221 results about "Undirected graph" patented technology

The invention discloses an electromagnetic field simulation grid adaptive generation method based on a neural network. The method comprises the following steps: performing mesh generation on a semiconductor device simulation model to obtain original generation data, and constructing node features; an undirected graph is constructed, graph nodes of the undirected graph adopt node features of grid points, and connecting edges adopt Euclidean distances between the grid points and adjacent grid points; inputting the undirected graph into a double-branch neural network, and outputting a predicted node position; and correcting each node of the original subdivision data by using the predicted node position obtained by the double-branch neural network to form new subdivision data for electromagnetic field simulation. According to the method, physical field information can be fused to efficiently adjust the node density, and the geometric boundary and topological structure characteristics of the device can be strictly kept.

The invention relates to the field of heliostat calibration, and discloses a scheduling method for calibrating heliostats through cooperation of artificial light sources and cameras in a large-scale heliostat field, and the method comprises the following steps: determining the heliostat range covered by each camera, determining the heliostat range covered by each artificial light source, and determining the heliostat range covered by each camera; the method comprises the following steps: determining the center and size of a light spot in an image shot by a camera when the heliostats are calibrated, determining the heliostats which can be calibrated in the coverage range of each artificial light source-camera combination, regarding each effective calibration combination as a node to construct an undirected graph, dividing the nodes into a plurality of groups through a graph grouping algorithm, and ensuring that the nodes in the same group are not connected with each other, therefore, all combinations in the same group can execute calibration in parallel. According to the method disclosed by the invention, the problem of affiliation misjudgment caused by light spot interference between heliostats is solved, possible shadow and shielding problems are avoided, dynamic scheduling of the artificial light source and the camera is realized, and invalid operation time is shortened.

The invention discloses a GCN-LSTM-based tailing dam multi-point settlement deformation prediction method. The method comprises the steps of collecting and preprocessing original settlement monitoring data of monitoring points in a research area; constructing a graph structure for settlement data between all monitoring point pairs, setting a threshold value, connecting node pairs with significant correlation coefficient relationships by using edges, constructing a weighted undirected graph, and converting the weighted undirected graph into a normalized adjacent matrix as the input of a graph convolutional network GCN; extracting the spatial topology of each monitoring point by using a GCN; capturing long-term time dependence in the settlement process by using a gating mechanism of the LSTM network; and fusing the GCN and the LSTM network, and finally outputting a predicted value through a full connection layer. According to the method, the spatial topological graph among the monitoring points of the tailing dam is constructed, and the GCN and LSTM networks are fused, so that the spatial correlation among the monitoring points and the time dynamic characteristics of the settlement data are effectively captured, and high-precision tailing dam multipoint settlement prediction is realized.

The invention relates to a capacity expansion optimization method, system and equipment based on network performance marginal gain, and belongs to the technical field of network communication. The method comprises the following steps: constructing an undirected graph of communication network topology; defining a service requirement for each pair of nodes in the undirected graph, endowing each edge with a capacity value, and constructing to obtain an MCFP model; on the basis of the Lagrange duality theory, a duality model of the MCFP model is constructed, and a column generation algorithm is adopted to carry out double-model synchronous solution to obtain a maximum concurrency factor, optimal path flow and capacity constraint optimal duality variable; performing network key bottleneck identification according to the capacity constraint optimal dual variable and generating a plurality of capacity expansion candidate schemes; and comprehensively evaluating the capacity expansion candidate scheme by combining the network performance marginal gain, the influence degree of the link capacity change and the implementation cost, and selecting the optimal capacity expansion scheme for implementation. According to the invention, accurate load evaluation, bottleneck quantitative identification and efficient capacity expansion optimization of the communication network can be realized.

The invention relates to a heat supply prediction method and system based on spatial-temporal feature fusion deep learning, and the method comprises the following steps: S1, carrying out the collection and fusion of multi-source heterogeneous data, and constructing an integrated data set; s2, preprocessing the data; s3, constructing a graph structure model of the heat supply system, and constructing a weighted undirected graph; s4, constructing and executing forward calculation of the space-time double-flow deep network; s5, designing a composite loss function including mean square error loss and physical constraint loss, and performing joint optimization training on the space-time double-flow deep network; and S6, performing multi-step heat supply load prediction by using the trained model, outputting a heat supply load curve of each heat exchange station in a specified time period in the future, and integrating a prediction result with a heat supply scheduling system. The method has the advantages that the prediction precision is improved compared with that of a traditional machine learning model by capturing the spatial-temporal characteristics at the same time, and the advantages are more remarkable in extreme weather.

