Land space path intelligent management method and system based on big data analysis

Abstract

The invention relates to the technical field of geographic information management, in particular to a land space path intelligent management method and system based on big data analysis. The method comprises the following steps: obtaining a target territorial geographic space model, carrying out geographic scientific information collection, carrying out disaster rescue path estimation, and generating a disaster response rescue first estimation management path; a corresponding disaster response geographical environment change constraint is obtained and rescue path environment constraint optimization is carried out to generate a disaster response rescue second pre-estimation management path, path deviation measurement is carried out to obtain disaster response rescue pre-estimation path deviation, and if the disaster response rescue pre-estimation path deviation is smaller than a preset path deviation threshold value, the disaster response rescue second pre-estimation management path is obtained. If so, carrying out rescue intervention intelligent management; and if the disaster response emergency rescue estimated path deviation is greater than or equal to a preset path deviation threshold value, performing path deviation punishment calculation and emergency rescue path optimization management. According to the invention, the management efficiency and analysis depth of disaster rescue paths can be improved.

Description

Technical Field

[0001] The present invention relates to the field of geographic information management technology, and in particular to a national land space path intelligent management method and system based on big data analysis. Background Art

[0002] With the rapid development of big data technology, big data analysis methods have gradually been introduced into the field of disaster management, aiming to improve the response speed of post-disaster rescue and the accuracy of path planning. Big data analysis can accurately grasp the geographical environment, traffic conditions and disaster impact range of the post-disaster area by collecting multi-dimensional data from satellite remote sensing, drone aerial photography, sensor networks, traffic monitoring, etc. in real time, thereby providing richer information support for path planning. However, the existing path planning methods based on big data have certain bottlenecks when processing massive spatial data. For example, there are problems of low data integration and insufficient real-time processing capabilities, which to a certain extent affect the disaster prediction efficiency of geographic information and cannot quickly provide the optimal rescue route after a disaster occurs, thereby reducing the management efficiency of the rescue route. Summary of the invention

[0003] Based on this, it is necessary for the present invention to provide a method and system for intelligent management of national space paths based on big data analysis to solve at least one of the above-mentioned technical problems.

[0004] To achieve the above purpose, a land space path intelligent management method based on big data analysis includes the following steps:

[0005] Step S1: Obtain the target national territory geospatial model, and use geographic information collection equipment to collect geographic science information on the corresponding disaster response geospatial blocks in the target national territory geospatial model to obtain a target disaster response geospatial information big data set, including the target geospatial location distribution, land use data, traffic flow data and environmental monitoring data corresponding to the disaster response geospatial blocks; transmit the target disaster response geospatial information big data set to the big data processing platform in real time through the big data transmission network;

[0006] Step S2: Based on the land use data and traffic flow data corresponding to the disaster response geographic space block, a big data processing platform is used to estimate the disaster rescue path for the corresponding target geographic space location distribution to generate a first estimated management path for disaster response rescue;

[0007] Step S3: Obtain the corresponding disaster response geographic environment change constraints through the environmental monitoring data corresponding to the disaster response geographic space block, and optimize the rescue path environmental constraints of the first disaster response rescue estimate management path based on the disaster response geographic environment change constraints to generate a second disaster response rescue estimate management path; measure the path deviation according to the first disaster response rescue estimate management path and the second disaster response rescue estimate management path to obtain the disaster response rescue estimate path deviation;

[0008] Step S4: Compare and judge the disaster response and rescue estimated path deviation according to a preset path deviation threshold. If the disaster response and rescue estimated path deviation is less than the preset path deviation threshold, the disaster response and rescue second estimated management path is used to perform intelligent management of rescue intervention for the disaster response geographic space block; if the disaster response and rescue estimated path deviation is greater than or equal to the preset path deviation threshold, the disaster response and rescue first estimated management path and the disaster response and rescue second estimated management path are calculated based on the disaster response and rescue estimated path deviation to obtain the disaster response and rescue estimated path deviation penalty; based on the disaster response and rescue estimated path deviation penalty and the disaster response and rescue second estimated management path, the disaster response geographic space block is optimized for rescue path management.

[0009] Furthermore, the present invention also provides a land space path intelligent management system based on big data analysis, which is used to execute the land space path intelligent management method based on big data analysis as described above, and the land space path intelligent management system based on big data analysis includes:

[0010] The target block geographic science information collection module is used to obtain the target land geospatial model, and use the geographic information collection equipment to collect geographic science information on the corresponding disaster response geospatial block in the target land geospatial model, so as to obtain a target disaster response geospatial information big data set, including the target geospatial location distribution, land use data, traffic flow data and environmental monitoring data corresponding to the disaster response geospatial block; the target disaster response geospatial information big data set is transmitted to the big data processing platform in real time through the big data transmission network;

[0011] The first disaster rescue path estimation module is used to estimate the disaster rescue path based on the land use data and traffic flow data corresponding to the disaster response geospatial block using the big data processing platform for the corresponding target geospatial location distribution, so as to generate the first disaster response rescue estimation management path;

[0012] The rescue path environmental constraint and deviation measurement module is used to obtain the corresponding disaster response geographic environment change constraints through the environmental monitoring data corresponding to the disaster response geographic space block, and optimize the rescue path environmental constraints of the first disaster response rescue estimate management path based on the disaster response geographic environment change constraints to generate the second disaster response rescue estimate management path; measure the path deviation according to the first disaster response rescue estimate management path and the second disaster response rescue estimate management path, so as to obtain the disaster response rescue estimate path deviation;

[0013] The emergency rescue estimated path deviation penalty management module is used to compare and judge the disaster response emergency rescue estimated path deviation according to a preset path deviation threshold. If the disaster response emergency rescue estimated path deviation is less than the preset path deviation threshold, the disaster response geographic space block is intelligently managed according to the disaster response emergency rescue second estimated management path; if the disaster response emergency rescue estimated path deviation is greater than or equal to the preset path deviation threshold, the path deviation penalty is calculated for the disaster response emergency rescue first estimated management path and the disaster response emergency rescue second estimated management path based on the disaster response emergency rescue estimated path deviation to obtain the disaster response emergency rescue estimated path deviation penalty; the disaster response geographic space block is optimized for emergency rescue path management based on the disaster response emergency rescue estimated path deviation penalty and the disaster response emergency rescue second estimated management path.

[0014] Beneficial effects of the present invention:

[0015] 1. The intelligent management method of national space path based on big data analysis proposed by the present invention is beneficial to the fact that, compared with the prior art, the present application has the following beneficial effects: the acquisition of the target national geospatial model is the basis of the entire disaster response process, and has a significant role in supporting geographic data, which can provide an accurate spatial information basis for subsequent disaster response decisions. This model covers detailed information on topography, landform, climate, land use, distribution of natural resources, etc., which helps to fully understand the geographical characteristics and spatial layout of the target country, and thus provide a more detailed spatial analysis basis for disaster response. By using geographic information acquisition equipment to collect geographic scientific information on the corresponding disaster response geospatial blocks in the target national geospatial model, real-time and comprehensive data on the disaster response geospatial blocks can be obtained, thereby providing an accurate scientific basis for decision-making. The data types collected include multi-dimensional information such as land use, traffic flow, and environmental monitoring data. This information is crucial for understanding the expansion scope of disasters, assessing the impact of disasters, and formulating post-disaster recovery plans. It can also provide data support for subsequent disaster analysis, prediction, and recovery work. At the same time, by using the big data transmission network to transmit the target disaster response geographic science information big data set to the big data processing platform in real time, it can provide powerful information processing capabilities and decision-making support for disaster response. Through the high-speed big data transmission network, it can ensure the accurate transmission of real-time data, avoid information lag or loss, and ensure the timeliness of disaster emergency response. The powerful computing power of the big data processing platform can quickly analyze and process a large amount of complex geographic data, thereby improving the integration of geographic science information data, ensuring timely and effective rescue work, and providing a scientific basis for post-disaster recovery work. Secondly, by using land use data and traffic flow data, and with the help of a big data processing platform, the disaster rescue path of the target geographic space is estimated. The key to this step is that through accurate geospatial data analysis, reasonable route planning can be provided for disaster response actions to ensure that the rescue team can reach the disaster area efficiently and safely. Land use data provides regional resource distribution, the status of infrastructure and the impact of disasters for analysis. Traffic flow data helps predict road capacity and reasonably arrange the driving routes of rescue vehicles. Through comprehensive analysis of these data, the first estimated management path for disaster response and rescue can be generated. When facing different types of disasters (such as earthquakes, floods, etc.), these path estimates can be flexibly adjusted according to the characteristics of the disaster, which can effectively avoid traffic congestion, disaster spread and other problems, and reduce time loss and resource waste caused by road problems during the rescue process, thereby improving the real-time processing capability of geographic science information and the efficiency of disaster prediction.Then, by using environmental monitoring data to optimize the disaster response rescue path with environmental constraints, the second estimated management path for disaster response rescue is generated. The key to this step is that by analyzing the environmental monitoring data, the changing factors in the post-disaster environment, such as pollutant diffusion, ground collapse, climate change, etc., can be identified. These factors will affect the safety and traffic capacity of the rescue path. Therefore, timely constraints and optimization of these environmental changes in the path estimation process can improve the safety and effectiveness of path selection. Environmental constraint optimization helps to take into account the changes in post-disaster environmental conditions, such as post-disaster road destruction and rising flood levels, and can ensure that the rescue route can avoid potential dangerous areas and ensure that the rescue team can complete the task safely and quickly, so as to ensure that the optimal rescue route is quickly provided after the disaster occurs. In addition, the measurement and optimization of path deviation not only helps to improve the accuracy of rescue operations, but also can timely identify and resolve the differences between the estimated path and the actual situation, ensuring the efficient coordination of rescue operations and disaster response systems. Finally, by judging, analyzing and optimizing the estimated path deviation, the intelligent management of the disaster response geospatial blocks can be achieved. The key to this step is the measurement and comparison of path deviation. By setting the path deviation threshold and comparing the difference between the actual rescue path and the estimated path, the path problems in the rescue operation can be quickly identified to prevent the reduction of rescue efficiency or waste of resources due to improper path selection. If the path deviation is less than the preset threshold, the optimized second estimated path can be directly used for rescue intervention to improve efficiency. On the other hand, if the path deviation exceeds the threshold, a penalty calculation will be performed between the first and second estimated paths, so as to adjust the original path planning and perform necessary path optimization. At this time, through the path deviation penalty mechanism, not only the flexibility of path planning can be improved, but also the rescue path can be dynamically adjusted to more accurately respond to sudden complex situations after the disaster, such as traffic interruption, road damage, climate change and other factors. Rescue path management based on path optimization can maximize the efficiency of rescue path management, thereby ensuring the timeliness and accuracy of disaster response.

