Three-proofing emergency command method and system based on meteorological big data

Abstract

The invention belongs to the technical field of emergency management, and discloses a three-proofing emergency command method and system based on meteorological big data. Comprising the following steps: collecting disaster meteorological associated data, and identifying meteorological evolution modes corresponding to various disasters; collecting current meteorological data and environment state data in real time, and generating a three-proofing risk progressive curve; acquiring weather forecast data, calculating weather similarities between the weather forecast data and the weather evolution modes, predicting disaster risk factors of various disasters in combination with a three-proofing risk progressive curve, and determining intervention disasters; according to disaster risk factors of the intervention disaster, feasible time periods and expected effects of different artificial influence weather operations are analyzed; the optimal operation type and the optimal time window are intelligently identified, three-proofing emergency resources are intelligently scheduled, and a preventive resource deployment scheme is generated; according to the invention, a full-chain intelligent three-proofing emergency command system is constructed, and the technical bottlenecks of a traditional emergency system in the aspects of early warning timeliness, intervention capability, resource allocation and the like are broken through.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of emergency management, more particularly, the present application relates to a three-proof emergency command method and system based on meteorological big data. BACKGROUND

[0002] Traditional three-proof emergency management mainly relies on emergency response after disaster occurs, and simple threshold early warning is carried out through limited data provided by meteorological monitoring stations. When the monitoring index exceeds the preset value, the emergency plan is started. This passive emergency mode has problems such as poor timeliness of early warning, lagging resource allocation, and single disaster prevention measures. Although meteorological monitoring technology has developed rapidly in recent years, a large amount of historical meteorological data and real-time monitoring data has been accumulated, but the existing system only uses these meteorological big data for weather forecasting and simple disaster warning, and fails to deeply mine the internal correlation between meteorological evolution mode and disaster occurrence, resulting in lack of scientific basis for disaster prevention decision-making.

[0003] The existing three-proof emergency command system has many technical defects: first, it lacks dynamic monitoring capability for disaster formation process, and cannot quantitatively evaluate the state evolution and risk accumulation process of disaster-bearing bodies (such as forest flammable materials, watershed soil, buildings, etc.) under the action of meteorological conditions; second, it lacks active intervention mechanism, and only starts emergency response when disaster is about to occur or has occurred, missing the best opportunity to eliminate disaster hazards in advance through artificial weather modification; third, it fails to fully utilize the value of meteorological big data, and cannot predict disaster risks through similarity analysis of historical disaster cases and current meteorological conditions; fourth, the emergency resource scheduling lacks foresight, and often only after the disaster occurs, the resources are urgently allocated, causing rescue delay and resource waste; therefore, an intelligent three-proof emergency command system is urgently needed, which can fully mine the value of meteorological big data, realize dynamic monitoring of disaster risks, and support active intervention decision-making.

[0004] In view of this, the present application proposes a three-proof emergency command method and system based on meteorological big data to solve the above problems. SUMMARY

[0005] In order to overcome the above-mentioned defects of the prior art and achieve the above-mentioned purpose, the present application provides the following technical scheme: a three-proof emergency command method based on meteorological big data, comprising: Collecting disaster meteorological correlation data, identifying meteorological evolution modes corresponding to various disasters in the disaster meteorological correlation data, and constructing a three-proof meteorological precursor mode library; Real-time acquisition of current meteorological data and environmental state data, evaluation of progressive evolution process of vulnerability of disaster-bearing bodies corresponding to various disasters, and generation of a three-proof risk progression curve; acquire meteorological forecast data, calculate the meteorological similarity between the meteorological forecast data and each meteorological evolution mode in the three-proof meteorological precursor mode library, and combine the three-proof risk progression curve to predict the disaster risk elements of each type of disaster, and determine the intervention disaster based on the disaster risk elements; According to the disaster risk elements of the intervention disaster, analyze the feasible time period and expected effect of different artificial weather modification operations corresponding to the intervention disaster, and intelligently identify the best operation type and best time window based on the feasible time period and expected effect; Based on the best operation type and best time window of the intervention disaster, intelligently schedule three-proof emergency resources, generate a preventive resource deployment scheme, and command various disaster prevention forces to execute the preventive resource deployment scheme.

[0006] Further, the method for collecting disaster meteorological correlation data comprises: acquire historical meteorological data covering the target area, the historical meteorological data including meteorological observation records collected at each historical time in the target area; acquire disaster archive data corresponding to the same period as the historical meteorological data, the disaster archive data including records of various disaster events that have occurred in the target area in the past; According to the occurrence time in each disaster event record, extract the corresponding correlation meteorological sequence from the historical meteorological data; perform meteorological element splitting on each correlation meteorological sequence to obtain a meteorological element sequence corresponding to each meteorological element; and associate each meteorological element sequence with the corresponding disaster event record to form disaster meteorological correlation data.

[0007] Further, the method for constructing the three-proof meteorological precursor mode library comprises: According to the disaster type of each disaster event record in the disaster meteorological correlation data, the disaster meteorological correlation data is divided into a fire correlation data set, a flood correlation data set, and a wind disaster correlation data set; For the fire correlation data set, extract the meteorological evolution mode of fire and use it as a fire precursor mode; For the flood correlation data set, extract the meteorological evolution mode of flood and use it as a flood precursor mode; For the wind disaster correlation data set, extract the meteorological evolution mode of wind disaster and use it as a wind disaster precursor mode; The fire precursor mode, the flood precursor mode, and the wind disaster precursor mode are summarized to construct the three-proof meteorological precursor mode library.

[0008] Further, the method for generating the three-proof risk progression curve comprises: The current meteorological data includes meteorological observation records collected at the current time in the target area; the environmental state data includes fire state data, flood state data, and wind disaster state data; The fire state data includes combustible moisture content and ground dryness, the flood state data includes soil moisture content, river water level and drainage pipe network load rate, and the wind disaster state data includes building wind resistance grade, temporary facility number and tree lodging risk index. According to the current meteorological data and the fire state data, the progressive evolution process of the fire corresponding to the vulnerability of the disaster-bearing body is evaluated, a progressive sequence of fire vulnerability is formed, and a progressive curve of fire risk is drawn. According to the current meteorological data and the flood state data, the progressive evolution process of the flood corresponding to the vulnerability of the disaster-bearing body is evaluated, a progressive sequence of flood vulnerability is formed, and a progressive curve of flood risk is drawn. According to the current meteorological data and the wind disaster state data, the progressive evolution process of the wind disaster corresponding to the vulnerability of the disaster-bearing body is evaluated, a progressive sequence of wind disaster vulnerability is formed, and a progressive curve of wind disaster risk is drawn. The progressive curves of fire risk, flood risk and wind disaster risk are integrated to generate a three-protection risk progressive curve.

[0009] Further, the method for predicting disaster risk elements of various disasters includes: The meteorological forecast data includes meteorological forecast records of the target area at each future time. From the meteorological forecast data, a fire forecast vector, a flood forecast vector and a wind disaster forecast vector are sequentially extracted, and a fire meteorological similarity corresponding to the fire forecast vector, a flood meteorological similarity corresponding to the flood forecast vector and a wind disaster meteorological similarity corresponding to the wind disaster forecast vector are calculated. The progressive evolution value of each future time is predicted by trend extrapolation of the fire risk progressive curve, forming a fire prediction progressive curve. The time when the progressive evolution value first reaches the preset fire progressive threshold in the fire prediction progressive curve is obtained and marked as the fire critical time. The fire remaining time is calculated according to the fire critical time and the current time. The risk evolution rate is calculated according to the fire risk progressive curve. The fire meteorological similarity and the risk evolution rate are weighted and summed based on the preset fire risk weight to obtain the fire occurrence probability. The fire influence range is obtained according to the fire meteorological similarity corresponding to the fire precursor mode. The fire risk elements are formed by integrating the fire remaining time, the fire occurrence probability and the fire influence range. According to the prediction method of the fire risk elements, the disaster risk elements of the flood and the wind disaster are predicted respectively, and are taken as the flood risk elements and the wind disaster risk elements respectively.

[0010] Further, the method for determining intervention disasters based on disaster risk elements includes: The intervention necessity judgment is sequentially performed for each group of disaster risk elements; a fire intervention threshold is preset, and the fire disaster risk elements are compared with the fire intervention threshold; the fire intervention threshold includes a fire time threshold and a fire probability threshold; if the fire remaining time is less than or equal to the fire time threshold, and the fire occurrence probability is greater than or equal to the fire probability threshold, it is determined that the fire needs intervention; if the fire remaining time is greater than the fire time threshold, or the fire occurrence probability is less than the fire probability threshold, it is determined that the fire does not need intervention; the same determination method is used to determine the intervention necessity of floods and wind disasters according to the flood risk elements and the wind disaster risk elements, respectively; All disaster types determined to need intervention are collected to form an intervention disaster list; if there are multiple disaster types in the intervention disaster list, the intervention urgency of each disaster type in the intervention disaster list is calculated, the disaster types in the intervention disaster list are sorted in descending order according to the intervention urgency, and an intervention disaster sequence is generated; according to the ascending order of the intervention disaster sequence, each disaster type is marked as an intervention disaster in turn, and a decreasing numerical label is set as the disaster priority of each disaster type.