The present disclosure relates to a method, a device, and a program product for training a model. The method includes: receiving at least one unlabeled sample and at least one labeled sample for training a pre-training model, the pre-training model being used to extract features of the samples; creating an undirected graph associated with the pre-training model using the at least one unlabeled sample and a set of training samples associated with the pre-training model; dividing the undirected graph to form a plurality of sub-graphs based on corresponding features of the unlabeled sample and the set of training samples, the plurality of sub-graphs corresponding to a plurality of classifications of the samples, respectively; and training, based on the plurality of sub-graphs and the at least one labeled sample, the pre-training model to generate a training model. A corresponding device and a corresponding computer program product are provided.

The invention discloses a motor temperature prediction transfer learning method based on a physical constraint graph neural network, and the method comprises the following steps: S1, constructing an undirected graph with a label based on a physical structure of a source domain motor; s2, on the basis of the undirected graph of the label, constructing a physical constraint graph neural network; s3, training the physical constraint graph neural network by using operation data and temperature data of a source domain motor to obtain a pre-training model; s4, on the basis of the physical structure of the target motor, constructing an undirected graph of the target motor, and multiplexing the heat capacity parameter and the heat conductivity function in the pre-training model so as to obtain an initialized physical constraint graph neural network for the target motor; and S5, obtaining a temperature prediction model of the target motor. According to the method, the physical heat transfer rule is embedded into the transferable graph neural network structure, so that a high-precision temperature prediction model with physical interpretability can be quickly constructed for a new motor only by using small-batch data.

The invention discloses a video abstract generation method and system based on graph-guided adaptive key frame sampling, and relates to the technical field of video abstract generation, and the method comprises the steps: obtaining and extracting different scale features of each video frame, and generating multi-scale fusion features through the weighted fusion of scale attention weights; calculating inter-frame similarity to construct a weighted undirected graph, obtaining global structured frame features of each video frame through multi-layer feature propagation, and calculating graph guide weight of each frame; introducing a learnable distribution focusing parameter to perform power scaling on the graph guide weight to obtain an adaptive sampling weight, and calculating a final comprehensive weight; and according to the video frame length of the original video, calculating the number of sampling frames through a video length adaptive function, and according to the comprehensive weight and the number of sampling frames, sampling key frames by adopting a frame screening strategy based on sorting to generate a video abstract. According to the method, the video abstract with better coverage, diversity and stability balance can be generated.

The invention discloses a graph enhancement-based rolling bearing small sample fault diagnosis method, which comprises the following steps of: firstly, mapping a time-frequency image into a weighted undirected graph capable of accurately describing local texture and global semantic association through a self-adaptive dynamic graph construction strategy by calculating a pixel neighborhood variance and a global expectation thereof and dynamically generating a connection threshold value; the space-frequency dependency relationship between the pixels is explicitly coded; a graph feature enhancement residual block is designed in the diffusion denoising process, and the feature expression of a diffusion model in the denoising process is enhanced by cooperating with the local perception of the convolutional neural network and the global reasoning ability of the graph neural network by using the gating fusion and attention mechanism. And finally, the modules are integrated in the graph enhanced U-shaped network, so that high-quality and high-diversity fault sample generation is realized. Experiments show that the method significantly improves sample diversity and diagnosis accuracy on two bearing data sets, and provides a new approach for intelligent fault diagnosis under small sample conditions.

The invention relates to the technical field of path planning, in particular to a priority-based multi-agent path planning method and system, and the method comprises the steps: abstracting a target scene into an undirected graph; setting a set of agents participating in path planning in the target scene; setting a starting point and an ending point of each agent; defining a priority, a calculation formula of the priority, an initialization rule of a definition and an updating rule in a subsequent path planning step for each agent, wherein the corridor priority represents the defined agent, and the movement priority represents the defined agent; and performing path planning on the agents in the set based on the graph, the starting point and the ending point of each agent, the priority and the calculation formula of the priority. The method is used for improving the quality of the solution generated in the map with the corridor structure.