[0016] 2. The land space path intelligent management system based on big data analysis proposed in the present invention is composed of a target area geographic science information collection module, a disaster rescue first path estimation module, a rescue path environmental constraint and deviation measurement module, and a rescue estimation path deviation penalty management module. It can realize any land space path intelligent management method based on big data analysis described in the present invention, and is used to combine the operations between computer programs running on each module to realize the land space path intelligent management method based on big data analysis. The internal structures of the system cooperate with each other, which can greatly reduce duplication of work and manpower investment, and can quickly and effectively provide a more accurate and efficient land space path intelligent management process based on big data analysis, thereby simplifying the operation process of the land space path intelligent management system based on big data analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0018] Figure 1 It is a schematic diagram of the steps of the intelligent management method of land space paths based on big data analysis of the present invention;

[0019] Figure 2 for Figure 1 Detailed step flow diagram of step S1;

[0020] Figure 3 for Figure 2 Detailed step flow chart of step S13 in FIG. DETAILED DESCRIPTION

[0021] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0022] To achieve this, please refer to Figures 1 to 3 The present invention provides a method for intelligent management of land space paths based on big data analysis, the method comprising the following steps:

[0023] Step S1: Obtain the target national territory geospatial model, and use geographic information collection equipment to collect geographic science information on the corresponding disaster response geospatial blocks in the target national territory geospatial model to obtain a target disaster response geospatial information big data set, including the target geospatial location distribution, land use data, traffic flow data and environmental monitoring data corresponding to the disaster response geospatial blocks; transmit the target disaster response geospatial information big data set to the big data processing platform in real time through the big data transmission network;

[0024] Step S2: Based on the land use data and traffic flow data corresponding to the disaster response geographic space block, a big data processing platform is used to estimate the disaster rescue path for the corresponding target geographic space location distribution to generate a first estimated management path for disaster response rescue;

[0025] Step S3: Obtain the corresponding disaster response geographic environment change constraints through the environmental monitoring data corresponding to the disaster response geographic space block, and optimize the rescue path environmental constraints of the first disaster response rescue estimate management path based on the disaster response geographic environment change constraints to generate a second disaster response rescue estimate management path; measure the path deviation according to the first disaster response rescue estimate management path and the second disaster response rescue estimate management path to obtain the disaster response rescue estimate path deviation;

[0026] Step S4: Compare and judge the disaster response and rescue estimated path deviation according to a preset path deviation threshold. If the disaster response and rescue estimated path deviation is less than the preset path deviation threshold, the disaster response and rescue second estimated management path is used to perform intelligent management of rescue intervention for the disaster response geographic space block; if the disaster response and rescue estimated path deviation is greater than or equal to the preset path deviation threshold, the disaster response and rescue first estimated management path and the disaster response and rescue second estimated management path are calculated based on the disaster response and rescue estimated path deviation to obtain the disaster response and rescue estimated path deviation penalty; based on the disaster response and rescue estimated path deviation penalty and the disaster response and rescue second estimated management path, the disaster response geographic space block is optimized for rescue path management.

[0027] In the embodiment of the present invention, please refer to Figure 1 As shown, it is a schematic diagram of the steps of the intelligent management method of land space paths based on big data analysis of the present invention. In this example, the intelligent management method of land space paths based on big data analysis includes the following steps:

[0028] Step S1: Obtain the target national territory geospatial model, and use geographic information collection equipment to collect geographic science information on the corresponding disaster response geospatial blocks in the target national territory geospatial model to obtain a target disaster response geospatial information big data set, including the target geospatial location distribution, land use data, traffic flow data and environmental monitoring data corresponding to the disaster response geospatial blocks; transmit the target disaster response geospatial information big data set to the big data processing platform in real time through the big data transmission network;

[0029] In an embodiment of the present invention, the geographic space of the target land area is comprehensively collected through remote sensing technology and geographic information system (GIS). In the specific operation, satellite remote sensing data, drone aerial images and ground survey equipment (such as total station, GPS measuring instrument) are first used to collect the geographic spatial information of the target land. These data include but are not limited to topography, landforms, urban buildings, rivers, road networks and other natural and artificial features. The remote sensing data is processed using high-resolution satellite images, combined with GIS technology to vectorize and rasterize spatial data. Subsequently, with the help of three-dimensional modeling tools in the GIS platform, such as ArcGIS, QGIS, etc., a geographic spatial model of the target land is constructed to obtain the geographic spatial model of the target land. After obtaining the target country's geospatial model, the next step is to make spatial divisions according to the needs of disaster response. First, according to the needs of different types of disaster responses, set the division standards for disaster response areas. For example, for flood disasters, they can be divided according to terrain height differences, surface water flow paths, historical flood data, etc.; for earthquake disasters, they are divided according to factors such as earthquake-vulnerable areas, building seismic resistance, and population density. During the division process, spatial analysis technology is used to rasterize the target country's geospatial model based on the GIS platform. By setting a series of spatial analysis conditions, such as terrain height, population density, traffic conditions, etc., overlay analysis, buffer zone analysis and other technologies are used to form multiple disaster response geospatial blocks, thereby obtaining disaster response geospatial blocks. At the same time, after completing the division of disaster response areas, the geographic science information collection stage begins. The core of this stage is to collect various information in the disaster response blocks in real time and dynamically through a variety of geographic information collection equipment. The main equipment includes high-precision GPS receivers, remote sensing image acquisition systems, ground monitoring sensors, drones, etc. These devices can collect spatial location distribution, land use data, traffic flow, environmental monitoring data and other information of the target blocks in real time. Then, through the use of big data transmission networks, these information are transmitted to the big data processing platform in real time. In order to ensure the accuracy and timeliness of the data, a high-speed and stable data transmission network is used, such as optical fiber networks, 5G networks or satellite communication systems. All collected disaster response geographic science information will be pre-processed and cleaned, and converted into a format suitable for big data platform processing. During the transmission process, data compression, encryption and other technologies are used to ensure the integrity and security of the data to avoid loss or tampering during the transmission process. On the big data processing platform, a big data processing framework (such as Hadoop and Spark) is used to store, analyze and visualize the received massive data. Through data fusion and multi-dimensional analysis, the platform can generate decision support information such as disaster response predictions and resource allocation suggestions in real time.

[0030] Step S2: Based on the land use data and traffic flow data corresponding to the disaster response geographic space block, a big data processing platform is used to estimate the disaster rescue path for the corresponding target geographic space location distribution to generate a first estimated management path for disaster response rescue;

[0031] In the embodiment of the present invention, within the disaster response geographic space block, the land use data of the area is first comprehensively collected through the big data processing platform, and then the dynamic changes of the land use pattern are analyzed by comparing the historical data with the current data using the spatiotemporal analysis technology. The land use change pattern around the disaster response block is identified through an efficient data mining algorithm. For example, if the disaster occurs in an urban fringe area, the transformation of the surrounding land from farmland to construction land, as well as the changing trends of related transportation and infrastructure construction will be analyzed. In addition, in the process of obtaining the initial location distribution of the disaster rescue response, all the available land use data are first collected and calibrated. The disaster occurrence site, the starting point of the rescue team, and the relevant rescue resource assembly site can be obtained through the disaster monitoring system to obtain real-time disaster occurrence point distribution data, and the initial location distribution is determined in combination with social infrastructure data (such as fire stations, hospitals, transportation hubs, etc.). Based on these disaster rescue response initial location distributions, the path planning algorithm (such as Dijkstra algorithm or A* algorithm) is used to simulate the rescue path within the disaster response geographic space block. During the path simulation process, factors such as road network and traffic conditions need to be considered to generate a path network from the starting position to the target position, thereby generating a corresponding disaster response rescue path simulation network.At the same time, in the process of traffic accessibility assessment and analysis, each path in the disaster response and emergency rescue path simulation network is first subjected to a detailed traffic flow data analysis. This analysis uses traffic flow monitoring equipment, road sensors and other data sources to obtain information such as real-time road traffic flow and traffic congestion conditions. Through the real-time traffic simulation tool based on the big data platform, the traffic flow density, congestion coefficient and traffic capacity of each path are calculated. The smoothness of the path is analyzed by combining the land use change pattern (such as traffic changes in different plots such as commercial areas, industrial areas, and residential areas) to obtain the smoothness score of each path. The feasibility optimization of each path in the disaster response and emergency rescue path simulation network is estimated based on the previously obtained smoothness score. The specific optimization process adopts optimization algorithms based on machine learning, such as genetic algorithms, particle swarm algorithms, etc., through comprehensive consideration of the smoothness index, road congestion data and other constraints (such as geographical conditions, road conditions, resource availability, etc.). Consider and evaluate the feasibility of each path. The optimization algorithm will calculate the feasibility optimization estimated path based on factors such as path smoothness, rescue efficiency and safety. Then, based on the disaster rescue resource scheduling and personnel deployment decision-making goals, combined with the feasibility optimization estimated path obtained by previous optimization, the rescue path management collaborative optimization is carried out. First, according to the severity of the disaster, the availability of resources and the feasibility evaluation of the path, the rescue resources (such as rescue equipment, medical resources, personnel team, etc.) are reasonably allocated. The resource scheduling algorithm will dynamically adjust the allocation of rescue resources in the rescue path simulation network according to the traffic smoothness, time cost and resource demand of the path. The collaborative optimization process uses multi-objective optimization methods, such as linear programming, integer programming, etc., to ensure that the resource scheduling and personnel deployment of the optimal path are completed in the shortest time. The generated "disaster response rescue first estimated management path" is the comprehensive optimal path based on various conditions and goals, and finally the disaster response rescue first estimated management path is generated.