[0011] Further, the method for analyzing the feasible time period and the expected effect of the intervention disaster corresponding to different artificial weather modification operations comprises: According to the disaster type of the intervention disaster, a corresponding candidate operation type set is obtained from a pre-constructed operation type library; the candidate operation type set includes a candidate operation type and an operation implementation condition, and the candidate operation type is an artificial weather modification operation type; meteorological forecast records of each future time are extracted from meteorological forecast data, and each meteorological forecast record of each future time is compared with each operation implementation condition item by item; if the parameters in the meteorological forecast record meet the same operation implementation condition, the corresponding future time is taken as a feasible time for the corresponding candidate operation type; the feasible time period corresponding to each candidate operation type is collected to form the feasible time period corresponding to each candidate operation type; Different numerical labels are set for different candidate operation types and are marked as operation labels; the disaster risk elements of each candidate operation type corresponding to the intervention disaster, the meteorological forecast record of each feasible time, and the operation label are combined to obtain a plurality of change prediction sets; each change prediction set is input into a trained change prediction model to predict a meteorological change set of each intervention disaster after the action of each candidate operation type at different feasible times, and the meteorological change set is taken as the expected effect of each candidate operation type; the meteorological change set includes temperature change value, relative humidity change value, wind speed change value, and precipitation change value.

[0012] Further, the method for intelligently identifying the best operation type and the best time window comprises: The feasible time period of each candidate operation type is compared with the disaster remaining time corresponding to the disaster intervention, the disaster remaining time includes the fire disaster remaining time, the flood disaster remaining time and the wind disaster remaining time, if at least one feasible time in the feasible time period is within the corresponding disaster remaining time, the corresponding candidate operation type is taken as an effective operation type; According to the expected effect of each effective operation type, the risk reduction rate of each effective operation type at different feasible time is calculated, according to the feasible time period of each effective operation type, the time period score of each effective operation type is calculated, according to the risk reduction rate, the benefit score of each effective operation type is calculated, and combined with the corresponding time period score, the operation comprehensive score of each effective operation type is calculated, based on the preset score weight, the benefit score and the time period score are weighted and summed to obtain the operation comprehensive score, the operation comprehensive scores of the effective operation types corresponding to the same disaster intervention are compared, and the effective operation type with the highest operation comprehensive score is selected as the best operation type of the corresponding disaster intervention; According to the feasible time period of each best operation type, a time interval composed of continuous feasible time is identified and marked as a candidate time window, for each candidate time window, the corresponding window optimal score is calculated in turn, the window optimal scores of the candidate time windows corresponding to the same best operation type are compared, and the candidate time window with the highest window optimal score is selected as the best time window of the corresponding best operation type.

[0013] Further, the method for generating the preventive resource deployment scheme comprises: According to the disaster type and the best operation type of each disaster intervention, the emergency resource demand list corresponding to each disaster intervention is obtained from the pre-constructed resource configuration library, the current state information of the schedulable emergency resource is obtained, and according to the emergency resource demand list and the emergency resource state information, the resource supply-demand matching is carried out in turn according to the disaster priority of the disaster intervention, the scheduling resource list of each disaster intervention is determined according to the matching result, the operation equipment, operation personnel and operation materials to be scheduled are included in the scheduling resource list, and are collectively referred to as scheduling resources; The center position of the target area is determined, and the current position and the scheduling speed of each scheduling resource are obtained from the emergency resource state information, the resource scheduling path corresponding to each scheduling resource is calculated according to the current position of each scheduling resource and the center position of the target area, the scheduling departure time of each scheduling resource is calculated according to the length of the resource scheduling path corresponding to each scheduling resource and the scheduling speed, the scheduling resource list of the same disaster intervention and the scheduling departure time of each scheduling resource are summarized to generate the emergency resource scheduling scheme of each disaster intervention, and the resource scheduling schemes of each disaster intervention are summarized to generate the preventive resource deployment scheme.

[0014] The three-protection emergency command system based on meteorological big data implements the three-protection emergency command method based on meteorological big data, and comprises the following steps: A meteorological mining module is used to collect disaster meteorological correlation data, identify meteorological evolution modes corresponding to various disasters in the disaster meteorological correlation data, and construct a three-protection meteorological precursor mode library. A risk monitoring module is used to collect current meteorological data and environmental state data in real time, evaluate the progressive evolution process of the vulnerability of the disaster-affected body corresponding to various disasters, and generate a three-protection risk progression curve. A disaster research and judgment module is used to obtain meteorological forecast data, calculate the meteorological similarity between the meteorological forecast data and each meteorological evolution mode in the three-protection meteorological precursor mode library, and predict the disaster risk elements of various disasters in combination with the three-protection risk progression curve, and determine the intervention disaster based on the disaster risk elements. An intervention identification module is used to analyze the feasible time period and expected effect of different artificial weather modification operations corresponding to the intervention disaster according to the disaster risk elements of the intervention disaster, intelligently identify the best operation type and the best time window based on the feasible time period and the expected effect. An emergency command module is used to intelligently schedule three-protection emergency resources based on the best operation type and the best time window of the intervention disaster, generate a preventive resource deployment scheme, and command various disaster prevention forces to execute the preventive resource deployment scheme.

[0015] The three-protection emergency command method and system based on meteorological big data have the following technical effects and advantages: By deeply exploring the inherent correlation between historical disasters and meteorological evolution, a database of meteorological precursor models for disaster prevention, mitigation, and hazard mitigation is constructed. Combined with dynamic quantitative assessment of the vulnerability of disaster-bearing bodies, a progressive risk curve for disaster prevention, mitigation, and hazard mitigation is generated, realizing a paradigm shift from traditional "post-disaster emergency response" to "pre-disaster prevention." Innovatively, by calculating the similarity between meteorological forecast data and precursor models, the probability of disaster occurrence, remaining time, and scope of impact are accurately predicted. Based on deep learning models, the feasible time periods and expected effects of different artificial weather modification operations are analyzed, and the best operation type and optimal time window are intelligently identified. In the early stages of disaster formation, artificial rain enhancement, rain suppression, and wind reduction technologies are used to proactively eliminate or weaken disaster risks, filling the technological gap in traditional emergency systems that lack proactive intervention capabilities. Emergency resources are intelligently matched based on disaster priority and optimal time window. The shortest path algorithm optimizes the scheduling path and accurately calculates the departure time, enabling the forward-looking deployment of emergency resources and avoiding the delays and waste of resources caused by the lag in resource scheduling in the traditional model. It fully releases the application value of meteorological big data, upgrading meteorological big data from a simple weather forecasting tool to a core driving force supporting intelligent decision-making. It constructs a full-chain intelligent three-defense emergency command system integrating "risk identification, dynamic monitoring, proactive intervention, and intelligent scheduling", breaking through the technical bottlenecks of traditional emergency systems in terms of early warning timeliness, intervention capability, and resource allocation. It has important practical value and promotion significance for improving natural disaster prevention capabilities and protecting people's lives and property. Attached Figure Description

[0016] Figure 1 This is a flowchart of the emergency command method for three-defense based on meteorological big data according to Embodiment 1 of the present invention; Figure 2 This is a schematic diagram of the three-defense emergency command system based on meteorological big data according to Embodiment 2 of the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] Example 1 Please see Figure 1 As shown in this embodiment, the emergency command method for disaster prevention, mitigation, and hazard mitigation based on meteorological big data includes the following: Collect meteorological data related to disasters, identify meteorological evolution patterns corresponding to various disasters in the meteorological data related to disasters, and construct a database of meteorological precursor patterns for disaster prevention, mitigation, and disaster relief.

