1548 results about "Edge server" patented technology

The invention discloses a power plant specific area personnel behavior identification and early warning system, and relates to the technical field of industrial safety intelligent monitoring, the power plant specific area personnel behavior identification and early warning system comprises a data acquisition module, an edge calculation module and a central processing platform, the edge computing module carries out lightweight processing and localized decision making on original data, the load of the central processing platform is reduced, and the central processing platform realizes full-process safety management and control of a high-risk area through multi-modal data fusion, dynamic authority management and trajectory analysis. According to the invention, lightweight AI models are embedded in various cameras of a work card authentication terminal and a visual perception unit, preliminary reasoning is directly completed at the work card authentication terminal and the cameras, so that the work card authentication terminal and the cameras have edge computing capability, and independent edge servers or industrial personal computers are deployed near data sources of various regions of a power plant. And serving as a regional edge computing node.

The invention relates to a secure communication method between an edge server and terminal equipment. The secure communication method comprises the following steps: establishing a physical layer channel state information database, generating a multi-dimensional feature vector and encoding the multi-dimensional feature vector into a terminal equipment identifier, generating an identity authentication request by the terminal equipment, and performing hash operation to obtain a first hash value; the identity authentication request and the first hash value are sent to the edge server, the edge server verifies the identity authentication request and queries a corresponding device key, performs hash operation to obtain a second hash value, generates an authentication response message after successfully comparing the second hash value with the first hash value, encrypts the authentication response message by using the device key, and sends the encrypted authentication response message to the edge server; and sending the encrypted authentication response message to the terminal equipment. And the terminal equipment decrypts by using the equipment key to obtain the session key, and communicates with the edge server based on the session key. By using the physical layer channel information and the equipment hardware characteristics, the security communication method fusing dynamic identity authentication and efficient key management improves the security, reliability and anti-attack ability of communication between the edge server and the terminal equipment.

The embodiment of the invention provides a dynamic allocation method and device for AI reasoning tasks, and the method comprises the steps: monitoring the workload, memory availability, network delay, bandwidth and energy consumption of each computing node in a cloud edge cooperation system in real time, the computing node comprising a local edge device, an edge server and a cloud platform; according to the delay requirement, the calculation requirement and the data privacy requirement of the task and the real-time state of each calculation node, dynamically distributing the task to different calculation nodes; adjusting the complexity of an AI model used for executing the task according to the resource use condition of the computing node; and according to the historical performance data and the real-time network condition in the task execution process, optimizing a task allocation strategy.

The invention discloses an event early warning efficient management method and system based on park management, and relates to the technical field of safety management, and the method comprises the steps: constructing a hexagonal cellular unit layout, generating an equipment registry and a network topology structure, and forming a structured data set through data alignment and sliding window verification; the edge server loads an initial weight, calculates a dynamic weight matrix based on the LSTM network, and generates a high-order feature vector set in combination with the graph neural network; inputting the high-order feature vector set into a space-time prediction model to generate an environment evolution trend prediction value, fusing network topology and BIM model parameters to calculate a dynamic risk index, and triggering graded early warning; the command center analyzes the early warning signal to generate a fusion visual interface, historical cases are matched through federal learning, a resource allocation scheme is optimized, and an optimal disposal strategy is output through Monte Carlo simulation. By dynamically adjusting the weight of the sensor, the weight of the infrared sensor in the high-temperature-sensitive area is increased, and the abnormality capturing efficiency is improved.

Disclosed are various embodiments for dynamic availability zones in radio-based networks. In one embodiment, excess resource capacity on a radio access network (RAN)-enabled edge server in a cloud provider network is determined. The RAN-enabled edge server is located at a cell site and is configured to perform distributed unit (DU) and / or centralized unit (CU) functions for a RAN. The excess resource capacity is offered as part of a cellular capacity zone that is generally available to customers of the cloud provider network.

The invention is suitable for the technical field of artificial intelligence and cloud computing crossing, and provides a cloud mobile phone control system based on a large language model, comprising an interaction agent used for receiving a cloud mobile phone control instruction input by a user by using a natural language, and sending the cloud mobile phone control instruction to a large language model agent; the large language model agent is used for analyzing and constructing the instruction and sending a tool calling instruction to the MCP client; the MCP client is used for initiating a remote procedure call request to the MCP server; the MCP server side is used for sending a task instruction to the cloud mobile phone control platform; the cloud mobile phone control platform is used for sending the task instruction and the equipment information to the edge server; and the edge server is used for transmitting the task instruction and the equipment information to the cloud mobile phone management service node, so that the cloud mobile phone management service node executes corresponding operation on the target cloud mobile phone. According to the invention, intelligent control of the cloud mobile phone can be realized, and the management efficiency of the cloud mobile phone is improved.