[0032] Step S3: Obtain the corresponding disaster response geographic environment change constraints through the environmental monitoring data corresponding to the disaster response geographic space block, and optimize the rescue path environmental constraints of the first disaster response rescue estimate management path based on the disaster response geographic environment change constraints to generate a second disaster response rescue estimate management path; measure the path deviation according to the first disaster response rescue estimate management path and the second disaster response rescue estimate management path to obtain the disaster response rescue estimate path deviation;

[0033] In an embodiment of the present invention, detailed geospatial data of the disaster response area is obtained through a geographic information system (GIS) platform. The data generally includes information such as terrain, climate, road network, and building density. On this basis, real-time dynamic monitoring and analysis of the disaster response area is performed by integrating environmental monitoring data (such as meteorological monitoring, satellite remote sensing data, and abnormal climate change data). The collection of these data uses remote sensing technology and sensor networks to ensure the real-time and accuracy of the data. Then, data analysis tools (such as data analysis libraries in Python, machine learning models, etc.) are used to classify and evaluate the environment of the geospatial blocks, thereby extracting the change constraints of the geographical environment. For example, climate data such as temperature, precipitation changes, and wind speed are analyzed, and combined with road and building density to analyze the impact of climate change on the disaster response area. The concentration degree is used to identify the geographical environmental characteristics that affect disaster rescue, and based on the geographical environmental change constraints of disaster response, an appropriate path analysis model is selected to calculate the environmental load of the rescue path. By using a graph theory model, the first estimated path of disaster response rescue is modeled and analyzed through network analysis tools (such as the path analysis function of ArcGIS or QGIS). In the path analysis, multiple factors of environmental load are considered, including the density of buildings in the area, abnormal climate changes (such as heavy rainfall, typhoons, etc.), and terrain undulations and collapses. In addition, the environmental pressure of the first estimated path of disaster rescue is quantitatively evaluated based on the environmental load data of the disaster area previously obtained. This evaluation process is achieved by establishing an environmental pressure index (EPI, Environmental Pressure Index). The environmental pressure index model is based on the disaster rescue path prediction method. The model considers multiple variables, such as building density, climate change, road traffic conditions, terrain complexity, etc. All variables are weighted according to their influence on the path. The environmental pressure index can be modeled using a linear weighted method or a more complex multi-factor decision analysis method. Specifically, each factor (such as building density, climate change, etc.) is assigned a weight value according to its impact on the disaster rescue task, and all factors are converted into a unified quantitative index through standardization to obtain the environmental pressure index value of the disaster rescue path. At the same time, the corresponding disaster response rescue first estimated management path is evaluated by combining the previously quantified environmental pressure index. The optimization process of environmental constraints on emergency paths uses intelligent algorithms, such as genetic algorithms (GA) or particle swarm optimization algorithms (PSO). These optimization algorithms can search for the optimal path under complex environmental load constraints. Specifically, by establishing a path optimization model, the environmental pressure index is introduced as a constraint in the model, and the starting and ending points of the path are set. At the same time, the environmental load changes that may occur during the path optimization process (such as road collapse, climate anomalies, etc.) are taken into account. Using genetic algorithms, multiple alternative paths can be generated by simulating natural selection, and then the advantages and disadvantages of the paths are evaluated according to the size of the environmental pressure index, thereby optimizing a new emergency path that adapts to environmental constraints.Thus, the second estimated management path of disaster response and rescue is generated. Then, by combining the time variable parameters, the relative position distance corresponding to the first estimated management path of disaster response and rescue, the arrival time efficiency, the maximum deviation allowed time, the road traffic flow, the traffic speed and related parameters of the second estimated management path of disaster response and rescue, a suitable path deviation calculation formula is formed to measure the path deviation of the first estimated management path of disaster response and rescue and the second estimated management path of disaster response and rescue, so as to evaluate the difference between the two paths under the conditions of environmental load and actual disaster changes, and finally obtain the estimated path deviation of disaster response and rescue. ,

[0034] Step S4: Compare and judge the disaster response and rescue estimated path deviation according to a preset path deviation threshold. If the disaster response and rescue estimated path deviation is less than the preset path deviation threshold, the disaster response and rescue second estimated management path is used to perform intelligent management of rescue intervention for the disaster response geographic space block; if the disaster response and rescue estimated path deviation is greater than or equal to the preset path deviation threshold, the disaster response and rescue first estimated management path and the disaster response and rescue second estimated management path are calculated based on the disaster response and rescue estimated path deviation to obtain the disaster response and rescue estimated path deviation penalty; based on the disaster response and rescue estimated path deviation penalty and the disaster response and rescue second estimated management path, the disaster response geographic space block is optimized for rescue path management.

[0035] In an embodiment of the present invention, a comparison is made between the previously quantified disaster response and rescue estimated path deviation and a preset path deviation threshold. In specific implementation, the historical data of the current disaster response path, geographic spatial information and real-time disaster development are collected and analyzed to calculate the actual deviation value of the disaster response and rescue estimated path. If the actual path deviation is less than the preset threshold (for example, the set path deviation threshold is 10 kilometers), intelligent management of rescue intervention is performed based on a more optimized disaster response and rescue second estimated management path. The management path combines a geographic information system (GIS) to accurately calibrate the disaster response distribution position within the disaster response geographic spatial block, and adjusts the intervention strategy through an intelligent algorithm according to the characteristics of different types of disasters (such as floods, earthquakes, fires, etc.), so as to achieve fast and efficient rescue operations. When the deviation of the disaster response and rescue estimated path is greater than or equal to the preset path deviation threshold, the deviation evolution dynamic correction analysis stage is entered. In this step, the historical data of the disaster response path is first deeply learned through big data analysis, including path deviation, historical patterns of disaster response, meteorological information and geographical changes. Then, machine learning algorithms, such as regression analysis and time series analysis, are used to predict and correct the deviation change trend of the disaster response path. Through these analyses, a deviation evolution correction factor is obtained, and a suitable path deviation penalty calculation formula is constructed by combining the speed vector, available resource density, deviation evolution correction factor, resource distribution vector and related parameters to calculate the path deviation penalty for the first estimated management path of disaster response and rescue and the second estimated management path of disaster response and rescue, so as to quantify the path deviation penalty of path deviation on disaster response efficiency.At the same time, after calculating the path deviation penalty, the second estimated management path for disaster response and rescue is simulated and optimized by path deviation penalty. The specific operation is to simulate multiple possible scenarios of the disaster response path and optimize the path based on the results of the path deviation penalty. The optimization process relies on advanced path planning algorithms, such as A* algorithm, Dijkstra algorithm, etc. These algorithms recalculate the rescue path according to the optimization objectives (such as shortest path, fastest response time, and least risk). In the simulation optimization process, multiple optimized paths will be generated, and the deviation penalty value of each path will be evaluated to obtain the optimal path. Assuming that the deviation of the second estimated path is large, it will be adjusted according to the path penalty result to generate a more reasonable rescue path, which can minimize the path deviation in actual operation and achieve the best rescue result based on The optimized disaster rescue deviation penalty management path optimizes the path management of the disaster response distribution location within the disaster response geographic space block. At this stage, real-time monitoring technology, drone patrol data and sensor networks are used to continuously track the real-time dynamics in the disaster area, and GIS and big data analysis platforms are used to accurately locate the specific location of the disaster area, and optimize the path on this basis. Through the real-time feedback mechanism, the optimized path can be dynamically adjusted according to geographic information and actual rescue needs. For example, in actual disaster response, if it is found that roads in certain areas are impassable or new dangerous areas appear, the scheduling plan can be readjusted according to the optimized path. Based on accurate path planning and path optimization management, disaster response actions can be completed more efficiently, thereby improving the timeliness and accuracy of rescue.

[0036] Further, as an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 Detailed step flow diagram of step S1 in FIG. 1 , in this embodiment, step S1 includes the following steps:

[0037] Step S11: Obtaining the target land geographic spatial model;

[0038] In an embodiment of the present invention, the geographic space of the target land area is comprehensively collected through remote sensing technology and geographic information system (GIS). In the specific operation, satellite remote sensing data, drone aerial images and ground survey equipment (such as total station, GPS measuring instrument) are first used to collect the geographic space information of the target land. These data include but are not limited to topography, landforms, urban buildings, rivers, road networks and other natural and artificial objects. The remote sensing data is processed using high-resolution satellite images, combined with GIS technology to vectorize and rasterize spatial data. Subsequently, with the help of three-dimensional modeling tools in the GIS platform, such as ArcGIS, QGIS, etc., a geospatial model of the target land is constructed to form a high-precision three-dimensional digital ground model (DTM) and digital elevation model (DEM). These models can truly reflect the terrain characteristics of the geographic space, and finally obtain the geospatial model of the target land.

[0039] Step S12: performing disaster response spatial division on the target land geographic spatial model to obtain disaster response geographic spatial blocks;

[0040] In an embodiment of the present invention, after obtaining the geospatial model of the target country, the next step is to perform spatial division according to the needs of disaster response. First, according to the needs of different types of disaster responses, the division standards of disaster response areas are set. For example, for flood disasters, the division can be based on terrain height difference, surface water flow path, historical flood data, etc.; for earthquake disasters, the division is based on earthquake-vulnerable areas, building seismic resistance, and population density. In the division process, spatial analysis technology is used to rasterize the target country's geospatial model based on the GIS platform. By setting a series of spatial analysis conditions, such as terrain height, population density, traffic conditions, etc., overlay analysis, buffer zone analysis and other technologies are used to form multiple disaster response geospatial blocks. These blocks represent areas that need to be responded to when a disaster occurs, and finally disaster response geospatial blocks are obtained.

[0041] Step S13: using geographic information collection equipment to collect geographic science information on the disaster response geographic space block to obtain a target disaster response geographic science information big data set, including the target geographic space location distribution, land use data, traffic flow data and environmental monitoring data corresponding to the disaster response geographic space block;

[0042] In an embodiment of the present invention, after completing the division of the disaster response area, the geographic science information collection stage begins. The core of this stage is to use a variety of geographic information collection equipment to perform real-time and dynamic collection of various information in the disaster response block. The main equipment includes high-precision GPS receivers, remote sensing image collection systems, ground monitoring sensors, drones, etc. These devices can collect land use data, traffic flow, environmental monitoring data and other information of the target block in real time. The land use data includes information such as agriculture, forestry, urban construction, and industrial land in the block; traffic flow data is obtained through sensors set on the road or through vehicle-mounted GPS equipment to obtain real-time traffic flow, traffic congestion, etc.; environmental monitoring data includes meteorological data such as air quality, temperature and humidity, and air pressure, as well as environmental data such as water quality and soil pollution. All these data are transmitted to the data center in real time through the sensor network and data collection platform to provide data support for further analysis and decision-making. All collected data will be organized into a structured large data set, including spatial location distribution, time series data and other information, and finally a large data set of geographic science information for target disaster response is obtained.

[0043] Step S14: The target disaster response geographic science information big data set is transmitted in real time to the big data processing platform through the big data transmission network.

[0044] In an embodiment of the present invention, this information is transmitted to a big data processing platform in real time by using a big data transmission network. In order to ensure the accuracy and timeliness of the data, a high-speed and stable data transmission network is used, such as a fiber optic network, a 5G network or a satellite communication system. All collected disaster response geographic science information will be pre-processed and cleaned, and converted into a format suitable for processing by the big data platform. During the transmission process, data compression, encryption and other technologies are used to ensure the integrity and security of the data to avoid loss or tampering during the transmission process. On the big data processing platform, a big data processing framework (such as Hadoop, Spark) is used to store, analyze and visualize the received massive data. Through data fusion and multi-dimensional analysis, the platform can generate decision support information such as disaster response predictions and resource allocation suggestions in real time.