[0019] The methods for collecting disaster meteorological correlation data include: obtaining historical meteorological data covering the target area from a meteorological data center, the historical meteorological data including meteorological observation records collected at each historical time in the target area; the target area refers to a specific geographical range targeted by the three-proof emergency command post; the meteorological observation records include but are not limited to site number, observation time, temperature value, relative humidity value, wind speed value, wind direction value, air pressure value, precipitation, etc.; obtaining disaster archive data corresponding to the same period as the historical meteorological data from an emergency management department, the disaster archive data including records of various disaster events that have occurred in the target area in history; the disaster event records include but are not limited to disaster type, occurrence time, influence range, etc.; the disaster type includes fire, flood and wind disaster; According to the occurrence time in each disaster event record, the corresponding associated meteorological sequence is extracted from the historical meteorological data; specifically, taking the occurrence time in the disaster event record as the reference, a preset time window is traced back, all meteorological observation records within the time window are obtained, and are arranged in ascending order according to the observation time to form the associated meteorological sequence; wherein the length of the time window is pre-set by the person skilled in the art according to the actual situation; for example, the length of the time window is set to 30 days, and the meteorological observation records within 30 days before the disaster occurs are extracted; The meteorological elements of each associated meteorological sequence are separated to obtain meteorological element sequences corresponding to each meteorological element; the meteorological elements are, for example, temperature value, relative humidity value, wind speed value, wind direction value, air pressure value, precipitation, etc., and the meteorological element sequences are, for example, temperature sequence, humidity sequence, wind speed sequence, wind direction sequence, air pressure sequence, precipitation sequence, etc.; each meteorological element sequence is associated with the corresponding disaster event record to form disaster meteorological association data.

[0020] The method for constructing the three-proof meteorological precursor mode library comprises: According to the disaster type of each disaster event record in the disaster meteorological association data, the disaster meteorological association data is divided into fire association data set, flood association data set and wind disaster association data set; For the fire association data set, the corresponding meteorological evolution mode of the fire is extracted and used as the fire precursor mode; specifically, the cumulative feature calculation is performed on the temperature sequences of all associated meteorological sequences in the fire association data set to obtain the continuous high-temperature duration and cumulative temperature deviation of each temperature sequence; the continuous feature calculation is performed on the humidity sequences of all associated meteorological sequences in the fire association data set to obtain the continuous low-humidity duration and average humidity level of each humidity sequence; the deficiency feature calculation is performed on the precipitation sequences of all associated meteorological sequences in the fire association data set to obtain the continuous no-precipitation duration and cumulative precipitation deficiency of each precipitation sequence; the cumulative feature, continuous feature and deficiency feature of the same associated meteorological sequence are combined into a fire feature vector, and the time series clustering algorithm is used to perform clustering analysis on all fire feature vectors to identify the fire precursor mode before the fire occurs. For the flood-related data set, the corresponding meteorological evolution mode of the flood is extracted and used as the flood precursor mode; specifically, the intensity feature of the precipitation sequence of all related meteorological sequences in the flood-related data set is calculated to obtain the number of short-time heavy rain and the total amount of cumulative precipitation of each precipitation sequence; the change feature of the pressure sequence of all related meteorological sequences in the flood-related data set is calculated to obtain the number of pressure drops and the pressure fluctuation amplitude of each pressure sequence; the intensity feature and the change feature of the same related meteorological sequence are combined into a flood feature vector, and a time series clustering algorithm is used to cluster analyze all the flood feature vectors to identify the flood precursor mode before the occurrence of the flood; For the wind disaster-related data set, the corresponding meteorological evolution mode of the wind disaster is extracted and used as the wind disaster precursor mode; specifically, the cumulative feature of the wind speed sequence of all related meteorological sequences in the wind disaster-related data set is calculated to obtain the duration of sustained gale and the maximum gust wind speed of each wind speed sequence; the trend feature of the pressure sequence of all related meteorological sequences in the wind disaster-related data set is calculated to obtain the duration of sustained pressure drop and the minimum pressure value of each pressure sequence; the cumulative feature and the trend feature of the same related meteorological sequence are combined into a wind disaster feature vector, and a time series clustering algorithm is used to cluster analyze all the wind disaster feature vectors to identify the wind disaster precursor mode before the occurrence of the wind disaster; The fire precursor mode, the flood precursor mode, and the wind disaster precursor mode are summarized to construct a three-prevention meteorological precursor mode library.

[0021] Wherein, the definition of cumulative feature is: the continuous high temperature duration is the longest duration that the temperature value in the temperature sequence is continuously greater than the preset high temperature threshold, which is used to reflect the cumulative influence of high temperature duration on the environment; the cumulative temperature deviation is the sum of the difference between all temperature values greater than the high temperature threshold and the high temperature threshold, which is used to reflect the cumulative influence of high temperature intensity on the environment; The definition of the continuous feature is: the continuous low humidity duration is the longest duration that the relative humidity value in the humidity sequence is continuously less than the preset low humidity threshold, which is used to reflect the continuous degree of dry state; the average humidity level is the arithmetic mean of all relative humidity values in the humidity sequence, which is used to reflect the overall humidity condition; The definition of the deficiency feature is: the continuous no precipitation duration is the longest duration that the precipitation amount in the precipitation sequence is continuously equal to 0 or less than the preset trace threshold, which is used to reflect the drought duration; the cumulative precipitation deficit amount is the absolute value obtained by cumulatively summing the difference between all precipitation amounts less than the preset normal threshold and the normal threshold, which is used to reflect the cumulative degree of insufficient precipitation; The definition of the intensity feature is that the number of short-time heavy rain refers to the number of continuous heavy rain events in the precipitation sequence, which is used to reflect the frequency and intensity of heavy rain events; the continuous heavy rain event is defined as a continuous time period with precipitation greater than a preset heavy rain threshold and a duration greater than or equal to a preset duration threshold; the cumulative total precipitation refers to the index obtained by summing all precipitation amounts in the precipitation sequence, which is used to reflect the intensity of total precipitation; The definition of the change feature is that the number of sudden pressure drops refers to the number of times when the difference between the pressure values of two adjacent time points (i.e., the pressure value at the previous time minus the pressure value at the next time) is greater than a preset pressure threshold, which is used to reflect the frequency of rapid pressure drops; the pressure fluctuation amplitude refers to the index obtained by calculating the difference between the maximum and minimum values of the pressure sequence, which is used to reflect the overall amplitude of pressure changes; The definition of the cumulative feature is that the duration of continuous gale refers to the longest duration of continuous wind speed greater than a preset wind speed threshold in the wind speed sequence, which is used to reflect the duration of strong wind and cumulative impact; the maximum gust wind speed refers to the maximum wind speed value in the wind speed sequence, which is used to reflect the instantaneous wind intensity and destructive power; The definition of the trend feature is that the duration of continuous pressure drop refers to the longest duration of continuous pressure drop in the pressure sequence, which is used to reflect the duration of the pressure drop trend; the minimum pressure value refers to the minimum pressure value in the pressure sequence, which is used to reflect the extreme level of pressure change.

[0022] It should be understood that the recognition methods of fire precursor mode, flood precursor mode and wind disaster precursor mode are the same, and the recognition method of fire precursor mode is taken as an example for specific description; the method for recognizing the fire precursor mode before the fire occurs is: clustering all fire feature vectors to obtain multiple feature clusters; obtaining the fire feature vector corresponding to the cluster center of each feature cluster and marking it as a center feature vector; comparing each center feature vector with a preset fire feature range, which includes the normal value range of each feature in the fire feature vector; if the center feature vector is within the fire feature range, the corresponding center feature vector is not used as a fire precursor mode; if the center feature vector exceeds the fire feature range, the corresponding center feature vector is used as a fire precursor mode; It should be noted that the time series clustering algorithm is a well-known technique in the art, and the specific process will not be described in detail here; the high temperature threshold, low humidity threshold, trace threshold, normal threshold, heavy rain threshold, duration threshold, pressure threshold, wind speed threshold and fire feature range are all pre-set by a person skilled in the art according to actual conditions.

[0023] Real-time collection of current meteorological data and environmental state data, evaluation of the progressive evolution process of the vulnerability of various disasters to the disaster-bearing body, and generation of a three-protection risk progression curve.

