3440 results about "Cloud server" patented technology

The invention provides a lightweight multi-model collaborative edge intelligent target detection system and a lightweight multi-model collaborative edge intelligent target detection method, belongs to the technical field of edge target detection, and aims to solve the problem that a traditional target monitoring scheme depends on a cloud server to carry out deep learning model reasoning; in order to solve the problem that high-precision and low-delay real-time target monitoring cannot be realized on a resource-limited edge device, the detection system comprises an edge calculation module, an image acquisition module and a storage module. The detection method comprises the following steps: acquiring a to-be-detected image, and calling an IPS module through a performance core and an energy efficiency core to pre-process the acquired image; optimizing the YOLO model, and inputting the preprocessed image into a deep learning model; performing target detection on the preprocessed image data through a deep learning model; and a detection result is input into the storage module for storage and is uploaded to equipment connected with the peripheral interface for visual display and a remote monitoring center.

The invention is suitable for the technical field of intelligent door locks, and provides a voice interaction processing method, device and system, an intelligent door lock and a cloud server, and the method comprises the steps: receiving a voice instruction sent by a user, and carrying out the local recognition, so as to obtain a local recognition result and the confidence of the local recognition result; when the local recognition result is matched with the local instruction set and the confidence is high, executing a local operation corresponding to the local recognition result; otherwise, establishing a secure communication session with the cloud server based on voiceprint biological characteristics extracted from the voice instruction; sending the voice instruction to a cloud server through the secure communication session, and receiving a cloud operation instruction and / or a dynamic response text returned by the cloud server; and executing corresponding operation according to the cloud operation instruction, and / or converting the dynamic response text into voice for broadcasting through a text-to-voice engine. The intelligent door lock voice interaction system solves the problem that the real-time performance, the reliability, the safety and the interaction intellectualization are difficult to balance in the existing intelligent door lock voice interaction technology.

The invention discloses an intelligent resource scheduling method and system based on task characteristics and system state perception, and relates to an operating system kernel optimization technology. According to the method, resource demand types, importance labels and time sensitivity of tasks are captured in real time through an eBPF technology, system bottlenecks are recognized by combining / proc and sysfs file system data, a dynamic scheduling strategy is generated by adopting an improved Q-Learning model, and resource allocation is executed through a schemed * function and a cgroup v2 interface. The problems that a traditional scheduler is poor in self-adaptive capacity and resources are mismatched are solved, the actually-measured resource utilization rate is increased to 85%-92%, and the key task delay standard reaching rate gt is achieved; the method is suitable for edge computing, cloud servers and other high-concurrency scenes.

The invention relates to the technical field of rail traffic equipment maintenance and artificial intelligence image recognition, in particular to a rail vehicle cloud edge cooperative detection method and system and inspection equipment. The method comprises the following steps: acquiring image data of an area to be detected, synchronously recording attitude information of shooting equipment, carrying out image quality scoring on the image data, if the image quality score reaches a preset threshold value, calling a local target detection model to carry out defect identification on an image, and outputting an identification result containing a target type, a position and confidence; if the confidence coefficient of the recognition result is lower than a set threshold value, the image data and the posture information are uploaded to a cloud server, a cloud high-precision recognition model is called for secondary recognition, and a cloud recognition result is obtained. The real-time requirement is met through quick response of the local model, the cloud model rechecks a low-confidence result, efficiency and precision are both considered, and the contradiction that in the prior art, manual judgment standards are different, and speed and precision are difficult to consider is solved.

Disclosed in the present invention are a model training method and apparatus based on federated learning, and a device and a storage medium. The method comprises: training a local model on the basis of power data, so as to generate a fault analysis model used for fault analysis of a power device; and uploading local model parameters to a cloud server, such that the cloud server aggregates the local model parameters, then updates a corresponding global model, and issues updated global model parameters to edge nodes, wherein when aggregating the local model parameters, the cloud server marks the edge node corresponding to an abnormal local model parameter as a suspected abnormal node, monitors the marked suspected abnormal node, and removes, when it is detected that the suspected abnormal node is abnormal, the local model parameters uploaded by the suspected abnormal node. By means of the present invention, it can be ensured that the performance of a fault analysis model obtained by training a local model is not degraded.