[0045] Further, as an embodiment of the present invention, refer to Figure 3 As shown, Figure 2 FIG. 1 is a schematic diagram of a detailed step flow chart of step S13 in FIG. 1 . In this embodiment, step S13 includes the following steps:

[0046] Step S131: using a GPS positioning device to perform target geospatial positioning processing on the target disaster response position corresponding to the disaster response geospatial block, so as to obtain the target geospatial position distribution corresponding to the disaster response geospatial block;

[0047] In an embodiment of the present invention, the target geospatial positioning processing is performed on the disaster response geospatial block by using a GPS positioning device. The specific operation is to use a high-precision GPS positioning device to perform real-time positioning of multiple key points in the disaster response area, obtain their longitude and latitude coordinates, and correct them through sensor data to ensure the accuracy of positioning. In the disaster response geospatial block, the GPS device usually uses differential GPS or RTK (real-time dynamic positioning) technology to improve the positioning accuracy to the centimeter level. The obtained positioning data is then uploaded and stored through the data acquisition system and summarized into a geospatial location distribution map, which calibrates the specific target locations in the disaster response area, such as the severely affected areas after the disaster, the emergency command center or the affected key infrastructure (such as hospitals, fire stations, etc.), to ensure that each key location in the disaster response area can be accurately located, and finally obtain the target geospatial location distribution corresponding to the disaster response geospatial block.

[0048] Step S132: using a geographic information system to refine the land use attributes of the disaster response geographic space block to obtain land use data corresponding to the disaster response geographic space block, wherein the land use data includes land use type, land building facility distribution, and land population distribution density;

[0049] In an embodiment of the present invention, the land use attributes of the disaster response geographic space block are refined by using a geographic information system (GIS). In the specific implementation process, the existing land use data in the disaster response area is obtained through the geographic information system platform, including the land use type (such as farmland, residential area, industrial area, etc.), the distribution of building facilities (such as schools, hospitals, commercial areas, etc.) and the population distribution density on the land. First, the GIS system extracts the land use type information in the area through remote sensing images and high-precision map data, and combines the remote sensing data and ground field survey data to accurately calibrate the distribution of building facilities in each area. In order to further improve the accuracy of the refined processing, the GIS system will analyze the building density and population distribution of the land according to urban planning, land use rights and census data to form a refined data map of land use, and finally obtain the land use data corresponding to the disaster response geographic space block.

[0050] Step S133: using traffic flow collection equipment to monitor the traffic flow of the disaster response geographic space block in real time, and obtaining traffic flow data corresponding to the disaster response geographic space block, wherein the traffic flow data includes traffic network flow density, traffic network travel efficiency and traffic network congestion status;

[0051] In an embodiment of the present invention, traffic flow real-time monitoring is performed on the disaster response geographic space block by using traffic flow collection equipment. During the implementation process, traffic flow sensors, such as geomagnetic induction, infrared sensors or video monitoring equipment, are deployed at key locations such as major traffic sections, intersections, bridges, etc. in the disaster response area. These devices collect traffic flow data in real time and record the number, speed and traffic conditions of vehicles passing through the area. The data collection equipment uploads the traffic flow data to the background system in real time through a wireless network. The traffic flow monitoring system combines the real-time data to calculate the traffic density, traffic efficiency and congestion of the traffic network. During the data processing process, a traffic flow modeling algorithm is used to conduct a comprehensive analysis of the data to obtain the traffic change trend and congestion warning of each section. Furthermore, it can also be connected to the road navigation system to automatically adjust the timing plan of the traffic lights, optimize post-disaster traffic guidance, and alleviate traffic pressure, so as to ensure accurate grasp of the traffic conditions in the disaster area and efficient implementation of emergency response, and finally obtain traffic flow data corresponding to the disaster response geographic space block.

[0052] Step S134: using environmental monitoring equipment to monitor environmental changes in the disaster response geographic space block in real time, and obtaining environmental monitoring data corresponding to the disaster response geographic space block, wherein the environmental monitoring data includes disaster geographic environment data and climate environment data;

[0053] In an embodiment of the present invention, environmental monitoring equipment is used to monitor environmental changes in the disaster response geographic space block in real time. Specifically, various types of environmental monitoring sensors are deployed, such as air quality monitoring equipment, temperature and humidity sensors, soil moisture monitors, and water quality monitoring equipment, etc., to collect environmental change data in the disaster area in real time. The sensor network can monitor the climate environment and geographical environment changes in the disaster area around the clock, such as wind speed, temperature, humidity, precipitation, air pollution index and other environmental factors. Through the data acquisition system, these monitoring data are transmitted to the centralized analysis platform in real time for processing. The environmental change monitoring system uses data fusion technology to integrate and analyze data from multiple environmental monitoring devices to generate a multi-dimensional data set for environmental monitoring, including post-disaster climate change trends, air pollution concentrations, rainfall changes, soil moisture content and other contents. The analysis results are displayed by means of data visualization to provide a reference for post-disaster recovery and environmental protection measures. The key technology of this step lies in the efficient collection and real-time processing of multi-source environmental data to ensure that changes in the post-disaster environment can be fed back in a timely manner, and finally obtain environmental monitoring data corresponding to the disaster response geographic space block.

[0054] Step S135: integrating the target geographic spatial location distribution, land use data, traffic flow data and environmental monitoring data corresponding to the disaster response geographic spatial block to obtain a large dataset of target disaster response geographic scientific information.

[0055] In an embodiment of the present invention, geographic science information is integrated by integrating the target geographic spatial location distribution, land use data, traffic flow data and environmental monitoring data corresponding to the disaster response geographic spatial block. This step firstly formats the above-mentioned various types of data (including GPS positioning data, land use data, traffic flow data and environmental monitoring data) in a unified manner through a big data platform. Subsequently, a geographic information system (GIS) is used to perform spatial analysis and data fusion on these data. A spatial database is used to combine all data with geographic information layers to perform a comprehensive analysis of multiple dimensions and multiple spatiotemporal scales. The implicit laws and trends in the data are extracted through data mining and machine learning algorithms to provide accurate decision-making basis for disaster response and management. The integrated data set can not only present the geographical distribution characteristics of the disaster area, but also provide information support in many aspects such as disaster impact assessment, traffic diversion and environmental protection. On this basis, a visualization report and decision support tools are further generated to ensure that multi-source information can be efficiently integrated on a unified platform, and finally a large data set of target disaster response geographic science information is obtained.

[0056] Further, step S2 includes the following steps:

[0057] Step S21: using a big data processing platform to dynamically analyze the land use pattern of the land use data corresponding to the disaster response geographic space block, and obtain the land use change pattern around the disaster response block;

[0058] In an embodiment of the present invention, within the disaster response geographic space block, firstly, the land use data of the area is comprehensively collected through the big data processing platform. Specifically, the land use type in the area can be calibrated through multiple data sources such as remote sensing data, satellite images, and urban land planning data. The data processing platform performs spatial analysis on these data through GIS (geographic information system) tools. Next, the spatiotemporal analysis technology is used to analyze the dynamic changes in land use patterns by comparing historical data with current data. The land use change pattern around the disaster response block is identified through an efficient data mining algorithm. For example, if a disaster occurs in an urban fringe area, the transformation of the surrounding land from farmland to construction land and the changing trends of related transportation and infrastructure construction will be analyzed, and finally the land use change pattern around the disaster response block will be obtained.

[0059] Step S22: obtaining the initial location distribution of the disaster rescue response, and performing disaster response rescue path simulation on the target geographic space location distribution corresponding to the disaster response geographic space block based on the initial location distribution of the disaster rescue response, so as to generate a disaster response rescue path simulation network corresponding to the starting location distribution to the target location distribution;

[0060] In the embodiment of the present invention, by first collecting and calibrating all possible disaster occurrence locations, the starting points of the rescue teams, and the relevant rescue resource assembly locations during the acquisition of the initial location distribution of the disaster rescue response, the real-time disaster occurrence point distribution data can be obtained through the disaster monitoring system, and the initial location distribution is determined in combination with social infrastructure data (such as fire stations, hospitals, transportation hubs, etc.). At the same time, based on these initial location distributions of disaster rescue responses, a path planning algorithm (such as Dijkstra algorithm or A* algorithm) is used to simulate the rescue passage path within the disaster response geographic space block. During the path simulation process, factors such as road networks and traffic conditions need to be considered to generate a path network from the starting position to the target position. The simulation is adjusted through real-time data input to ensure the accuracy and timeliness of the path planning, and finally a disaster response rescue passage path simulation network corresponding to the starting position distribution to the target position distribution is generated.

[0061] Step S23: Based on the land use change pattern and traffic flow data around the disaster response block, each disaster response emergency path in the disaster response emergency path simulation network is evaluated and analyzed for traffic accessibility, so as to obtain a traffic accessibility index corresponding to each disaster response emergency path;

[0062] In an embodiment of the present invention, during the process of traffic accessibility assessment and analysis, each path in the disaster response and rescue route simulation network is first subjected to a detailed traffic flow data analysis. The analysis uses traffic flow monitoring equipment, road sensors and other data sources to obtain information such as real-time road traffic flow and traffic congestion conditions. The traffic flow density, congestion coefficient and traffic capacity of each path are calculated through a real-time traffic simulation tool based on a big data platform. The smoothness of the path is analyzed by combining land use change patterns (such as traffic changes in different plots such as commercial areas, industrial areas, and residential areas), and a traffic accessibility index is evaluated for each path. Specifically, the traffic accessibility index can be calculated by the weighted average method, taking into account factors such as road conditions, vehicle density, and road capacity, to obtain a traffic accessibility score for each path, and finally obtain a traffic accessibility index corresponding to each disaster response and rescue path.

[0063] Step S24: performing feasibility optimization estimation on each corresponding disaster response emergency path in the disaster response emergency path simulation network based on the traffic accessibility index corresponding to each disaster response emergency path, and obtaining the disaster response emergency feasibility optimization estimation path;

[0064] In an embodiment of the present invention, the feasibility of each path in the disaster response and rescue route simulation network is optimized and estimated based on the previously obtained traffic accessibility index. The specific optimization process adopts an optimization algorithm based on machine learning, such as a genetic algorithm, a particle swarm algorithm, etc. The feasibility of each path is evaluated by comprehensively considering the accessibility index, road congestion data and other constraints (such as geographical conditions, road conditions, resource availability, etc.). The optimization algorithm will calculate the optimal path based on factors such as path accessibility, rescue efficiency and safety. Through training with a large amount of historical data, the optimization algorithm can predict the feasibility of the path under different circumstances and obtain the optimal estimated path for disaster response and rescue. This process can also dynamically adjust the path optimization strategy in combination with the type and scale of the disaster, so that each disaster response can be executed in the most reasonable path, and finally obtain the feasibility optimized estimated path for disaster response and rescue.

[0065] Step S25: Obtain disaster rescue resource scheduling and personnel deployment decision-making goals, and perform rescue path management collaborative optimization on the disaster response and rescue feasibility optimization estimated path based on the disaster rescue resource scheduling and personnel deployment decision-making goals to generate a first disaster response and rescue estimated management path.