[0024] wherein, the current weather data covering the target area is obtained from the official API of the meteorological department, and the current weather data includes the weather observation records collected at the current time in the target area; the environmental state data refers to the state information of the hazard-bearing body related to the three disaster types of fire, flood and wind disaster, including fire state data, flood state data and wind disaster state data, which are obtained through the environmental monitoring system; wherein, the fire state data includes the moisture content of combustible materials and the surface dryness; the flood state data includes the soil moisture content, the river water level and the drainage pipe network load rate; the wind disaster state data includes the wind resistance grade of buildings, the number of temporary installations and the tree lodging risk index; The moisture content of combustible materials refers to the proportion of water in the total weight of combustible materials such as undergrowth, dead branches and fallen leaves; the surface dryness refers to the dryness of the surface soil; the soil moisture content refers to the proportion of water in the total volume of soil; the river water level refers to the current water surface height of the river; the drainage pipe network load rate refers to the ratio of the actual drainage capacity of the pipe network to the designed drainage capacity; the wind resistance grade of buildings refers to the actual wind intensity that the building can withstand; the number of temporary installations refers to the number of temporary buildings or facilities in the target area that are susceptible to wind; and the tree lodging risk index refers to the risk of trees being blown down by wind; The environmental monitoring system is composed of remote sensing satellites, Internet of Things sensors and ground inspection systems; the Internet of Things sensors include but are not limited to soil moisture sensors, near-infrared moisture sensors, ultrasonic water level meters, flow sensors, building structure health monitoring sensors (such as inclination sensors, strain gauges, etc.), tree inclination sensors, etc.; the ground inspection system includes but is not limited to unmanned aerial vehicle inspection (such as visible light, infrared, laser radar, etc.), fixed video monitoring (such as roadside cameras, construction site cameras, etc.), manual auxiliary inspection (such as handheld temperature and humidity meters, handheld soil moisture meters, etc.), etc.; It should be noted that the wind resistance grade of buildings, the tree lodging risk index and other comprehensive environmental state indicators are calculated by a variety of sensor data and ground inspection information, combined with statistical scoring, engineering models or multi-source data fusion methods, and the specific calculation method is a known technology in the art, which will not be described in detail here; for example, the wind resistance grade of buildings and the tree lodging risk index are respectively the conventional evaluation indicators in the fields of building engineering and landscape management, and their calculation methods have been clearly specified and maturely applied in relevant national standards and industry specifications, therefore, they belong to the known technology in the art.

[0025] wherein, the method for evaluating the progressive evolution process of the vulnerability of the hazard-bearing body to various disasters includes: The progressive evolution process of the fire vulnerability of the corresponding disaster-bearing body is evaluated, and a fire vulnerability progressive sequence is formed. Specifically, according to the temperature value and the relative humidity value in the current meteorological data, the atmospheric dryness index at the current time is calculated. According to the moisture content of combustible and the ground dryness in the fire state data, the combustible inflammable index at the current time is calculated. The atmospheric dryness index and the combustible inflammable index are normalized respectively, and corresponding fire weights are set respectively. The normalized atmospheric dryness index and the normalized combustible inflammable index are weighted and summed based on the fire weights, to obtain the fire vulnerability at the current time. A fire vulnerability time sequence queue is constructed, which is used to store the fire vulnerability at each time. The fire vulnerability at the current time is added to the fire vulnerability time sequence queue, and the fire vulnerability increment corresponding to each two adjacent times in the fire vulnerability time sequence queue is calculated in turn to form a fire vulnerability increment sequence. The fire vulnerability increment is equal to the fire vulnerability at the next time minus the fire vulnerability at the previous time. The progressive evolution trend of the fire vulnerability increment sequence is analyzed by using a moving average algorithm or an exponential smoothing algorithm, to form the fire vulnerability progressive sequence. The progressive evolution process of the water disaster vulnerability of the corresponding disaster-bearing body is evaluated, and a water disaster vulnerability progressive sequence is formed. Specifically, according to the precipitation and the air pressure value in the current meteorological data, the precipitation intensity index at the current time is calculated. According to the soil moisture content and the river water level in the water disaster state data, the ground saturation index at the current time is calculated. According to the drainage pipe network load rate in the water disaster state data, the drainage pressure index at the current time is calculated. The precipitation intensity index, the ground saturation index and the drainage pressure index are normalized respectively, and corresponding water disaster weights are set respectively. The normalized precipitation intensity index, the normalized ground saturation index and the normalized drainage pressure index are weighted and summed based on the water disaster weights, to obtain the water disaster vulnerability at the current time. A water disaster vulnerability time sequence queue is constructed, which is used to store the water disaster vulnerability at each time. The water disaster vulnerability at the current time is added to the water disaster vulnerability time sequence queue, and the water disaster vulnerability increment corresponding to each two adjacent times in the water disaster vulnerability time sequence queue is calculated in turn to form a water disaster vulnerability increment sequence. The progressive evolution trend of the water disaster vulnerability increment sequence is analyzed by using a moving average algorithm or an exponential smoothing algorithm, to form the water disaster vulnerability progressive sequence. The progressive evolution process of the wind disaster on the vulnerability of the corresponding disaster-bearing body is evaluated, and a progressive sequence of wind disaster vulnerability is formed. Specifically, according to the wind speed value and the air pressure value in the current meteorological data, the wind force intensity index at the current time is calculated; according to the building wind resistance grade and the number of temporary facilities in the wind disaster state data, the structure vulnerability index at the current time is calculated; according to the tree lodging risk index in the wind disaster state data, the vegetation risk index at the current time is obtained; the wind force intensity index, the structure vulnerability index and the vegetation risk index are normalized respectively, and the corresponding wind disaster weights are set respectively; the normalized wind force intensity index, the structure vulnerability index and the vegetation risk index are weighted and summed based on the wind disaster weight, and the wind disaster vulnerability at the current time is obtained; a wind disaster vulnerability time sequence queue is constructed, which is used to store the wind disaster vulnerability at each time; the wind disaster vulnerability at the current time is added to the wind disaster vulnerability time sequence queue, and the wind disaster vulnerability increment corresponding to each two adjacent times in the wind disaster vulnerability time sequence queue is calculated in turn to form a wind disaster vulnerability increment sequence; the progressive evolution trend of the wind disaster vulnerability increment sequence is analyzed by using the moving average algorithm or the exponential smoothing algorithm, and a progressive sequence of wind disaster vulnerability is formed.

[0026] The calculation method of the atmospheric dryness index is: the temperature value is normalized to obtain a standard temperature value; the relative humidity value is normalized to obtain a standard humidity value; the difference between one and the standard humidity value is calculated, and the calculation result is multiplied by the standard temperature value to obtain the atmospheric dryness index; the atmospheric dryness index is used to reflect the dryness degree of the atmospheric environment, and the larger the value is, the drier the atmosphere is; The calculation method of the combustible material flammability index is: the difference between one and the combustible material moisture content is calculated to obtain the combustible material dryness rate; the average value of the combustible material dryness rate and the surface dryness is calculated to obtain the combustible material flammability index; the combustible material flammability index is used to reflect the flammability of the combustible material, and the larger the value is, the more easily the combustible material burns; The calculation method of the precipitation intensity index is: the precipitation amount is normalized to obtain a standard precipitation amount; the air pressure change rate (i.e. the air pressure value at the current time minus the air pressure value at the previous time) is calculated according to the air pressure value, and the air pressure change rate is normalized to obtain a standard air pressure change rate; the standard precipitation amount and the standard air pressure change rate are respectively set with corresponding precipitation weights, and the precipitation intensity index is calculated by weighted summation based on the precipitation weights; the precipitation intensity index is used to reflect the intensity and persistence of precipitation, and the larger the value is, the stronger the precipitation is; The calculation method of the surface saturation index is: the soil moisture content is normalized to obtain a standard soil moisture content; the river water level is normalized to obtain a standard river water level; the average value of the standard soil moisture content and the standard river water level is calculated to obtain the surface saturation index; the surface saturation index is used to reflect the water saturation degree of the surface, and the larger the value is, the more saturated the surface is; The calculation method of the drainage pressure index is: normalizing the drainage pipe network load rate to obtain the drainage pressure index; the drainage pressure index is used to reflect the bearing pressure of the drainage system, and the larger the value is, the greater the drainage pressure is; The calculation method of the wind intensity index is: normalizing the wind speed value to obtain a standard wind speed value; calculating the air pressure drop amplitude (i.e. the air pressure value at the previous moment minus the air pressure value at the current moment) according to the air pressure value, and normalizing the air pressure drop amplitude to obtain a standard air pressure drop amplitude; setting corresponding wind power weights for the standard wind speed value and the standard air pressure drop amplitude, and performing weighted summation calculation based on the wind power weights to obtain the wind intensity index; the wind intensity index is used to reflect the intensity and development trend of the wind, and the larger the value is, the stronger the wind is; The calculation method of the structure vulnerability index is: inversely normalizing the building wind resistance grade to obtain the building vulnerability degree; normalizing the number of temporary facilities to obtain the temporary facility risk degree; performing mean value calculation on the building vulnerability degree and the temporary facility risk degree to obtain the structure vulnerability index; the structure vulnerability index is used to reflect the vulnerability degree of the building structure, and the larger the value is, the more vulnerable the structure is; The vegetation risk index, i.e. the tree lodging risk index in the wind disaster state data, is used to reflect the lodging risk of vegetation under strong wind conditions, and the larger the value is, the higher the lodging risk is.

[0027] It should be noted that each fire weight, flood weight, wind disaster weight, precipitation weight and wind power weight is pre-set by a person skilled in the art according to actual conditions; the moving average algorithm and the exponential smoothing algorithm are both known techniques in the art, and the specific process will not be described in detail here; the calculation methods of the flood vulnerability increment and the wind disaster vulnerability increment are the same as the calculation method of the fire vulnerability increment; the normalization processing refers to mapping the original value to the range of 0 to 1 to eliminate the dimensional difference.