The invention discloses a multi-mode intelligent inspection system and device for an oil field gathering and transportation station yard, and belongs to the technical field of oil field gathering and transportation station yard inspection. The multi-mode intelligent inspection system comprises a data acquisition module, an abnormity judgment module, a station yard model simulation analysis module and a decision analysis and execution module; comprising a vibration camera sensor, a temperature camera sensor, a pressure camera sensor, a flow camera sensor, a liquid level camera sensor, a gas camera sensor, an ultraviolet flame camera sensor, an infrared thermal imaging camera sensor, a visible light camera sensor and a depth camera sensor and is used for collecting process equipment, environment states and personnel operation behavior data of a current oil field gathering and transportation station and recording the data collected by the sensors in a near-field edge server and a cloud server; the time difference of data acquisition is eliminated through a space-time alignment algorithm, and a time sequence health vector in a unified format is generated. According to the multi-mode intelligent inspection system and device for the oil field gathering and transportation station yard, multi-mode inspection can be carried out on the oil field gathering and transportation station yard based on the type of the oil field gathering and transportation station yard, and typical anomalies are recognized and processed.

Disclosed are various embodiments for automated deployment and management of distributed units (DUs) in a radio-based network. In one embodiment, it is determined to deploy a radio-based network at least partially using infrastructure of a cloud provider network. A radio access network (RAN)-enabled edge server of the cloud provider network is deployed to a physical location of the radio-based network. The RAN-enabled edge server is configured to perform a set of distributed unit (DU) functions for the radio-based network.

The invention discloses a multi-edge device collaborative reasoning method and system for a hybrid expert large model, and the method comprises the steps: collecting and analyzing system data, and adjusting the expert layout according to the system data; in the first stage, the number of experts required by each layer of a server is dynamically determined by balancing activation diversity and memory resource limitation; in the second stage, according to the expert number and the activation mode of each layer obtained in the first stage, low-time-delay reasoning is achieved by minimizing the calling times of remote experts, and the experts are distributed to all the servers. The system includes a global scheduler and an edge server participating in the system. By using the method, edge multi-machine joint reasoning is achieved, the deployment method is optimized, online adjustment deployment can be performed according to data changes, and the reasoning speed is increased compared with other deployment technologies. The method can be widely applied to the technical field of distributed machine learning.

The invention provides a medicine raw material label consistency comparison method, system and device and a medium, and belongs to the technical field of medicine raw material label identification. The edge server searches a local template library according to the template index based on the comparison picture, and obtains a template tag picture and a feature vector file; extracting a feature vector of a comparison label picture by using a reconstructed Resnet18 network, calculating the similarity between the feature vector of the template label picture and the feature vector of the comparison label picture, and obtaining a label consistency result of the template picture and the comparison picture; and carrying out result visualization display on the label consistency result. Through a traditional image processing algorithm and a deep learning network feature extraction technology, the verification workload is reduced, and the verification efficiency is improved. The feature vectors are extracted by using the reconstructed Resnet18 network, and the consistency of the tag styles can be accurately judged in combination with an SIFT key point matching algorithm.

The invention discloses a reversible lane traffic flow prediction method based on edge calculation, and relates to the technical field of intelligent traffic. The method comprises the following steps: acquiring reversible lane configuration data, service data, traffic flow data and road network data through an edge server and a cloud server; preprocessing the data; constructing a static road network diagram based on the reversible lane configuration data and the road network data; generating a dynamic road network diagram in combination with time granularity; constructing a generative adversarial network model fusing a multi-head attention mechanism and a graph neural network, and performing adversarial training; and deploying the optimized model to an edge server to realize prediction of the reversible lane traffic flow. According to the method, the precision and timeliness of traffic flow prediction are improved, the perception ability of the model to spatial-temporal characteristics is enhanced, and the improvement of traffic efficiency and the intelligent application of edge resources are promoted.

The invention belongs to the technical field of federated learning, and relates to a pedestrian re-identification system and method based on federated learning. The system comprises a cloud server, a plurality of edge servers and a plurality of terminal devices, the cloud server is used for pre-training an initial global model according to the public data, dynamically allocating aggregation weights based on clustering quality evaluation results of the local models uploaded by the plurality of edge servers, and generating an updated target global model through weighted average; the edge server is used for receiving the initial global model and the pedestrian image data uploaded by the plurality of terminal devices, constructing a local data set based on the pedestrian image data, and performing localization training on the initial global model through an unsupervised training method to generate a local model; and the terminal equipment is used for collecting pedestrian image data and uploading the pedestrian image data to the edge server corresponding to the terminal equipment.

