93 results about "Region analysis" patented technology

The invention relates to the technical field of remote sensing geological prediction, in particular to a slope support stability prediction method and system based on remote sensing data, and the method comprises the steps: obtaining a multispectral remote sensing image of a target slope region, and generating a vegetation mask through employing a normalized vegetation index; removing interference pixels of a vegetation coverage area in combination with morphological filtering and connected area analysis, then identifying support structure features through an improved edge detection algorithm, delimiting an influence area by adopting a region growing algorithm based on machine learning, inputting an area image into a convolutional neural network model, and obtaining an image of the support structure; a deformation probability graph is output by using a data enhancement technology and a weight optimization layer, finally, a threshold value is determined according to historical data, slope support stability categories are divided in combination with spatial neighborhood information and a voting mechanism, vegetation interference is effectively eliminated, a support structure is accurately recognized, prediction precision is improved, slope support stability can be accurately judged in time, and the method is suitable for popularization and application. And a reliable basis is provided for early warning and protection of slope disasters.

The invention relates to the technical field of twin models, in particular to a subway station flood prevention simulation method and system based on a three-dimensional model. According to the method, local important evaluation indexes are obtained through placename approximate analysis and concavity-convexity analysis of structures of point cloud data in a neighborhood space, and structural important evaluation indexes of single point cloud data are determined by combining and analyzing density distribution complexity in the neighborhood space; clustering the point cloud data and dividing the point cloud data into different regions; analyzing depth distribution of all the point cloud data in the regions; combining structural importance evaluation, determining an attention rate of each region, performing differential modeling and semantic processing to obtain a semantic three-dimensional model; and combining a hydrodynamic model to obtain a digital twinborn model. According to the method, differentiated three-dimensional modeling is carried out by evaluating the importance of each point cloud data in subway station flood prevention simulation, and flood prevention analysis is carried out more comprehensively and accurately by combining a digital twin model with a hydrodynamic model, so that the protection capability of subway flood prevention is improved.

The invention discloses an individual tree segmentation method based on machine learning, and particularly relates to the field of individual tree segmentation. The method comprises the following steps: respectively acquiring forest point cloud data through a ground scanner and an unmanned aerial vehicle, registering the forest point cloud data into a complete data set, preprocessing the point cloud data, extracting geometric, reflective and spatial distribution multi-dimensional features, and fusing the geometric, reflective and spatial distribution multi-dimensional features into a comprehensive feature vector; training a model by using a machine learning method based on the labeled data, taking the feature vector as input, and outputting whether the point belongs to a tree or not; predicting a point category by using the trained model, performing individual tree instance segmentation by using a connected component clustering and graph segmentation method through CRF post-processing optimization, constructing a 3D model and calculating key parameters; and finally, performing post-processing on a preliminary segmentation result, filtering noise by using connected region analysis, filling the deficiency by using a three-dimensional hole, optimizing a boundary based on graph segmentation, and optimizing a block seam by using an ICP (Inductively Coupled Plasma) algorithm.

The invention relates to the technical field of vehicle damage detection and identification based on computer vision, and discloses a vehicle damage detection and identification method based on computer vision. The method comprises the steps of image acquisition, polarization image acquisition, Stokes parameter calculation, polarization feature extraction, anomaly evaluation, connected region analysis and the like. A polarization statistical model is established by setting an image coordinate system, collecting a multi-angle polarization diagram and calculating the polarization degree and the polarization angle of each pixel and taking an artificially selected nondestructive area as a reference, so that anomaly measurement and adaptive threshold segmentation are performed on the pixels, and a structured vehicle damage detection result is output in combination with corrosion, expansion and connected domain analysis. Physical interpretability and detection precision are enhanced by using polarization characteristics, recesses or scratches can be accurately identified even in a vehicle body area with a smooth surface or complex reflection, a standardized report containing position information and abnormality is provided, and automation and accuracy of vehicle damage assessment are effectively improved.

