741 results about "Node clustering" patented technology

The invention relates to the technical field of data processing, provides a multi-node carbon emission intelligent contract verification method based on a block chain, and aims to solve the problems that data verification in an existing carbon asset transaction system is non-transparent, high in trust cost and difficult to adapt to policy changes. Distributed storage and dynamic verification of data are realized by constructing a hierarchical block chain architecture, the data are collected by using edge computing nodes, and third-party verification data are obtained through an oracle machine node cluster. The dynamic rule engine monitors data changes in real time, triggers a multi-stage verification process, and improves the data accuracy. And meanwhile, an improved Byzantine fault-tolerant mechanism is adopted to reach a consensus, and the system has the functions of strategy dynamic updating and security enhancement, so that the flexibility and security of the system are improved. According to the method, multi-party consensus and real-time verification of the carbon emission data are realized, trust cost of cooperation among enterprises is reduced, and healthy development of a carbon emission permit trading market is promoted.

The invention discloses an industrial data real-time acquisition monitoring system fusing edge computing and 5G, and belongs to the technical field of industrial Internet of Things. The system is composed of a multi-source heterogeneous data acquisition module, an edge computing node cluster, a 5G communication network and a cloud analysis platform, an edge-cloud collaborative architecture is innovatively adopted, a multi-protocol adapter is integrated to realize unified access of heterogeneous data of industrial equipment, a low-delay transmission channel is constructed by using a 5G network slicing technology, and the heterogeneous data of the industrial equipment is transmitted to the cloud analysis platform. And transmitting the preprocessed data to the edge computing node in parallel. And the edge layer realizes dynamic resource scheduling by adopting a containerization technology, and realizes millisecond-level response and local decision feedback. And meanwhile, through an edge-cloud data synchronization mechanism, a distributed time sequence database is constructed, and visual monitoring and deep analysis of multi-dimensional data are supported. The system improves the real-time processing capability of industrial field data and the reliability of the system, and has the technical advantages of low time delay, high concurrency and optimized resource utilization rate.

The invention relates to the technical field of computers, and discloses a computing power resource multi-dimensional scheduling method and system based on dynamic weight, and the method comprises a data perception step, a weight generation step, an intelligent decision-making step and a scheduling optimization step. The system corresponds to the method. The method comprises the following steps: a data sensing step: collecting multi-dimensional state parameters of computing power nodes and carrying out feature modeling to construct a global feature space; a weight generation step: dynamically adjusting the weight of each dimension based on a machine learning model and a rule engine; an intelligent decision-making step of screening candidate nodes in the global feature space and evaluating priorities, generating an optimal node cluster and performing resource dynamic slice distribution; and a scheduling optimization step: monitoring an execution effect and performing closed-loop feedback so as to iteratively optimize a weight strategy and decision logic. The problems that in the prior art, the sensing dimension is single, and decision-making weight is rigid are solved, and multi-dimensional accurate sensing, dynamic weight decision making and elastic resource allocation of computing power resources are achieved.

The invention discloses an elevator running state multi-source sensing internet-of-things inspection system which comprises the following steps: S1, a multi-mode sensing acquisition module for synchronously acquiring data and generating a multi-channel sensing data packet; s2, a data preprocessing module used for preprocessing the data packet; s3, the edge computing node cluster is used for executing preliminary anomaly judgment on the structured multi-modal data sequence and generating local event description information; s4, a multi-modal feature fusion module which is used for receiving local event description information from each edge computing node and generating a unified feature vector sequence; s5, a heterogeneous sensor collaborative scheduling module enables different sensors to be coordinated and consistent in triggering conditions, data frequencies and data transmission paths; and S6, the state recognition and exception labeling module is used for outputting the corresponding elevator running state label and the exception event identification code. The method has the advantages of being comprehensive in sensing dimension, low in response delay and high in anomaly recognition precision.

The invention discloses an edge computing assisted wireless communication system, which relates to the technical field of edge computing, and comprises an edge computing node cluster which is deployed at a base station and an access point and provides distributed computing and storage capability; the resource sensing module is used for monitoring computing resources, communication resources and task queue states of the edge nodes in real time; the dynamic scheduling controller is used for dynamically deciding a task unloading path based on reinforcement learning and game theory algorithms, wherein the task unloading path comprises local processing, edge node cooperative processing, cloud unloading and global time delay and energy consumption optimization; the cross-layer communication interface supports multi-protocol fusion of 5G NR and Wi-Fi 6, and realizes low-delay data interaction between edge nodes; and the security verification module is used for ensuring credibility and integrity of data between edge nodes through a lightweight block chain and a TEE (Trusted Execution Environment). According to the invention, through a hybrid decision framework of reinforcement learning and game theory, the problem that a single algorithm in a traditional scheme cannot give consideration to dynamic environment adaptability and multi-node benefit coordination is solved.

