4536 results about "Data entry" patented technology

The invention relates to the technical field of stamping part detection, and discloses a stamping part size and defect synchronous detection method and system. The method comprises the steps that the multi-sensor measurement module is used for collecting line laser scanning morphology data, infrared thermal image strain data and structured light projection contour data of a stamping part; multi-sensor data registration is achieved through a feature point matching algorithm, and a three-dimensional space coordinate mapping relation is generated; calculating the thermal expansion compensation amount of the material in combination with a thermal deformation correction model; filtering the structured light projection contour data, and extracting key contour feature points and defect region boundaries; inputting the related data into a multi-source data fusion model to obtain a dimensional deviation and defect fusion detection result; based on this, a measurement path is updated through a dynamic path planning algorithm, and a synchronous detection scheme is output. The device can synchronously detect the size and defect of the stamping part, improves the detection precision and efficiency, achieves the quality grade classification, and is high in adaptability.

The invention relates to the technical field of subway train driving strategy optimization, and discloses a subway line real-time data driven DAS driving strategy optimization method, which comprises the following steps: acquiring multi-dimensional operation data including a train real-time position sequence, station passenger flow data and a trackside signal equipment state; extracting line operation characteristics through a convolution space-time encoder, generating a passenger flow fluctuation prediction map by using a time sequence decomposition algorithm, and performing characteristic fusion on the trackside signal equipment state to generate an equipment health degree evaluation matrix; inputting the multi-dimensional data into the driving strategy model to generate an initial driving instruction sequence, dividing operation control priorities through a regional clustering algorithm, and constructing a dynamic optimization strategy network in combination with a genetic algorithm to generate a final driving strategy scheme; and acquiring an execution state log in real time, and updating the strategy network through the abnormal decision detection model. According to the method, the dynamic optimization of the subway driving strategy is realized, and the operation safety, efficiency and comfort are improved.

The invention provides a deep learning-driven coastline change dynamic monitoring method, and belongs to the technical field of image understanding and recognizing.The deep learning-driven coastline change dynamic monitoring method comprises the steps that a time sequence attention matrix is formed by constructing a multi-source satellite data fusion network, and coastline form change features are extracted by applying a fourth-order time sequence convolutional neural network to construct a first fluctuation matrix; and performing dimension reduction processing by using a space-time attention mechanism to generate a second fluctuation matrix, and converting the second fluctuation matrix into a quantitative index through a fluctuation conversion matrix. The method comprises the steps of inputting data into a pre-trained CoastDynNet model to analyze a physical mechanism, performing fine adjustment by applying a coastline evolution optimization function, performing multi-scale decomposition by using a WaveletTempNet network to separate long and short term changes, and finally constructing a multi-model integration framework by using a Bayesian model averaging method to generate a comprehensive coastline dynamic evaluation report.

The invention discloses an intelligent regulation and control method and system for a photovoltaic energy storage air conditioner. The method comprises the steps that photovoltaic related data, energy storage related data and air conditioner operation related data are collected; inputting the photovoltaic related data into the photovoltaic power generation prediction model to obtain a photovoltaic power generation prediction result; inputting the air conditioner operation related data into the air conditioner load prediction model to obtain an air conditioner load prediction result; inputting the photovoltaic generating capacity prediction result, the air conditioning load prediction result, the energy storage related data and the photovoltaic related data into an energy storage optimization scheduling model to obtain an energy storage charging and discharging decision; constructing a power supply strategy core rule base based on the energy storage related data, the electricity price peak time period and output results of the photovoltaic power generation prediction model and the air conditioner load prediction model; and optimizing an output result of the energy storage optimization scheduling model based on the power supply strategy core rule base. The method has the outstanding advantages of high reliability, high photovoltaic utilization rate, low dependence degree on a power grid and the like.