The invention discloses a document proofreading system and method based on artificial intelligence, and relates to the technical field of natural language processing, and the method comprises the steps: analyzing a document, dividing semantic units, and obtaining a document with a context label based on context type library labeling; performing initial error detection by using the corresponding rule set, and comparing the format of the document and the text quality characteristics with a standard sample vector space to obtain an initial error set; constructing a defect conduction chain network, and locating root cause error nodes causing a plurality of secondary errors by tracing the defect conduction chain network; generating an intelligent proofreading report; receiving a new-version document revised by the user, comparing the new-version document with the original-version document, positioning a change area, and analyzing a quality difference of the change area on a related quality dimension; based on the quality difference, an incremental proofreading report is output, and the incremental proofreading report comprises newly introduced errors and unsolved root cause errors.

The invention discloses a chip aging test method based on thermal migration analysis. The method comprises the following steps: acquiring power consumption distribution data, material attribute data and manufacturing process data; discrete mapping and dynamic adjustment are carried out on the power consumption distribution data by adopting finite element network nodes to obtain an initial heat distribution diagram; processing the initial thermal distribution diagram based on a thermal imaging technology to generate a temperature mapping diagram of the surface of the chip; performing network division based on the temperature mapping graph, and generating a heat transfer path graph in combination with a gradient tracking algorithm; based on the heat transfer path diagram, screening a potential area through a preset temperature threshold value, and generating a potential heat distribution diagram through clustering analysis; performing microstructure analysis on the abnormal area according to the potential thermal distribution diagram to generate an abnormal analysis report; and solving high-temperature region distribution according to the manufacturing process data and the anomaly analysis report, and performing region analysis to generate a thermal identification report. According to the method, the problem that the heat transfer path cannot be accurately captured and the hot spot area cannot be identified under the non-destructive test can be solved.

The invention discloses a lung three-dimensional reconstruction method and system for intraoperative positioning, and the method comprises the steps: processing a lung CT image in a DICOM format through an improved lung parenchyma segmentation algorithm, precisely extracting a lung structure through a global threshold method, connected region analysis and mathematical morphology processing, and then processing a mask generated through segmentation through a real-time smooth interpolation method, and through a dynamic parameter adaptation technology, accurate matching of a segmentation result and a gray value range of modeling data is ensured. According to the method, the problems of artifacts, redundant surfaces and gray level jump of the lung parenchyma area caused by separation of segmentation and reconstruction in a traditional method are avoided, full-process automation from data reading and lung parenchyma segmentation to three-dimensional modeling and visualization is achieved, meanwhile, a user-friendly interaction interface is designed, and a convenient tool is provided for intraoperative navigation.

The invention provides an image processing method, device and equipment based on hardware perception and dynamic rarefaction, and relates to the technical field of image processing, and the method comprises the steps: inputting hardware operation state data into a preset PPO strategy network, so as to obtain the sparse rate of each convolution layer; reserving a specified number of channels as effective calculation channels; performing saliency region analysis on an input to-be-processed image to generate a pixel-level saliency map corresponding to the to-be-processed image; dividing the to-be-processed image into a key target area and a background area; allocating a first preset precision to the key target area for image processing, and allocating a second preset precision to the background area for image processing; according to the sparse rate of each convolutional layer, the first preset precision allocated to the key target region and the second preset precision allocated to the background region, collaborative image processing is carried out on the to-be-processed image; according to the invention, the large-scale landing capability and continuous optimization performance of the edge intelligent vision system can be improved.

The invention relates to the technical field of heat exchangers, and discloses a control method and system for a spiral wound tube type heat exchanger based on the Internet of Things. The method comprises the following steps: acquiring flow velocity distribution data in a pipe in real time through a multi-point sensor to form a first data set, performing regional analysis to obtain a flow velocity deviation value, evaluating heat exchange abnormality, positioning an abnormal position, and generating an abnormal region distribution map; a dynamic parameter adjustment scheme is calculated in combination with a heat exchange efficiency target, a first adjustment instruction set is generated, a second flow rate data set is obtained after execution, and the matching degree is evaluated through a fuzzy control algorithm; if the preset standard is not met, a second adjusting instruction set is generated in combination with working condition requirements, and finally an operation state report is output. The method has the following effects that the flow velocity distribution in the spiral wound tube type heat exchanger is accurately controlled, the problems of local overheating and uneven heat exchange are effectively solved, the heat exchange efficiency is improved, the purpose of balancing energy consumption is achieved, and stable operation of the system is guaranteed.