[0066] In an embodiment of the present invention, based on the disaster rescue resource scheduling and personnel deployment decision-making goals, combined with the previously optimized disaster response rescue feasibility optimization estimated path, the rescue path management collaborative optimization is performed. First, according to the severity of the disaster, the availability of resources and the feasibility assessment of the path, the rescue resources (such as rescue equipment, medical resources, personnel teams, etc.) are reasonably deployed. The resource scheduling algorithm will dynamically adjust the allocation of rescue resources in the rescue path simulation network according to the traffic smoothness, time cost and resource demand of the path. The collaborative optimization process uses multi-objective optimization methods, such as linear programming, integer programming, etc., to ensure that the resource scheduling and personnel deployment of the optimal path are completed in the shortest time. The generated "disaster response rescue first estimated management path" is a comprehensive optimal path based on various conditions and goals. The path takes into account rescue resources, time, road conditions, risks and other factors to ensure the efficient execution of disaster response, and finally generates the disaster response rescue first estimated management path.

[0067] Further, step S3 includes the following steps:

[0068] Step S31: obtaining corresponding disaster response geographic environment change constraints through environmental monitoring data corresponding to the disaster response geographic space block;

[0069] In an embodiment of the present invention, detailed geospatial data of the disaster response area is obtained through a geographic information system (GIS) platform. The data generally includes information such as terrain, climate, road network, and building density. On this basis, the disaster response area is dynamically monitored and analyzed in real time by integrating environmental monitoring data (such as meteorological monitoring, satellite remote sensing data, and abnormal climate change data). The collection of these data uses remote sensing technology and sensor networks to ensure the real-time and accuracy of the data. Then, data analysis tools (such as data analysis libraries in Python, machine learning models, etc.) are used to classify and evaluate the environment of the geographic space blocks, so as to extract the change constraints of the geographic environment. For example, climate data such as temperature, precipitation changes, and wind speed are analyzed, and combined with road and building density, the geographic environment characteristics that affect disaster rescue are identified. These change constraints can be represented by numerical models or rule models, and finally the disaster response geographic environment change constraints are obtained.

[0070] Step S32: performing rescue path environmental load analysis on the first estimated disaster response rescue management path based on the geographical environment change constraint of the disaster response, and obtaining the disaster area environmental load corresponding to the first estimated disaster rescue path, wherein the disaster area environmental load includes the corresponding building density, abnormal climate change, and terrain and road collapse in the area;

[0071] In an embodiment of the present invention, an appropriate path analysis model is selected based on the geographical environment change constraint of disaster response to calculate the environmental load of the rescue path, so that the first estimated path of disaster response rescue is modeled and analyzed by using a graph theory model and a network analysis tool (such as the path analysis function of ArcGIS or QGIS). In the path analysis, multiple factors of environmental load are considered, including the density of buildings in the area, abnormal climate changes (such as heavy rainfall, typhoons, etc.), and terrain ups and downs and collapses. The analysis of building density can be carried out through spatial statistical technology, such as calculating the building density of each block through building density data, so as to evaluate whether the rescue path needs to be detoured; the assessment of the impact of climate change depends on meteorological monitoring data, and the combination of historical climate data and real-time data is used to predict the potential impact of climate anomalies on the path; terrain analysis analyzes terrain changes through elevation data combined with a digital terrain model (DTM) to identify terrain obstacles (such as landslides, collapses, etc.), and the comprehensive analysis of these data derives the environmental load of the disaster area, and finally obtains the environmental load of the disaster area corresponding to the first estimated path of disaster rescue, which includes the corresponding building density, abnormal climate changes, and terrain road ups and downs and collapses in the area.

[0072] Step S33: performing a quantitative evaluation of the path environmental pressure of the corresponding first estimated disaster response and rescue management path based on the disaster area environmental load corresponding to the first estimated disaster response and rescue path, so as to generate an environmental pressure index of the first estimated disaster response and rescue path;

[0073] In an embodiment of the present invention, a quantitative assessment of the environmental pressure of the first estimated path of disaster rescue is performed based on the environmental load data of the disaster area previously obtained. This assessment process is carried out by establishing an environmental pressure index (EPI, Environmental Pressure Index) model, which takes into account multiple variables, such as building density, climate change, road traffic conditions, terrain complexity, etc. All variables are weighted according to their degree of influence on the path. The environmental pressure index can be modeled using a linear weighted method or a more complex multi-factor decision analysis method. Specifically, each factor (such as building density, climate change, etc.) is assigned a weight value according to its impact on the disaster rescue task, and all factors are converted into a unified quantitative indicator through standardization. Finally, these weights and indicators are synthesized to obtain the environmental pressure index value of the disaster rescue path. This value can accurately reflect the ability of the rescue path to withstand environmental pressure, and finally generate the environmental pressure index of the first estimated path of disaster rescue.

[0074] Step S34: performing disaster response and rescue path environmental constraint optimization on the first estimated disaster response and rescue path based on the environmental pressure index of the first estimated disaster response and rescue path to generate a second estimated disaster response and rescue path;

[0075] In an embodiment of the present invention, the corresponding first estimated management path of disaster response and rescue is optimized under environmental constraints by combining the environmental pressure index obtained by quantification previously. The optimization process adopts intelligent algorithms, such as genetic algorithm (GA) or particle swarm optimization algorithm (PSO). These optimization algorithms can search for the optimal path under complex environmental load constraints. Specifically, by establishing a path optimization model, the environmental pressure index is introduced as a constraint condition in the model, the starting point and end point of the path are set, and the environmental load changes that may occur during the path optimization process (such as road collapse, climate anomalies, etc.) are taken into account. Using the genetic algorithm, multiple alternative paths can be generated by simulating natural selection, and then the advantages and disadvantages of the paths are evaluated according to the size of the environmental pressure index, so as to optimize a new rescue path that adapts to environmental constraints. The optimized path is called the second estimated management path of disaster response and rescue. This path can reduce environmental pressure to the greatest extent, improve rescue efficiency, reduce possible risks and obstacles, and finally generate the second estimated management path of disaster response and rescue.

[0076] Step S35: using the disaster response rescue path deviation calculation formula to measure the path deviation of the first disaster response rescue estimated management path and the second disaster response rescue estimated management path to obtain the disaster response rescue estimated path deviation.

[0077] In an embodiment of the present invention, a suitable disaster response and rescue path deviation calculation formula is formed by combining the deviation metric calculation starting time point, the deviation metric calculation ending time point, the time variable parameter, the relative position distance, the distance deviation metric impact weight coefficient, the arrival time efficiency, the maximum deviation allowed time, the time efficiency deviation metric impact weight coefficient, the road traffic flow, the traffic flow deviation metric impact weight coefficient, the traffic speed, the traffic speed path deviation attenuation coefficient and related parameters to perform path deviation measurement on the first estimated management path of the disaster response and rescue and the second estimated management path of the disaster response and rescue, so as to evaluate the difference between the two paths under the conditions of environmental load and actual disaster changes, and finally obtain the disaster response and rescue estimated path deviation.

[0078] Further, step S31 includes the following steps:

[0079] Perform environmental data standardization on the environmental monitoring data corresponding to the disaster response geospatial block to eliminate the dimensional differences and deviations between the geographical environment and climate environment data sources, and obtain standardized environmental monitoring data;

[0080] In an embodiment of the present invention, in the process of disaster response, the environmental monitoring data involved come from different sources, including climate monitoring stations, geographic information systems (GIS), sensor networks, etc. The dimensional differences of these data will have an adverse effect on the analysis results. In order to eliminate the dimensional differences and deviations between the geographical environment and climate environment data sources, the monitoring data needs to be standardized. First, various environmental monitoring data in the disaster response geographic space block, such as temperature, precipitation, humidity, wind speed, soil moisture, air quality and other parameters, are collected, and these data are converted into dimensionless standardized values ​​through standardization methods such as Z-score standardization or Min-Max normalization. For example, Z-score standardization calculates the difference between each data value and the mean of the data set, and then divides it by the standard deviation of the data set to ensure that the results of each data source are on a unified scale. The standardized data can be further processed and analyzed to ensure the comparability between data sources, and finally obtain environmental monitoring standardized data.

[0081] Preferably, the disaster response geographic spatial block is divided into disaster-affected and non-disaster-affected areas to obtain disaster response geographic disaster-affected sub-areas and disaster response geographic non-disaster-affected sub-areas;

[0082] In an embodiment of the present invention, by accurately dividing the disaster-affected area and identifying the affected sub-areas and non-affected sub-areas, the geographical boundaries of the affected area can be accurately extracted through remote sensing images, geographic information systems (GIS) and post-disaster on-site survey data. This process first uses image processing technology, such as change detection methods based on NDVI (normalized difference vegetation index) and other spectral data, to identify the changed areas of the surface before and after the disaster. By comparing the pre-disaster and post-disaster images, the specific scope of the disaster-affected area is determined, and then spatial analysis tools are used to divide different areas on the GIS platform to clearly distinguish the affected sub-areas from the non-affected sub-areas. In this process, algorithms such as K-means clustering analysis and threshold segmentation method can be used to accurately divide the area in combination with different types of disasters (such as floods, earthquakes, droughts, etc.), and finally obtain disaster response geographical affected sub-areas and disaster response geographical non-disaster sub-areas.

[0083] Preferably, based on the disaster response geographical affected sub-regions and the disaster response geographical non-disaster sub-regions, the corresponding environmental monitoring standardized data are analyzed for regional environmental differences to obtain the degree of environmental differences between the affected sub-regions and the non-disaster sub-regions;

[0084] In an embodiment of the present invention, after completing the division of disaster-affected and non-disaster-affected areas, the next step is to perform regional environmental difference analysis on the environmental monitoring data in these areas, so as to clarify the specific changes caused by the disaster impact on the environment by calculating the degree of difference in environmental monitoring data between the disaster-response geographical disaster-affected sub-areas and the non-disaster-affected sub-areas. In the specific operation process, statistical analysis methods, such as analysis of variance (ANOVA) or t-test, can be used to compare the mean differences and distribution differences in various environmental monitoring data of the two types of areas. For example, the differences in temperature, precipitation, soil moisture, etc. between the disaster-affected areas and the non-disaster-affected areas are analyzed, and the statistical significance of each environmental data is calculated. At the same time, in order to comprehensively analyze the environmental differences, multivariate statistical analysis methods such as principal component analysis (PCA) can also be used to reduce the dimensionality of multidimensional environmental data and extract the main components that affect the environmental differences, thereby evaluating the relative degree of difference in environmental characteristics between different regions, and finally obtaining the degree of environmental difference between the disaster-affected sub-areas and the non-disaster sub-areas.