The invention relates to the technical field of robots, and discloses a remote upgrading method of a robot, the robot and a system. According to the method, equipment state information of the robot is obtained, under the condition that the equipment state information meets upgrading conditions, an upgrading request is obtained, the upgrading request is sent to a cloud server, an upgrading package sent by the cloud server is obtained, and the robot is remotely upgraded according to the upgrading package. The equipment state information of the robot is obtained, if the equipment state information meets the upgrading condition, it is determined that the robot is remotely upgraded, and therefore the success rate of remote upgrading of the robot can be increased.

The invention relates to the technical field of chronic kidney disease screening, and discloses an intelligent chronic kidney disease early screening instrument which comprises a physiological parameter detection module configured to synchronously collect multi-dimensional bio-electricity signals, optical characteristic parameters and body fluid biochemical parameters of a subject and output original signals; the multi-modal data processing module is in communication connection with the physiological parameter detection module and is configured to receive original signals, perform time domain and frequency domain conjoint analysis and construct a parameter incidence matrix; the wireless communication module is configured to realize encrypted interaction between the screening data and the cloud server and block chain evidence storage; and the man-machine interaction module is configured to display the risk level map in real time. According to the method, holographic dynamic correlation modeling of kidney function related micro-electrophysiological fluctuation and optical metabolism characteristics is realized, and a specific cross-modal pathological correlation mode of early renal injury can be effectively identified based on a time-frequency domain combined characteristic extraction and dynamic coupling algorithm.

The invention discloses a machine tool thermal error compensation system based on digital twinning and cloud edge collaboration, which belongs to the technical field of precision manufacturing and comprises a physical error control layer, a digital twinning data layer, a virtual error control layer, an edge server and a cloud server. And performing real-time prediction on the acquired temperature and thermal error data through a long-sequence space-time fusion parallel network model deployed in an edge server, and issuing a compensation instruction to the CNC controller. And the cloud server is responsible for training and updating the model. According to the method, high-precision modeling and low-delay real-time compensation of the thermal error are realized through the cloud edge cooperation and digital twinning technology, the thermal error of the main shaft is reduced by 80% at most, the response delay of the system is reduced by about 40%, and the machining precision and stability of a machine tool are remarkably improved.

The invention relates to the technical field of big data analysis, and discloses a new energy automobile intelligent fast charging scheduling method based on multi-source data analysis, which comprises the following steps: S1, collecting multi-source charging scheduling data: constructing a charging scheduling multi-source data set; s2, multi-source data preprocessing and fusion: obtaining a charging scheduling fusion decision data set; s3, generating a charging scheduling decision: making the charging scheduling decision; s4, instruction issuing and execution control; s5, real-time monitoring and dynamic adjustment: dynamically adjusting a charging strategy; s6, feedback collection and optimization iteration are carried out; multi-source charging scheduling data are collected in real time through a vehicle-mounted terminal, a charging pile terminal, a power grid monitoring terminal and a traffic environment data terminal, a charging scheduling strategy is formulated through a cloud server, opinions are continuously fed back to a mobile phone user through a man-machine interaction terminal, charging scheduling feedback evaluation is carried out, model parameters are optimized, full-dimensional data driving is achieved, and the charging scheduling efficiency is improved. The charging efficiency is effectively improved, and the user experience is comprehensively optimized.

The invention discloses a cloud edge collaborative task scheduling method based on a directed acyclic graph (DAG) and a near-end policy optimization (PPO) algorithm, and belongs to the technical field of deep reinforcement learning and mobile edge computing. The method comprises the following steps of: initializing a cloud edge environment containing mobile equipment, an edge server and a cloud server, and constructing a task dependency graph containing task calculation amount, dependency relationship and data transmission amount by using a DAG (Directed Acyclic Graph); establishing a function by taking minimization of the total response time of the application program as a target, and converting a scheduling problem into a Markov decision process; and inputting the current state to the trained intelligent agent based on the PPO algorithm, obtaining final action probability distribution through task dependence screening and legal action mask filtering, and sampling and executing scheduling. According to the method, the intelligent agent adopts a PPO algorithm and is trained based on DAG, the adaptive capacity to cloud edge collaborative scene resources and network changes is achieved, task accumulation delay is remarkably reduced, the resource utilization rate is remarkably increased, and the method has wide applicability.

