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.

公开(公告)号：US20250159064A1

公开(公告)日：2025-05-15

申请号：US18541472

申请日：2023-12-15

Applicant: BEIJING UNIVERSITY OF POSTS AND TELECOMMUNICATIONS

Inventor： Bo He ,  Haoran Zhao ,  Qi Qi ,  Yuhan Jing ,  Jingyu Wang ,  Jing Wang

IPC: H04L69/324 ,  H04L69/164

Abstract: A data transmission method and system for Internet of Things devices, includes: by a machine type communication gateway, reading, short data packets sent by all of the Internet of Things devices, acquiring QUIC data streams corresponding to the Internet of Things devices sending the short data packets, and placing data in the short data packets into to-be-sent queues for the acquired QUIC data streams; by the machine type communication gateway, newly creating an empty data packet; popping up, in chronological order in which to-be-sent data is placed into the to-be-sent queues for the QUIC data streams, the to-be-sent data one by one from a to-be-sent queue for each of QUIC data streams that contains the to-be-sent data; encapsulating the popped-up to-be-sent data into a streamframe and then loading the streamframe into the newly created data packet; and finally sending the data packet loaded with multiple streamframes to a central base station. The present disclosure relates to the field of information communication networks, which can guarantee an integrity of the original data of a short data packet based on a scenario with massive Internet of Things, and can effectively reduce the number of data packets and the total amount of data forwarded from the machine type communication gateway to a central base station.

公开(公告)号：US11974027B2

公开(公告)日：2024-04-30

申请号：US18115110

申请日：2023-02-28

Applicant: BEIJING UNIVERSITY OF POSTS AND TELECOMMUNICATIONS

Inventor： Zirui Zhuang ,  Jingyu Wang ,  Huairuo Xu ,  Haifeng Sun ,  Daoxu Sheng ,  Jing Wang

IPC: H04N21/81 ,  H04N21/24 ,  H04N21/414 ,  H04N21/6405 ,  H04N21/647

CPC classification number: H04N21/816 ,  H04N21/2407 ,  H04N21/41407 ,  H04N21/6405 ,  H04N21/64769

Abstract: A system and method for real-time transmission of a panoramic video, which propose a new grouping method and bitrate decision method specifically for a panoramic 360-degree video. The grouping method takes into account fields of view of different users, thus effectively reducing the bandwidth consumption of repeated video segments, while ensuring user fairness and making full use of network bandwidth resources when allocating resources. The system and method of the invention can maximize the long-term QoE of users under the condition of limited bandwidth, and avoid the problem that the existing schemes are complex and difficult to meet real-time requirements of users.

公开(公告)号：US20230401243A1

公开(公告)日：2023-12-14

申请号：US18095196

申请日：2023-01-10

Applicant: BEIJING UNIVERSITY OF POSTS AND TELECOMMUNICATIONS

Inventor： Haifeng Sun ,  Zirui Zhuang ,  Bing Ma ,  Jingyu Wang ,  Cheng Zhang ,  Tong Xu ,  Jing Wang

IPC: G06F16/332 ,  G06F16/33 ,  G06N3/08

CPC classification number: G06F16/3329 ,  G06F16/3347 ,  G06F16/3344 ,  G06N3/08

Abstract: The multi-turn dialogue system based on retrieval includes the following modules: a representation module, a matching module, an aggregation module and a prediction module; the multi-turn dialogue method based on retrieval includes the following steps: (1) by a representation module, converting each turn of dialogue into a cascade vector of the dialogue, and converting a candidate answer into a cascade vector of the candidate answer; (2) by a matching module, dynamically absorbing context information based on a global attention mechanism, and calculating a matching vector; (3) by aggregation module, obtaining a short-term dependence information sequence and a long-term dependence information sequence; (4) by a prediction module, calculating the matching score of the context and candidate answer involved in the matching; (5) selecting a candidate answer with the highest matching score as a correct answer.

公开(公告)号：US12292905B2

公开(公告)日：2025-05-06

申请号：US18095196

申请日：2023-01-10

Applicant: BEIJING UNIVERSITY OF POSTS AND TELECOMMUNICATIONS

Inventor： Haifeng Sun ,  Zirui Zhuang ,  Bing Ma ,  Jingyu Wang ,  Cheng Zhang ,  Tong Xu ,  Jing Wang

IPC: G06F17/00 ,  G06F16/3329 ,  G06F16/334 ,  G06N3/08

Abstract: The multi-turn dialogue system based on retrieval includes the following modules: a representation module, a matching module, an aggregation module and a prediction module; the multi-turn dialogue method based on retrieval includes the following steps: (1) by a representation module, converting each turn of dialogue into a cascade vector of the dialogue, and converting a candidate answer into a cascade vector of the candidate answer; (2) by a matching module, dynamically absorbing context information based on a global attention mechanism, and calculating a matching vector; (3) by aggregation module, obtaining a short-term dependence information sequence and a long-term dependence information sequence; (4) by a prediction module, calculating the matching score of the context and candidate answer involved in the matching; (5) selecting a candidate answer with the highest matching score as a correct answer.