The invention discloses a privacy protection system based on federated learning, and relates to the technical field of privacy protection. The system comprises a distributed participating node cluster, wherein each participating node is configured with a local model training unit and a privacy protection module; the coordination server is connected with each participating node through a secure communication layer and comprises a model aggregation module and a dynamic trust evaluation module; the global model distribution channel is used for broadcasting the encrypted global model parameters to participating nodes; and the privacy protection module is integrated in a local participating node and comprises a homomorphic encryption engine and a local differential privacy injector. According to the method, privacy protection strength improvement, model utility optimization, system efficiency breakthrough and security boundary expansion are synchronously achieved under a federated learning framework, and an industrial-grade solution is provided for cross-domain data collaborative learning.

The invention discloses a railway intelligent construction site safety penetration type management messenger platform which comprises a multi-modal data fusion processing module, an edge computing node cluster module, a three-dimensional visual penetration type management interface module, an intelligent early warning and emergency response module, a self-adaptive network transmission module and the like. Real-time cleaning, alignment and correlation analysis are realized by using a dynamic data calibration algorithm, and a data island is broken; the edge computing node cluster carries out localization preprocessing and the like on data in a key area, so that the load of a central server is reduced; the three-dimensional visual interface is based on a digital twinborn construction model, supports drilling type viewing and realizes three-dimensional monitoring; the intelligent early warning system adopts a reinforcement learning model to automatically trigger multi-channel early warning; and the adaptive network transmission module dynamically switches communication modes to ensure low-delay transmission of key data. The platform realizes real-time acquisition and integration of construction site data and reduces manual intervention.

The invention discloses an industrial equipment intelligent operation and maintenance management system and method based on 5G-MOM, and belongs to the technical field of industrial internet and intelligent manufacturing. The system comprises a multi-source heterogeneous data acquisition layer deployed in industrial equipment, an edge computing node cluster based on 5G, a cloud intelligent analysis platform and a man-machine collaborative operation and maintenance terminal. The method comprises the following steps of collecting equipment vibration, temperature and current multi-dimensional working condition data in real time through a 5G network; performing data cleaning and feature extraction by using edge computing nodes, and constructing an equipment operation digital twin model; a cloud deep neural network is adopted to carry out fusion analysis on the multi-dimensional time series data, and self-adaptive diagnosis and residual life prediction of a fault mode are realized; a dynamic maintenance strategy is generated based on an MOM system, and field personnel are guided to execute precise maintenance through an AR terminal. According to the invention, 5G ultra-low time delay communication and an industrial mechanism model are creatively combined, and real-time visual management and predictive maintenance decision optimization of the equipment health state are realized.

The invention discloses an enterprise financial document unified management system and method based on distributed storage, and relates to the technical field of enterprise financial document management, and the system comprises a metadata processing module which is connected to a distributed storage node cluster and is used for converting the metadata attribute of an enterprise financial document into a high-dimensional sparse vector. According to the enterprise financial file unified management system and method based on distributed storage, efficient management of multi-dimensional financial file data is realized through dynamic metadata topology reconstruction and a dual-channel index optimization mechanism. A vectorization metadata packaging technology is adopted to convert traditional discrete attributes into high-dimensional association vectors, and quantum annealing path optimization and a three-section aggregation verification strategy are combined, so that the response time of multi-condition combination query is shortened compared with that of a traditional scheme, and the network bandwidth consumption is reduced.

The invention relates to the technical field of software time synchronization, and discloses a software time synchronization method and system for multi-sensor data fusion, and the method comprises the steps: extracting temperature, load and drift frequency characteristics through principal component analysis based on the working state and historical drift data of a sensor, and constructing a confidence evaluation model to calculate the credibility of a timestamp; identifying an abnormal node group by using k-means and an isolated forest algorithm, analyzing a phase deviation fluctuation and network delay interaction effect, extracting a nonlinear drift feature in combination with a Prophet algorithm, and calculating a phase correlation value by using Hilbert cross-correlation; and dynamically adjusting node clock parameters and generating a calibration timestamp according to the network influence weight and the stability evaluation result. According to the method, the problem of time desynchrony caused by clock drift and network delay factors in a distributed system is effectively solved, and the overall time consistency and reliability of the system are improved.