The invention discloses a vehicle path problem solving method, system and equipment and a medium, and particularly relates to a vehicle path problem solving method based on clustering decomposition and graph matching, which comprises the following steps: S1, receiving a large-scale vehicle path problem instance to be solved, modeling into a weighted undirected graph, and combining a series of constraint conditions and optimization targets; s2, constructing an offline knowledge base with a diversified structure, inputting a group of preset parameters in the step, and outputting a knowledge base stored in the memory; s3, aiming at the large-scale vehicle path problem instance to be solved, executing initialization operation to generate a global initial solution; and S4, by taking the global initial solution as a starting point, executing an iterative local search framework to carry out deep optimization on the solution until a preset termination bar is met. The technical problems that in the prior art, when a large-scale complex logistics network is processed, the calculation time consumption is long, the planning cost is high, and the result is unstable are solved.

The invention provides a global path planning method and system for a wheel-foot robot in multiple motion modes, and relates to the technical field of robot path planning, and the method comprises the steps: obtaining multi-source data of the wheel-foot robot; calculating actual motion cost values of the wheel-foot robot in various motion modes in different terrains; constructing a deep learning network model; outputting a motion cost prediction value through a deep learning network model; constructing a loss function, and optimizing the deep learning network model by taking the minimum function value of the loss function as a target; sampling the global map through a path planning algorithm to generate an undirected graph; through the optimized deep learning network model, motion cost prediction values of all sampling points in the undirected graph in different motion modes are output; determining a plurality of middle sampling points through a heuristic search algorithm; and connecting the initial sampling point, each middle sampling point and the target sampling point in sequence to obtain a global path of the wheel-foot robot in various motion modes.

The invention discloses an intelligent equipment one-key inspection method and system based on a block chain. Aiming at the challenges of insufficient abnormity identification, limited fault diagnosis, dispersed data management, low maintenance response efficiency and the like in traditional intelligent home maintenance, the system realizes comprehensive upgrading by deeply integrating multiple frontier technologies. The core of the method is that a double-chain framework is adopted, a main chain is used for tampering-free evidence storage of key data, and an auxiliary chain is used for processing high-frequency original sensor data and carrying out real-time health analysis and anomaly detection. A system automatically constructs a dynamic digital twinborn weighted undirected graph, and after an adaptive threshold algorithm accurately recognizes abnormal operation of equipment, a three-degree association algorithm is combined with a hierarchical causal graph and a graph convolutional neural network to carry out fault root analysis. And finally, the system can generate an optimal inspection path in a second level and automatically distribute a work order, and the operation and maintenance of the smart home are converted from passive response to active prediction and accurate intervention, so that the data security, the operation efficiency and the system toughness are remarkably improved.

The invention discloses a task processing method and device based on quantum computing, equipment and a storage medium. The method comprises the steps of determining a maximum cut problem corresponding to a target task and a weighted undirected graph of the maximum cut problem; performing community detection division on the weighted undirected graph to obtain a plurality of community sub-graphs; mapping the community sub-graph into a sub Hamiltonian and constructing a parameterized quantum circuit; updating parameters of the parameterized quantum circuit by adopting a gradient descent algorithm to minimize a global Hamiltonian expected value, and outputting a binary string of a quantum state corresponding to the global Hamiltonian expected value as an initial solution; generating a plurality of candidate solutions for the initial solution based on a neighborhood search algorithm, calculating cut values of the initial solution and the candidate solutions, and selecting a better feasible solution based on the optimal cut value; and applying a preset disturbance operator in the parameterized quantum circuit to construct a disturbance quantum circuit, updating parameters of the disturbance quantum circuit by adopting a gradient descent algorithm, and outputting a binary string of a quantum state corresponding to the global Hamiltonian expected value as a final solution of the target task by minimizing the global Hamiltonian expected value after disturbance.

The invention discloses an open source environment software hidden vulnerability patch identification method, which is based on a multi-stage architecture and collaborative relationship modeling, and provides a new patch group identification scheme: firstly, obtaining candidate code submission from an open source warehouse, extracting correlation characteristics of vulnerabilities and candidate code submission, including rule-based characteristics and semantic characteristics, calculating a correlation score and screening high-correlation submission; pairwise pairing the high-correlation submissions, and fusing multi-dimensional features to predict a cooperative relationship between the submissions; and finally, constructing an undirected graph based on the correlation score, dividing a maximum connected sub-graph, fusing the features in the group through maximum pooling, calculating the correlation with the vulnerability, and outputting an optimal patch group. Meanwhile, an existing patch identification technology based on sorting learning is combined, an enhancement method based on a submission cooperative relation is provided, ranking logic submitted by candidate codes is updated through internal association between code submission and by means of correlation between group vectors and vulnerabilities, and the identification precision in a multi-patch scene is improved.

