公开(公告)号：US10736032B2

公开(公告)日：2020-08-04

申请号：US16193805

申请日：2018-11-16

Applicant: Huazhong University of Science and Technology

Inventor： Feng Lu ,  Ziqian Shi ,  Ruoxue Liu ,  Song Wu ,  Hai Jin

IPC: G06F9/46 ,  H04W52/02 ,  H04L29/08 ,  H04W88/02

Abstract: The present invention relates to a method for cloudlet-based optimization of energy consumption, comprises: building a cloudlet system that comprises: at least two cloudlets and a mobile device wirelessly connected to the cloudlets, so that the cloudlets provide the mobile device wirelessly connected thereto with cloud computing services; acquiring system data related to the mobile device from the cloudlet system for analyzing a data volume to be handled by the mobile device locally and setting an initial operating frequency FLinitial for a first processor of the mobile device according to the data volume; and based on a tolerable latency range T of a task queue, dynamically deciding a scheduling strategy for individual task of the task queue using a Markov Decision Process, and setting a present operating frequency FL for the first processor of the mobile device corresponding to the scheduling strategy, so as to enable the mobile device to complete the tasks within the tolerable latency range T with minimal energy consumption.

公开(公告)号：US12026260B2

公开(公告)日：2024-07-02

申请号：US17444612

申请日：2021-08-06

Applicant: Huazhong University of Science and Technology

Inventor： Deqing Zou ,  Jing Tang ,  Zhen Li ,  Hai Jin

IPC: G06F21/00 ,  G06F18/214 ,  G06F21/54 ,  G06F21/55 ,  G06F21/56 ,  G06F21/57 ,  G06N3/08 ,  G06N3/094

CPC classification number: G06F21/577 ,  G06F18/214 ,  G06F21/54 ,  G06F21/554 ,  G06F21/563 ,  G06N3/08 ,  G06N3/094

Abstract: The present invention relates a device for improving robustness of deep-learning based detection of source-code vulnerability, the device at least comprises a code-converting module, a mapping module, and a neural-network module, wherein the mapping module is in data connection with the code-converting module, the mapping module is in data connection with the neural-network module, respectively, and the neural-network module includes at least two first classifiers, based on a received first training program source code, the mapping module maps a plurality of code snippets, and the neural-network module trains the at least two first classifiers according to a first sample vector. The present invention improves the robustness of detection of source-code vulnerability by performing classification training on the feature generators and the classifiers.

公开(公告)号：US20230351213A1

公开(公告)日：2023-11-02

申请号：US17935833

申请日：2022-09-27

Applicant: Huazhong University of Science and Technology

Inventor： Feng ZHAO ,  Xiangyu Gui ,  Hai Jin ,  Ruilin Zhao

IPC: G06N5/02

CPC classification number: G06N5/022

Abstract: The present invention relates to an interference-based method for knowledge graph completion and system thereof, wherein the method at least comprises: when performing sampling on a knowledge graph, constructing a knowledge graph completion model; performing model training and performance evaluation on the knowledge graph completion model; and performing prediction on missing elements of incomplete triples in the knowledge graph; the knowledge graph completion model is constructed through: based on optical interference and superposition principles, constructing a score function from data of superposed luminous intensities, mirroring the triples in the knowledge graph to a process of superposition of the luminous intensities, and differentiating between positives and negatives obtained during the sampling of the knowledge graph.

公开(公告)号：US11783258B2

公开(公告)日：2023-10-10

申请号：US17247238

申请日：2020-12-04

Applicant: HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY

Inventor： Jiang Xiao ,  Minrui Wu ,  Huichuwu Li ,  Hai Jin

IPC: H04W4/90 ,  G06Q10/0635 ,  H04W4/029 ,  H04W4/80 ,  G01S5/00 ,  G01S5/02 ,  G01S19/42 ,  G06Q10/0639

CPC classification number: G06Q10/0635 ,  G01S5/013 ,  G01S5/019 ,  G01S5/0252 ,  G01S19/421 ,  G06Q10/06395 ,  H04W4/029 ,  H04W4/80 ,  H04W4/90 ,  G01S5/012

Abstract: The present invention relates to a multimodal sensing positioning system orientated to a high-risk production environment, the positioning system comprising: at least one positioning terminal, configured to be worn by a to-be-positioned subject and use at least one positioning technique to conduct multimodal sensing positioning so as to identify a current location information of the subject in the high-risk production environment; and a monitoring terminal, communicating with the positioning terminal so as to remotely monitor the current location of the subject. The present invention improves positioning precision while ensuring realtimeness of multimodal positioning.