The invention discloses an e-commerce live broadcast real-time interaction quality evaluation system based on edge calculation, and relates to the technical field of e-commerce live broadcast, and the system comprises a multi-modal interaction data collection module which collects multi-modal interaction data of a live broadcast stream in real time through a distributed edge calculation node cluster, and constructs a multi-dimensional quality feature vector, the multi-modal interaction data comprises a video coding parameter, an audio quality index, user interaction behavior data and network transmission state data; according to the invention, the distributed edge computing node cluster collects the multi-modal interaction data of the live stream in real time, the lightweight space-time attention neural network model carries out data fusion processing, the deep reinforcement learning network generates a quality optimization scheme, and the adaptive fuzzy inference system corrects the optimization scheme in real time. And dynamic parameter adjustment is carried out in combination with network bandwidth fluctuation and a terminal device resource state, so that the effect of accurately and comprehensively evaluating the e-commerce live broadcast interaction quality in real time is achieved.

The invention provides an expandable block chain identity authentication method and system for a distributed resource aggregation scene, and relates to the technical field of block chain identity authentication, and the method comprises the steps: receiving a user identity authentication request, generating an identity identification string through a distributed Hash algorithm, and selecting a verification node cluster to deploy a smart contract; each verification node executes the smart contract to verify the identity identification string, constructs an access authority control strategy and generates an authentication block; and when the number of the blocks reaches a preset threshold value, selecting a newly added verification node based on the terminal equipment information, deploying an intelligent contract, and realizing distributed storage through the verification node cluster broadcast authentication blocks. According to the invention, the expandability of identity authentication is improved, the dynamic expansion of the verification node is realized, and the reliable storage and efficient propagation of the authentication information are ensured.

The invention provides a data flow monitoring method and system based on a large model, and the method comprises the steps: obtaining a data flow record set generated by a to-be-monitored system in a continuous operation period, carrying out the correlation path construction of the data flow record set, generating a data flow topological graph containing a node interaction relation and a time sequence dependency relation, and carrying out the correlation path construction of the data flow record set; calling a pre-trained circulation behavior analysis large model to perform node sequence pattern recognition on the data circulation topological graph, and generating behavior abnormal confidence and abnormal pattern labels of each node in the data circulation topological graph; and according to the abnormal behavior confidence and the abnormal mode label, screening an abnormal interaction node cluster in the data flow topological graph. According to the method, relevance between abnormal nodes and time sequence relevance are considered, missing detection or false detection is avoided, and the reliability of the monitoring effect is improved.

The invention discloses a network security vulnerability identification and repair method and system, a medium and a program product, and the method comprises the steps: segmenting a system behavior sequence into a plurality of subsequences; constructing a behavior dependency graph; calculating functional similarity, and dividing the functional similarity into node clusters; calculating a behavior consistency score, and determining a potential vulnerability region; determining call chain information; constructing a vulnerability propagation path, and calculating criticality; dividing first-level hazard vulnerabilities, second-level hazard vulnerabilities and third-level hazard vulnerabilities according to the criticality; determining a repair priority, and generating a vulnerability report; according to the vulnerability types, the repair priorities and the propagation path information, corresponding repair strategies are sequentially matched from a preset repair template library according to the sequence of the repair priorities; and performing hierarchical repair on the application code based on the repair strategy obtained by matching to obtain a repair code, and deploying the repair code to the target system. According to the invention, the accuracy and efficiency of identifying and repairing network security vulnerabilities are improved.

The invention relates to the technical field of dynamic monitoring, in particular to an AI-based coal mine underground and roadway three-dimensional earthquake dynamic monitoring system, which comprises an underground edge computing node cluster module, an underground edge computing node cluster module and an underground edge computing node cluster module, the multi-source heterogeneous data fusion processing module is used for receiving the original signal data set, performing space-time alignment and feature decoupling processing, and generating a standardized seismic-electric feature matrix; the three-dimensional geological dynamic modeling module is used for generating a three-dimensional geological dynamic model updated in real time through a dynamic voxel compensation algorithm based on the standardized seismoelectric characteristic matrix; the abnormal characteristic evolution analysis module is used for receiving time sequence data of the three-dimensional geological dynamic model and constructing a space-time two-dimensional abnormal degree evolution graph; and the visual early warning decision module is used for generating graded early warning signals and a three-dimensional visual interface. According to the invention, the six-level progressive processing architecture is innovatively designed, so that the performance of the three-dimensional earthquake dynamic monitoring system for the underground coal mine and the roadway is remarkably improved.