Described is a system for updating an LLM-generated SQL query preventing double counting by receiving a natural language query from a user at a cloud-based server, where the query requests access to data in a database. The data platform identifies semantic data from the query and, using a large language model (LLM), generates a SQL query containing join functions. The SQL query is then parsed to identify operation types and data sources. An undirected graph is constructed from the parsed query, with nodes representing data sources and edges representing join functions. The undirected graph is converted to a directed graph by adding relationship characteristics to the edges. Based on this directed graph, the data platform validates the SQL query to detect and resolve potential double counting issues and updates the SQL query as necessary to ensure accurate results.

The application relates to a causal driving unsupervised multi-modal small sample double cycle data fusion method. Each modality data of each lesion sample is respectively preprocessed and feature dimension alignment is performed to obtain an aligned feature matrix. An undirected graph is constructed based on the aligned feature matrix. A causal consistency sample pair set is constructed by using kernel independent component analysis, medical priori and causal consistency test technology, comparative learning of a feature extraction network is performed on the set, causal enhancement features are output, and an updated causal graph is constructed. The updated causal graph is input into a dynamic fusion weight calculation model to calculate dynamic fusion weights, the causal enhancement features after weighted summation and standardization are calculated, preliminary fusion features are generated, the preliminary fusion features are screened, the screened effective fusion features are input into a downstream diagnosis model to correct and update the causal graph, and global fine tuning is performed on the feature extraction network, the dynamic fusion weight calculation model and the downstream diagnosis model to construct an unsupervised small sample fusion model.

The invention belongs to the technical field of image interpolation, and particularly discloses an image interpolation method based on dual-stage disturbance and DR splitting and expansion. According to the method, the linear interpolation operator is used as an initialization module of the network for initial interpolation, the linear interpolation operator is mapped into the graph adjacency matrix through the interpolation operator theorem, and the stability of the training process and the reliability of the interpolation result are ensured. Besides, a dual-stage optimization model of a directed graph disturbance matrix and an undirected graph disturbance matrix is introduced, and a learnable neural network structure is expanded by using a DR splitting iterative algorithm, so that high-precision and interpretable image interpolation is realized. Wherein the directed graph carries out adaptive modeling and correction on the connection relation between the observation pixels and the pixels to be interpolated, and the undirected graph carries out local refining constraint on the smoothness between the interpolation pixels, so that the high-frequency details and the overall smoothness of the image are effectively enhanced while the original structure information is kept, and the precision of the image interpolation result is ensured.

The invention discloses a cable physical path target connection method and system based on recursive expansion. The method comprises the following steps: initializing data of all equipment and distribution frames and a cable connection relationship between the distribution frames, and constructing a bidirectional adjacency list based on a relationship between specific physical distribution frame ports and ports; performing path search based on the bidirectional adjacency list to obtain a plurality of paths conforming to parameter adjustment, and obtaining a global path group; based on the optimal path length and the distribution frame port occupancy rate weight, selecting an optimal path from the global path group, and generating an optimal cable physical path target connection scheme; and according to the obtained optimal cable physical path target connection scheme, a user selects the optimal cable physical path target connection scheme, and cable physical path target connection is completed. According to the method, bidirectional adjacency list data preprocessing, grouping traversal parallel computing, path dynamic memory, undirected graph loop searching forbidding and distribution frame port occupancy rate weight pre-arranged planning are combined, the performance, usability and practicability of a distribution frame port line searching algorithm are improved, and the problem of line searching and line connecting work efficiency among a large number of distribution frames in a machine room is solved.

The invention discloses a DVQE-based gene phasing method, device and equipment and a storage medium, which are used for solving the problems that the existing gene phasing method is easy to fall into local optimum and is insufficient in convergence precision when processing large-scale sequencing data. The method comprises the following steps: mapping obtained gene sequencing fragments into nodes of an undirected graph, and taking a difference base number of the gene sequencing fragments on an SNP (Single Nucleotide Polymorphism) site as an edge weight between the nodes; converting a gene phasing problem into a maximum cut problem of an undirected graph; constructing a target function according to the maximum cut problem of the undirected graph, and mapping the target function into a global Hamiltonian of the Isin model based on the constructed target function; decomposing the global Hamiltonian into a plurality of sub-Hamiltonian based on the bearable bit number of the quantum processor; adopting a distributed quantum variational character solicitation solver DVQE to execute parallel solution on each sub Hamiltonian to obtain a global solution; and determining a haplotype source of each sequencing fragment according to the global solution.