The application relates to the technical field of product copying, in particular to a product copying software system for three-dimensional model import and conversion, and discloses the following scheme: a primary three-dimensional model is generated by acquiring a main view image and a sub-view image, extracting a first characteristic parameter and a second characteristic parameter; target parameter adjustment is carried out based on the bidirectional mapping relationship between the target parameter and an inferred parameter, and a parameter combination is generated; the response coefficient of the inferred parameter is corrected through reverse deduction, a bidirectional correlation matrix is optimized, and the consistency of the target parameter and the inferred parameter is ensured. Through shadow area analysis and surface fitting technology of multi-view images, the problem of bottom area data loss is solved, and accurate three-dimensional reconstruction of the object surface and the bottom area is realized.

The invention relates to the technical field of image processing, in particular to a geochemical element layer distinguishing method and system.The method comprises the steps that a copper element layer is subjected to grid division, the copper element color concentration change rate of adjacent grid points is calculated, and the grid points exceeding a set change rate threshold value are marked as mutation areas; and analyzing the copper element content difference of adjacent grid points in the abrupt change area, marking boundary points, and obtaining the distribution information of the copper element boundary points. According to the method, the mutation region is accurately recognized by calculating the copper element concentration change rate, and the problem of boundary fuzziness caused by data sparsity is reduced. A connection mode is optimized based on boundary curvature change, boundary information is ensured to be continuous and complete, and space expression precision is improved. The sampling point density calculation is clear in high and low density areas, the interpolation calculation is optimized, and errors caused by non-uniform data are reduced. The color concentration gradient of the abrupt change area is analyzed, the interpolation mode is adjusted, element transition is smoother, and error accumulation is reduced.

The invention provides an end-to-end real-time analysis method for an endoscope image fluorescence brightness area based on double deep learning model joint training and a self-group iteration upgrading device. The end-to-end real-time analysis method comprises the following steps: acquiring an image of a biological tissue and processing the image by using a deep learning algorithm to obtain a training data set; sequentially constructing and training an image preprocessing deep learning model and an unsupervised image segmentation deep learning model based on the training data set; inputting image data acquired by the endoscope into an image preprocessing deep learning model to obtain a first output image; inputting the first output image into an unsupervised image segmentation deep learning model to obtain a second output fluorescence image; and carrying out brightness analysis on the second output fluorescence image, and visually outputting and storing the second output fluorescence image. The real-time performance and the accuracy of fluorescence region analysis can be improved. According to the self-group iteration upgrading device, model training iteration upgrading can be carried out in multiple modes, and the performance of the device is continuously improved.

The embodiment of the invention relates to the technical field of machine learning, in particular to a method and device for removing noisy points of a scanned document image, computing equipment and a storage medium. The method comprises the following steps: acquiring a scanned document image; performing preprocessing operation on the document image to obtain a preprocessed image; performing connected region analysis on the preprocessed image, for a connected region with the area smaller than a threshold value T, taking the gravity center of the connected region as the center, intercepting an image block on the preprocessed image, then inputting the image block into a classification model, and outputting the probability that the connected region is a noisy point as the output of the classification model; if the output value indicates that the connected region is a noisy point, removing the connected region from the image I; and finally, performing post-processing operation on the document image to obtain a processing result image of the noisy point removal method. According to the scheme, text-independent noisy points introduced in the scanning process can be removed, meanwhile, related contents such as texts and tables in the document image cannot be damaged, and the attractiveness of the document image and the performance of follow-up document analysis and recognition are improved.