The invention relates to the technical field of chip welding, in particular to a pin lossless welding device for chip processing and a welding method thereof.The method comprises the steps that laser scanning processing is conducted on a chip pin area to obtain three-dimensional space coordinate data of a chip, and the three-dimensional space coordinate data comprises a plurality of data points; generating a plurality of connection nodes according to the incidence relation of the plurality of data points in the space, and performing clustering processing on the plurality of connection nodes to obtain a plurality of regional node clusters; performing welding path optimization processing and heat flow distribution simulation processing on the plurality of regional node clusters to obtain a temperature change curve of each path; and performing data analysis processing and dynamic adjustment processing on the temperature change curve to obtain a final welding control strategy, and controlling the welding robot to weld the chip based on the final welding control strategy. According to the method, the defects of an existing welding technology in the aspects of precision, stability and adaptability are effectively overcome by dynamically adjusting the control strategy.

The invention relates to a brain inspired data service system and a brain inspired data service method, which are characterized in that a layered architecture is constructed, the layered architecture comprises a data node cluster deployed in a mixed manner, the data node cluster specifically comprises a core node, an acquisition node and a gateway node, and the core node, the acquisition node and the gateway node are respectively used for processing core service data, real-time edge data and cross-domain connection; the small-world connection layer realizes same-domain efficient communication through high-clustering local connection, and breaks a data island through dynamic long-range cross-domain connection; the intelligent control layer integrates a DMN control center, a collaborative state monitoring engine, a prediction analysis module and a reinforcement learning driven resource scheduler. The system initializes a topological structure through a small-world network manager, and when the communication frequency of a cross-domain node exceeds a threshold value, long-range connection is dynamically inserted to ensure that the hop count of a cross-domain path is stably not higher than a preset value. The DMN control center realizes dual-mode switching based on a system load threshold; in an idle period, data pre-cleaning, knowledge graph construction, predictive pre-fetching and resource pre-allocation are executed; and optimizing routing in combination with a graph traversal algorithm in a task period.

The invention provides a data knitting system and method based on dynamic metadata identification and DAG optimization, and relates to the technical field of data knitting, the data knitting system comprises a metadata management layer, a data processing layer and an execution layer, the metadata management layer comprises a dynamic metadata identification module and a labeling storage engine module, the data processing layer comprises an adaptive DAG optimization engine module and a dynamic task distributor module, and the execution layer comprises a data computing node cluster module and a multi-source data connector module; the method comprises the steps that a DAG task scheduling strategy is established, and dynamic optimization is achieved; according to the method, the service labels and DAG task scheduling are deeply bound to form a'data-calculation-service 'closed loop, the execution sequence and resource allocation of the tasks can be adjusted according to the service labels changing in real time, so that the task scheduling not only considers the use of calculation resources, but also can optimize the tasks in real time according to service requirements, and the task scheduling efficiency is improved. Therefore, the overall treatment efficiency is improved.

The present disclosure relates to a method for generating a knowledge graph. The method includes determining a causal chain of events indicating a cause-and-effect relationship among entities within the input data based on a causal expression. Further, the method includes assigning attribute labels such as a topic label, a sentiment label, and a temporal label to the entities using a Natural Language Processing (NLP) technique. Further, the method includes creating nodes indicating a collection of entities having the assigned attribute labels. Furthermore, the method includes generating a knowledge graph based on clustering the nodes. The knowledge graph indicates a visual depiction of the causal chain of events such that the nodes are interlinked through a directional edge representing the causal chain of events. In the method, the generated knowledge graph along with the assigned attribute labels is retrieved based on at least one of a user-query input or parameter filters.

The invention provides a double-chain fusion product quality tracing method and system applied to a production line. The method comprises the following steps: firstly, collecting comprehensive data of each production node and attribute information containing a unique stage number; according to the total number of production stages, randomly selecting nodes with different numbers as initial clustering centers, and grouping all the nodes according to stage attributes by using a reverse clustering algorithm to form a node cluster; and constructing a basic traceability chain for each node cluster, and integrating data in corresponding stages to generate a distributed account book. And then screening core nodes from each basic chain to establish a cross-stage quality tracing chain, and realizing synchronous updating and inter-chain data verification of the core nodes on basic account books through an intelligent contract. And finally, a whole-process data tracing service is provided based on a quality tracing chain, and the information credibility is guaranteed by using the non-tampering characteristic of the block chain. According to the invention, product quality tracing with high reliability and high credibility can be realized.