The invention discloses a data security sharing method and system, and relates to the technical field of data sharing. The method comprises the steps that a data provider uploads original data, a privacy budget value is calculated through a differential privacy algorithm, noise is added to obtain noisy data, and the noisy data is processed through an anonymous privacy protection algorithm based on maximum dissimilarity degree clustering to obtain desensitized data; encrypting the desensitized data by adopting a block chain decentralization-based ciphertext policy attribute-based encryption method, obtaining an encrypted data ciphertext, uploading the encrypted data ciphertext to a cloud server, and obtaining a content addressing hash value; encrypting the hash value through an elliptic curve encryption algorithm, and storing the encrypted hash value to a block chain account book; and when an access request of a data requester is received, the cloud server verifies the authority by using a non-interactive zero-knowledge proof protocol and returns an encrypted hash value after passing the verification, and the requester decrypts to obtain the hash value and decrypts the encrypted ciphertext to obtain desensitized data, thereby realizing data sharing.

The invention discloses a distributed photovoltaic short-term power prediction method and system, a medium and equipment, and belongs to the technical field of new energy power prediction, and the method comprises the steps: building a sample set based on distributed photovoltaic station power data, meteorological measured data and meteorological forecast data of all participants, and dividing the sample set into a training set and a test set; through a federated learning architecture based on edge equipment-master station server-cloud server and in combination with a client selection mechanism, each participant utilizes an artificial intelligence algorithm to cooperatively train a prediction model; after the performance of the model is evaluated, the model meeting the precision requirement is used for prediction. According to the method, the problems of low communication efficiency and poor training effect of small samples and traditional federal learning architecture can be solved, and the prediction precision is improved while secure sharing of data is ensured.

The invention discloses a low-sample neural network structure reliability evaluation system and evaluation method, and relates to the technical field of engineering structure safety monitoring, and the evaluation system comprises a cloud server which is used for constructing a recurrent neural network model containing a static variable embedding mechanism, completing model training and converting a model format; the edge calculation terminal is used for receiving and preprocessing real-time data of the sensor, executing multi-step prediction to output a future time period response sequence, and calculating a future failure probability through virtual Monte Carlo simulation; the sensor assembly is used for collecting structure state time sequence data; and the communication module is used for realizing data interaction and alarm signal transmission operation. According to the method, collaborative modeling of time-varying and static uncertainty is realized by adopting a static variable embedded recurrent neural network model, failure probability distribution is generated at an edge computing terminal in combination with a virtual Monte Carlo technology, failure risk prediction in a future time period is supported, and real-time and accurate reliability early warning can be realized in a resource limited scene.

The invention relates to the technical field of artificial intelligence and Internet of Things equipment, and discloses an AI (artificial intelligence) agent personality switching method based on NFC (near field communication) identification, which realizes dynamic switching of AI agent personality in a physical mode, and comprises the following steps: S1, an equipment end obtains and decrypts an NFC label signal of an agent; s2, the equipment end obtains an AI virtual role ID corresponding to the intelligent agent according to the decryption information, and sends a request parameter to a cloud server; s3, the cloud server obtains personality configuration of the intelligent agent from a role database of the cloud server according to the request parameters and returns the personality configuration to the equipment end, wherein the personality configuration comprises an image, voice tone, speed, tone, role background, story index information and a knowledge template; and S4, the device side updates and switches the personality state corresponding to the intelligent agent according to the personality configuration, and performs voice interaction with the user according to the current personality state parameter. The invention further discloses an AI agent personality switching device for implementing the AI agent personality switching method.

The invention discloses a reinforcement learning-based spring steel wire drawing control method, which comprises the following steps of: acquiring real-time process parameters to form a process state data sequence; inputting the process state data sequence into the state space model, and constructing a virtual working condition sample; based on the virtual working condition sample, pre-training a reinforcement learning controller and outputting an initial control strategy; inputting the initial control strategy into a lower-layer strategy network, and outputting a wire drawing speed adjusting instruction; the current process state and the wire drawing speed adjusting instruction serve as synchronous input, and an implicit context vector is generated; extracting control strategy characteristics in the edge controller, performing compressed encoding and forming control strategy representation; uploading the control strategy representation to a cloud server, and outputting a unified global control strategy model; and carrying out anomaly detection on the current process state, and if a detected state reconstruction error exceeds an anomaly judgment threshold, triggering safety control logic. The spring steel wire drawing control device realizes spring steel wire drawing control.