The application discloses a kind of area energy storage configuration methods for improving power distribution network carrying capacity under source-load coupling scene.First, the source-load comprehensive carrying capacity coefficient calculation model of power distribution network area is constructed, for calculating the source-load comprehensive carrying capacity coefficient of each typical day of area;Then, the source-load comprehensive carrying capacity feasible region analysis model of power distribution network area is established, for calculating the source-load comprehensive carrying capacity feasible region area of area;Finally, based on the source-load comprehensive carrying capacity coefficient and source-load comprehensive carrying capacity feasible region area of each typical day of area, double-layer optimization model is constructed, and double-layer optimization model is solved using hierarchical solving method, and the optimal energy storage configuration scheme is obtained.The method considers source-load coupling phenomenon, the carrying capacity bottleneck of area is characterized by source-load comprehensive carrying capacity coefficient, the source-load comprehensive carrying capacity of area is quantitatively evaluated by source-load comprehensive carrying capacity feasible region area, and the problem that traditional method is not accurate for power distribution network carrying capacity evaluation is solved.

The invention relates to the technical field of low-frequency sonar systems, in particular to an active azimuth history graph suspected target prompting method based on image segmentation, which comprises the following steps: firstly, carrying out binarization processing on an active azimuth history graph through a maximum between-class variance method, then, carrying out morphological processing and connected region analysis on a binary image to realize 8 connected region marking, and finally, carrying out image segmentation on the image; secondly, calculating the area and the mass center of each connected region, filtering the region with the large area to obtain a discrete target region mask image, multiplying the discrete target region mask image with an original binary image to obtain a discrete target region image, and finally, carrying out BFS search on the mass center of each discrete target region to obtain a discrete target region image; and calculating the sum of the Euclidean distances between the active azimuth history graph and five nearest connected regions, marking the mass centers of five discrete target regions with the maximum Euclidean distance sum on the active azimuth history graph, and realizing isolated bright spot positioning, thereby realizing automatic prompting of suspected targets in the active azimuth history graph of the sonar system so as to reduce the difficulty of target identification of a worker.

The embodiment of the invention provides a pop-up window processing method and device and a storage medium. In the embodiment of the invention, based on a collaborative architecture of two AI models, pop-up window processing is divided into two stages of potential pop-up window area analysis and pop-up window feature recognition, a potential pop-up window area in a screen image is analyzed by using a first AI model, and a sub-image of the potential pop-up window area is cut out from the screen image; and performing multi-dimensional feature analysis and popup window feature identification based on the sub-images by using the second AI model, positioning position information of closing options according to the multi-dimensional feature analysis and the popup window feature identification, executing popup window closing operation based on the position information, cutting out the sub-images of potential popup window areas, converting global analysis into local analysis, reducing calculation overhead of irrelevant areas, and on the basis, improving the popup window closing efficiency. Model reasoning is used for analyzing the cut sub-images, the efficiency and accuracy of pop-up window detection and closing are effectively improved, then the probability that automatic testing is interrupted due to pop-up window interference is reduced, and the testing stability and continuity are improved.

The invention discloses an aerodynamic simulation analysis method and system based on thermodynamic coupling, and relates to the technical field of simulation analysis, and the method comprises the steps: calculating a sensitive index and an uncertain index of each reference parameter, and fully considering the characteristics of the reference parameters to accurately enhance the robustness for the description of a simulation model. According to the method, the geometric features of each region, the reference parameter features and the sensitive indexes of the reference parameters are counted to determine the corresponding required grid density of the region, and the grid densities of different regions of the geometric three-dimensional model are specifically set according to different features of the regions and the reference parameter features, so that the analysis and calculation requirements of different regions are met. According to the uncertain indexes of the reference parameters, the reference parameters in the simulation model are endowed with credibility, ship turbine equipment is subjected to simulation analysis through the simulation model, the calculation precision of different areas is reasonably distributed, and the complex and changeable working conditions of the equipment are met. The multi-physics coupling condition is effectively captured, and the accuracy and adaptability of simulation analysis are improved.