[0085] Preferably, based on the degree of environmental difference between the disaster-affected sub-areas and the non-disaster-affected sub-areas, a geographic environment change constraint analysis is performed on the corresponding disaster response geographic space blocks to obtain the disaster response geographic environment change constraints corresponding to the disaster response geographic space blocks, which include climate change, geographical environment, and environmental change limiting factors corresponding to the disaster occurrence response.

[0086] In an embodiment of the present invention, based on the degree of environmental difference obtained by the previous analysis, the geographical environment change of the disaster response geographical space block is constrained and analyzed. This step aims to identify the impact of disasters on geographical environment changes and find out the corresponding limiting factors, such as climate change, geographical conditions, type and intensity of disasters, etc. First, the disaster response block is analyzed for change trends using post-disaster environmental monitoring data. Through the geographic information system (GIS) spatial analysis tool, combined with the results of environmental difference analysis, a mathematical model is established to analyze the changes in the geographical environment before and after the disaster. For example, a relationship model between climate variables and geographical environment changes can be established through regression analysis. The model is used to determine the degree of influence of climate factors on environmental changes in disaster areas. At the same time, combined with factors such as topography and land use changes, the constraints of the geographical environment on the changes in disaster response blocks are analyzed. Different models can be used to predict and constrain environmental changes for different types of disasters. For example, flood disasters have a greater impact on wetlands and river areas, while drought disasters have a serious impact on the moisture of farmland soil and vegetation growth. Combined with the long-term trend of climate change, geographical characteristics, and the type and intensity of disasters, the geographical environment change constraints of the disaster response geographic space block are obtained, and finally the disaster response geographical environment change constraints corresponding to the disaster response geographic space block are obtained.

[0087] Furthermore, the calculation formula of the disaster response rescue path deviation in step S35 is specifically:

[0088]

[0089] Where θ is the estimated path deviation of disaster response and rescue, t0 is the starting time point of deviation measurement calculation, and t f is the end time point of the deviation measurement calculation, t is the outer product time variable parameter, t′ is the inner product time variable parameter, D1(t) is the relative position distance of the first estimated management path of disaster response and rescue at time t, D2(t) is the relative position distance of the second estimated management path of disaster response and rescue at time t, α1 is the distance deviation measurement influence weight coefficient, T1(t) is the arrival time efficiency of the first estimated management path of disaster response and rescue at time t, T2(t) is the arrival time efficiency of the second estimated management path of disaster response and rescue at time t, T maxis the maximum allowable deviation time, α2 is the influence weight coefficient of time efficiency deviation measurement, S1(t′) is the road traffic flow of the first estimated management path of disaster response and rescue at time t′, S2(t′) is the road traffic flow of the second estimated management path of disaster response and rescue at time t′, α3 is the influence weight coefficient of traffic flow deviation measurement, V1(t′) is the traffic speed of the first estimated management path of disaster response and rescue at time t′, V2(t′) is the traffic speed of the second estimated management path of disaster response and rescue at time t′, and β is the traffic speed path deviation attenuation coefficient.

[0090] The present invention obtains a disaster response rescue path deviation calculation formula by using a specific mathematical model and verification, which is used to measure the path deviation of the first estimated management path of the disaster response rescue and the second estimated management path of the disaster response rescue. The formula fully considers the disaster response rescue estimated path deviation θ, the deviation measurement calculation starting time point t0, the deviation measurement calculation end time point t f , outer product time variable parameter t, inner product time variable parameter t′, relative position distance D1(t) of the first estimated management path for disaster response and rescue at time t, relative position distance D2(t) of the second estimated management path for disaster response and rescue at time t, distance deviation measurement influence weight coefficient α1, arrival time efficiency T1(t) of the first estimated management path for disaster response and rescue at time t, arrival time efficiency T2(t) of the second estimated management path for disaster response and rescue at time t, maximum deviation allowable time T max , the time efficiency deviation measurement influence weight coefficient α2, the road traffic flow S1(t′) of the first estimated management path of disaster response and rescue at time t′, the road traffic flow S2(t′) of the second estimated management path of disaster response and rescue at time t′, the traffic flow deviation measurement influence weight coefficient α3, the traffic speed V1(t′) of the first estimated management path of disaster response and rescue at time t′, the traffic speed V2(t′) of the second estimated management path of disaster response and rescue at time t′, the traffic speed path deviation attenuation coefficient β, according to the mutual correlation between the disaster response and rescue estimated path deviation θ and the above parameters, a functional relationship is formed:

[0091]

[0092] This formula can realize the path deviation measurement process of the first estimated management path of disaster response and rescue and the second estimated management path of disaster response and rescue. The disaster response and rescue path deviation calculation formula measures the deviation of the disaster response path through multi-dimensional comprehensive calculation, so as to comprehensively evaluate the difference between the first and second paths of disaster rescue. The formula not only considers the relative position distance, time efficiency, traffic flow, traffic speed and other factors of the path, but also quantitatively evaluates these factors by weighting and integrating them, which can comprehensively reflect the changes of the disaster response path at different time nodes. This multi-dimensional comprehensive evaluation makes the optimization of the disaster response path more accurate and can comprehensively identify the potential problems of different paths. By calculating the deviation between different estimated paths, it is helpful to discover and correct the deficiencies in the rescue path planning. The path deviation is not limited to distance, but also covers important factors that affect the rescue efficiency, such as time efficiency, traffic flow and traffic speed. This helps to optimize the path planning more accurately and avoid time delays or resource waste caused by unreasonable path design in the actual disaster response process. The integral term in the formula (including the outer product time variable and the inner product time variable) enables the path deviation measure to dynamically adapt to the spatiotemporal changes in the disaster response process, which can accurately reflect the actual performance of the disaster response path over time and the changes in the disaster situation, and provide a more flexible basis for path adjustment. By evaluating the environmental load changes of the path in real time, the path can be quickly adjusted according to the development of the disaster to ensure the timeliness and efficiency of the rescue operation. The formula takes into account the impact of multiple environmental factors on path selection, such as building density, abnormal climate changes, and terrain undulations. The changes in these factors will directly affect the feasibility and efficiency of the rescue path. The formula helps identify which areas of the path may be greatly affected by the environmental load by calculating the deviation of the environmental load, thereby optimizing the path selection, avoiding inappropriate path design, and improving the overall rescue effect. The various weighted coefficients in the formula can be flexibly adjusted according to different emergency needs and environmental conditions, which allows the path deviation measure to be customized according to actual conditions. For example, in busy traffic or bad weather conditions, more attention needs to be paid to the deviation of time efficiency or traffic flow, while in complex terrain environments, the spatial distance and accessibility of the path become more important reference factors. By introducing factors such as traffic flow and speed attenuation, it can adapt to complex traffic environments and disaster site conditions. For example, in some disaster areas, traffic flow changes due to blockage or damage. The formula can dynamically reflect the impact of these changes on path deviation, helping decision makers to adjust emergency path planning in a timely manner. In addition, the traffic speed attenuation of the path can also be adjusted through coefficients, thereby more realistically simulating the complex road conditions after the disaster.This refined path deviation assessment can promote long-term optimization of disaster response rescue paths. After a disaster occurs, rescue operations are not completed in a short period of time. Many emergency actions need to be adjusted at different stages and time points. The path deviation measurement method provided by the formula can support continuous path monitoring and optimization, ensuring that the rescue path is always in the best condition under changes in disaster conditions and environment, thereby improving the overall efficiency of emergency response.

[0093] Further, step S4 includes the following steps:

[0094] Step S41: comparing and judging the estimated path deviation of disaster response and rescue according to a preset path deviation threshold, if the estimated path deviation of disaster response and rescue is less than the preset path deviation threshold, then performing intelligent management of emergency intervention for the corresponding disaster response distribution position in the disaster response geographic space block according to the second estimated management path of disaster response and rescue;

[0095] In an embodiment of the present invention, the previously quantified disaster response and rescue estimated path deviation is compared and judged according to a preset path deviation threshold. In specific implementation, the actual deviation value of the disaster response and rescue estimated path is calculated by collecting and analyzing the historical data, geographic spatial information and real-time disaster development of the current disaster response path. If the actual path deviation is less than the preset threshold (for example, the set path deviation threshold is 10 kilometers), intelligent management of rescue intervention is performed according to a more optimized disaster response and rescue second estimated management path. The management path combines a geographic information system (GIS) to accurately calibrate the disaster response distribution position within the disaster response geographic spatial block, and adjusts the intervention strategy through an intelligent algorithm according to the characteristics of different types of disasters (such as floods, earthquakes, fires, etc.) to achieve fast and efficient rescue operations. For example, if the deviation of the rescue path is small and within the threshold range, the rescue force can be immediately dispatched to the disaster area ahead according to the second estimated management path.

[0096] Step S42: if the disaster response and emergency rescue estimated path deviation is greater than or equal to a preset path deviation threshold, then a deviation evolution dynamic correction analysis is performed on the disaster response and emergency rescue estimated path deviation to obtain a disaster response and emergency rescue estimated path deviation evolution correction factor;

[0097] In an embodiment of the present invention, when the deviation of the disaster response and rescue estimated path is greater than or equal to a preset path deviation threshold, the deviation evolution dynamic correction analysis stage is entered. In this step, the historical data of the disaster response path is first deeply learned through big data analysis, including path deviation, historical patterns of disaster response, meteorological information and geographical changes, etc. Then, machine learning algorithms, such as regression analysis and time series analysis, are used to predict and correct the deviation change trend of the disaster response path. Through these analyses, a deviation evolution correction factor is obtained, which can accurately and dynamically adjust the deviation of the disaster response path. For example, if the deviation of the current path exceeds 10 kilometers and continues to grow, the correction factor will automatically generate adjustment suggestions based on historical patterns, thereby reducing deviations in future path planning, and finally obtaining a disaster rescue estimated path deviation evolution correction factor.

[0098] Step S43: Calculate the path deviation penalty for the first disaster response and rescue estimated management path and the second disaster response and rescue estimated management path based on the disaster response and rescue estimated path deviation evolution correction factor using the path deviation penalty calculation formula to obtain the disaster response and rescue estimated path deviation penalty;

[0099] In an embodiment of the present invention, a suitable path deviation penalty calculation formula is formed by combining the spatial area where the disaster response path is located, the spatial coordinates of the disaster response path, the spatial resource penalty weight coefficient, the speed vector, the available resource density, the disaster rescue estimated path deviation evolution correction factor, the resource distribution vector and related parameters to perform path deviation penalty calculation on the first estimated management path of the disaster response rescue and the second estimated management path of the disaster response rescue to quantify the impact of the path deviation on the disaster response efficiency, and finally obtain the disaster response rescue estimated path deviation penalty.