The invention discloses a multi-scale semantic guidance image compression method and system and a storage medium, and the method comprises the following steps: obtaining input image data, carrying out the preprocessing of an input image, and obtaining standardized image data; inputting the standardized image data into a pre-trained semantic segmentation network to generate a multi-scale semantic feature map and a semantic weight map corresponding to the multi-scale semantic feature map; a three-stage pyramid encoder is constructed, and the standardized image data is subjected to the following steps of: sampling under depth separable convolution to generate multi-scale features; the reversible neural network carries out nonlinear transformation on the multi-scale features; the multi-scale feature subjected to nonlinear transformation is decomposed into a low-frequency sub-band and a high-frequency sub-band through adaptive discrete wavelet transformation, dynamic selective state space modeling is executed on the high-frequency sub-band based on a semantic weight map, and a compressed code stream is generated; and inputting the compressed code stream into a decoder, decoding based on a lightweight Mama module, and reconstructing an image in combination with inverse wavelet transform and a semantic weight map.

The invention relates to the technical field of breeding planning, in particular to an intelligent breeding planning and decision-making method and system based on a large model. The method comprises the following steps: acquiring a multi-source breeding data set; constructing a structured breeding knowledge graph based on the multi-source breeding data set; performing breeding data association on the structured breeding knowledge graph according to a preset large model to generate a special breeding basic model; obtaining a breeding instruction input by a user; performing user semantic recognition on a breeding instruction input by a user to generate breeding semantic recognition data; inputting the breeding semantic recognition data into a breeding special basic model for breeding intention analysis, and generating user breeding intention data; and determining data information needing to be called based on the breeding intention data of the user, analyzing and screening to generate germplasm resource screening data and a breeding plan / breeding decision scheme. According to the method, the intelligence and operability of breeding planning are improved through integration of multi-source data, intelligent semantic recognition, combined genetic analysis and executable evaluation.

The invention discloses an intelligent emergency and management and control method for a stadium, and belongs to the technical field of stadium safety management and control. According to the method, video stream data are collected through a monitoring camera array, and coverage areas of all cameras in the array have 15%-20% of overlapping areas; inputting the data into a pre-trained people density identification model to generate a real-time people flow distribution thermodynamic diagram; the retention index of each partition is calculated, and an emergency evacuation mode is activated in combination with a preset safety threshold value; in the emergency mode, the infrared sensor group monitors the instantaneous pedestrian flow speed, and an optimal evacuation path is generated by a dynamic path planning algorithm; the path is converted into a control instruction to drive an electromagnetic access control gate, emergency lighting and an electronic guide identifier, feedback data triggers a path re-calculation mechanism, and a two-dimensional code scanning device counts the number of evacuated people so as to start manual re-checking. Real-time situation awareness, dynamic risk assessment and intelligent evacuation guidance of the stadium are achieved, emergency response and evacuation efficiency is effectively improved, and crowd safety is guaranteed.

The invention provides an enterprise intelligent diagnosis method, system and device based on a large model and a medium, and belongs to the technical field of enterprise diagnos.The method comprises the steps that enterprise heterogeneous data are collected through a multi-source data interface, cleaning, feature extraction and cross-modal alignment fusion are carried out, and enterprise real-time data are obtained; constructing a knowledge graph through a graph attention network on the basis of an industry index to which an enterprise belongs, and updating association weights among nodes at regular time; inputting enterprise real-time data into the pre-trained multi-modal large model for preliminary analysis, and outputting a risk thermodynamic diagram; key abnormal indexes are identified from the risk thermodynamic diagram, sub-graphs related to the key abnormal indexes are extracted from the knowledge graph, structured prompt words are generated from the sub-graphs, then the structured prompt words and standardized enterprise real-time data are jointly input into a multi-modal large model for joint reasoning analysis, and then a visual diagnosis report is generated. Accurate identification and intelligent diagnosis of enterprise risks are realized, and decision-making efficiency is improved.