The invention discloses an end-edge collaborative lightweight voice interaction large model optimization method and system, belongs to the technical field of data mining, data analysis and artificial intelligence, and aims to solve the technical problems that the existing webpage control technology is low in integration level, high in resource demand, insufficient in robustness and limited in adaptability. According to the technical scheme, the method comprises the following steps of: analyzing a natural language instruction: capturing the natural language instruction of a user on end-side equipment by utilizing an ASR model, converting a voice signal into text data, and performing semantic recognition and intention recognition on an edge server through a generative large model so as to generate a structured task instruction; scene vocabulary extraction and ASR model fine tuning: constructing a scene exclusive vocabulary library based on a control scene, performing fine tuning on the pre-trained ASR model, and improving the speech recognition accuracy in a specific scene; semantic understanding is optimized based on the RAG model; optimizing instruction generation based on a cue word technology; performing instruction verification and error correction; performing automatic webpage operation; and performing model optimization and reasoning acceleration.

The invention discloses a server fault monitoring system, which relates to the technical field of servers, and is characterized in that a data acquisition terminal deployed in a machine room acquires environment monitoring data and software monitoring data of a server, and the environment monitoring data and the software monitoring data are used as server monitoring data to be sent to a corresponding edge server; and when the edge server detects that the software / hardware monitoring data is abnormal, extracting related abnormal data from the corresponding server monitoring data, and generating an abnormal report log. And the central server determines that the server has a fault according to the exception report log and the related exception data, and generates fault data information. And the monitoring terminal locates a graphic object corresponding to the fault server in the three-dimensional machine room virtual model according to the equipment identifier, updates the display state of the graphic object of the server into a fault state, and generates a fault data interaction label according to the fault data information. According to the invention, the problem of relatively large fault response delay in related technologies can be solved, and the server fault monitoring efficiency can be effectively improved.

The invention relates to the technical field of content transmission methods, in particular to a content transmission method based on a multi-modal streaming media fusion technology system, which comprises the following steps: S1, multi-source data acquisition and time-space alignment: adopting an IEEE 1588PTP protocol, deploying a hardware clock synchronization module at a camera, a microphone and IMU equipment, improving the timestamp precision to a mu s level, and performing time-space alignment on the camera, the microphone and the IMU equipment; carrying out sampling rate normalization on the sensor data; s2, feature level cross-modal fusion: extracting each modal feature by using a lightweight Transform model, executing cross-modal attention calculation in an edge server, and generating a fusion feature tensor Ffusion belonging to RN * D; the system content transmission method based on the multi-modal streaming media fusion technology solves the problems that a traditional multi-modal transmission system usually adopts a separated transmission architecture, video streams are transmitted through an RTMP protocol, audio streams are encoded through Opus and are transmitted through WebRTC, sensor data are sent through an MQTT protocol in a JSON format, ABR only adjusts the video code rate, and the transmission efficiency is low. And joint optimization of multi-modal data is not coordinated.

An end-side-cloud three-in-one active chat robot system for high-emotional merchants comprises an end side, a local edge server and a cloud end, and the end side is used for collecting multi-modal data of a user and performing local lightweight real-time processing and response execution; the local edge server is used for receiving and fusing the multi-modal features and the context information from the end side, and carrying out sentiment calculation, dialogue management and active trigger decision making with medium complexity; the cloud end is used for operating a super-large-scale model and providing global knowledge management, long-term user portrait storage and model training optimization; and the end side, the local edge server and the cloud end carry out cooperative communication through an encrypted channel to form a distributed intelligent processing architecture. According to the method, global optimization is realized by integrating end-side lightweight sensing, edge multi-modal fusion and cloud long-term memory. A composite finite state machine (FSM) active questioning mechanism is combined with sentiment calculation, and is different from traditional rule type triggering. Off-line and on-line fusion scheduling and multi-agent role playing are combined to be applied to a high-emotional-quotient interaction scene, and the simulation is improved. Multi-modal emotion perception circulation is introduced, and the problem of single text emotion misjudgment is solved.

