result; and providing the network capability to the third-party device. Further, a network capability exposure device, a network capability exposure system and a non-transitory computer-readable storage medium are also disclosed.

    PRIVACY-ENHANCED FEDERATED DECISION-MAKING METHOD, APPARATUS, SYSTEM AND STORAGE MEDIUM
    18.
    发明申请
    PRIVACY-ENHANCED FEDERATED DECISION-MAKING METHOD, APPARATUS, SYSTEM AND STORAGE MEDIUM 有权

    公开(公告)号：US20230095905A1

    公开(公告)日：2023-03-30

    申请号：US17848420

    申请日：2022-06-24

    Applicant: Beijing University of Posts and Telecommunications

    Inventor： Rentao GU ,  Haiyu LIU ,  Xiaoya ZHANG ,  Yunxuan LI ,  Yuefeng JI

    IPC: G06F21/60 ,  G06K9/62

    Abstract: A privacy-enhanced federated decision-making method, apparatus, system and a storage medium are provided for training a global decision-making model for ensuring data privacy of data terminals. Each federated data terminal reports information about a local decision-making model to a federated coordinator, and a federated coordinator trains a global decision-making model by using the information about the local decision-making model reported by the federated data terminals. The trained global decision-making model can be used for coordinating decision making of the federated data terminals, such as coordinating a decision-making sequence of the federated data terminals or coordinating whether the federated data terminals need to participate in a decision-making task. The method resolves the problem of difficult coordination across the data terminals, and improves the decision-making accuracy of the data terminals. The federated data terminals adaptively use the federated decision-making model for improving the decision-making flexibility of the federated data terminals.

    Deep reinforcement learning-based information processing method and apparatus for edge computing server
    19.
    发明授权
    Deep reinforcement learning-based information processing method and apparatus for edge computing server 有权

    公开(公告)号：US11616683B2

    公开(公告)日：2023-03-28

    申请号：US17520744

    申请日：2021-11-08

    Applicant: Beijing University of Posts and Telecommunications

    Inventor： Lanlan Rui ,  Yang Yang ,  Xuesong Qiu ,  Jingyang Yan ,  Zhipeng Gao ,  Wenjing Li

    IPC: H04L41/0631 ,  H04L41/16

    Abstract: A deep reinforcement learning-based information processing method includes: determining whether a target edge computing server enters an alert state according to a quantity of service requests received by the target edge computing server within a preset time period; when the target edge computing server enters the alert state, obtaining preset system status information from a preset memory library; computing an optimal action value corresponding to the target edge computing server based on a preset deep reinforcement learning model according to the preset system status information and preset strategy information; and generating an action corresponding to the target edge computing server according to the optimal action value, and performing the action on the target edge computing server. A deep reinforcement learning-based information processing apparatus for an edge computing server includes a first determining module, an acquisition module, a first computing module, a first generation module.

Patent Agency Ranking