The invention provides an AI-based smart old-age care service method, system and device, and a storage medium, and relates to the technical field of smart old-age care. The method comprises the following steps: collecting vital sign data, behavior data and environment data of the elderly, and carrying out standardization processing on past case data to obtain standard case data; performing management fusion on the standard case data, the vital sign data, the behavior data and the environment data to obtain multi-dimensional health data; inputting the multi-dimensional health data into a preset health state evaluation model to obtain health state information; matching the health state information with maintenance knowledge in a preset knowledge base to obtain a plurality of alternative maintenance schemes, and inputting the plurality of alternative maintenance schemes into a preset maintenance effect prediction model to obtain a plurality of maintenance effect prediction results; and taking the alternative maintenance scheme with the highest evaluation score as a target maintenance scheme. Through the alternative scheme, the effect of the pension service is improved.

The invention discloses a server health state diagnosis method based on a GAT-LP algorithm, and relates to the technical field of server health diagnosis, and the method comprises the steps: collecting multi-dimensional operation state data of a server, transmitting the multi-dimensional operation state data to a data analysis platform, and carrying out the preprocessing, inputting the preprocessed historical operation state data of the server into a GAT-LP network for training to obtain a GAT-LP network model, evaluating health conditions of the server and the process and generating an overall health condition according to a health state diagnosis result of the server and health score features extracted based on the GAT-LP network model, converting an evaluation result into a visual health state, and displaying the visual health state in the GAT-LP network model. And triggering an alarm mechanism when the health state of the server is lower than a preset threshold value. By constructing a multi-dimensional health assessment index system, the running state of the server is visually displayed, potential risks are found in advance, and prevention measures are made.

The invention provides a wafer edge defect detection method and system based on image recognition and a storage medium, and belongs to the technical field of semiconductor manufacturing, and the method comprises the steps: processing annular image data, and obtaining target image data; inputting the target image data into the edge defect prediction model to obtain a defect probability distribution diagram; based on the defect probability distribution diagram, identifying a pixel region with a probability value greater than or equal to a preset threshold value as a candidate defect region; performing feature extraction on the candidate defect region to obtain a target feature vector; inputting the target feature vector into a defect classification model, and determining the defect type and classification confidence of the candidate defect region; based on the defect type and / or the classification confidence, screening out a target defect area from the candidate defect areas; obtaining three-dimensional point cloud data of the target defect area, and calculating three-dimensional geometric parameters of the target defect area based on the three-dimensional point cloud data; and determining a detection result of the target wafer based on the defect type and the three-dimensional geometric parameters.

The invention relates to a cardiovascular disease risk prediction system, which comprises a user terminal module, an edge computing module, a cloud intelligent module, an application service module and a system support module, wherein the user terminal module comprises an intelligent sensing equipment cluster unit and a mobile terminal data entry unit; and the intelligent sensing equipment cluster unit adopts a millimeter wave radar-PPG fusion sensor, monitors subcutaneous 0.5 mm depth arterial vibration through a 60GHz radar array, is aligned with a photoplethysmogram signal in a space-time manner, and performs user data acquisition based on a surface plasma resonance chip. According to the cardiovascular disease risk prediction method and system, real-time signal processing is realized by adopting JetsonAGX through a heterogeneous calculation architecture, medical image accelerated calculation is performed by using NVIDIAClara, non-out-of-domain joint modeling of data of hospitals is supported through federal learning, privacy protection reasoning based on homomorphic encryption is realized, and full-process closed-loop management is realized by adopting a layered modular architecture. And the accuracy of cardiovascular disease risk prediction is improved.