[0028] The method for generating the three-proofing risk progressive curve comprises: drawing a fire risk progressive curve with time as the horizontal axis and the progressive evolution value in the fire vulnerability progressive sequence as the vertical axis, for intuitively displaying the progressive evolution trend of the fire vulnerability with time; drawing a flood risk progressive curve with time as the horizontal axis and the progressive evolution value in the flood vulnerability progressive sequence as the vertical axis, for intuitively displaying the progressive evolution trend of the flood vulnerability with time; drawing a wind disaster risk progressive curve with time as the horizontal axis and the progressive evolution value in the wind disaster vulnerability progressive sequence as the vertical axis, for intuitively displaying the progressive evolution trend of the wind disaster vulnerability with time; integrating the fire risk progressive curve, the flood risk progressive curve and the wind disaster risk progressive curve to generate the three-proofing risk progressive curve.

[0029] Obtaining meteorological forecast data, calculating the meteorological similarity between the meteorological forecast data and each meteorological evolution mode in the three-proof meteorological precursor mode library, and combining the three-proof risk progressive curve to predict the disaster risk elements of each type of disaster, and determining the intervention disaster based on the disaster risk elements.

[0030] Wherein, the meteorological forecast data covering the target area is obtained from the official API of the meteorological department, and the meteorological forecast data includes the meteorological forecast records of the target area at each future time; the meteorological forecast records include but are not limited to site number, forecast time, forecast temperature value, forecast relative humidity value, forecast wind speed value, forecast precipitation, forecast cloud thickness, forecast cloud bottom height, etc.; wherein, the range of forecast time is pre-set by the person skilled in the art according to the actual situation; for example, the range of forecast time is set to 72 hours in the future, then the meteorological forecast records within 72 hours in the future are obtained.

[0031] The method for calculating the meteorological similarity between the meteorological forecast data and each meteorological evolution mode includes: From the meteorological forecast data, the fire feature vector, the flood feature vector and the wind disaster feature vector are extracted in turn, and are marked as fire forecast vector, flood forecast vector and wind disaster forecast vector respectively; The fire forecast vector and each fire precursor mode are normalized, the Euclidean distance between the normalized fire forecast vector and each fire precursor mode is calculated, and the minimum Euclidean distance is taken as the fire feature distance; the fire feature distance is converted into similarity to obtain the fire meteorological similarity; The method for similarity conversion is: calculating the ratio of fire feature distance to preset distance normalization coefficient, and taking one minus the calculation result to obtain the fire meteorological similarity; According to the calculation method of fire meteorological similarity, the flood meteorological similarity corresponding to the flood forecast vector and the wind disaster meteorological similarity corresponding to the wind disaster forecast vector are calculated in turn.

[0032] Wherein, the method for predicting the disaster risk elements of each type of disaster includes: The disaster risk elements of the fire are predicted, and are taken as the fire risk elements; specifically, a linear regression algorithm or an exponential smoothing algorithm is used to perform trend extrapolation on the fire risk progression curve to predict the progressive evolution values at each future time, forming a fire prediction progression curve; the time when the progressive evolution value in the fire prediction progression curve first reaches a preset fire progression threshold is obtained, and is marked as a fire critical time; the difference between the fire critical time and the current time is calculated to obtain a fire remaining time; the slope of the fire risk progression curve (i.e., the tangent slope of the fire risk progression curve at the current time) is calculated and normalized to obtain a risk evolution rate; the fire disaster meteorological similarity and the risk evolution rate are respectively set with corresponding fire risk weights, and the fire disaster meteorological similarity and the risk evolution rate are weighted and summed based on the fire risk weights to obtain a fire occurrence probability; according to the fire disaster meteorological similarity corresponding to the fire precursor mode, a disaster event record associated with the fire precursor mode is obtained, and the influence range in the disaster event record is extracted as the fire influence range; the fire remaining time, the fire occurrence probability and the fire influence range are integrated to form the fire risk elements; According to the prediction method of the fire risk elements, the disaster risk elements of the flood and the wind disaster are respectively predicted and taken as the flood risk elements and the wind disaster risk elements.

[0033] Among them, the method for determining the intervention disaster based on the disaster risk elements comprises: For each group of disaster risk elements, the intervention necessity is judged in turn; specifically, a fire intervention threshold is preset, and the fire risk elements are compared with the fire intervention threshold; wherein the fire intervention threshold includes a fire time threshold and a fire probability threshold; if the fire remaining time is less than or equal to the fire time threshold, and the fire occurrence probability is greater than or equal to the fire probability threshold, it is determined that the fire needs to be intervened; if the fire remaining time is greater than the fire time threshold, or the fire occurrence probability is less than the fire probability threshold, it is determined that the fire does not need to be intervened; the same determination method is used to determine the intervention necessity of the flood and the wind disaster according to the flood risk elements and the wind disaster risk elements respectively; All disaster types determined to need intervention are summarized to form an intervention disaster list; if there are multiple disaster types in the intervention disaster list, the disaster types in the intervention disaster list are prioritized; specifically, the intervention urgency of each disaster type in the intervention disaster list is calculated, the disaster types in the intervention disaster list are sorted in descending order according to the intervention urgency, and an intervention disaster sequence is generated; according to the positive order of the intervention disaster sequence, each disaster type is marked as an intervention disaster in turn, and a decreasing digital label is set as the disaster priority of each disaster type; Wherein, the calculation method of intervention urgency of each disaster type is consistent, and the intervention urgency corresponding to the fire is taken as an example for detailed description; the calculation method of intervention urgency is: the time urgency is obtained by reverse normalization processing on the remaining time of the fire; the probability urgency and the range urgency are obtained by normalization processing on the fire occurrence probability and the fire influence range respectively; the corresponding urgency weight is set for the time urgency, the probability urgency and the range urgency respectively, and the time urgency, the probability urgency and the range urgency are weighted and summed based on the urgency weight to obtain the intervention urgency; It should be noted that the linear regression algorithm is a known technology in the art, and the specific process will not be described here; the distance normalization coefficient, the fire risk weight, the fire progression threshold, the fire intervention threshold and the urgency weight are all pre-set by the person skilled in the art according to the actual situation.

[0034] According to the disaster risk elements of the intervened disaster, the feasible time period and the expected effect of different artificial weather modification operations corresponding to the intervened disaster are analyzed, and the best operation type and the best time window are intelligently identified based on the feasible time period and the expected effect.

[0035] Wherein, the method for analyzing the feasible time period and the expected effect of different artificial weather modification operations corresponding to the intervened disaster comprises: According to the disaster type of the intervened disaster, the corresponding candidate operation type set is obtained from the pre-constructed operation type library; the candidate operation type set includes candidate operation types (i.e. artificial weather modification operation types) and operation implementation conditions; for example, the candidate operation types corresponding to the fire include but are not limited to artificial rain enhancement operation, artificial humidity enhancement operation, etc.; the candidate operation types corresponding to the flood include but are not limited to artificial rain weakening operation, artificial precipitation weakening operation, etc.; the candidate operation types corresponding to the wind disaster include but are not limited to artificial fog weakening operation, artificial wind weakening operation, etc.; the operation implementation conditions include temperature condition, humidity condition, cloud layer condition and wind speed condition; the temperature condition refers to the temperature range required for implementing artificial weather modification operation, the humidity condition refers to the relative humidity range required for implementing artificial weather modification operation, the cloud layer condition refers to the cloud layer thickness range and the cloud bottom height range required for implementing artificial weather modification operation, and the wind speed condition refers to the wind speed range required for implementing artificial weather modification operation; the operation type library is pre-constructed by the person skilled in the art according to the artificial weather modification technical specification; For each candidate operation type, analyze the corresponding feasible time period; specifically, extract the meteorological forecast record of each future time from the meteorological forecast data, and compare each meteorological forecast record of each future time with each operation implementation condition item by item; if the predicted temperature value, the predicted relative humidity value, the predicted wind speed value, the predicted cloud thickness and the predicted cloud base height in the meteorological forecast record all meet the same operation implementation condition, the corresponding future time is taken as a feasible time for the corresponding candidate operation type; if any parameter in the meteorological forecast record does not meet the same operation implementation condition, the corresponding future time is taken as an infeasible time for the corresponding candidate operation type; the feasible time corresponding to each candidate operation type is summarized to form the feasible time period corresponding to each candidate operation type; Different digital tags are set for different candidate operation types and are marked as operation tags; the disaster risk elements of the intervention disaster corresponding to each candidate operation type, the meteorological forecast record of one feasible time and the operation tag are combined to obtain a plurality of change prediction sets; each change prediction set includes a set of disaster risk elements, a meteorological forecast record of one feasible time and an operation tag; each change prediction set is input into the trained change prediction model to predict the meteorological change set of each intervention disaster after the action of each candidate operation type at different feasible times, which is taken as the expected effect of each candidate operation type; the meteorological change set includes temperature change value, relative humidity change value, wind speed change value and precipitation change value; Specifically, the change prediction model is a deep neural network model, which includes an input layer, a hidden layer and an output layer; each hidden layer includes a plurality of neurons, and each neuron is connected with the next layer of neurons, and the connection includes a weight which determines the importance and influence of data transmission in the neural network; an activation function is applied to each neuron between the hidden layer and the output layer, which introduces nonlinearity and allows the network to learn more complex patterns and features; the training process of the change prediction model includes: Pre-collect Different change prediction sets are grouped, and the corresponding meteorological change set is set for each change prediction set, is an integer greater than 1; the change prediction set and the corresponding meteorological change set are converted into a corresponding set of feature vectors; the meteorological change set corresponding to the change prediction set is collected by those skilled in the art in the process of analyzing the expected effect of different artificial weather modification operations on different intervention disasters Different change prediction sets are grouped, and the candidate operation type corresponding to the operation tag in each change prediction set is implemented in turn; after the implementation of the candidate operation type, the meteorological change set corresponding to each change prediction set is collected, and Different change prediction sets are grouped, and the corresponding meteorological change set is set for each change prediction set; each group of feature vectors as an input of a change prediction model, the change prediction model taking a group of predicted meteorological change sets corresponding to each group of change prediction sets as an output, taking a group of actual meteorological change sets corresponding to each group of change prediction sets as a prediction target, the actual meteorological change set being a meteorological change set corresponding to the change prediction set and set in advance; taking minimizing the sum of prediction errors of all change prediction sets as a training target; wherein the calculation formula of the prediction error is: ; in the formula, is the prediction error, is the group number of the feature vector corresponding to the change prediction set, is the predicted meteorological change set corresponding to the first group of change prediction sets, is the actual meteorological change set corresponding to the first group of change prediction sets; the change prediction model is trained until the sum of prediction errors reaches convergence to stop training.