The invention discloses a wearable plantar pressure and three-dimensional gait analysis system, and relates to the technical field of gait analysis, the system comprises a wearable in-shoe plantar pressure analysis subsystem and a three-dimensional gait analysis subsystem; the wearable in-shoe plantar pressure analysis subsystem comprises a pressure sensor module, a pressure integration module, an intelligent transmission module, a detection software module, a power supply module, an instantaneous pressure and balance detection module, a standing balance detection module, a balance and gait detection module and a cloud server; the three-dimensional gait analysis subsystem comprises a hardware unit and a software unit; according to the invention, a wearable plantar pressure and three-dimensional gait analysis collaborative system is constructed, bidirectional verification compensation is realized by means of data fusion of two subsystems, and traditional single-dimensional limitation is broken; pressure sensing and a double-view reconstruction technology are fused, data are dynamically captured, and bidirectional error correction is carried out; the limitation of traditional equipment is solved, the evaluation accuracy and robustness are improved, and a quantitative basis is provided for clinical diagnosis, rehabilitation and the like.

The invention discloses a cloud side-end collaborative architecture and task unloading method for an airport apron intelligent monitoring system, and relates to the technical field of cloud side-end collaborative computing. Comprising a terminal layer, an edge server layer and a cloud server layer, the task unloading method of the system under the cloud side-end collaborative architecture is designed and comprises the steps that a task model, a time delay model, an energy consumption model and an accuracy rate model of the system are constructed, and a multi-objective optimization problem of time delay-energy consumption-accuracy rate is formed; modeling an optimization problem into a Markov decision process, and designing a state space, an action space and a reward function required by deep reinforcement learning; and designing a task unloading method based on multi-agent deep reinforcement learning, and finding an optimal task unloading strategy of the system. According to the method, the computing tasks can be dynamically, scientifically and reasonably distributed and cooperatively scheduled among the terminal, the edge and the cloud, so that the time delay, the energy consumption and the accuracy are comprehensively optimized, and the overall performance of the system is improved.

The invention provides an anti-quantum fuzzy keyword processing method and system and electronic equipment, and relates to the technical field of networks and security. The method comprises the following steps: a client performs wildcard character extension on a keyword set based on a target shared key, generates an encryption index, performs authentication encryption on file identifiers by using the target shared key, forms an encrypted file identifier set, constructs an index table, and uploads the index table and the encrypted file set to a cloud server. The server generates a second wildcard character set according to the query keyword and a fault-tolerant threshold value, generates a trap door set based on the same target shared key and a pseudo-random function and sends the trap door set to the cloud server, and the cloud server traverses the index table, compares the index table with the trap door set and sends the trap door set to the server; and finding out the matched target encryption index and the associated target encryption file identifier and returning the matched target encryption index and the associated target encryption file identifier to the server, and decrypting and acquiring the target file from the cloud server by the server. In this way, high-safety, high-efficiency and extensible privacy protection search service is achieved.

According to the privacy enhancement type (k, d)-truss community search method for the social network, a novel KTG tree structure is constructed by fusing k-truss and G-tree indexes. According to the index structure, hierarchical community decomposition of a social graph and social distance information are fused, a refined boundary vector coding scheme is designed to support efficient distance calculation, and a double-cloud-server non-collusion architecture integrating improved homomorphic encryption and matrix encryption technologies is constructed. Through a two-stage security query process of first structure filtering and then distance verification, on the premise of protecting full-process privacy of a graph structure, a query intention, a distance matrix and an intermediate calculation result, efficient and accurate search of a close community in a large-scale social network is realized. The method is suitable for various scenes such as social recommendation, risk control, public opinion analysis and anti-fraud, and the problems of privacy disclosure and calculation efficiency in social network analysis are effectively solved.

The invention discloses a gas safety intelligent inspection method and system, and belongs to the crossing field of artificial intelligence technology and safety production management. The method comprises the following steps: acquiring image data through a field data acquisition terminal; a preliminary hidden danger identification module in the cloud server innovatively adopts a scene perception target detection model and a scene reasoning multi-label model for collaborative analysis; and the comprehensive risk assessment module performs deep correlation analysis on the hidden dangers based on a preset gas safety knowledge graph, and determines a quantitative comprehensive risk value by calculating a basic risk accumulated value of each hidden danger and a correlation risk increment generated by a correlated hidden danger pair. According to the method, the defects that traditional inspection depends on subjective experience and composite risks are difficult to quantify are overcome, amplification risks caused by concurrence of multiple hidden dangers can be accurately identified and quantitatively evaluated, continuous self-improvement of system capability is realized through a closed-loop mechanism, and the intelligent level of gas safety management is remarkably improved.