The invention relates to the technical field of computer security, in particular to a security isolation method for an edge computing node of the Internet of Things, which comprises the following steps of: identifying a trust domain in the edge computing node of the Internet of Things, defining a sensitive data source, and generating a sensitive data identifier set, and based on the sensitive data identifier set, planning minimum central processing unit time and maximum memory bandwidth for each isolation domain to form an isolation domain resource limit, and establishing initial security isolation configuration. According to the method, the identification mechanism based on the sensitive data identification set is introduced into the edge computing node of the Internet of Things, the definition of the trust domain can be realized, and the resource limit is constructed in combination with the minimum central processing unit time and the maximum memory bandwidth of each isolation domain, so that the basic distribution mode of computing resources is restrained, and the computing efficiency is improved. And resources are prevented from being occupied by high-frequency low-priority tasks. After a data entry is positioned on a system level and stain marks are applied according to sensitive attributes, sensitive data images have identifiable features on a memory level.

The embodiment of the invention provides a medical record generation model training method, a medical record generation method and related equipment. The method comprises the steps of obtaining multiple pieces of doctor-patient dialogue sample data and corresponding medical record labels; the dialogue score of each piece of doctor-patient dialogue sample data is calculated, target doctor-patient dialogue sample data is selected from the multiple pieces of doctor-patient dialogue sample data based on the dialogue scores, and a medical record label corresponding to the target doctor-patient dialogue sample data is a target medical record label; performing cooperative training on the initial medical record generation model based on the multiple pieces of language specification capability sample data to obtain a medical record generation model; inputting the target doctor-patient dialogue sample data into a medical record generation model one by one for data prediction processing to obtain a predicted medical record; and updating the medical record generation model based on the predicted medical record and the loss value of the target medical record label, the updated medical record generation model being used for performing medical record generation based on the doctor-patient dialogue data, and improving the accuracy and reliability of the generated medical record when generating the medical record according to the actual doctor-patient dialogue data.

The invention provides an ocean subsurface thermohaline reconstruction method based on multi-scale spatial-temporal feature fusion, and solves the technical problem of poor thermohaline reconstruction precision caused by incapability of capturing deep-level spatial-temporal dependence in ocean data in the prior art. The method comprises the steps of obtaining an ocean temperature-salinity anomaly feature data set, performing preprocessing to obtain time sequence data and space sequence data, inputting a multi-scale spatial-temporal feature fusion network model to perform feature fusion to obtain a temperature-salinity anomaly value, performing reverse normalization, and superposing a climate average value to obtain a temperature-salinity reconstruction result; the multi-scale spatio-temporal feature fusion network model comprises a spatial feature extraction branch, a temporal feature extraction branch and a spatio-temporal feature fusion module. The method can be widely applied to the technical field of marine science.

The invention discloses a thermal load prediction method based on iTransform, and belongs to the technical field of heat supply system thermal load prediction, and the method comprises the steps: collecting historical meteorological data and corresponding thermal load data, and constructing a thermal load data set; constructing an iTransform-based network model, and performing learnable adversarial attack training on the network model by using the thermal load data set to obtain a thermal load prediction model; inputting the meteorological data of the prediction area into the thermal load prediction model, and outputting a corresponding thermal load prediction result; according to the method, thermal load prediction is realized by constructing the iTransform-based network model, prediction errors caused by label correlation are eliminated, and the robustness of the provided model is improved through a learnable adversarial attack training method.

The invention discloses a forest-town junction region fire dynamic early warning method based on multi-source data assimilation, and the method comprises the following steps: inputting collected multi-source observation data into a fire risk prediction model for training, and outputting a fire risk grid map covering the whole forest-town junction region for monitoring a high-risk building group; constructing a fire spreading numerical model covering multi-material, multi-scale and multi-physical mechanism coupling; a fire propagation characteristic quantitative model is constructed, and the building heat influence is evaluated; and constructing a data assimilation and fire dynamic prediction model, and dynamically predicting and outputting fire spreading parameters and a spreading trend chart. According to the method, a forest-building-oriented complex scene is constructed, and propagation behaviors of flames under multiple mechanisms of convection, radiation and conduction are effectively described; through the modes of risk identification, dynamic simulation, data assimilation, visual early warning and the like, the precision, response speed and engineering applicability of forest-town boundary region fire prediction are remarkably improved.