[0100] Step S44: performing path deviation penalty simulation optimization on the second disaster response and emergency rescue estimated management path based on the disaster response and emergency rescue estimated path deviation penalty to generate a disaster response and emergency rescue deviation penalty optimized management path;

[0101] In an embodiment of the present invention, after calculating the deviation penalty result of the estimated path of disaster response and rescue, a path deviation penalty simulation optimization is performed on the second estimated management path of disaster response and rescue. The specific operation is to simulate multiple possible scenarios of the disaster response path and optimize the path in combination with the result of the path deviation penalty. The optimization process relies on advanced path planning algorithms, such as A* algorithm, Dijkstra algorithm, etc. These algorithms recalculate the rescue path according to the optimization objectives (such as shortest path, fastest response time, and least risk). In the simulation optimization process, multiple optimized paths will be generated, and the deviation penalty value of each path will be evaluated to obtain the optimal path. Assuming that the deviation of the second estimated path is large, it will be adjusted according to the path penalty result to generate a more reasonable rescue path, which can minimize the path deviation in actual operation. For example, under severe weather conditions, the path optimization process can be dynamically adjusted to select a route with less weather impact, and finally optimize the generated disaster rescue deviation penalty optimization management path.

[0102] Step S45: performing rescue path optimization management for the disaster response distribution locations corresponding to the disaster response geographic space block according to the disaster rescue deviation penalty optimization management path.

[0103] In an embodiment of the present invention, path optimization management is performed on the disaster response distribution positions within the disaster response geographic space block based on the optimized disaster rescue deviation penalty management path. At this stage, real-time monitoring technology, drone patrol data and sensor networks are used to continuously track the real-time dynamics within the disaster area, and GIS and big data analysis platforms are used to accurately locate the specific location of the disaster area, and optimize the path on this basis. Through the real-time feedback mechanism, the optimized path can be dynamically adjusted according to geographic information and actual rescue needs. For example, in actual disaster response, if it is found that roads in certain areas are impassable or new dangerous areas appear, the scheduling plan can be readjusted according to the optimized path. Based on precise path planning and path optimization management, disaster response actions can be completed more efficiently, thereby improving the timeliness and accuracy of rescue.

[0104] Furthermore, the path deviation penalty calculation formula in step S43 is specifically:

[0105]

[0106] Where P peis the penalty for the deviation of the disaster response and rescue estimated path, Ω is the spatial area where the disaster response path is located, x is the spatial coordinate of the disaster response path, γ is the spatial resource penalty weight coefficient, v1(x) is the velocity vector of the first estimated management path of disaster response and rescue at the spatial position x, v2(x) is the velocity vector of the second estimated management path of disaster response and rescue at the spatial position x, ρ(x) is the available resource density at the spatial position x, ε is the correction factor for the deviation evolution of the disaster response and rescue estimated path, u1(x) is the resource distribution vector of the first estimated management path of disaster response and rescue at the spatial position x, u2(x) is the resource distribution vector of the second estimated management path of disaster response and rescue at the spatial position x, and η is the correction coefficient for the penalty for the deviation of the disaster response and rescue estimated path.

[0107] The present invention obtains a path deviation penalty calculation formula by using a specific mathematical model and verifying it, which is used to calculate the path deviation penalty for the first estimated management path of disaster response and rescue and the second estimated management path of disaster response and rescue. The path deviation penalty calculation formula can dynamically correct the deviation between the actual disaster response path and the expected path through the evolution correction factor of the path deviation and the calculation of the path deviation penalty, which makes it possible to adapt to the changes of the disaster site in real time, such as the progress of the disaster, changes in resource conditions, traffic closures or new obstacles. The dynamic correction analysis of the deviation evolution in the formula ensures that the path prediction can be self-adjusted to avoid fixed path planning leading to inefficiency or rescue operations cannot proceed smoothly. The formula integrates multiple factors such as speed vector, resource density, resource distribution, etc. Through these factors, the feasibility and optimization potential of different paths in a specific spatial area can be more accurately evaluated. The speed vector reflects the real-time travel speed of different paths. Combined with the resource density and resource distribution vector, the path selection can be optimized so that the rescue team can reach the disaster area as quickly as possible. By introducing the spatial resource penalty weight coefficient, the scarcity or importance of resources in different spatial regions can be reflected. By adjusting the coefficient, higher priority can be given to resource-scarce or key areas, thereby ensuring that resource utilization efficiency can be maximized in key areas, so that the optimal allocation of resources can be achieved when optimizing the path, and response delays in some areas can be avoided due to excessive concentration or insufficient resources. The penalty formula comprehensively considers the optimization of two estimated management paths (the first estimated path and the second estimated path), which helps to avoid the limitations of single path planning, thereby improving the flexibility of emergency response. The role of path deviation penalty makes it possible to maintain disaster response efficiency and accuracy by appropriately adjusting the second path even if there is a large deviation between the first path and the second path. Through the penalty terms in the formula (such as speed, resource distribution, resource density, etc.), the path can be adjusted in real time to avoid manual adjustments that rely too much on fixed rules. This makes path planning more intelligent in the disaster response process, reduces the probability of human errors, and improves overall rescue efficiency. This path adjustment based on real-time data can effectively respond to post-disaster environmental changes, such as road damage, traffic congestion and other emergencies, thereby ensuring fast and efficient rescue operations. In summary, this formula fully considers the disaster response rescue estimation path deviation penalty P pe, the spatial area Ω where the disaster response path is located, the spatial coordinates x of the disaster response path, the spatial resource penalty weight coefficient γ, the velocity vector v1(x) of the first estimated management path of the disaster response rescue at the spatial position x, the velocity vector v2(x) of the second estimated management path of the disaster response rescue at the spatial position x, the available resource density ρ(x) at the spatial position x, the deviation evolution correction factor ε of the disaster response rescue estimated path, the resource distribution vector u1(x) of the first estimated management path of the disaster response rescue at the spatial position x, the resource distribution vector u2(x) of the second estimated management path of the disaster response rescue at the spatial position x, the correction coefficient η of the deviation penalty of the disaster response rescue estimated path, according to the deviation penalty P of the disaster response rescue estimated path pe The correlation between the above parameters constitutes a functional relationship This formula can realize the path deviation penalty calculation process for the first estimated management path of disaster response and rescue and the second estimated management path of disaster response and rescue. At the same time, by introducing the correction coefficient η of the disaster response and rescue estimated path deviation penalty, it can be adjusted according to the error situation occurring in the calculation process, thereby improving the accuracy and applicability of the path deviation penalty calculation formula.

[0108] Furthermore, the present invention also provides a land space path intelligent management system based on big data analysis, which is used to execute the land space path intelligent management method based on big data analysis as described above, and the land space path intelligent management system based on big data analysis includes:

[0109] The target block geographic science information collection module is used to obtain the target land geospatial model, and use the geographic information collection equipment to collect geographic science information on the corresponding disaster response geospatial block in the target land geospatial model, so as to obtain a target disaster response geospatial information big data set, including the target geospatial location distribution, land use data, traffic flow data and environmental monitoring data corresponding to the disaster response geospatial block; the target disaster response geospatial information big data set is transmitted to the big data processing platform in real time through the big data transmission network;

[0110] The first disaster rescue path estimation module is used to estimate the disaster rescue path based on the land use data and traffic flow data corresponding to the disaster response geospatial block using the big data processing platform for the corresponding target geospatial location distribution, so as to generate the first disaster response rescue estimation management path;

[0111] The rescue path environmental constraint and deviation measurement module is used to obtain the corresponding disaster response geographic environment change constraints through the environmental monitoring data corresponding to the disaster response geographic space block, and optimize the rescue path environmental constraints of the first disaster response rescue estimate management path based on the disaster response geographic environment change constraints to generate the second disaster response rescue estimate management path; measure the path deviation according to the first disaster response rescue estimate management path and the second disaster response rescue estimate management path, so as to obtain the disaster response rescue estimate path deviation;

[0112] The emergency rescue estimated path deviation penalty management module is used to compare and judge the disaster response emergency rescue estimated path deviation according to a preset path deviation threshold. If the disaster response emergency rescue estimated path deviation is less than the preset path deviation threshold, the disaster response geographic space block is intelligently managed according to the disaster response emergency rescue second estimated management path; if the disaster response emergency rescue estimated path deviation is greater than or equal to the preset path deviation threshold, the path deviation penalty is calculated for the disaster response emergency rescue first estimated management path and the disaster response emergency rescue second estimated management path based on the disaster response emergency rescue estimated path deviation to obtain the disaster response emergency rescue estimated path deviation penalty; the disaster response geographic space block is optimized for emergency rescue path management based on the disaster response emergency rescue estimated path deviation penalty and the disaster response emergency rescue second estimated management path.

[0113] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for intelligent management of national land space paths based on big data analysis, characterized in that: The following steps are involved: Step S1: Obtain the target national territory geospatial model, and use geographic information collection equipment to collect geographic science information on the corresponding disaster response geospatial blocks in the target national territory geospatial model to obtain a target disaster response geospatial information big data set, including the target geospatial location distribution, land use data, traffic flow data and environmental monitoring data corresponding to the disaster response geospatial blocks; transmit the target disaster response geospatial information big data set to the big data processing platform in real time through the big data transmission network; Step S2: Based on the land use data and traffic flow data corresponding to the disaster response geographic space block, a big data processing platform is used to estimate the disaster rescue path for the corresponding target geographic space location distribution to generate a first estimated management path for disaster response rescue; Step S3: Obtaining corresponding disaster response geographic environment change constraints through environmental monitoring data corresponding to the disaster response geographic space block, and optimizing the first estimated management path of disaster response rescue based on the disaster response geographic environment change constraints to generate a second estimated management path of disaster response rescue; Path deviation measurement is performed according to the first estimated management path of disaster response and rescue and the second estimated management path of disaster response and rescue to obtain the estimated path deviation of disaster response and rescue; Step S4: Compare and judge the disaster response and rescue estimated path deviation according to a preset path deviation threshold. If the disaster response and rescue estimated path deviation is less than the preset path deviation threshold, the disaster response and rescue second estimated management path is used to perform intelligent management of rescue intervention for the disaster response geographic space block; if the disaster response and rescue estimated path deviation is greater than or equal to the preset path deviation threshold, the disaster response and rescue first estimated management path and the disaster response and rescue second estimated management path are calculated based on the disaster response and rescue estimated path deviation to obtain the disaster response and rescue estimated path deviation penalty; based on the disaster response and rescue estimated path deviation penalty and the disaster response and rescue second estimated management path, the disaster response geographic space block is optimized for rescue path management.

2. The method for intelligent management of national land space paths based on big data analysis according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: Obtaining the target land geographic spatial model; Step S12: performing disaster response spatial division on the target land geographic spatial model to obtain disaster response geographic spatial blocks; Step S13: using geographic information collection equipment to collect geographic science information on the disaster response geographic space block to obtain a target disaster response geographic science information big data set, including the target geographic space location distribution, land use data, traffic flow data and environmental monitoring data corresponding to the disaster response geographic space block; Step S14: The target disaster response geographic science information big data set is transmitted in real time to the big data processing platform through the big data transmission network.