公开(公告)号：US11631007B2

公开(公告)日：2023-04-18

申请号：US17169869

申请日：2021-02-08

Applicant: HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY

Inventor： Feng Zhao ,  Tao Xu ,  Langjunqing Jin ,  Hai Jin

IPC: G06F40/295 ,  G06N5/02 ,  G06F40/30 ,  G06N3/08 ,  G06N3/048

Abstract: The present invention relates to method and device for text-enhanced knowledge graph joint representation learning, the method at least comprises: learning a structure vector representation based on entity objects and their relation linking in a knowledge graph and forming structure representation vectors; discriminating credibility of reliable feature information and building an attention mechanism model, aggregating vectors of different sentences and obtain association-discriminated text representation vectors; and building a joint representation learning model, and using a dynamic parameter-generating strategy to perform joint learning for the text representation vectors and the structure representation vectors based on the joint representation learning model. The present invention selective enhances entity/relation vectors based on significance of associated texts, so as to provide improved semantic expressiveness, and uses 2D convolution operations to train joint representation vectors. As compared to traditional translation models, the disclosed model has better performance in tasks like link prediction and triad classification.

公开(公告)号：US11568268B2

公开(公告)日：2023-01-31

申请号：US16748284

申请日：2020-01-21

Applicant: Huazhong University of Science and Technology

Inventor： Hai Jin ,  Xiaofei Liao ,  Long Zheng ,  Haikun Liu ,  Xi Ge

IPC: G06N3/04 ,  G06N3/10 ,  G06F9/50 ,  G06N3/08

Abstract: A deep learning heterogeneous computing method based on layer-wide memory allocation, at least comprises steps of: traversing a neural network model so as to acquire a training operational sequence and a number of layers L thereof; calculating a memory room R1 required by data involved in operation at the ith layer of the neural network model under a double-buffer configuration, where 1≤i≤L; altering a layer structure of the ith layer and updating the training operational sequence; distributing all the data across a memory room of the CPU and the memory room of the GPU according to a data placement method; performing iterative computation at each said layer successively based on the training operational sequence so as to complete neural network training.

公开(公告)号：US11080371B2

公开(公告)日：2021-08-03

申请号：US16169632

申请日：2018-10-24

Applicant: HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY

Inventor： Hai Jin ,  Weizhong Qiang ,  Zezhao Dong

IPC: G06F21/12 ,  G06F11/14 ,  G06F11/07 ,  G06F21/53 ,  G06F21/74 ,  G06F21/30 ,  H04L9/32 ,  H04L29/06 ,  G06F9/455 ,  G06F21/57

Abstract: The present invention involves with a method and system of state consistency protection for Intel software guard extension (SGX). In a method of state consistency protection for a central processing unit capable of creating enclaves, the central processing unit supports creation of at least one enclave, wherein the central processing unit communicates with a remote server providing services for the central processing unit through remote communication and the remote server has a remote attestation module, configuring the remote attestation module to facilitate the completion of every execution state storing operation and/or every execution state restoring operation, wherein the remote attestation refers to an attestation mechanism by which the central processing unit proves to the remote server that it has created the specific enclave in a local platform so that the remote server trusts the specific enclave. The present invention does not require special hardware and is favorable to cross-platform migration.

公开(公告)号：US20210191763A1

公开(公告)日：2021-06-24

申请号：US16947055

申请日：2020-07-16

Applicant: Huazhong University of Science and Technology

Inventor： Xiaofei LIAO ,  Yicheng Chen ,  Yu Zhang ,  Hai Jin ,  Jin Zhao ,  Xiang Zhao ,  Beibei Si

IPC: G06F9/48 ,  G06F30/331 ,  G06F9/30 ,  G06F9/38 ,  G06F9/50

Abstract: The present disclosure relates to an FPGA-based dynamic graph processing method, comprising: where graph mirrors of a dynamic graph that have successive timestamps define an increment therebetween, a pre-processing module dividing the graph mirror having the latter timestamp into at least one path unit in a manner that incremental computing for any vertex only depends on a preorder vertex of that vertex; an FPGA processing module storing at least two said path units into an on-chip memory directly linked to threads in a manner that every thread unit is able to process the path unit independently; the thread unit determining an increment value between the successive timestamps of the preorder vertex while updating a state value of the preorder vertex, and transferring the increment value to a succeeding vertex adjacent to the preorder vertex in a transfer direction determined by the path unit, so as to update the state value of the succeeding vertex.

公开(公告)号：US20210097221A1

公开(公告)日：2021-04-01

申请号：US16895545

申请日：2020-06-08

Applicant: Huazhong University of Science and Technology

Inventor： Xiaofei Liao ,  Qingxiang Chen ,  Long Zheng ,  Hai Jin ,  Pengcheng Yao

IPC: G06F30/331 ,  G06F16/901 ,  G06F12/0806 ,  G06F9/54 ,  G06F9/38

Abstract: The present invention relates to an optimization method for graph processing based on heterogeneous FPGA data streams. The method can balance processing loads between the CPU processing module and the FPGA processing module during acceleration of graph data processing.

公开(公告)号：US20200349054A1

公开(公告)日：2020-11-05

申请号：US16774016

申请日：2020-01-28

Applicant: Huazhong University of Science and Technology

Inventor： Weiqi Dai ,  Hai Jin ,  Deqing Zou ,  Bingcheng Zhao

IPC: G06F11/36 ,  H04L9/06 ,  H04L9/00

Abstract: The present disclosure involves a sidechain testing system and method for improving security and stability of a smart contract.