The invention discloses a configurable flexible job shop scheduling method based on a multi-agent game model, and the method comprises the steps: mapping a scheduling problem into a dynamic disjunction graph model to describe the relation between a process and equipment, representing process nodes, equipment nodes and the mutual relation through a node set and an edge set, and combining the flexibility of a dynamic disjunction graph to obtain a flexible job shop scheduling model. And matching of equipment and processes is dynamically adjusted according to changes of production requirements, so that the equipment utilization rate is optimized. And a clustering method based on structure entropy is adopted, and process nodes are clustered into sub-graphs, so that the search space of a scheduling problem is reduced, and the calculation complexity is reduced. Construction of an order agent and an equipment agent and a game and cooperation process between the order agent and the equipment agent are covered. And each agent optimizes a decision through a deep Q network, and cooperates or competes according to a respective target. An automatic optimization configurator is used for optimizing hyper-parameters and a network structure of a deep Q network in a multi-agent system, and scheduling performance and adaptability are further improved.

The invention provides an application environment and version management method and system suitable for a low-code platform, and relates to the technical field of platform management.The application environment and version management method comprises the steps that a directed dependency graph is constructed by obtaining change records, and a dependency loop is detected and intelligently decomposed through a depth-first traversal algorithm; and packaging the node clusters into micro-services based on a function relevancy model to form an acyclic directed dependency graph, constructing a version backtracking index and a difference analysis matrix to determine a change influence range, executing incremental deployment according to a topological sequence, and recording deployment information. According to the method, the problem of version management and environment dependence in a low-code platform is solved, and the application deployment efficiency and the system stability are improved.

The invention relates to a check point reading and writing method and device in distributed training, a storage medium and a program product. The method comprises the steps that in response to check point file generation and the number of check point files in a memory of a training node cluster corresponding to a target distributed training task does not reach N, an idle target memory is determined in the memory of the training node cluster, and the check point files are written into the target memory, the memory of the training node cluster comprises the memory of each training node in the training node cluster; and in response to a fault of any training node in the training node cluster, reading the target check point file from the memory of the training node cluster according to the metadata of the target check point file corresponding to the training node, and recovering training based on the target check point file. According to the method and the device, the check point file can be quickly read from the memory of the training node for recovery when the training node fails.

The invention discloses an Internet of Things equipment monitoring data stream processing method and system. The method comprises the following steps: step 1, collecting and preprocessing multi-source heterogeneous data; step 2, dynamic routing distribution; step 3, edge calculation processing; 4, performing real-time feedback regulation and control; 5, performing anomaly detection and fault tolerance; step 6, data persistence storage; step 7, performing multi-dimensional analysis; and step 8, security enhancement processing. According to the method, intelligent distribution of data streams is realized through the dynamic routing engine, optimal nodes are matched, and resource waste is reduced; the edge computing node cluster completes preliminary screening and filtering, reduces core pressure, adopts an active-active storage subsystem, combines hot and cold storage, reduces cost and guarantees access performance, a safety protection module constructs a full-link safety system, and cooperates with a dual-mode redundancy architecture to improve system availability and fault switching second-level response.

The invention provides a block chain dynamic trust evaluation system and method based on artificial intelligence, and the method comprises the steps: carrying out the time sequence modeling of the transaction data of a block chain node and the consensus historical record of the node participation consensus, obtaining the behavior credibility of the block chain node, calculating the resource contribution degree of each transaction node, and carrying out the calculation of the resource contribution degree. Fusing the behavior credibility and each resource contribution degree to obtain a consensus score of each transaction node; constructing a node graph neural network of the block chain based on the transaction topological relation and the interaction frequency between the transaction nodes, detecting a plurality of malicious nodes in the block chain by using the node graph neural network, and further evaluating a consensus influence coefficient of the current malicious node aggregation on the block chain node consensus; and performing punitive correction on the consensus score of each malicious node through the consensus influence coefficient to obtain a final trust score of each transaction node in the block chain. Based on the above scheme, punishment correction of malicious node aggregation in blockchain node trust evaluation can be realized.