The invention discloses a self-adaptive dynamic task unloading method and system for an edge computing power network, and the method comprises the steps: carrying out the modeling of a computing task of a user, obtaining a directed acyclic graph of the computing task, and generating a task execution sequence according to the topological sorting of the tasks in the directed acyclic graph; features of tasks in the task execution sequence are coded into high-dimensional vectors, sequence information is embedded through position coding, and a task matrix is obtained; the task matrix is input into a trained Transform model, and a task related information sequence is generated; inputting the task related information sequence into the trained dual Q network model to obtain an optimal unloading decision sequence; carrying out local calculation or edge server unloading on the calculation task based on the optimal unloading decision sequence; according to the method, efficient, low-delay and low-energy-consumption task scheduling optimization can be realized, and the task unloading efficiency is improved.

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 discloses a self-adaptive cloud edge-end cooperative task unloading method based on multi-agent reinforcement learning, and belongs to the technical field of cloud edge cooperative task unloading. The method comprises the following steps: constructing a cloud edge-end three-layer cooperation model; the terminal user optimizes the edge device selected to cooperate and the unloading task amount, and the edge end server comprises a fixed edge server and an unmanned aerial vehicle server; the unmanned aerial vehicle server optimizes a flight path according to the scheduling position of the cloud; the cloud data center optimizes and dispatches the unmanned aerial vehicle position according to the load condition; mobile equipment energy consumption and task completion time delay in the cloud side end cooperative task unloading process are modeled into a comprehensive system cost optimization problem, and the comprehensive system cost optimization problem is further converted into a Markov decision process; designing a multi-agent reinforcement learning algorithm to optimize a task unloading strategy; on the premise of meeting various constraints, the task execution efficiency can be effectively improved, meanwhile, the energy consumption of the mobile equipment is reduced to the maximum extent, and particularly, the service duration and quality of the unmanned aerial vehicle are improved.

The invention provides an edge server dynamic activation method and system based on deep reinforcement learning, and the method comprises the following steps: S1, building system models, including building a network model, an energy consumption model, a communication and service delay model and a state switching cost model, the network model including RES and MES; s2, optimizing a network model by calculating the sum of the cost of the energy consumption model, the communication and service delay model and the state switching cost model; s3, constructing a Markov decision process model, and improving RES stability; s4, predicting a traffic load; s5, calculating a baseline value; s6, training the network model through a centralized intelligent scheduling algorithm CDDS to obtain a trained strategy network model; s7, dividing the trained strategy network model through a federated distributed intelligent scheduling algorithm FDDS, and training the model based on federated learning to obtain a DDPG model; and S8, the DDPG model is deployed to each RES.

The invention provides a real-time warning condition data processing method and system based on edge calculation, and relates to the technical field of traffic management, which comprises the steps of collecting traffic warning condition original data, transmitting the data to a nearby edge server in real time, constructing a lightweight deep learning model on an edge side, generating a traffic situation prediction result, and simultaneously, combining police force information to obtain a real-time warning condition prediction result. And constructing a police deployment optimization matrix, uploading the matrix to the cloud platform, generating a traffic optimization strategy, and issuing the traffic optimization strategy to the edge computing node of the accident area. The method can improve the integrity and timeliness of accident information perception, optimizes the police resource distribution and traffic dispersion decision, and remarkably enhances the intelligence and cooperation capability of traffic accident emergency management.

The invention discloses an Internet of Things secure access method based on cloud edge collaboration, which comprises the following steps: firstly, an Internet of Things device and an edge server respectively register in a CSC (Content Service Controller), and obtain an intelligent card or related data to complete information updating and storage; the equipment is inserted into an intelligent card to log in, and data are sent to the edge server after identity password verification; the edge server verifies the timestamp and then forwards the data to the CSC; the CSC verifies the timestamp and the identity, generates a session key parameter and sends the session key parameter to the edge server; the edge server verifies the identity of the CSC and then generates session key encrypted data to be transmitted back, and after the verification of the device is passed, secure communication is established. According to the method, mutual verification and encryption protection are adopted in identity verification; a timestamp, a random value and strict verification are used for message transmission to prevent replay and man-in-the-middle attack; secret key management guarantees safety through dynamic change of secret values, attacks such as physical capture are resisted in combination with PUF, and communication safety is comprehensively guaranteed.

The invention provides a personalized federal learning method suitable for an edge network, which is characterized in that a collaborative training network topology between clients is constructed based on a graph, and local models of the clients and aggregation relationships thereof are described as points and edges of the graph. Secondly, a personalized model aggregation mode based on group dynamics is established, a personalized aggregation matrix is obtained according to the adjacency matrix and the aggregation weight matrix, and finally, the personalized aggregation matrix is used for weighting personalized model parameters uploaded by all clients to obtain a personalized aggregation model; the adjacency matrix is used for controlling the personalized model of the client to move towards the personalized models of other clients aggregated by the client in the state space; the aggregation weight matrix is used for controlling the moving degree of the personalized model; therefore, the personalized model aggregation is rapidly realized in the edge server, and the personalized model automatically completes clustering in the convergence movement in the state space along with the continuous proceeding of training and aggregation, so that the collaborative training of the personalized model between clients is realized.

