107 results about "Path (graph theory)" patented technology

The invention discloses a data communication method, system and device under a disaster condition, and belongs to the field of power systems, and the method comprises the steps: determining a graph structure model based on a current network topology structure and network topology change information under the disaster condition, carrying out the calculation through a graph theory algorithm, and determining a transmission node and a standby path; if the node connection is abnormal, performing multi-path planning calculation on the standby path to obtain a planning result; splitting the power grid information packet into a plurality of data packets, performing data transmission through a multi-path planning result, and monitoring a transmission progress and arrival confirmation information in real time; and if it is monitored that the transmission is overtime or lost, updating the planning result based on a preset path switching rule to obtain a target planning result, and performing rerouting processing on the remaining data packets according to the target planning result to realize data communication under the disaster condition. And efficient, reliable and stable operation of data communication of the power grid under disaster conditions can be realized.

The invention provides a park integrated energy system low-carbon scheduling method combining demand response and carbon emission flow, and belongs to the technical field of energy system low-carbon scheduling. Establishing a directed weighted carbon flow network model based on a graph theory, tracking a carbon emission transmission path by adopting a maximum flow minimum cut theorem and a proportional allocation principle, constructing a space-time coupled dynamic carbon flow state space model, and performing state estimation by adopting a Kalman filtering algorithm; the carbon emission responsibilities are distributed based on a Shapley value method, a stepped carbon transaction cost function is established, an optimal scheduling strategy is solved through a double-layer iterative optimization framework, and the technical problem that the carbon emission responsibilities are difficult to distribute reasonably due to the fact that a park integrated energy system cannot accurately track a carbon emission transmission path when electric heat gas multi-energy flow coupling is considered is solved.

The invention provides a structural engineering bearing capacity field detection method, and belongs to the technical field of structural engineering detection.The structural engineering bearing capacity field detection method comprises the steps that a multi-axial acceleration sensor and a strain gauge array are installed on the surface of a to-be-detected structural member, and an intelligent loading device is adopted to apply incremental loads; a mobile data acquisition terminal is utilized to acquire vibration response data and strain response data in real time, modal parameters are extracted based on a frequency domain analysis method to establish a load-modal parameter relation curve, the bearing capacity of a component is analyzed and calculated, a graph theory shortest path algorithm is adopted to optimize load transmission path analysis, and the load transmission path analysis is optimized. The bearing performance of the component is accurately evaluated through the structural response prediction model based on the Transform architecture, the technical integration of multi-dimensional detection data fusion, intelligent loading control, quantitative bearing capacity evaluation and accurate performance prediction is realized, and the technical problem of insufficient detection precision of the bearing capacity of the structural component is solved.

The invention provides a method for constructing an arch-shaped large-span shell steel roof, and belongs to the technical field of arch-shaped large-span shell steel roof construction. A temporary supporting system is built, and distributed optical fiber sensors are arranged to monitor the lifting process of a main arch; a cable force distribution scheme of a cable supporting system is calculated by adopting a double-layer game optimization model to realize cooperative control of stress uniformity and form precision, tensioning force is applied by using an intelligent tensioning system in stages, and a crane moving path is planned in combination with a path optimization algorithm based on a graph theory to realize graded unloading of a temporary supporting system. The technical problem that it is difficult to achieve structural stress uniform distribution and form accurate control of an arched large-span shell steel roof at the same time in the tensioning process of a cable supporting system is solved.

The invention discloses a carbon dioxide seepage dominant channel judgment and permeation enhancement effect evaluation method and system, and the method comprises the following steps: obtaining three-dimensional image data through the three-dimensional CT scanning of a rock sample before and after a CO2 mineralization storage experiment reaction, extracting a crack network as a topological structure center line skeleton, calculating the topological indexes of a network structure, and calculating the permeability enhancement effect of the network structure; a fracture network topological structure model constructed based on a graph theory is coupled with a discrete fracture network model for CO2 flow simulation, an equivalent permeability tensor is obtained, an improved Dijkstra shortest path algorithm is adopted, spatial distribution of CO2 seepage dominant channels is obtained, dominant channel characteristics before and after transformation are compared with the equivalent permeability tensor, the seepage enhancement effect is quantitatively evaluated, and the CO2 seepage enhancement effect is obtained. And changing injection conditions to perform multi-group simulation under different working conditions, calculating the seepage enhancement effect and the mineralization reaction rate under different injection conditions, establishing a quantitative evaluation model of the mineralization sealing permeation enhancement effect, and realizing sealing effect prediction and seepage enhancement effect evaluation.