The invention discloses a regional water supply emergency scheduling method and system. The method comprises the following steps: fusing GIS and IoT data to construct a dynamic three-dimensional topology model; historical water consumption and meteorological data are decomposed through wavelet multi-scale decomposition, and a prediction model is input to obtain a water consumption prediction value of a scheduling day period; on the basis of reservoir water storage, flow, water quality, rainfall and pollution source data collected in real time, a flow-water quality coupling model is used for predicting the reservoir inflow and water quality of a dispatching day; the method comprises the following steps: establishing a multi-objective function by combining water consumption prediction, storage prediction and current water storage, embedding a water quality constrained multi-objective optimization model, and solving by adopting an NSGA-II algorithm to obtain a Pareto optimal scheduling scheme set; and finally, a scheme is selected to be issued and executed. According to the method, data-physical collaborative intelligent scheduling decision is realized, the water supply demand is met under the condition that the water supply quality is stable, the condition of water shortage of the user terminal is avoided, and the water quality of the user terminal can continuously reach the standard.

The invention provides a multi-source data management method based on machine learning and a related device, and the method comprises the steps: obtaining a multi-source data set in an emergency command rescue scene, carrying out the data preprocessing of the multi-source data set, obtaining a standardized data set with a unified data form, extracting a data element information set from the standardized data set, and carrying out the processing of the data element information set. And calling a pre-trained blood relationship modeling model to perform association analysis processing on the data element information set, generating a blood relationship description set among the data entries in the standardized data set, and generating a data blood relationship tracking result based on the blood relationship description set. The data consanguinity tracking result comprises a historical record of the full life cycle of the data and cross-data entry dependency graph information. According to the invention, the method can provide a governance support with a data source capable of being checked, a processing process capable of being traced and a clear dependency relationship for emergency command rescue, enables a rescue decision to be developed based on reliable data consanguinity information, and effectively improves the support capability of data governance for the rescue decision.

The invention discloses a bearing degradation trend prediction method and system based on multi-domain feature dynamic fusion and dimensionality reduction, and the method comprises the steps: collecting full-life vibration signals of a bearing, synchronously marking three stages of health, degradation and fault, constructing multi-dimensional features such as a time domain, a multi-scale frequency domain, a time-frequency domain, and the like; evaluating the cross-stage difference of the features by using double criteria of mahalanobis distance and information entropy, and adaptively adjusting the weight to complete optimization; threshold cutting, linear proportion, Softmax or hierarchical weighting strategy empowerment are automatically selected according to data distribution, and energy is reserved through PCA for dimension reduction. And a TCN-GRU deep network model is constructed. Real-time data are input into the model to predict the degradation state, if errors exceed the limit, feature reconstruction and model retraining are triggered, and full-life-cycle high-precision high-robustness multi-stage continuous online monitoring is achieved. The method aims at solving the problems that the diagnosis precision is limited and the working condition adaptability is insufficient due to the fact that single time domain or frequency domain features are excessively depended and the features of each stage of fault evolution are difficult to comprehensively characterize.

Provided is a method for perceiving and eliminating an abnormal state of active distribution network based on data enhancement, including: acquiring, by synchrophasor measurement device, data of each node of active distribution network in target domain in real-time and transmitting to processor; inputting the acquired data into a classification model, and outputting abnormal detection and classification results in real time; and analyzing the abnormal detection and classification results, and transmitting an abnormal state eliminating instruction to a distribution terminal to eliminate the abnormal state. Wherein, hidden distribution features in node data of active distribution network are mined through dynamic clustering, a large amount of unlabeled data are clustered, a data label is generated through self-coding and label correction rule, training samples with balanced category distribution is generated through data enhancement and is used to train the classification model based on dynamic graph attention network by domain adaption method.