[0036] The method for intelligently identifying the best operation type and the best time window comprises: comparing the feasible time period of each candidate operation type with the disaster remaining time corresponding to the intervention disaster respectively; the disaster remaining time comprises the fire disaster remaining time, the flood disaster remaining time and the wind disaster remaining time; if at least one feasible time in the feasible time period is located within the corresponding disaster remaining time, the corresponding candidate operation type is taken as an effective operation type; if no feasible time in the feasible time period is located within the corresponding disaster remaining time, the corresponding candidate operation type is taken as an invalid operation type; According to the expected effect of each effective operation type, the risk reduction rate of each effective operation type to the corresponding intervention disaster at different feasible times is calculated; specifically, if the intervention disaster is fire, the humidity change value is normalized to obtain the humidity reduction contribution degree; the precipitation change value is normalized to obtain the precipitation reduction contribution degree; the reduction weight corresponding to the humidity reduction contribution degree and the precipitation reduction contribution degree is set respectively, and the humidity reduction contribution degree and the precipitation reduction contribution degree are weighted and summed based on the reduction weight to obtain the risk reduction rate of the fire; if the intervention disaster is flood, the ratio between the absolute value of the precipitation change value and the predicted precipitation in the corresponding change prediction set is calculated to obtain the precipitation reduction proportion; the precipitation reduction proportion is normalized to obtain the risk reduction rate of the flood; if the intervention disaster is wind, the ratio between the absolute value of the wind speed change value and the predicted wind speed in the corresponding change prediction set is calculated to obtain the wind speed reduction proportion; the wind speed reduction proportion is normalized to obtain the risk reduction rate of the wind disaster; According to the feasible time period of each effective operation type, a time period score of each effective operation type is calculated; specifically, the number of feasible time points in the feasible time period and the number of future time points in the range of the predicted time are counted respectively to obtain the feasible number and the future number; the ratio of the feasible number to the future number is calculated to obtain the time period score; the benefit score of each effective operation type is calculated according to the risk reduction rate, and the operation comprehensive score of each effective operation type is calculated in combination with the corresponding time period score; specifically, the risk reduction rates of the effective operation type at all feasible time points are averaged to obtain the average risk reduction rate; the average risk reduction rate is normalized to obtain the benefit score; the benefit score and the time period score are respectively set with corresponding score weights, and the benefit score and the time period score are weighted and summed based on the score weights to obtain the operation comprehensive score; the operation comprehensive scores of the effective operation types corresponding to the same intervention disaster are compared, and the effective operation type with the highest operation comprehensive score is selected as the best operation type corresponding to the intervention disaster.

[0037] According to the feasible time period of each best operation type, a time interval composed of consecutive feasible time points is identified and marked as a candidate time window; for each candidate time window, the corresponding window optimization score is calculated in turn; specifically, the difference between the start time of the candidate time window and the current time is calculated to obtain the window advance amount; the window advance amount is normalized to obtain the advance degree score; the duration of the candidate time window (i.e. the termination time of the candidate time window minus the start time) is calculated, and the duration is normalized to obtain the duration degree score; the average of the risk reduction rates corresponding to each feasible time point in the candidate time window is calculated to obtain the window reduction rate; the window reduction rate is normalized to obtain the reduction degree score; the advance degree score, the duration degree score and the reduction degree score are respectively set with corresponding window weights, and the advance degree score, the duration degree score and the reduction degree score are weighted and summed based on the window weights to obtain the window optimization score; The window optimization scores of the candidate time windows corresponding to the same best operation type are compared, and the candidate time window with the highest window optimization score is selected as the best time window corresponding to the best operation type.

[0038] It should be noted that each reduction weight, score weight and window weight is pre-set by a person skilled in the art according to actual conditions.

[0039] Based on the best operation type and the best time window of the intervention disaster, the three prevention emergency resources are intelligently dispatched, a preventive resource deployment scheme is generated, and various disaster prevention forces are commanded to execute the preventive resource deployment scheme.

[0040] The method for generating the preventive resource deployment scheme comprises: According to the disaster type of each intervention disaster and the optimal operation type, obtain the emergency resource demand list corresponding to each intervention disaster from a pre-constructed resource configuration library; wherein, the resource configuration library stores emergency resource demand lists corresponding to different disaster types and different artificial weather influencing operations, and the emergency resource demand list includes operation equipment demand, operation personnel demand, and operation material demand; the operation equipment demand includes equipment type and minimum operation capacity; the operation personnel demand includes personnel post and minimum qualification level; the operation material demand includes material type and required quantity; the operation equipment includes, but is not limited to, artificial weather influencing operation equipment such as artificial rain rocket launching rack, high gun operation system, aircraft spreading equipment, and ground combustion furnace; the operation personnel includes, but is not limited to, professional personnel such as weather operation commander, equipment operator, safety supervisor, and logistics support personnel; the operation material includes, but is not limited to, artificial weather influencing operation material such as silver iodide catalyst, liquid nitrogen, dry ice, and flame; the resource configuration library is pre-constructed by a person skilled in the art according to the specifications and historical records of artificial weather influencing operations; Obtain the current dispatchable emergency resource state information from the emergency resource management system, and the emergency resource state information includes operation equipment information, operation personnel information, and operation material information; wherein, the operation equipment information includes equipment type, current position, operation capacity (quantifying the performance level or operation efficiency of the operation equipment when performing artificial weather influencing operations), and dispatch speed of various operation equipment; the operation personnel information includes personnel post, current position, qualification level (measuring the professional ability and operation qualification of the operation personnel performing artificial weather influencing operations), and dispatch speed of various operation personnel; the operation material information includes material type, inventory quantity, current position, expiration date, and dispatch speed of various operation material; According to the emergency resource demand list and the emergency resource state information, perform resource supply-demand matching in order of disaster priority of the intervention disaster; specifically, match each item in the emergency resource demand list with the emergency resource state information; for each item, filter the emergency resource that meets the demand condition and is closest to the target area (i.e., the Euclidean distance between the current position and the corresponding center position of the target area is the smallest); wherein, the demand condition is as follows: for operation equipment demand, filter the operation equipment with the same equipment type and operation capacity greater than or equal to the minimum operation capacity; for operation personnel demand, filter the operation personnel with the same personnel post and qualification level greater than or equal to the minimum qualification level; for operation material demand, filter the operation material with the same material type, inventory quantity greater than or equal to the required quantity, and expiration date later than the termination time corresponding to the corresponding best time window; For each disaster intervention, a corresponding emergency resource scheduling scheme is generated; specifically, a scheduling resource list is determined according to the matching result, the scheduling resource list including the job equipment, job personnel and job materials to be scheduled; the center position of the target area is determined by a remote sensing satellite, and the shortest path algorithm is used to calculate the resource scheduling path corresponding to each scheduling resource according to the current position of each scheduling resource (i.e. the job equipment, job personnel and job materials to be scheduled in the scheduling resource list) and the center position of the target area, so as to minimize the time for the resource to reach the target area; the length of the resource scheduling path is counted and taken as the path length; the ratio of the path length to the scheduling speed corresponding to each scheduling resource is calculated to obtain the scheduling time of each scheduling resource; the difference between the starting time corresponding to the best time window and the scheduling time corresponding to each scheduling resource is calculated to obtain the scheduling departure time of each scheduling resource; the scheduling resource list and the scheduling departure time of each scheduling resource are summarized to generate an emergency resource scheduling scheme; it should be noted that the shortest path algorithm is a well-known technology in the art, and the specific process will not be described in detail here; The resource scheduling schemes for each disaster intervention are summarized to generate a preventive resource deployment scheme; according to the preventive resource deployment scheme, scheduling instructions are issued to the management units corresponding to each scheduling resource to command various disaster prevention forces to perform resource scheduling tasks according to the scheduling departure time.