The present application belongs to the technical field of parameterized modeling, and discloses a tunnel operation area dynamic parameterized modeling method; comprising: collecting measured data of a tunnel operation area; based on the collected measured data, establishing an initial model of the tunnel operation area; dividing the initial model of the tunnel operation area into a plurality of model regions, taking the model regions as nodes to construct an operation area undirected graph; assigning colors to the nodes in the operation area undirected graph; for each model region, determining a corresponding parameter group according to the assigned color, and updating to obtain an overall parameterized model based on the initial model of the tunnel operation area and the corresponding parameter groups of the model regions; namely, the dynamic parameterized modeling result of the entire tunnel operation area, which provides a scientific decision basis for design optimization, construction scheme formulation, risk assessment and operation management of tunnel projects.

The invention provides a line fault positioning method and device, equipment, a medium and a computer program product. The method comprises the following steps: analyzing acquired pipeline information to obtain a resource mapping relationship; performing multi-dimensional analysis on the fault original data according to the resource mapping relation to obtain a pre-positioned pipeline section set; converting the pipeline segment set to obtain a weighted undirected graph, and converting the weighted undirected graph to obtain an adjacency list; and determining a post-positioned target fault path based on the weighted undirected graph, the adjacency list and the OTDR measurement distance. The method comprises the following steps: performing multi-dimensional analysis on line fault information to obtain the breakpoint probability of each pipeline section in a fault area, and screening according to the probabilities to obtain a pre-positioned pipeline section set; and then, by inputting OTDR positioning conditions and results, marking out a route on a fault point path, displaying a pipeline position where a fault point is located, and improving the optical cable fault positioning precision through path visualization.

The invention relates to the field of data management, in particular to a BRM business rule automatic reasoning method based on a knowledge graph. Comprising the following steps: obtaining a resource description framework triple based on a heterogeneous time series data stream containing a blade CNC machining log and thermal barrier coating process parameters, loading the triple into a graph database, and constructing a manufacturing knowledge graph data model; extracting historical time sequence data, and initializing a completely undirected graph; based on the process mechanism model and condition independence test, determining a data dependence path, and outputting a directed acyclic graph; performing analysis through intervention calculation, and calculating an average causal effect value; forming a causal knowledge graph by taking the average causal effect value as an attribute and the data dependence path as a relationship; and querying thermal spraying parameter nodes with average causal effect values exceeding a threshold value in the causal knowledge graph, and converting the thermal spraying parameter nodes into storage strategy rules. According to the method, the causal knowledge graph is converted into the storage strategy rule, so that automatic and closed-loop management from data acquisition to rule optimization is realized.

The invention provides an intelligent denoising processing method for signals of an ocean multi-parameter precision measuring instrument, and belongs to the technical field of intelligent denoising processing for the signals of the ocean multi-parameter precision measuring instrument. Noise sub-bands are eliminated according to sub-band signal-to-noise ratio evaluation indexes, signals are reconstructed, a weighted undirected graph is constructed according to partial correlation coefficients among sensors, and joint sparse optimization with physical smoothness constraint is executed in an atlas domain; and finally, multi-channel parallel denoising and time sequence alignment output are realized through a work stealing scheduling strategy. The technical problem that full-band adaptive decomposition, physical priori constraint drift compensation, impact noise accurate separation and multichannel physical consistency collaborative optimization cannot be simultaneously realized in a complex marine environment in a multichannel sensor signal denoising process is solved.

The application provides a standard single point positioning method based on a big data cross-modal residual model compensation, adopts a non-directional graph to establish the connection between the time and the residual, the space and the residual, the satellite elevation angle and the residual, and the satellite azimuth angle and the residual conditions, then utilizes random walk to establish the global relationship, and finally performs cross-modal representation learning on the tuples generated by the random walk to establish a historical relationship model. In prediction, the final prediction result is obtained according to the input space condition, the satellite elevation angle condition and the satellite azimuth angle condition combined with the output strategy. The residual is finally compensated into the standard single point positioning algorithm. The application has higher precision, does not need to depend on external networks at all times, and can ensure that the update of the model can be used for localization calculation with the best precision within 60 days.