This invention relates to the field of marine engineering safety early warning and intelligent prediction, and in particular to a point-to-area short-term wave height prediction method and system for offshore construction early warning. The invention takes historical pattern wave height, historical reference monitoring wave height, and future pattern wave height of a measurement point as inputs. It constructs a short-term prediction model based on a Transformer encoder and introduces a joint loss function including absolute error, large value underestimation penalty, trend asymmetry, residual, and peak time terms to automatically output the future correction results for each measurement point. Then, based on the mapping relationship between the measurement point and the corresponding coverage area, the correction results of the measurement point are extended to the entire target area to form a corrected wave height field. Combined with construction thresholds, it automatically determines the levels of normal, attention, alert, and work stoppage. Without requiring continuous manual interpretation, it forms a complete closed loop from data acquisition, regional analysis, prediction, regional correction to graded early warning and result storage and push.

The invention discloses a power distribution cabinet operation state intelligent monitoring method and system, and belongs to the technical field of power distribution cabinet state monitoring, and the method comprises the steps: carrying out the real-time analysis of each power distribution cabinet needing to be subjected to state monitoring, determining a state target, needing to be subjected to timestamp alignment monitoring, of each power distribution cabinet, and marking the state target as a time monitoring target; performing real-time simulation analysis on the time monitoring target, determining an alignment optimization mode of the time monitoring target, and adjusting a corresponding timestamp alignment mode in the corresponding power distribution cabinet according to the alignment optimization mode; monitoring the power distribution cabinet in real time to obtain monitoring data; analyzing the monitoring data to obtain state analysis data of the power distribution cabinet; carrying out regional analysis on the state analysis data of the power distribution cabinet, obtaining the state analysis data in real time, carrying out regional influence evaluation on the state analysis data, and determining whether the state analysis data has a regional risk; and when the regional risk is judged to exist, carrying out regional risk early warning.

The present application relates to a kind of password algorithm artificial intelligence side channel analysis method based on dimension reduction and clustering, belong to information security cryptography field.First, the energy trace obtained is analyzed, to determine the area of the energy trace in which the execution of the decryption process is related to secret information operation.Analyze the energy trace of the key operation part, use the method based on sliding window gradient value to divide each operation, obtain energy trace segment.Combined with the implementation of cryptographic algorithm, the energy trace segment is analyzed, and the operation type is identified.Use principal component analysis on energy trace segment for dimension reduction, take the component corresponding to the expected dimension as the principal component of each operation.Combined with the characteristics of energy trace segment, the cluster number obtained by clustering is estimated.Use clustering algorithm to cluster the energy trace segment after dimension reduction, analyze the clustering result to determine the operation type represented by each cluster, obtain the operation type corresponding to the energy trace segment, finally obtain the secret index sequence, realize the efficient analysis of the side channel of cryptographic algorithm.

The invention provides a slow action generation method based on motion focus area analysis. The method comprises the following steps: determining a video of a slow action to be generated; detecting a motion focus area in the video, and grading the motion focus area; and for different grades of motion focus areas, different strategies are adopted to carry out motion modeling and differential interpolation processing, and a slow motion frame sequence is generated. According to the invention, through identification and grading processing of the motion focus area, high-precision calculation of the core motion object, simplified calculation of the secondary area and simplest processing of the static background, compared with a traditional scheme of uniform and dense calculation of the whole frame, the method has the advantages of high calculation complexity and lower calculation amount, and guarantees the visual effect of the core area.