[0041] The embodiment realizes the paradigm shift from traditional "post-disaster emergency" to "pre-disaster prevention" by deeply mining the internal correlation rules between historical disasters and meteorological evolution to construct a three-protection meteorological precursor mode library, and combining dynamic quantitative evaluation of the vulnerability of disaster-bearing bodies to generate a three-protection risk progression curve; innovatively, the risk elements such as disaster occurrence probability, remaining time and impact range are accurately predicted by calculating the similarity between meteorological forecast data and precursor mode, and the feasible time period and expected effect of different artificial weather modification operations are analyzed based on a deep learning model, the best operation type and the best time window are intelligently identified, and the disaster hidden danger is actively eliminated or weakened through artificial rain enhancement, rain reduction, wind reduction and other technical means in the early stage of disaster formation, filling the technical gap of the lack of active intervention capability in traditional emergency systems; according to the disaster priority and the best time window, the emergency resources are intelligently matched, the scheduling path is optimized by the shortest path algorithm, and the departure time is accurately calculated, realizing the forward deployment of emergency resources, avoiding the rescue delay and resource waste caused by the lag of resource scheduling in the traditional mode; the application value of meteorological big data is fully released, meteorological big data is upgraded from a simple weather forecasting tool to a core driving force supporting intelligent decision-making, an intelligent three-protection emergency command system is constructed, which integrates "risk identification-dynamic monitoring-active intervention-intelligent scheduling" in one, breaking through the technical bottlenecks of traditional emergency systems in terms of early warning timeliness, intervention capability, resource allocation, etc., and having important practical value and promotional significance for improving the natural disaster prevention capability and protecting people's life and property safety.

[0042] Embodiment 2 Please refer to Figure 2 As shown in the drawings, the embodiments not described in detail are described in the description of embodiment 1. A three-proofing emergency command system based on meteorological big data is provided, including a meteorological mining module, a risk monitoring module, a disaster research module, an intervention identification module, and an emergency command module. Each module is connected through wired and / or wireless means to achieve data transmission between modules.

[0043] The meteorological mining module is used to collect disaster meteorological correlation data, identify the corresponding meteorological evolution mode of each disaster in the disaster meteorological correlation data, and construct a three-proofing meteorological precursor mode library. The risk monitoring module is used to collect current meteorological data and environmental state data in real time, evaluate the progressive evolution process of the vulnerability of each disaster to the disaster body, and generate a three-proofing risk progression curve. The disaster research module is used to obtain meteorological forecast data, calculate the meteorological similarity between the meteorological forecast data and each meteorological evolution mode in the three-proofing meteorological precursor mode library, and predict the disaster risk elements of each disaster in combination with the three-proofing risk progression curve, and determine the intervention disaster based on the disaster risk elements. The intervention identification module is used to analyze the feasible time period and expected effect of different artificial weather modification operations corresponding to the intervention disaster according to the disaster risk elements of the intervention disaster, and intelligently identify the best operation type and best time window based on the feasible time period and expected effect. The emergency command module is used to intelligently schedule three-proofing emergency resources based on the best operation type and best time window of the intervention disaster, generate a preventive resource deployment scheme, and command various disaster prevention forces to execute the preventive resource deployment scheme.

[0044] Embodiment 3 The present application also provides an electronic device. The electronic device can include one or more processors and one or more memories. The memory stores computer readable code, which when executed by the one or more processors, can perform the three-proofing emergency command method based on meteorological big data as described above.

[0045] The method or system according to the embodiments of the present application can also be implemented by means of the architecture of the electronic device shown in the present application. The electronic device can include a bus, one or more CPUs, ROM, RAM, a communication port connected to a network, input / output, a hard disk, etc. The storage device in the electronic device, such as ROM or hard disk, can store the three-proofing emergency command method based on meteorological big data provided by the present application. Further, the electronic device can also include a user interface. Of course, the architecture shown in the present application is only exemplary, and when implementing different devices, one or more components of the electronic device shown in the present application can be omitted according to actual needs.

[0046] Embodiment 4 One embodiment of the present application discloses a computer readable storage medium. The computer readable storage medium stores computer readable instructions. When the computer readable instructions are run by a processor, the weather big data based tri-proof emergency command method according to the embodiments of the present application described above with reference to the accompanying drawings can be executed. The storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. The volatile memory may, for example, include random access memory (RAM) and cache memory, etc. The non-volatile memory may, for example, include read-only memory (ROM), hard disk, flash memory, etc.

[0047] In addition, according to the embodiments of the present application, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, the present application provides a non-transitory machine readable storage medium storing machine readable instructions executable by a processor to perform instructions corresponding to the method steps provided by the present application, for example, the weather big data based tri-proof emergency command method. When the computer program is executed by a central processing unit (CPU), the above functions defined in the method of the present application are executed.

[0048] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art can modify the technical solutions described in the foregoing embodiments or make equivalent replacements to some technical features. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0049] The formulas in the present specification are dimensionless numerical values, and the formulas are obtained by software simulation of a large amount of data to obtain a formula of the most recent real situation. The preset parameters and threshold values in the formula are set by those skilled in the art according to the actual situation.

[0050] Although the embodiments of the present application have been shown and described, those skilled in the art can understand that various changes, modifications, replacements and deformations can be made to these embodiments without departing from the principles and spirit of the present application, and the scope of the present application is defined by the claims and their equivalents.

Claims

1. A three-proofing emergency command method based on meteorological big data, characterized in that, The method for collecting disaster-meteorological correlation data comprises the following steps: acquiring historical meteorological data covering a target area, the historical meteorological data comprising meteorological observation records collected at each historical time in the target area; acquiring disaster archive data corresponding to the same period as the historical meteorological data, the disaster archive data comprising records of disaster events that have occurred in the target area in the past; extracting a corresponding meteorological sequence from the historical meteorological data according to the time of occurrence of each disaster event record; performing meteorological element splitting on each meteorological sequence to obtain a meteorological element sequence corresponding to each meteorological element; and associating each meteorological element sequence with the corresponding disaster event record to form disaster-meteorological correlation data. The method for constructing a three-protection meteorological precursor mode library comprises the following steps: dividing the disaster-meteorological correlation data into a fire correlation data set, a flood correlation data set, and a wind disaster correlation data set according to the type of disaster in each disaster event record in the disaster-meteorological correlation data; extracting a meteorological evolution mode of fire as a fire precursor mode for the fire correlation data set; 2.The weather big data-based three-proofing emergency command method according to claim 1, characterized in that, extracting a meteorological evolution mode of flood as a flood precursor mode for the flood correlation data set; extracting a meteorological evolution mode of wind disaster as a wind disaster precursor mode for the wind disaster correlation data set; summarizing the fire precursor mode, the flood precursor mode, and the wind disaster precursor mode to construct a three-protection meteorological precursor mode library. 3.The weather big data-based three-proofing emergency command method according to claim 2, characterized in that, The method for generating a three-protection risk progression curve comprises the following steps: the current meteorological data comprises meteorological observation records collected at the current time in the target area; and the environmental state data comprises fire state data, flood state data, and wind disaster state data; wherein the fire state data comprises the moisture content of combustible materials and the ground dryness; the flood state data comprises the soil moisture content, the river water level, and the drainage pipe network load rate; and the wind disaster state data comprises the wind resistance grade of buildings, the number of temporary installations, and the tree down risk index; evaluating the progressive evolution process of the vulnerability of the corresponding disaster body to fire according to the current meteorological data and the fire state data, forming a fire vulnerability progression sequence, and drawing a fire risk progression curve; ​ ​ 4. The weather big data-based three-proofing emergency command method according to claim 3, characterized in that, ​ ​ ​ ​ According to the current meteorological data and flood state data, the progressive evolution process of the flood corresponding to the vulnerability of the disaster-bearing body is evaluated, the progressive sequence of the flood vulnerability is formed, and the progressive curve of the flood risk is drawn; According to the current meteorological data and wind disaster state data, the progressive evolution process of the wind disaster corresponding to the vulnerability of the disaster-bearing body is evaluated, the progressive sequence of the wind disaster vulnerability is formed, and the progressive curve of the wind disaster risk is drawn; The fire risk progressive curve, the flood risk progressive curve and the wind disaster risk progressive curve are integrated to generate a three-protection risk progressive curve.