The invention provides an intelligent tactile stick interaction method and system based on multi-modal perception and edge calculation, and relates to the technical field of intelligent auxiliary equipment. The method comprises the following steps: acquiring environment and position data through a camera, a GPS and an inertial measurement unit; performing multi-modal data fusion and deep learning identification by using an edge calculation module to generate a dynamic environment map; performing real-time path planning and obstacle avoidance based on a map and a destination; analyzing a user instruction through voice recognition and interactively adjusting a path; haptic and auditory bimodal feedback is provided through a vibration module and a voice synthesis module according to a navigation result; and when an emergency obstacle is detected or a user actively alarms, a local and remote alarm mechanism is triggered. The system correspondingly comprises an intelligent tactile stick terminal and a cloud server. According to the invention, accurate and real-time perception and intelligent navigation of the environment are realized, visual and natural interaction experience is provided, an effective emergency help channel is established, and the safety, independence and convenience of travel of visually impaired people are significantly improved.

In various examples, systems and techniques are provided that are directed to processing, using a language model, a user query associated with an artificial intelligence (AI) task. The system and techniques are used to obtain a recommendation to use, in performance of the AI task, one or more AI services—such as inference microservices—provided by, for example, a cloud AI server.

The invention provides a multi-modal emotion recognition fusion method based on a multi-head attention mechanism, and the method comprises the steps: carrying out the feature extraction and fusion of various data, capturing the internal relation of a modal through the multi-head attention mechanism, achieving the information complementation between modals through cross-modal interaction, and dynamically adjusting the weight according to the quality of the modals. And a self-built database containing a large amount of Chinese data is constructed, and a culture adaptation optimization strategy is combined, so that the generalization performance and culture adaptability of the model in Chinese user groups are improved. The system is deployed on a cloud server, optimized hardware and software configuration is adopted, efficient model reasoning and multi-user concurrent processing are achieved, and the large-scale real-time application requirement is met. The emotion of the user can be monitored in real time and early warning can be provided in scenes such as psychological counseling and group emotion monitoring, professionals are assisted in better understanding the emotion state of the user, and the service effect is improved.

The invention provides an image restoration model training method, an image restoration method and related equipment, and relates to the technical field of image processing. The training method is applied to a cloud server, and comprises the following steps: acquiring a training sample set comprising a plurality of high-definition sample images; performing compression processing on the high-definition sample image to obtain a corresponding sample compression image; determining a sample residual image according to the high-definition sample image and the sample compressed image; based on an image restoration model, performing restoration processing on the sample compressed image according to the sample residual image to obtain a prediction restoration image; determining target loss according to the prediction restoration image, the high-definition sample image and the sample residual image; and training an image restoration model according to the target loss to obtain a trained image restoration model. The image restoration model trained through the method can effectively restore the quality degradation problem caused by loss of compression information, so that the restoration precision and the playing image quality can be improved when the terminal equipment deployment model carries out image restoration.

The invention provides a fault diagnosis method for a conveying belt. The fault diagnosis method comprises the steps that vibration data, pressure data and temperature data in the belt running process are collected through a sensor module; carrying out denoising processing on the collected vibration data, pressure data and temperature data, and removing abnormal values; feature parameters are extracted from the data subjected to data preprocessing; the extracted feature parameters are uploaded to a private cloud server through an Internet of Things module, and a lightweight algorithm is adopted to analyze the feature parameters; according to the analysis result of the lightweight algorithm, a preset fault threshold value is matched, and the fault type of the belt is output. According to the method, multi-source data fusion and targeted feature extraction are adopted, the fault false alarm rate is reduced to 10% or below, industrial data leakage is avoided through private cloud deployment, and the deployment cost is reduced by 60% compared with public cloud; based on a sensor and an open source tool, deployment can be completed within 30 days without professional teams, and belt conveyors in different scenes such as mine underground and logistics sorting can be adapted.