The invention provides a ship traffic flow prediction method and device, electronic equipment and a storage medium, and belongs to the field of marine traffic management. The method comprises the following steps: acquiring ship trajectory data of a to-be-detected port, and performing bidirectional trajectory prediction restoration on the ship trajectory data to obtain restored trajectory data; performing direction identification trajectory clustering on the repaired trajectory data to obtain trajectory clustering data, and performing density adaptive parameter node clustering on the trajectory clustering data to obtain node clustering data; and performing spatial-temporal feature extraction and prediction output on the node clustering data to obtain a ship traffic flow prediction result. According to the method, the integrity of ship trajectory data is ensured through bidirectional trajectory prediction and restoration, trajectory direction information is mined while clustering is performed through direction recognition trajectory clustering, and node comprehensive information is mined while clustering is performed through density adaptive parameter node clustering; dynamic transformation information and a deep relationship can be reserved, data can be effectively integrated, and the accuracy of ship traffic flow prediction is improved.

The invention relates to the technical field of power loads, in particular to a power load dynamic optimization prediction method based on reinforcement learning, which comprises the following steps: acquiring real-time voltage frequency power of nodes, tracking frequency difference direction change of adjacent nodes, marking reverse disturbance to generate a distribution map, and identifying a frequent disturbance area according to the distribution map; clustering node groups with consistent fluctuation trends to determine a target area; monitoring power fluctuation inversion to lock energy steering nodes; constructing a prediction input set; comparing prediction and actual trends to extract a deviation interval, adjusting stride and rate of a reinforcement learning model, updating a decision and smoothing a curve, and outputting a power load dynamic prediction curve. According to the method, disturbance space-time dynamic identification is realized through multi-layer correlation analysis, judgment precision is improved through frequency power joint calibration, load path consistency and area extension are reflected through node clustering, power transmission tracking is enhanced through energy node identification, a feedback closed loop is constructed through offset monitoring, and curve continuity and response rate are improved. Stable convergence is predicted to be consistent with the trend under multiple disturbances.

The invention relates to the technical field of reasoning optimization, in particular to a PD separation reasoning framework optimization method oriented to a large language model, which comprises the following steps: S1, reconstructing a memory structure of a KV Cache, adjusting an original discrete storage structure allocated according to a model layer into a continuous storage structure allocated according to blocks, and changing the memory structure from [layer, k / v, block id, numhead, head, block size] into [block id, layer, k / v, numhead, head size, block size]; s2, dividing a short sequence, a medium sequence and a long sequence according to the length of the cue word, combining the short sequence into a Batch group, and preferentially extruding the short sequence and then processing the long sequence; and S3, deploying a hybrid throughput node cluster, and according to the input prompt word length dynamic allocation request, allocating a short request to a low throughput TP node of the throughput, and allocating a long request to a high throughput TP node of the throughput. The method is more suitable for a PD separated system architecture, and the transmission efficiency of the KV cache and the calculation efficiency of the GPU are improved, so that the throughput of the system is improved, and the maximum resource utilization is achieved.

The invention discloses a mirror image management method and device, electronic equipment and a computer program product. Relates to the field of cloud and edge computing, and the method comprises the following steps: obtaining network load data of a storage node cluster, fragmenting a to-be-deployed mirror image according to the network load data to obtain N mirror image fragments, and uploading the N mirror image fragments to the storage node cluster, the to-be-deployed mirror image refers to a file required for deploying the preset model, and N is a positive integer; under the condition that a server deployment request is received, N mirror image fragments are extracted from the storage node cluster according to the server deployment request, and a mirror image file is formed by the N mirror image fragments; and loading the mirror image file, and deploying the preset model to the target area. Through the method and the device, the technical problems of low uploading efficiency and low storage resource utilization rate when the mirror image is uploaded and stored in related technologies are solved.

The invention relates to an energy-saving method and an energy-saving system based on electric power big data, and belongs to the technical field of energy-saving optimization data processing. The method comprises the following steps: constructing a data model based on time-space fusion multi-source data through a cloud through an intelligent electric meter and external data access; establishing a dynamic reference of an operation scene based on a data model to perform group division on nodes, and then obtaining a multi-dimensional comprehensive sequence and generating an energy-saving reconstruction node list based on group evaluation index deviation; and completing energy-saving optimization by bidirectionally analyzing the node list, including upwards aggregating the nodes to generate a scheduling strategy and downwards decomposing the load identification equipment to optimize the energy consumption of the user. According to the method, a unified data model is constructed through an intelligent electric meter and multi-source data real-time acquisition and encrypted transmission, and node clustering and feature extraction are carried out by utilizing a machine learning clustering optimization operation reference; node deviation is calculated in real time, an energy-saving potential list is generated, and node resource scheduling and high-energy-consumption equipment optimization are achieved through bidirectional analysis.