公开(公告)号：US11909592B2

公开(公告)日：2024-02-20

申请号：US18115453

申请日：2023-02-28

Applicant: BEIJING UNIVERSITY OF POSTS AND TELECOMMUNICATIONS

Inventor： Jingyu Wang ,  Qi Qi ,  Zirui Zhuang ,  Yuebin Guo ,  Lingqi Guo ,  Tong Xu ,  Jing Wang

IPC: H04L41/0894 ,  H04L41/08

CPC classification number: H04L41/0894 ,  H04L41/0886

Abstract: A method for multi-policy conflict avoidance in an autonomous network comprising: collecting network state information; acquiring a set of multiple policies to be verified; constructing a policy ordering space tree containing all multi-policy execution sequences; performing a depth-first traversal on the policy ordering space tree, extracting a multi-policy execution sequence to be verified, then constructing an initial simulation data plane, injecting each policy in the multi-policy execution sequence into the simulation data plane one by one in sequence, and storing a simulation data plane after each policy is inserted; detecting whether there is a conflict in the simulation data plane generated after each policy is executed, inferring dependencies among multiple policies in the conflict policy sequence, pruning the policy ordering space tree, to efficiently select and update the multi-policy execution sequence avoiding conflicts.

公开(公告)号：US11514309B2

公开(公告)日：2022-11-29

申请号：US16215033

申请日：2018-12-10

Applicant: Beijing University of Posts and Telecommunications

Inventor： Jianxin Liao ,  Jingyu Wang ,  Jing Wang ,  Qi Qi ,  Jie Xu

IPC: G06N3/08 ,  G06N3/04

Abstract: Embodiments of the present invention provide a method and apparatus for accelerating distributed training of a deep neural network. The method comprises: based on parallel training, the training of deep neural network is designed as a distributed training mode. A deep neural network to be trained is divided into multiple sub-networks. A set of training samples is divided into multiple subsets of samples. The training of the deep neural network to be trained is performed with the multiple subsets of samples based on a distributed cluster architecture and a preset scheduling method. The multiple sub-networks are simultaneously trained so as to fulfill the distributed training of the deep neural network. The utilization of the distributed cluster architecture and the preset scheduling method may reduce, through data localization, the effect of network delay on the sub-networks under distributed training; adapt the training strategy in real time; and synchronize the sub-networks trained in parallel. As such, the time required for the distributed training of the deep neural network may be reduced and the training efficiency of the deep neural network may be improved.

公开(公告)号：US11411865B2

公开(公告)日：2022-08-09

申请号：US16906867

申请日：2020-06-19

Applicant: Beijing University of Posts and Telecommunications

Inventor： Jing Wang ,  Jingyu Wang ,  Haifeng Sun ,  Qi Qi ,  Bo He ,  Jianxin Liao

IPC: H04L45/00 ,  H04L45/302

Abstract: A network resource scheduling method, apparatus, an electronic device and a storage medium are disclosed. An embodiment of the method includes: upon receipt of a network data stream, determining a traffic type of the network data stream based on the number of data packets of the network data stream received within a specified period of time, lengths of the data packets and reception times of the data packets; for each data packet comprised in the network data stream, determining a target transmission path for the data packet, based on node state parameters of nodes in the network cluster, link state parameters of links in the network cluster, and the traffic type of the network data stream when the data packet is received; and transmitting the data packet via the target transmission path.

公开(公告)号：US10833995B2

公开(公告)日：2020-11-10

申请号：US16209865

申请日：2018-12-04

Applicant: Beijing University of Posts and Telecommunications

Inventor： Jianxin Liao ,  Qi Qi ,  Jing Wang ,  Jingyu Wang ,  Jiannan Bao

IPC: H04L12/801 ,  H04L29/08 ,  H04L29/06

Abstract: Embodiments of the present invention provide a congestion control method and apparatus based on a software defined network SDN, and an SDN controller. The method comprises: obtaining a packet_in message sent by a switch; determining a data packet included in the packet_in message; performing a first congestion control processing for a network where the SDN controller is located based on a topological structure and link information of the network when the data packet is a handshake information SYN packet for requesting to establish a TCP connection; performing a second congestion control processing for the network based on the link information when the data packet is a finish information FIN packet for responding to disconnection of a TCP connection; deleting information of a TCP connection stored in a database and corresponding to the data packet when the data packet is an FIN packet requesting to disconnect a TCP connection. As compared with the prior art, by using the solutions according to the embodiments of the present invention, the SDN controller may improve fairness of the bandwidth between each data flow, and reduce TCP retransmission and timeout caused by the highly burst short traffic, and achieve the control of the TCP Incast congestion existing in the datacenter.