The invention discloses a method for exploring a heterogeneous catalytic reaction network based on a deep potential energy surface model, and the method comprises the steps: carrying out the accurate prediction of the free energy change of all possible element reactions on a catalyst through the combination of transfer learning and a density functional theory, and constructing a reaction network diagram based on a graph theory method; an improved Dijkstra method is used for searching a reaction network diagram to determine a reaction mechanism, and the selectivity of the catalyst is explored based on a Markov chain method. According to the technical scheme provided by the invention, when the CO2 reduction reaction mechanism on the monatomic alloy is explored, the prediction error MAE of the electron energy of each intermediate is only 0.16 eV, the calculated amount is reduced by 90%, the dominant path of the CO2 reduction reaction is visually displayed, and a new normal form is provided for complex mechanism exploration and catalyst screening.

The invention provides a power distribution network fault self-healing control method based on artificial intelligence, and relates to the field of power system intelligent control, in particular to a power distribution network fault self-healing technology, which comprises the steps of acquiring real-time operation state data of a power distribution network, extracting features to establish a fault prediction rule base, monitoring faults in real time and determining positions, and constructing a topological structure based on a graph theory algorithm. And calculating the load transfer capacity of the selectable reconstruction path, solving the multi-objective optimization function by adopting an improved particle swarm algorithm to obtain an optimal reconstruction scheme, generating a control instruction sequence to isolate a fault area, and recovering power supply of a non-fault area. The intelligent level of power distribution network fault processing is improved, the fault recovery time is shortened, and the power supply reliability is improved.

The invention relates to the technical field of electronic design automation, and discloses a standard cell layout legalization method and system based on a graph theory constraint graph, and the method comprises the steps: building a bidirectional directed constraint graph based on an existing layout and a design rule, and building a directed edge between adjacent graph edges according to the design rule; traversing the constraint graph, detecting whether a directed edge which does not meet a constraint condition exists, and if so, identifying the directed edge as a constraint violation edge; for two end points of each constraint violation edge, searching a key path based on a depth-first search algorithm, and determining a maximum movable distance in combination with a greedy strategy; moving the endpoint to a legal position according to the critical path and the maximum movable distance, and updating the position of a related node in the constraint graph; and mapping the position changes of the nodes in the constraint graph back to the corresponding graph edges in the layout, and outputting the legalized layout, so that efficient and automatic repair of design rule violation is realized through the method, and the layout compliance rate and the area optimization effect are remarkably improved.

The invention discloses a biomass pyrolytic reaction network prediction method based on a graph theory and quantum chemistry, which comprises the following steps: analyzing the molecular structure of a biomass initial reactant, abstracting the molecular structure into a directed graph molecular model, marking a potential conversion path after molecular mechanics optimization, generating a unique identifier by using an atom numbering rule and a Hash algorithm, and predicting the biomass pyrolytic reaction network. Functional groups are extracted and packaged into sub-graph modules, chemical bond parameters are obtained in combination with quantum chemistry calculation and are converted into fracture probabilities, basic reaction building blocks are predefined to traverse and mark breakable bonds, fragments are recombined and then de-weighted through Hash, and then reaction activation energy weights are given to side chemical bond fracture reactions; an energy optimal path is screened by means of a priority queue search algorithm, accurate analysis of a chemical bond fracture path and intermediate product conversion in the biomass pyrolysis reaction network is finally achieved, reaction path and product distribution are efficiently predicted, and the calculation efficiency and precision of a complex system are balanced.

The invention discloses a legal contract risk monitoring and early warning method, and particularly relates to the technical field of risk early warning. The method comprises the following steps: constructing a multi-contract risk propagation network by identifying transmissible terms in a plurality of legal contract texts, and generating a multi-contract propagation path topology network model by adopting a graph theory algorithm; identifying a cascade trigger mechanism of risk propagation terms between contracts by using time sequence causal analysis, and outputting a cascade risk propagation link; performing sensitivity grading on each risk propagation path to obtain propagation path sensitivity grading data; integrating the cascaded risk propagation link and propagation path sensitivity grading data, constructing a contract network risk propagation comprehensive evaluation model, and outputting a comprehensive risk evaluation result; comparing the comprehensive risk assessment result with a preset risk early warning threshold rule to generate corresponding risk prompt information; according to the method, the propagation trend and the diffusion path of the legal contract risk can be effectively predicted, and the timeliness and the accuracy of contract risk management and control are improved.