The embodiment of the invention relates to the technical field of intelligent robots, in particular to an intelligent robot control method and device, equipment and a medium, and the method comprises the steps: collecting environment data covering N regions, mapping an environment image into a preset grid map, and obtaining an environment grid map comprising a plurality of grid units; based on the environment data and the environment grid map, space-time pollution potential energy fields of the N areas are constructed, and an environment state distribution map is obtained based on the space-time pollution potential energy fields; performing connected region analysis and threshold segmentation based on the environmental state distribution diagram, and identifying a target connected region with the highest pollution score as a first region; based on historical operation data of a first area and pollution potential energy distribution of the first area in the space-time pollution potential energy field, determining at least one operation route according to a first path search function; and controlling the intelligent robot to operate according to the operation route. According to the scheme, precise management and control of the intelligent robot are realized, and the operation efficiency of the intelligent robot is improved.

The invention discloses a distributed load early warning management method and system based on a power grid, relates to the technical field of power system automation, and solves the problem that the prior art neglects the priority state of each region during early warning, so that the early warning efficiency is high when a plurality of regions are subjected to data analysis at the same time. The technical problem of low early warning efficiency caused by the fact that an area in urgent need of early warning is not analyzed timely and effectively is solved. A regional analysis priority is generated according to regional power grid data; constructing a regional power grid topological graph; generating a regional prediction load according to the regional analysis priority and the regional power grid topological graph, and generating equipment adjustment parameters according to the regional prediction load; according to the method, the alarm signal is generated according to the regional prediction load, and the power grid data of each region is analyzed from multiple angles, so that important regions can be preferentially concerned during load early warning, and meanwhile, corresponding equipment parameters are dynamically adjusted according to the load prediction of each region, so that the data accuracy is improved during high-load early warning. And the early warning efficiency and accuracy are improved.

The invention discloses an intelligent stratum exploration and analysis system and method based on artificial intelligence, and relates to the technical field of stratum exploration and analysis, and the method comprises the steps: obtaining a stratum exploration record of a region in a current period, analyzing the deformation condition and the slope safety state of the stratum of the region, and evaluating the soil layer water content condition of the stratum of the region; analyzing a stratum abnormal risk in the region to obtain a target region; analyzing reference values of other areas on the target area in stratum exploration to obtain a reference area; acquiring historical natural disaster records of the reference area, acquiring climate forecast data of the target area in the current period, and evaluating the natural disaster occurrence risk of the target area to obtain a risk target area; the disaster condition of the risk target area is predicted to obtain disaster prediction data, and the disaster prediction data is subjected to information push through the platform, so that the accuracy of early warning and natural disaster risk assessment is improved, and the harm caused by natural disasters is reduced.

The present application relates to the technical field of bearing texture optimization, and particularly relates to a sliding bearing surface texture optimization method and system. The technical scheme of the present application comprises the following steps: obtaining a load curve of a load of a rotating shaft in a sliding bearing changing with running time and a rotating speed curve of a rotating speed changing with running time; determining characteristic working conditions of the sliding bearing in a main running cycle according to the load curve and the rotating speed curve; performing feasible region analysis on each texture parameter of the sliding bearing according to the characteristic working conditions; taking a numerical interval of each texture parameter as a friction performance prediction input of a BP neural network model, and combining a genetic algorithm to perform friction performance optimization in the numerical interval, so as to determine a parameter combination corresponding to optimal friction performance as target texture parameters of the sliding bearing. The technical scheme improves optimization efficiency and accuracy when performing global optimization on local texture of the sliding bearing.

The application discloses a sea ice image recognition analysis method and system based on YOLOv8, the method comprises the following steps: acquiring sea ice image or video stream data and carrying out pretreatment, the pretreatment comprises geometric correction and image enhancement; based on the pre-trained YOLOv8 model, the sea ice region of the pretreated sea ice image data is preliminarily detected, and the boundary box containing the sea ice is output; the region of interest is extracted based on the boundary box, the fusion algorithm of watershed segmentation combined with random forest classification is applied, and the pixel-level sea ice mask is generated; the pixel-level sea ice mask is post-processed, and the post-processing includes morphological operation and connected region analysis; according to the post-processed pixel-level sea ice mask, the sea ice coverage ratio is calculated, and the calculation result of the sea ice coverage ratio is dynamically displayed at the predetermined position of the user interface. The application realizes the full-process automation from image input to risk output, without the need for personnel to continuously monitor and prevent, thereby reducing the labor intensity and human error rate.