The application discloses a method, device and electronic equipment for defending wormhole attack in a wireless sensor network, and belongs to the technical field of wireless communication. The method for defending wormhole attack comprises the following steps: dividing a weighted undirected graph corresponding to nodes in the wireless sensor network into a plurality of communities; reconstructing the weighted undirected graph by using a key node set in each community to obtain a reconstructed graph; simplifying the original large-scale network into a simplified network containing only key nodes by graph reconstruction, while retaining the key topological information of the original network, thereby providing a basis for efficient high-risk node pair selection. Further, high-risk node pairs corresponding to wormhole attacks are found from the reconstructed graph; the high-risk node pairs thus found are prone to be used by attackers to implement wormhole attacks with high concealment by using a selective forwarding method. Further, the high-risk node pairs corresponding to the wormhole attacks are defended, which can significantly improve the defense effect of the wormhole attack nodes deployed.

This invention discloses a cloud gaming vulnerability analysis and monitoring system based on cloud computing, relating to the field of game vulnerability analysis technology. The system includes a game monitoring module, an intelligent aggregation module, and a resource scheduling module. The game monitoring module collects performance parameters and interaction parameters of game instances through a lightweight monitor, and calculates anomaly frequency, coefficient of determination, kurtosis, and temporal anomalies using multidimensional modeling and statistical analysis. Based on this, it performs comprehensive calculations to generate risk assessment values ​​and screen suspicious targets. The intelligent aggregation module performs similarity calculations and undirected graph clustering on suspicious targets and their risk parameters to aggregate scattered suspicious targets into vulnerability analysis tasks. The resource scheduling module calculates an evidence collection index based on parameters such as task size, latency, average risk, and similarity. Based on the evidence collection index, it allocates vulnerability analysis tasks to parallel analysis lines in an isolated analysis cluster for execution, thereby achieving in-depth forensics and dynamic detection.

The invention belongs to the technical field of block chain information security, and relates to an Ethereum fraud detection method based on deep fusion of transaction semantics and graph structures, which comprises the following steps: acquiring and preprocessing Ethereum transaction records to obtain an account transaction sequence; inputting an account transaction sequence into the trained transaction sequence feature extraction network, and outputting a sequence embedding matrix; inputting the self-transaction sequence of the weighted undirected graph and the sequence embedding matrix into the trained graph neural network, and outputting a structural feature embedding matrix; performing element-level fusion on the self-transaction sequence of the sequence embedding matrix and the structural feature embedding matrix; inputting the self-transaction sequence of the sequence embedding matrix and the fused structure embedding matrix into a trained classifier to obtain a sequence prediction score and a structure prediction score, and combining the sequence prediction score and the structure prediction score to obtain an account prediction score; and judging whether the transaction account belongs to a fraudulent account or a normal account according to the account prediction score. According to the method, high-precision identification of the fraudulent account can be realized.

The application discloses a truss environment-oriented two-legged robot crawling landing point sequence planning method and belongs to the technical field of robots; the method first constructs a truss undirected graph topology model based on the spatial connection relationship of truss joints and members, takes nodes to represent the truss joints, takes edges to represent the members and takes the member length as the edge weight; the A star algorithm is adopted on the topology model to search for the node sequence and the member sequence of the robot from the starting member to the target member; subsequently, the axial position of the member is described through a normalized member parameter model, and the non-connected feasible landing area set of the robot foot end is represented in combination with One-Hot coding; on this basis, the least number of steps required for the robot to reach the target position is taken as an optimization target, a mixed integer quadratic constraint programming model is established, the landing point sequence is solved, and the optimal landing point sequence satisfying the truss topology constraint and the robot motion constraint is obtained. The application can realize the landing point sequence planning of a two-legged truss crawling robot on a complex truss structure.

The invention discloses a multi-center hierarchical management architecture unmanned cluster management method and system based on a minimum diameter spanning tree, and the method comprises the steps: collecting communication delay information among all nodes, and constructing a completely undirected graph which takes the nodes in an unmanned aerial vehicle group as vertexes and the communication delay among the nodes as edge weights; sorting the edges of the completely undirected graph from small to large according to the edge weights, and determining an optimal tree generation interval meeting the constraint of the multi-center hierarchical management architecture based on a bipartite enumeration method; solving a minimum diameter spanning tree of the sub-graph according to the sub-graph corresponding to the optimal spanning tree interval, and taking the minimum diameter spanning tree as the optimal spanning tree meeting the multi-center hierarchical management architecture; according to the degree of each node in the optimal generation tree and a central node of a diameter link, roles are distributed to each node; and when the inter-node communication index does not meet the preset threshold value, triggering regrouping by the master node. The method provided by the invention can still keep low delay and expandability in a complex scene.