The invention provides an online dynamic water quality fingerprint rapid acquisition and preprocessing device and method. The method comprises the steps that intelligent flow path selection is achieved through graph theory modeling, a water quality monitoring system is modeled into a directed weighted graph, bilateral connected component decomposition is carried out to recognize system vulnerabilities, and a redundant flow path is configured to improve the fault-tolerant capability; adopting an optimal transmission theory to optimize dilution control, modeling a dilution problem as an optimal transmission problem of spectral distribution, and calculating an optimal dilution ratio through a linear space super-gradient algorithm; a matrix flipping graph search algorithm is applied to accelerate spectrum calculation, a spectrum data matrix is abstracted into a flipping graph model, and an optimal matrix flipping operation sequence is found through heuristic search. According to the method, the efficiency, precision and robustness of water quality monitoring are remarkably improved, the monitoring efficiency is improved by 50%, the measurement error is reduced by 70%, and the calculation speed is improved by 5-10 times.

The invention relates to the technical field of big data mining and analysis, and discloses a charging pile intelligent site selection method and system based on big data analysis, and the method comprises the steps: obtaining traffic space-time big data, and generating a road network topological structure; determining a shortest path matrix based on the road network topological structure, generating an importance score in combination with a graph theory algorithm, and comparing the importance score with a preset score threshold; carrying out simulation evolution based on a comparison result, generating a propagation coefficient and an aggregation coefficient of the node, and obtaining a transmission influence value; acquiring spatial load data, and outputting a site selection scheme set in combination with a genetic algorithm; obtaining road network structure data of the scheme set, and determining a preliminary ranking; acquiring data of the ranking scheme to determine a to-be-optimized scheme, and updating by using the prediction model; and calculating a time expectation value based on the updated data, and outputting a final site selection scheme by combining a preset time threshold value for judgment. According to the method, the road network integrity and the dynamic association effect are quantitatively evaluated through big data analysis, and global optimization of charging pile site selection is realized.

The invention provides a construction method for load decomposition and transmission of a special-shaped beam curved template, and belongs to the technical field of building construction.The load change of each node of the curved template is monitored in real time by establishing a load jump identification matrix, and a supporting system abutting stability matrix is constructed to evaluate the bearing capacity of each abutting point; a graph theory shortest path algorithm is utilized to optimize a load transmission path and form a fluctuation evaluation vector, a prestressed reinforcement tension stability control matrix is constructed to realize symmetrical batch tension, and support system parameters and a tension program are adjusted in real time through a load transmission dynamic balance equation set. And a load transmission effect evaluation vector is established to perform continuity and controllability evaluation on an overall transmission path, and when the transmission efficiency is lower than a set value, the load distribution and path optimization program is executed again, so that the technical problem of instability of a support system caused by uncontrollability of the load transmission path in the construction process of the special-shaped beam curved template is solved.

The invention provides a deduction analysis method for underwater topography evolution, which belongs to the technical field of underwater topography evolution, and comprises the following steps: constructing a four-dimensional space-time topography grid and establishing a topography stability evaluation matrix by adopting a space-time Kriging interpolation optimization algorithm; the method comprises the following steps: extracting multi-scale topographic change characteristics by applying wavelet transform multi-resolution decomposition, establishing a topographic step change detection vector, designing a multi-coordinate transform composite matrix calculation mechanism to realize a hierarchical processing system, and establishing a topographic evolution path search algorithm based on a graph theory to construct a topographic state transition model. A terrain evolution energy minimization mechanism and a terrain abnormal state recognition matrix are established through a variational method, an optimal evolution path is selected according to a terrain evolution path evaluation vector to output a complete underwater terrain evolution deduction result, and the technical problem that the underwater terrain evolution process is difficult to accurately predict is solved.