The invention relates to the technical field of image processing, can be applied to business scenes of financial science and technology, medical health and the like, and discloses an image classification method, device, equipment and medium based on connected region analysis, comprising the following steps: converting a to-be-classified image into a grayscale image, traversing adjacent pixel pairs in the grayscale image and calculating a grayscale difference value; comparing the gray difference value with a difference threshold value to generate a structural binary image, and forming a foreground area at a position where the gray difference value exceeds the difference threshold value in the structural binary image; and performing connected region analysis on the structural binary image, determining all connected regions in the foreground region, calculating the pixel proportion of the maximum connected region in the structural binary image, and comparing the proportion with a classification threshold to output the classification type of the image. According to the method, the structural binary image is generated through the structural difference value, the image area distribution characteristics are analyzed based on connectivity, and automatic classification of images with different structural characteristics can be realized without a training sample or a model reasoning process.

The invention discloses a virtual power plant distributed optimization and feasible region analysis method and system. The method comprises the following steps: establishing an interactive physical model of a virtual power plant and a power distribution network; based on an interactive physical model, relaxation decoupling is carried out on wide-area and neighborhood time coupling constraints caused by the state of charge of the energy storage system through a Lyapunov optimization theory, and a multi-period optimization problem of the virtual power plant is converted into a single-period optimization sub-problem; aiming at the single-period optimization sub-problem, adopting a particle swarm optimization algorithm HSIPSO improved based on a hybrid strategy and fusing the particle swarm optimization algorithm HSIPSO into an ADMM distributed optimization framework to form an ADMM-HSIPSO algorithm, and carrying out distributed solution on the single-period optimization sub-problem; converting a multi-period virtual power plant feasible region representation problem into a calculation problem of each scheduling period feasible region; a mathematical model of the feasible region of the virtual power plant is constructed, and an ADMM-HSIPSO algorithm is adopted for solving; the coordination and unification of the optimal distribution of the dispatching power of the power distribution network among the virtual power plants and the privacy protection in the virtual power plants are realized.

This invention discloses a three-dimensional nearest neighbor search method for multi-objective composite requirements based on GIS and Python, belonging to the field of geographic information systems and spatial data analysis technology. The method includes the following steps: extracting the geographic three-dimensional coordinates of the center points of multiple objectives; digitally processing the multi-objective composite requirements; delineating the analysis area and defining analysis units; constructing a regional analysis index system based on GIS; and implementing three-dimensional nearest neighbor search analysis based on Python to capture nearest points that meet the target requirements. Starting from digitized multi-objective composite requirements, this invention establishes a large-scale regional requirement analysis index system using GIS tools, and then performs efficient collaborative screening of multi-objective composite requirement conditions based on Python. This solves the technical problem that traditional methods cannot simultaneously handle attribute constraints and geometric distances, and is applicable to scenarios requiring spatial optimization decisions such as building site selection, path planning, and resource allocation.

The invention discloses a surrounding rock damage degree identification system based on machine vision, and the system comprises an image collection module which is used for collecting a surrounding rock surface image of a tunnel face; the image acquisition module is arranged and fixed on an acquisition site through a bracket; the intelligent processing module is connected with the image acquisition module and is used for receiving and processing the surrounding rock surface image, a built-in deep learning model, synchronously identifying surrounding rock cracks and a stratified rock stratum structure and performing regional analysis to output a rock mass crushing degree grading result; the display module is connected with the intelligent processing module and is used for displaying the surrounding rock surface image and the analysis result; and the power supply module supplies power to the image acquisition module, the intelligent processing module and the display module. According to the invention, on the basis of a dual-task collaborative learning mechanism of a unified deep learning model architecture, a multi-scale feature fusion and refined blindage information extraction technology and detection innovation device configuration, automatic, real-time and accurate recognition of surrounding rock information is realized, and support is provided for optimization of tunnel blasting parameters.