5. The meteorological big data-based three-proofing emergency command method according to claim 4, characterized in that, The method for predicting disaster risk elements of various disasters comprises: The meteorological forecast data comprises meteorological forecast records of the target area at each future time. From the meteorological forecast data, a fire forecast vector, a flood forecast vector and a wind disaster forecast vector are sequentially extracted, and a fire weather similarity corresponding to the fire forecast vector, a flood weather similarity corresponding to the flood forecast vector and a wind disaster weather similarity corresponding to the wind disaster forecast vector are calculated. The fire risk progressive curve is trend extrapolated to predict the progressive evolution value at each future time, forming a fire prediction progressive curve. The time when the progressive evolution value in the fire prediction progressive curve first reaches a preset fire progressive threshold is obtained and marked as a fire critical time. The fire remaining time is calculated according to the fire critical time and the current time. The risk evolution rate is calculated according to the fire risk progressive curve. The fire weather similarity and the risk evolution rate are weighted and summed based on a preset fire risk weight to obtain a fire occurrence probability. The fire influence range is obtained according to the fire weather similarity corresponding to the fire precursor mode. The fire risk elements are formed by integrating the fire remaining time, the fire occurrence probability and the fire influence range. According to the prediction method of the disaster risk elements, the disaster risk elements of the flood and the disaster risk elements of the wind disaster are predicted respectively as the flood risk elements and the wind disaster risk elements. 6.The weather big data-based three-proofing emergency command method according to claim 5, characterized in that, The method for determining the intervention disaster based on the disaster risk elements comprises: For each set of disaster risk elements, the intervention necessity is judged in sequence. A fire intervention threshold is preset, and the fire risk elements are compared with the fire intervention threshold. The fire intervention threshold includes a fire time threshold and a fire probability threshold. If the fire remaining time is less than or equal to the fire time threshold, and the fire occurrence probability is greater than or equal to the fire probability threshold, it is determined that the fire needs intervention. If the fire remaining time is greater than the fire time threshold, or the fire occurrence probability is less than the fire probability threshold, it is determined that the fire does not need intervention. The same determination method is used to judge the intervention necessity of the flood and the wind disaster according to the flood risk elements and the wind disaster risk elements respectively. All disaster types determined to need intervention are summarized to form an intervention disaster list. If there are multiple disaster types in the intervention disaster list, the intervention urgency of each disaster type in the intervention disaster list is calculated, the disaster types in the intervention disaster list are sorted in descending order according to the intervention urgency, and an intervention disaster sequence is generated. According to the positive order of the intervention disaster sequence, each disaster type is marked as an intervention disaster in sequence, and a sequentially decreasing digital label is set as the disaster priority of each disaster type.

7. The meteorological big data-based three-proofing emergency command method according to claim 6, characterized in that, The method for analyzing the feasible time period and expected effect of the disaster intervention corresponding to different weather modification operations comprises the following steps: According to the disaster type of the intervention disaster, a corresponding candidate operation type set is obtained from a pre-constructed operation type library; the candidate operation type set includes a candidate operation type and an operation implementation condition, and the candidate operation type is a weather modification operation type; meteorological forecast records of each future time are extracted from meteorological forecast data, and each meteorological forecast record of each future time is compared with each operation implementation condition item by item; if the parameters in the meteorological forecast record meet the same operation implementation condition, the corresponding future time is taken as a feasible time for the corresponding candidate operation type; the feasible time corresponding to each candidate operation type is summarized to form a feasible time period corresponding to each candidate operation type; Different digital tags are set for different candidate operation types, and are marked as operation tags; the disaster risk elements of the intervention disaster, the meteorological forecast record of one feasible time and the operation tag corresponding to each candidate operation type are combined to obtain a plurality of change prediction sets; each change prediction set is input into a trained change prediction model to predict a meteorological change set of each intervention disaster after the action of each candidate operation type at different feasible times, and the meteorological change set is taken as the expected effect of each candidate operation type; the meteorological change set includes temperature change value, relative humidity change value, wind speed change value and precipitation change value. 8.The weather big data-based three-proofing emergency command method according to claim 7, characterized in that, The method for intelligently identifying the best operation type and the best time window comprises the following steps: The feasible time period of each candidate operation type is compared with the disaster remaining time corresponding to the intervention disaster; the disaster remaining time includes fire disaster remaining time, flood disaster remaining time and wind disaster remaining time; if at least one feasible time in the feasible time period is within the corresponding disaster remaining time, the corresponding candidate operation type is taken as an effective operation type; According to the expected effect of each effective operation type, the risk reduction rate of each effective operation type to the corresponding intervention disaster at different feasible times is calculated; according to the feasible time period of each effective operation type, the time period score of each effective operation type is calculated; the benefit score of each effective operation type is calculated according to the risk reduction rate, and the corresponding time period score is combined to calculate the operation comprehensive score of each effective operation type; the benefit score and the time period score are weighted and summed based on the preset score weight to obtain the operation comprehensive score; the operation comprehensive scores of the effective operation types corresponding to the same intervention disaster are compared, and the effective operation type with the highest operation comprehensive score is selected as the best operation type of the corresponding intervention disaster; According to the feasible time period of each best operation type, a time interval composed of consecutive feasible times is identified and marked as a candidate time window; for each candidate time window, the corresponding window optimization score is calculated in sequence; the window optimization scores of the candidate time windows corresponding to the same best operation type are compared, and the candidate time window with the highest window optimization score is selected as the best time window of the corresponding best operation type. 9.The weather big data-based three-proofing emergency command method according to claim 8, characterized in that, The method for generating a preventive resource deployment scheme comprises the following steps: According to the disaster type of each intervention disaster and the optimal operation type, obtain the emergency resource demand list corresponding to each intervention disaster from the pre-constructed resource configuration library; obtain the current state information of the schedulable emergency resources, and according to the emergency resource demand list and the emergency resource state information, perform resource supply-demand matching in turn according to the disaster priority of the intervention disaster; determine the scheduling resource list of each intervention disaster according to the matching result, wherein the scheduling resource list includes the operation equipment, operation personnel and operation materials to be scheduled, and is collectively referred to as scheduling resource; Determine the center position of the target area, and obtain the current position and scheduling speed of each scheduling resource from the emergency resource state information; calculate the resource scheduling path corresponding to each scheduling resource according to the current position of each scheduling resource and the center position of the target area; calculate the scheduling departure time of each scheduling resource according to the length of the resource scheduling path corresponding to each scheduling resource and the scheduling speed; aggregate the scheduling resource list of the same intervention disaster and the scheduling departure time of each scheduling resource to generate an emergency resource scheduling scheme for each intervention disaster; aggregate the resource scheduling scheme of each intervention disaster to generate a preventive resource deployment scheme.

10. The three-proofing emergency command system based on meteorological big data, implements the three-proofing emergency command method based on meteorological big data of any one of claims 1-9, characterized in that, It comprises: A meteorological mining module is used to collect disaster meteorological correlation data, identify the meteorological evolution mode corresponding to each type of disaster in the disaster meteorological correlation data, and construct a three-prevention meteorological precursor mode library; A risk monitoring module is used to collect current meteorological data and environmental state data in real time, evaluate the progressive evolution process of the vulnerability of the disaster-affected body corresponding to each type of disaster, and generate a three-prevention risk progression curve; A disaster research module is used to obtain meteorological forecast data, calculate the meteorological similarity between the meteorological forecast data and each meteorological evolution mode in the three-prevention meteorological precursor mode library, and predict the disaster risk elements of each type of disaster in combination with the three-prevention risk progression curve, and determine the intervention disaster based on the disaster risk elements; An intervention identification module is used to analyze the feasible time period and expected effect of different weather modification operations corresponding to the intervention disaster according to the disaster risk elements of the intervention disaster, and intelligently identify the optimal operation type and optimal time window based on the feasible time period and expected effect; An emergency command module is used to intelligently schedule three-prevention emergency resources based on the optimal operation type and optimal time window of the intervention disaster, generate a preventive resource deployment scheme, and command each type of disaster prevention force to execute the preventive resource deployment scheme.

Images