The invention provides an unmanned aerial vehicle cluster networking secure communication method, which comprises the following steps: acquiring real-time position information of each node in an unmanned aerial vehicle cluster, and calculating a relative distance between the nodes in combination with a preset communication range threshold; based on the communicable node pair set, constructing a communication topological graph of the unmanned aerial vehicle cluster by adopting a network topology analysis method based on a graph theory, and identifying a possible local congestion area in the network; in a local congestion area, dynamically increasing the interval between the nodes by adjusting the flight path of part of the nodes, and reducing the influence of channel competition and multipath effect; if the node distance is greater than a preset stability threshold value, a relay node is introduced to optimize a communication link, and continuity and reliability of data transmission are ensured; a clustering analysis method in a machine learning algorithm is adopted to perform grouping management on unmanned aerial vehicle clusters, the global configuration of networking intervals is optimized, and the overall performance of the network is improved.

The present application relates to the technical field of computers, and discloses an image recognition method and device. The disclosed image recognition method comprises: recognizing an image to be recognized into first-type grids and second-type grids, wherein the pixels of the first-type grids are greater than a pixel threshold, and the pixels of the second-type grids are greater than the pixel threshold; on the basis of a preset rule, dividing an area consisting of the first-type grids into a plurality of rectangles, and determining adjacent edges of any two adjacent rectangles as gateways, wherein the gateways are used for determining whether a target object can enter a second rectangle from a first rectangle through the gateways between the first rectangle and the second rectangle; generating a graph theory model on the basis of the gateways, wherein the vertices of the graph theory model are the gateways; and on the basis of the graph theory model, a starting point, and an ending point, determining a target path in said image.

The invention discloses an overlying strata fracture evolution characterization method based on topology and graph theory, and belongs to the technical field of mine ground pressure and rock stratum control. The method comprises the steps of firstly obtaining an overlying strata fissure image and extracting a topological skeleton thereof; constructing a multi-scale filtering pure complex sequence, and extracting essential topology invariants such as a zero-dimensional Betti number beta 0 and a one-dimensional Betti number beta 1 by applying a continuous coherence theory; then, fusing fracture geometric attributes to construct a weighted topological graph model, and calculating node betweenness centrality and algebraic connectivity to analyze a network key path and overall robustness; and finally, on the basis of a dynamic evolution rule of topological invariants and graph theory indexes, a critical through criterion is constructed, and a compaction area, a gas migration area and a reservoir area are divided. According to the method, the limitation of a traditional geometric characterization method is broken through, the isolated fracture and the through network can be differentiated from topological essence robustness, the percolation critical state of integral communication of the fracture network is accurately captured, and a quantitative decision basis is provided for accurate prevention and control of gas disasters.

The embodiment of the invention provides a switch setting method and device for a power gate control circuit, electronic equipment and a medium, and the method comprises the steps: constructing graph theory node models corresponding to a plurality of switches in a one-to-one manner, and obtaining the time sequence feature information of each switch; obtaining time sequence characteristic information of a plurality of switches; based on an ant colony algorithm, determining a target connection path for connecting each node by taking the time sequence characteristic information of the plurality of switches as path cost; and determining a series connection sequence of the plurality of switches according to the target connection path. According to the embodiment of the invention, a graph theory path is efficiently solved through a bionic optimization algorithm, falling into a local optimal solution is avoided, power gating time sequence delay and voltage fluctuation are remarkably reduced, meanwhile, static power consumption is optimized, and an intelligent optimization scheme is provided for a complex power gating circuit.

The invention relates to the technical field of industrial automation control, and discloses an auxiliary control workshop control system based on a DCS, and the system comprises a process topological graph construction module which is used for mapping a physical workshop into a dynamic graph containing an equipment digital object in real time; the task analysis module is used for converting the advanced task instruction into a quantitative target state set on a graph; the dynamic path planning module is used for automatically searching and generating an optimal atomic operation instruction sequence for reaching a target state based on the real-time state of the map; and the instruction execution and transaction management module and the exception handling and secure rollback module are used for ensuring atomic execution of the instruction sequence and secure rollback during failure. According to the method, a process control problem is converted into a graph theory path planning problem, so that the control system has the capabilities of dynamically avoiding faults and autonomously deciding, and the automation level, the reliability and the safety of the operation of the auxiliary control system are remarkably improved.

This application discloses a method, apparatus, and device for generating a scalable set of effective paths, relating to the field of path planning. The method includes: creating a family of Dial rules for filtering effective paths; selecting a rule from the Dial rule family as a compression rule, and filtering road segments in the traffic network that satisfy the compression rule to form a subnetwork; using the maximum flow algorithm in graph theory to determine the minimum edge cut from the start point to the end point in the subnetwork; determining a set of preceding effective paths from the start point to the preceding nodes of the minimum edge cut that satisfy the rule of increasing distance from the start point; determining a set of subsequent effective paths from the subsequent nodes of the minimum edge cut to the end point that satisfy the rule of increasing distance from the end point; and combining the preceding effective paths, the minimum edge cut, and the subsequent effective paths from the set of subsequent effective paths to obtain the set of effective paths from the start point to the end point. This application allows control over the number of effective paths.