The invention relates to a short-time heavy rainfall region collaborative early warning method based on multi-source fusion data. The method comprises the following steps: firstly, acquiring multi-source heterogeneous data of a ground rainfall station, a radar, a satellite and the like, and converting the multi-source heterogeneous data into a rainfall monitoring data set by adopting multi-scale interpolation and standardization processing; secondly, preprocessing the data set to extract precipitation space features, and combining wind field and air pressure field data to input a time sequence prediction model to generate a precipitation path prediction sequence; and then, processing the prediction sequence by using a graph structure segmentation algorithm, and generating a high-precision early warning region boundary sequence. And finally, carrying out space overlapping degree calculation on the early warning region boundary sequence and a historical disaster region, and when a preset threshold value is exceeded, comprehensively analyzing parameters such as a disaster type and an influence range by adopting a probability model to generate a graded early warning sequence. By adopting the method, the integrity and accuracy of the rainfall monitoring data set can be improved, and the timeliness and reliability of short-time heavy rainfall early warning can be effectively improved.

The invention provides a rusted reinforced concrete crack detection method and device based on YOLOV11, and belongs to the technical field of image processing. The method comprises the following steps: acquiring crack image data of a corroded reinforced concrete member, and marking the image data; combining the labeled image data with labels to form a data set; constructing a YOLOV11 cross-view comparison model, wherein the model comprises a backbone network, a neck network and a head network; the YOLOV11 cross-view comparison model is trained, and an optimal model is obtained; and acquiring crack video data of a to-be-detected rusted reinforced concrete member, inputting the crack video data into the DVTFVS module for image stabilization processing, transmitting a video into the YOLOV11 cross-view comparison model for crack detection, and outputting position, size and category information of the crack. According to the invention, the efficiency and the accuracy of corrosion reinforced concrete crack detection are ensured.

The invention relates to the technical field of industrial automatic detection and computer vision, in particular to a complex workpiece high-precision defect detection method based on a dynamic light source and multi-dimensional detection, which comprises the following steps: performing multi-dimensional data acquisition on a complex workpiece by using high-precision laser scanning equipment; working parameters of the workpiece are adjusted according to characteristics of the workpiece and environmental changes, and the image acquisition process is optimized; performing data preprocessing on three-dimensional coordinate data obtained by laser scanning and texture information obtained by structured light projection; respectively extracting geometric features, texture features and depth defect features of the workpiece from the preprocessed data; acquiring sample data from the database, selecting and optimizing a proper deep learning model, training the model by using the sample data, and constructing a defect detection model; and inputting the data subjected to preprocessing and feature extraction into a defect detection model, and detecting the defect degree of the workpiece.

The invention relates to the technical field of ecological environment monitoring, and discloses a coastal wetland intelligent monitoring method and system based on artificial intelligence, and the method comprises the steps: collecting unmanned plane data, satellite remote sensing data, Internet of Things sensor data and water quality monitoring buoy data of a coastal wetland; the method comprises the following steps: processing satellite remote sensing data by adopting a wavelet threshold denoising algorithm based on an attention mechanism, calibrating Internet of Things sensor data by adopting an LSTM network, and carrying out data space-time alignment based on a space-time attention fusion model to obtain preprocessed data; inputting the preprocessed data into a Transform-ResNet hybrid model to carry out environmental change evaluation, and outputting an ecological health index; when the predicted ecological health index is lower than a threshold value, a PPO algorithm is adopted to dynamically adjust a monitoring strategy according to the early warning level, and an early warning report is pushed; the whole process is intelligent, manual intervention is greatly reduced, and support is provided for coastal wetland ecological protection.

The invention relates to a high-resolution remote sensing image target detection method based on improved YOLOv8s, and belongs to the field of remote sensing image and target detection. The method comprises the following steps: firstly, acquiring high-resolution satellite optical remote sensing map data, and preprocessing the data; the preprocessed data are input into a backbone network of an improved YOLOv8s model for feature extraction, and multi-scale feature extraction is carried out through a plurality of C2f-PD modules based on PConv and DSConv; the multi-scale features are input into the neck network of the improved model for feature fusion, and a double-input single-output enhancement fusion module based on space attention is adopted to enhance the fusion degree between high-layer features and low-layer features; and inputting the fusion features into a head network of the improved model to carry out target detection, and carrying out target detection by adopting a PConv-based lightweight detection head. The method can improve the detection precision, reduces the calculation amount, and is excellent in performance.