The invention discloses a fault arc detection system and method based on multi-source fusion and federated self-learning. The system comprises a sensor, a data processing and feature extraction module, an edge AI module, a decision logic module, a cloud server and a communication module. The method comprises the following steps: firstly, carrying out system starting and self-inspection, then carrying out multi-source data synchronous acquisition, then carrying out data preprocessing, multi-modal feature generation and lightweight edge AI model reasoning, finally carrying out fault judgment and rapid breaking control, and carrying out logic judgment according to an AI model output result. And when the fault arc is judged to be true, the breaking action of the circuit breaker is quickly executed, and an event is recorded and reported. Through innovation in three aspects of multi-source information fusion, real-time AI identification and federal self-learning updating, full-working-condition, high-precision, fast-response and evolvable fault arc detection is realized, the problem of pain points in the prior art is solved, and the method can be widely applied to the field of low-voltage power distribution safety protection and has remarkable practical value and popularization prospect.

The invention discloses environment early warning and tampering detection equipment and method for a long-term storage container, and the equipment comprises an electronic container terminal integrated on the container, and the electronic container terminal is provided with a main control unit, and a bistable electronic display screen, a wireless communication unit, a multi-sensor unit and a power supply unit which are connected with the main control unit. The multiple sensor unit includes a tamper detection sensor for detecting a first opening of the container and an environmental sensor for monitoring environmental parameters. And the main control unit displays an abnormal warning when the environment exceeds a threshold value, and generates an irreversible opened state mark and permanently displays opening information according to the tampering signal. The terminal is connected with the cloud server and the user terminal through wireless communication, and identity and state information storage and basic authentication interaction are achieved. According to the invention, dynamic anti-counterfeiting, complete and traceable storage environment recording and active early warning functions can be provided.

The invention discloses a block chain technology-based traditional Chinese medicine whole industry chain quality tracing and supervision system and method, and the system comprises an upper information supervision module, a traditional Chinese medicine production process module, a public information query module and a warehouse logistics management module, and builds a planting-processing-storage-circulation whole process block chain credible tracing system. Wherein each node data is encrypted and chained through a block chain node, an AI quality evaluation unit is combined to construct a traditional Chinese medicine quality prediction model, and a receiving unit and an analysis processing unit of an upper information supervision module are integrated through a cloud server to realize real-time monitoring of production data by a supervision department. Meanwhile, based on a terminal interface optimization and identity verification unit of the public information query module, a transparent tracing mechanism in which multiple parties participate is constructed. According to the invention, the non-tampering characteristic of the block chain is combined with the real-time acquisition technology of the Internet of Things, AI intelligent analysis is supplemented, the traditional Chinese medicine quality supervision efficiency is effectively improved, and the whole-chain quality safety of the traditional Chinese medicine industry is ensured.

The invention discloses an industrial Internet of Things federated learning method based on a federated increment decision tree, and the method comprises the steps: a cloud server deploys and initializes a federated learning global model and the federated increment decision tree, and sets a statistical histogram bucket boundary set of each feature value; in each federated learning iteration, the cloud server broadcasts a federated learning global model parameter, each industrial device adopts a local data set to train and count to obtain a local gradient histogram parameter, the edge server performs local aggregation on the local gradient histogram parameter and the federated learning model parameter, and the edge server performs local aggregation on the local gradient histogram parameter and the federated learning global model parameter; and the cloud server globally aggregates the local aggregation parameters of the gradient histogram and then incrementally trains the federated increment decision tree, simultaneously aggregates the parameters of a federated learning global model, and adaptively calculates an aggregation weight based on a second-order gradient value during local aggregation and global aggregation of the parameters of the federated learning model. The federal learning overhead can be effectively reduced, and the performance of the federal learning model is improved.

The invention relates to the technical field of information security, in particular to a cluster self-discovery method suitable for a cloud server cipher machine, which comprises the following steps: when physical equipment of the cloud server cipher machine leaves a factory, a certificate management module generates an equipment certificate and a root CA certificate in combination with an enterprise CA system, and stores the equipment certificate and the root CA certificate; after the virtual cipher machine is created and started, the key management service module combines with the certificate management module to generate a virtual machine certificate, and stores the virtual machine certificate, the storage device certificate and the root CA certificate together; the cluster management service module enables the master node of the virtual cipher machine to discover the slave node of the virtual cipher machine in the same network domain through UDP broadcast, and executes three-level verification on the slave node of the virtual cipher machine from three aspects of an equipment certificate, a virtual machine certificate and an authentication signature; and the virtual cipher machine master node synchronizes the cluster master key to the virtual cipher machine slave node passing verification. According to the invention, hierarchical identity isolation and verification of the cloud server cipher machine host and the virtual cipher machine can be realized, and the security of cluster self-discovery and authentication stages is ensured.