This invention discloses a multi-scale method for identifying and controlling the propagation paths of airworthiness risks for autonomous vessels. The method includes: hierarchically modeling multi-source airworthiness risk factors based on ontology to construct a structured knowledge graph; establishing logical relationships between risk factors using structural equation modeling and converting them into a Bayesian network; dynamically evaluating input vessel operation data and identifying multi-scale airworthiness risk propagation paths and key risk nodes using graph theory topology analysis; and finally, generating a hierarchical control strategy based on the identification results. This invention enables dynamic and probabilistic assessment of the initial and ongoing airworthiness of autonomous vessels, effectively identifying risk propagation mechanisms and key links, and providing support for the safe design, operation, and supervision of autonomous vessels.

The application discloses a two-dimensional full coverage path planning method for a mobile robot and related equipment, and belongs to the technical field of robot full coverage path planning. In a complex two-dimensional environment model, for example, a two-dimensional map in which irregular obstacles and concave-convex polygon obstacles exist, firstly, Maklink lines generated by Maklink graph theory can effectively divide the map into multiple sub-regions, which is helpful to simplify the path search problem and improve the search efficiency; then, the order in which the robot visits each sub-region is calculated, and the optimal path for the robot to switch between each sub-region is calculated; finally, the Boustrophedon path is used for "bow" shape traversal, which can ensure that the robot efficiently covers the entire sub-region, reduces the possibility of omission and repeated cleaning, and moves between sub-regions according to the optimal switching path and the visiting order, which is helpful to reduce the repeated path and invalid movement of the robot when traversing the sub-region.

The invention discloses a control method of a double-layer reconfigurable battery system considering path optimization, which comprises the following steps: establishing a battery mathematical model based on a Thevenin equivalent circuit, designing a double-layer reconfigurable topological structure consisting of a battery cluster layer and a single battery layer, and simultaneously collecting SOC and fault states in real time; according to the battery mathematical model and the double-layer reconfigurable topological structure, constructing a weighted directed graph model based on a graph theory; the weighted directed graph model is solved by introducing an algorithm, an optimal path from a source node to a sink node is obtained, and high-SOC monomer preferential discharge, energy loss minimization and rapid isolation of a fault unit are realized. According to the method, the flexibility of a double-layer topological structure and the advantages of multi-dimensional weight optimization are combined, the capacity utilization rate of the battery pack can be effectively improved, the SOC consistency is improved, the safety and reliability of the system are remarkably enhanced, and the method has wide application prospects in electric vehicles, energy storage power stations and other scenes.

The embodiment of the invention relates to a processing method and device for measuring the diameter of a fiber based on a scanning electron microscope graph. The method comprises the following steps: constructing and training a prediction model; receiving an SEM graph X0 of any fiber sample, and inputting the SEM graph X0 into the prediction model to obtain corresponding edge point and center point probability graphs; utilizing a graph theory algorithm to extract a unique path of each fiber according to the central point probability graph to obtain a plurality of fiber center lines; identifying the radius of each point of each center line in the positive and negative normal directions according to the edge point probability graph to obtain a corresponding radius sequence; performing center line diameter optimization on each radius sequence according to a sub-pixel refinement method driven by an energy function; performing abnormal diameter elimination based on the global statistical distribution characteristics of each diameter sequence; and performing fiber diameter visual marking on the X0 based on each fiber center line and the corresponding diameter sequence. According to the invention, the measurement precision and the measurement robustness of the fiber diameter can be improved.

The invention provides a smart park emergency command method, apparatus and device, and a storage medium. The method comprises the steps of obtaining temperature data and wind direction of an accident area in a park, and the congestion degree and length of each road section in a park road network; judging whether the accident area is an unworkable area based on the temperature data; when the accident area is judged to be an unworkable area, an optimal evacuation path is generated based on the wind direction, the congestion degree and length of each road section and a graph theory model constructed according to the park road network distribution condition, and in the graph theory model, each evacuation point and exit in the park road network are taken as nodes, and the safety coefficient of the road section between the nodes is taken as an edge weight; and the optimal evacuation path is pushed and displayed, so that emergency commanders can carry out emergency commanding. Through the method disclosed by the invention, the timeliness and safety of park emergency command can be improved.