The invention discloses a traffic question and answer method, device and equipment based on a large language model, and a medium. A traffic safety knowledge graph is constructed in advance. After the question text is divided into a plurality of sub-question texts, for the plurality of sub-question texts, determining a target entity with the highest similarity corresponding to the sub-question texts in the traffic safety knowledge graph; and determining a target sub-graph having a first-order relationship with the target entity. And for the multiple sub-question texts, inputting the sub-question texts, the entities and relationships in the corresponding target sub-graphs and the traffic long text data into a large language model, and determining sub-answer texts corresponding to the sub-question texts based on the large language model. And finally, inputting the question text, the plurality of sub-question texts and the corresponding sub-answer texts into a large language model, and determining a target answer text corresponding to the question text based on the large language model. And the accuracy of the determined target answer text is ensured.

The invention provides an identity authentication and access control method and device for a low-altitude aircraft, and the method comprises the steps: obtaining environment data, equipment state data and a historical authentication log of the low-altitude aircraft, and obtaining collection data; inputting the collected data into an AI decision engine, and generating an authentication factor combination through a pre-trained deep reinforcement learning model to obtain a main factor and a standby factor; performing identity authentication of the aircraft by using the main factor, and when the matching degree of the identity authentication of the main factor is in a preset interval, triggering a standby factor to perform secondary identity authentication to obtain an authentication result; and an access token is generated according to the authentication result and the risk assessment model, and the aircraft performs access control according to the access token. The invention relates to the field of low-altitude security management and control, and solves the technical problems that the identity authentication security of a low-altitude aircraft is insufficient and the low-altitude aircraft cannot dynamically adapt to a complex airspace environment in the prior art.

The invention provides a power transmission line pollution flashover prediction method and system based on meteorological parameters and a random forest algorithm, and the method comprises the steps: collecting meteorological data around a power transmission line in real time, and building a pollution flashover prediction model in combination with historical pollution flashover data; and performing feature extraction and modeling on the acquired data by adopting a random forest algorithm, constructing a classification tree, integrating prediction results of a plurality of decision trees, and generating pollution flashover risk probability prediction through majority voting. The model is deployed on a cloud or a local server, receives meteorological data input in real time, dynamically outputs pollution flashover probability and risk level, and performs visual display through an upper computer and a cloud platform. And when the predicted risk exceeds a set threshold value, the system triggers an early warning mechanism and sends early warning information to operation and maintenance personnel to assist in formulating preventive maintenance measures. According to the method, the accuracy and the real-time performance of pollution flashover prediction are effectively improved, the operation risk caused by the pollution flashover fault of the power transmission line is remarkably reduced, and the method has relatively high application value and popularization prospect.

The embodiment of the invention provides a hail identification and prediction method based on multi-source meteorological data fusion and an attention mechanism. The method is applied to the technical field of meteorology and artificial intelligence processing, and comprises the following steps: collecting dual-polarization radar data, satellite remote sensing data and ground meteorological observation data, and carrying out time sequence alignment, data standardization and feature splicing processing; extracting physical mechanism features and statistical texture features of hail clouds from the dual-polarization radar data, the satellite remote sensing data and the ground meteorological observation data; extracting multiple spatio-temporal features of the hail cloud by using a spatio-temporal feature extraction network; and inputting real-time observation data into the trained spatial-temporal feature extraction network, and outputting a hail occurrence probability, a nuclear region position and intensity grade distribution. In this way, the technical problems that in the prior art, multi-modal data noise, inconsistency and insufficient time-space feature capture are caused, and the precision and real-time performance of hail recognition are limited can be solved.