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 relates to an internet of vehicles edge computing task unloading and resource scheduling optimization method, which comprises the following steps: constructing an internet of vehicles edge computing system model fusing a task jump mechanism and dual-priority scheduling, the system model comprising a road test unit deployment model, a communication model, a computing model and a task jump model; establishing a joint optimization function aiming at minimizing the total time delay and the total energy consumption of the system; decomposing a joint optimization problem into three sub-problems of unloading decision, computing resource allocation and communication strategy selection; a deep reinforcement learning algorithm is adopted to intelligently sense a road environment state, an optimal communication priority strategy combination is dynamically selected, and a task unloading decision and computing resource allocation are collaboratively optimized; and in each scheduling time slot, the edge server allocates communication bandwidth and computing resources to the vehicle tasks according to the selected strategy, and triggers a task preemption and cross-server jump mechanism, thereby realizing maximization of system throughput and minimization of task processing time delay.

The invention provides a timeliness training method, a timeliness training device and timeliness training equipment based on integration of communication, sensing and calculation, and the timeliness training method based on integration of communication, sensing and calculation comprises the following steps which are iteratively carried out until convergence conditions are met: each piece of edge end equipment receives a global model broadcasted by an edge server, replacing a local model with the global model; the edge end device executes a sensing process based on the global model and collects a new local data set; the edge end device performs local training by using all accumulated local data sets, determines a local model gradient and a local model loss function, and performs parameter updating; and all the edge end devices upload the local model gradient to the edge server for aggregation to obtain an aggregation gradient. According to the invention, the communication and energy efficiency of federal learning can be improved, the convergence speed is improved, and the problem of poor communication efficiency in the prior art is solved.

The invention discloses a power equipment control method based on cloud edge collaboration and electronic equipment. The method comprises the following steps: receiving initial resonance waveform data corresponding to a plurality of inverters in power equipment sent by an edge server; based on the initial resonance waveform data corresponding to the plurality of inverters, determining the resonance frequency dynamic correlation strength between every two inverters in the plurality of inverters; generating a cooperative control parameter based on the resonant frequency dynamic correlation strength between every two inverters; and sending the cooperative control parameters to an edge server, so that the edge server determines real-time resonance fluctuation data corresponding to the plurality of inverters, calculates a resonance suppression compensation control signal based on the real-time resonance fluctuation data, and compensates the initial control signals corresponding to the plurality of inverters based on the resonance suppression compensation control signal. According to the invention, the technical problem that the compensation accuracy is low when resonance compensation is carried out on the inverter in the power equipment in the prior art is solved.

The invention relates to the technical field of the Internet of Things, in particular to an edge computing privacy task unloading method, system and device based on reinforcement learning, and the method comprises the steps: obtaining computing task information and task unloading selection generated by each terminal device, and the task unloading selection comprises task selection local execution or task selection unloading to an edge server, local execution cost or unloading cost of each task is obtained based on the calculation; performing statistics to obtain the total cost of all tasks, and establishing an initial global optimization target; the privacy entropy of the task is calculated, and the privacy entropy of the task is used as unloading additional cost to be embedded into the initial global optimization target to update the global optimization target; and searching an optimal strategy of the updated global optimization target by adopting a single-agent reinforcement learning algorithm. The privacy guarantee strength and the dynamic scene adaptability are improved while the algorithm complexity is greatly reduced and the algorithm efficiency is improved, and the method can be suitable for large-scale node, high-dynamic and strong-privacy-constraint application scenes in edge calculation.

The invention discloses an artificial intelligence content generation task multi-server collaborative optimization method based on deep reinforcement learning, and relates to the crossing field of edge computing and artificial intelligence. According to the method, a user equipment-base station-edge server-core network four-layer architecture is constructed, distributed decision is realized through a deep Q network model, and the method comprises the following steps: defining a task and time delay model; a deep reinforcement learning framework is designed, a decision model is constructed through a state space, an action space and a reward function, and training stability is improved by adopting experience playback and a target network slow update mechanism; and providing an adaptive multi-server selection and load distribution strategy, and solving an optimal distribution proportion based on a time delay equality principle. According to the method, the average unloading time delay of the AIGC tasks is remarkably reduced, the task failure rate is reduced, the dynamic environment adaptability and the extreme scene robustness are improved, and the method is suitable for scenes with strict requirements for time delay and reliability.

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.