The invention relates to the technical field of fault diagnosis, in particular to a fault diagnosis system and method based on building electromechanical equipment, and the system comprises a state sequence construction module which is based on a relay on-off signal, a controller mode position and a pressure sensor analog quantity which are collected from an air conditioning unit controller in real time. According to the method, the real-time state transition path is constructed and analyzed, the operation process of the building electromechanical equipment is abstracted into a path analysis problem in a graph theory, and fault diagnosis of an equipment control logic level is realized. According to the mode, the execution sequence of the equipment running program is directly monitored, logic faults caused by control instruction errors, sensor feedback abnormity and execution mechanism clamping stagnation can be captured by checking the legality of state transition and the rationality of the residence time, for example, full-load running is directly started by skipping a necessary preheating state, and the reliability of the equipment running program is improved. Or the staying time in the starting stage is too long.

The application discloses a kind of based on graph theory's unmanned plane formation control method, belong to graph theory relevant application technical field;Including S1, the parameter of initialization unmanned plane formation, simultaneously to the operation environment of unmanned plane formation is modeled;S2, construct based on graph theory's unmanned plane adaptive dynamic communication topology, establish the communication and cooperation between unmanned plane;S3, based on graph theory consistency algorithm generation unmanned plane formation control signal;S4, based on S3 unmanned plane formation control signal fusion virtual force model carries out unmanned plane formation path optimization and obstacle avoidance;S5, formation consistency verification and parameter adaptive adjustment are carried out;S6, whether to complete formation task is judged, after task completion, enter termination control process, the application adopts above-mentioned method, constructs the adaptive dynamic graph topology and dynamic weight matrix updating mechanism of adaptation unmanned plane flight characteristic, solves the problem of poor robustness in the existing based on graph theory's unmanned plane formation control method in topology fixed.

A method for, at least, forming a graph representation of physical samples and identifying clusters of the physical samples. The method includes obtaining a plurality of physical samples from one or more wells, where each sample is associated with spatial-temporal data, and determining geochemical data for each sample. The method further includes constructing a graph representation of the plurality of physical samples, where in the graph representation each sample is represented as a node and a presence of an edge between any two nodes is based on the spatial-temporal data of the plurality of physical samples. The method further includes determining a weight for every edge in the graph representation and processing the graph representation with a graph-based algorithm to determine one or more clusters. The method may further include determining a wellbore plan that comprises a planned wellbore path to penetrate a hydrocarbon reservoir based on the determined clusters.

The application relates to the technical field of smart parks, in particular to a smart park intelligent equipment interconnection management method and system, real-time state data and position coordinate data of equipment are collected through a sensor network, after sudden task requirements are classified, a dynamic relationship graph among the equipment is constructed by using a graph theory algorithm, a cooperation path is extracted and a high-risk path is marked; a cooperation priority sequence is generated based on a priority queue algorithm in combination with a response time weight and a task urgency, resource allocation is dynamically adjusted through position coordinate data to eliminate competition; a confusion index set is constructed by using execution feedback data, a dynamic relationship graph is updated in a closed loop, and an equipment interconnection management configuration is output after verification. The corresponding system comprises eight function modules, and realizes full-process automatic collaboration. The application solves the problems of weak dynamic adaptation, extensive resource scheduling and poor cooperation stability in the prior art, significantly improves equipment cooperation efficiency and resource utilization, and guarantees the reliability of park normal operation and emergency disposal.

The present invention belongs to the technical field of ground-based laser radar point cloud data processing, and specifically relates to a method for separating branches and leaves from single tree point clouds based on graph theory. The present invention is based on multi-station scanning single tree point cloud data acquired by ground-based laser radar, and sequentially undergoes graph construction, hierarchical clustering, initial branch extraction, and final branch extraction to establish a method for separating branches and leaves from single tree point clouds for distinguishing the branch and leaf components of single tree point clouds. The present invention makes full use of the shortest path information of the graph, does not rely on prior knowledge and machine learning, and is streamlined and efficient while ensuring classification accuracy. It provides a new idea for separating branches and leaves from single tree point clouds, and can be further applied to forest parameter extraction, smart forestry, vegetation radiation transmission modeling and other fields.