3. The method for intelligent management of national land space paths based on big data analysis according to claim 2 is characterized in that: Step S13 includes the following steps: Step S131: using a GPS positioning device to perform target geospatial positioning processing on the target disaster response position corresponding to the disaster response geospatial block, so as to obtain the target geospatial position distribution corresponding to the disaster response geospatial block; Step S132: using a geographic information system to refine the land use attributes of the disaster response geographic space block to obtain land use data corresponding to the disaster response geographic space block, wherein the land use data includes land use type, land building facility distribution, and land population distribution density; Step S133: using traffic flow collection equipment to monitor the traffic flow of the disaster response geographic space block in real time, and obtaining traffic flow data corresponding to the disaster response geographic space block, wherein the traffic flow data includes traffic network flow density, traffic network travel efficiency and traffic network congestion status; Step S134: using environmental monitoring equipment to monitor environmental changes in the disaster response geographic space block in real time, and obtaining environmental monitoring data corresponding to the disaster response geographic space block, wherein the environmental monitoring data includes disaster geographic environment data and climate environment data; Step S135: integrating the target geographic spatial location distribution, land use data, traffic flow data and environmental monitoring data corresponding to the disaster response geographic spatial block to obtain a large dataset of target disaster response geographic scientific information.

4. The method for intelligent management of national land space paths based on big data analysis according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: using a big data processing platform to dynamically analyze the land use pattern of the land use data corresponding to the disaster response geographic space block, and obtain the land use change pattern around the disaster response block; Step S22: obtaining the initial location distribution of the disaster rescue response, and performing disaster response rescue path simulation on the target geographic space location distribution corresponding to the disaster response geographic space block based on the initial location distribution of the disaster rescue response, so as to generate a disaster response rescue path simulation network corresponding to the starting location distribution to the target location distribution; Step S23: Based on the land use change pattern and traffic flow data around the disaster response block, each disaster response emergency path in the disaster response emergency path simulation network is evaluated and analyzed for traffic accessibility, so as to obtain a traffic accessibility index corresponding to each disaster response emergency path; Step S24: performing feasibility optimization estimation on each corresponding disaster response emergency path in the disaster response emergency path simulation network based on the traffic accessibility index corresponding to each disaster response emergency path, and obtaining the disaster response emergency feasibility optimization estimation path; Step S25: Obtain disaster rescue resource scheduling and personnel deployment decision-making goals, and perform rescue path management collaborative optimization on the disaster response and rescue feasibility optimization estimated path based on the disaster rescue resource scheduling and personnel deployment decision-making goals to generate a first disaster response and rescue estimated management path.

5. The method for intelligent management of national land space paths based on big data analysis according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: obtaining corresponding disaster response geographic environment change constraints through environmental monitoring data corresponding to the disaster response geographic space block; Step S32: performing rescue path environmental load analysis on the first estimated disaster response rescue management path based on the geographical environment change constraint of the disaster response, and obtaining the disaster area environmental load corresponding to the first estimated disaster rescue path, wherein the disaster area environmental load includes the corresponding building density, abnormal climate change, and terrain and road collapse in the area; Step S33: performing a quantitative evaluation of the path environmental pressure of the corresponding first estimated disaster response and rescue management path based on the disaster area environmental load corresponding to the first estimated disaster response and rescue path, so as to generate an environmental pressure index of the first estimated disaster response and rescue path; Step S34: performing disaster response and rescue path environmental constraint optimization on the first estimated disaster response and rescue path based on the environmental pressure index of the first estimated disaster response and rescue path to generate a second estimated disaster response and rescue path; Step S35: using the disaster response rescue path deviation calculation formula to measure the path deviation of the first disaster response rescue estimated management path and the second disaster response rescue estimated management path to obtain the disaster response rescue estimated path deviation.

6. The method for intelligent management of national land space paths based on big data analysis according to claim 5 is characterized in that: Step S31 includes the following steps: Perform environmental data standardization on the environmental monitoring data corresponding to the disaster response geospatial block to eliminate the dimensional differences and deviations between the geographical environment and climate environment data sources, and obtain standardized environmental monitoring data; Divide the disaster response geographic spatial block into disaster-affected and non-disaster-affected areas to obtain disaster response geographic disaster-affected sub-areas and disaster response geographic non-disaster-affected sub-areas; Based on the disaster response geographical affected sub-regions and the disaster response geographical non-disaster sub-regions, the corresponding environmental monitoring standardized data are analyzed for regional environmental differences to obtain the degree of environmental differences between the affected sub-regions and the non-disaster sub-regions; Based on the degree of environmental difference between the disaster-affected sub-areas and the non-disaster-affected sub-areas, the corresponding disaster response geospatial blocks are subjected to geographic environmental change constraint analysis to obtain the disaster response geospatial blocks' corresponding geographic environmental change constraints, which include climate change, geographical environment, and environmental change limiting factors corresponding to disaster response.

7. The method for intelligent management of national land space paths based on big data analysis according to claim 5 is characterized in that: The calculation formula of the disaster response rescue path deviation in step S35 is specifically: In the formula, is the estimated path deviation of disaster response and rescue, t0 is the starting time point of deviation measurement calculation, and t f is the end time point of deviation measurement calculation, t is the outer product time variable parameter, t ′ is the inner product time variable parameter, D1(t) is the relative position distance of the first estimated management path of disaster response and rescue at time t, D2(t) is the relative position distance of the second estimated management path of disaster response and rescue at time t, α1 is the distance deviation measurement influence weight coefficient, T1(t) is the arrival time efficiency of the first estimated management path of disaster response and rescue at time t, T2(t) is the arrival time efficiency of the second estimated management path of disaster response and rescue at time t, T max is the maximum deviation allowed time, α2 is the time efficiency deviation measurement impact weight coefficient, S1(t ′ ) is the first estimated management path for disaster response and rescue at time t ′ The road traffic flow at the moment, S2(t ′ ) is the second estimated management path for disaster response and rescue at time t ′ The road traffic flow at the time, α3 is the traffic flow deviation measurement impact weight coefficient, V1(t ′ ) is the first estimated management path for disaster response and rescue at time t ′ Traffic speed at the time, V2(t ′ ) is the second estimated management path for disaster response and rescue at time t ′ The traffic speed at the time, β is the traffic speed path deviation attenuation coefficient.

8. The method for intelligent management of national land space paths based on big data analysis according to claim 1 is characterized in that: Step S4 includes the following steps: Step S41: comparing and judging the estimated path deviation of disaster response and rescue according to a preset path deviation threshold, if the estimated path deviation of disaster response and rescue is less than the preset path deviation threshold, then performing intelligent management of emergency intervention for the corresponding disaster response distribution position in the disaster response geographic space block according to the second estimated management path of disaster response and rescue; Step S42: if the disaster response and emergency rescue estimated path deviation is greater than or equal to a preset path deviation threshold, then a deviation evolution dynamic correction analysis is performed on the disaster response and emergency rescue estimated path deviation to obtain a disaster response and emergency rescue estimated path deviation evolution correction factor; Step S43: Calculate the path deviation penalty for the first disaster response and rescue estimated management path and the second disaster response and rescue estimated management path based on the disaster response and rescue estimated path deviation evolution correction factor using the path deviation penalty calculation formula to obtain the disaster response and rescue estimated path deviation penalty; Step S44: performing path deviation penalty simulation optimization on the second disaster response and emergency rescue estimated management path based on the disaster response and emergency rescue estimated path deviation penalty to generate a disaster response and emergency rescue deviation penalty optimized management path; Step S45: performing rescue path optimization management for the disaster response distribution locations corresponding to the disaster response geographic space block according to the disaster rescue deviation penalty optimization management path.

9. The method for intelligent management of national land space paths based on big data analysis according to claim 8 is characterized in that: The path deviation penalty calculation formula in step S43 is specifically: Where P pe is the penalty for the deviation of the disaster response and rescue estimated path, Ω is the spatial area where the disaster response path is located, x is the spatial coordinate of the disaster response path, γ is the spatial resource penalty weight coefficient, v1(x) is the velocity vector of the first estimated management path of disaster response and rescue at the spatial position x, v2(x) is the velocity vector of the second estimated management path of disaster response and rescue at the spatial position x, ρ(x) is the available resource density at the spatial position x, ε is the correction factor for the deviation evolution of the disaster response and rescue estimated path, u1(x) is the resource distribution vector of the first estimated management path of disaster response and rescue at the spatial position x, u2(x) is the resource distribution vector of the second estimated management path of disaster response and rescue at the spatial position x, and η is the correction coefficient for the penalty for the deviation of the disaster response and rescue estimated path.

10. A national land space path intelligent management system based on big data analysis, characterized in that: Used to execute the land space path intelligent management method based on big data analysis as claimed in claim 1, the land space path intelligent management system based on big data analysis includes: The target block geographic science information collection module is used to obtain the target land geospatial model, and use the geographic information collection equipment to collect geographic science information on the corresponding disaster response geospatial block in the target land geospatial model, so as to obtain a target disaster response geospatial information big data set, including the target geospatial location distribution, land use data, traffic flow data and environmental monitoring data corresponding to the disaster response geospatial block; the target disaster response geospatial information big data set is transmitted to the big data processing platform in real time through the big data transmission network; The first disaster rescue path estimation module is used to estimate the disaster rescue path based on the land use data and traffic flow data corresponding to the disaster response geospatial block using the big data processing platform for the corresponding target geospatial location distribution, so as to generate the first disaster response rescue estimation management path; The rescue path environmental constraint and deviation measurement module is used to obtain the corresponding disaster response geographic environment change constraints through the environmental monitoring data corresponding to the disaster response geographic space block, and optimize the rescue path environmental constraints of the first disaster response rescue estimate management path based on the disaster response geographic environment change constraints to generate the second disaster response rescue estimate management path; measure the path deviation according to the first disaster response rescue estimate management path and the second disaster response rescue estimate management path, so as to obtain the disaster response rescue estimate path deviation; The emergency rescue estimated path deviation penalty management module is used to compare and judge the disaster response emergency rescue estimated path deviation according to a preset path deviation threshold. If the disaster response emergency rescue estimated path deviation is less than the preset path deviation threshold, the disaster response geographic space block is intelligently managed according to the disaster response emergency rescue second estimated management path; if the disaster response emergency rescue estimated path deviation is greater than or equal to the preset path deviation threshold, the path deviation penalty is calculated for the disaster response emergency rescue first estimated management path and the disaster response emergency rescue second estimated management path based on the disaster response emergency rescue estimated path deviation to obtain the disaster response emergency rescue estimated path deviation penalty; the disaster response geographic space block is optimized for emergency rescue path management based on the disaster response emergency rescue estimated path deviation penalty and the disaster response emergency rescue second estimated management path.

Images