A meteorological disaster risk early warning method, system, equipment and medium

Abstract

A meteorological disaster risk warning method, system, equipment and medium relate to the field of meteorological disaster warning. In this method, the target type of meteorological disasters in a target area is determined based on historical meteorological data, and the meteorological disaster warning index of the target area is determined based on the target type; the warning threshold corresponding to each risk level of the meteorological disaster warning index is determined based on the influencing factors of the target area; the current meteorological data of the target area is obtained, and the predicted meteorological data within a preset time in the future is predicted in combination with the historical meteorological data of the target area, and the target data corresponding to the meteorological disaster warning index is extracted from the predicted meteorological data; the meteorological disaster risk level of the target area is determined based on the comparison result between the target data and the warning threshold, and when the meteorological disaster risk level is greater than the risk threshold, the warning information of the target area is generated based on the meteorological disaster risk level. The implementation of the technical solution provided by this application makes the warning information more accurate and targeted.

Description

Technical Field

[0001] The present application relates to the technical field of meteorological disaster warning, and specifically to a meteorological disaster risk warning method, system, electronic equipment and storage medium. Background Art

[0002] Meteorological disasters are one of the most common disasters in nature. They are extremely destructive and have a serious impact on human production and life. In order to reduce the losses caused by meteorological disasters, early warning of meteorological disasters is necessary.

[0003] At present, most of the meteorological disaster warning methods are based on historical meteorological data for prediction, and corresponding warning information is issued according to the prediction results. However, due to differences in meteorological conditions, geographical environment, population density and other factors in different regions, the risks and impacts of the same meteorological disaster in different regions are also different. Although some warning methods take into account certain specific factors of the region, such as topography and climate, these methods often lack a comprehensive consideration of the overall situation of the region, resulting in deviations between the warning results and the actual situation. At the same time, these warning methods usually use fixed warning thresholds when determining the risk level of meteorological disasters, and do not fully consider the differences that may exist in different regions when responding to the same meteorological disaster.

[0004] Therefore, how to formulate personalized meteorological disaster warning plans for specific areas and improve the accuracy and effectiveness of warnings has become an urgent problem to be solved. Summary of the invention

[0005] The present application provides a meteorological disaster risk warning method, system, electronic device and storage medium, which sets warning thresholds based on the specific conditions and influencing factors of the target area, making the warning information more accurate and targeted, thereby improving the effectiveness of meteorological disaster warnings.

[0006] In a first aspect of the present application, a meteorological disaster risk early warning method is provided, which is applied to a meteorological early warning platform. The early warning method comprises:

[0007] Determine the target type of meteorological disasters in the target area according to historical meteorological data, and determine the meteorological disaster warning indicators in the target area according to the target type;

[0008] Determine the warning threshold corresponding to each risk level of the meteorological disaster warning indicator according to the influencing factors of the target area, wherein the influencing factors include population density, vegetation coverage, building information and enterprise information;

[0009] Acquire the current meteorological data of the target area, predict the predicted meteorological data within a preset time in the future in combination with the historical meteorological data of the target area, and extract the target data corresponding to the meteorological disaster warning indicator from the predicted meteorological data;

[0010] The meteorological disaster risk level of the target area is determined according to the comparison result of the target data and the warning threshold, and when the meteorological disaster risk level is greater than the risk threshold, warning information of the target area is generated according to the meteorological disaster risk level.

[0011] By adopting the above technical solution, combining historical meteorological data to determine the target type of meteorological disasters in the target area, and setting specific early warning indicators according to this type, the accuracy of early warning can be greatly improved. Since the types of meteorological disasters in different regions may be different, personalized early warning indicators can better reflect the actual local situation. When setting the early warning threshold, not only meteorological data but also influencing factors such as population density, vegetation coverage, building information and enterprise information are considered. This comprehensive consideration method makes the early warning results more comprehensive and accurate, and can better reflect the potential impact of disasters on local society and economy. By combining the historical meteorological data of the target area to predict the predicted meteorological data within a preset time in the future, possible disaster situations can be known in advance. This prediction ability is crucial for taking disaster prevention and mitigation measures in a timely manner, and helps to reduce the losses caused by disasters. Generate personalized early warning information for the target area according to the meteorological disaster risk level. This method makes the early warning information more targeted and practical. Meteorological disasters in different regions may have different characteristics and impacts, so personalized early warning information can better meet local needs. When the meteorological disaster risk level exceeds the risk threshold, the meteorological early warning platform will automatically generate early warning information, which improves the timeliness and effectiveness of the early warning.

[0012] Optionally, the early warning method includes:

[0013] Divide the monitoring area into multiple target areas according to the monitoring range of the meteorological base station;

[0014] When there is an intersecting area between adjacent target areas, the intersecting area refers to an area where the first target area and the second target area intersect each other, the first target area and the second target area are adjacent target areas, and a first meteorological similarity value between the intersecting area and the first target area is calculated based on the historical meteorological data, and a second meteorological similarity value between the intersecting area and the second target area is calculated;

[0015] When the first meteorological similarity value is greater than the second meteorological similarity value, the intersection area is divided into the first target area.

[0016] By adopting the above technical solution, calculating the meteorological similarity values ​​of the intersecting areas and the respective target areas in the adjacent target areas, and dividing the intersecting areas into target areas with higher meteorological similarity, it is possible to ensure that the early warning meteorological warning platform evaluates the meteorological disaster risk in the area based on more accurate and relevant meteorological data. This helps to improve the pertinence and accuracy of the early warning and reduce the possibility of false alarms and missed reports. By dividing the intersecting areas into target areas with higher meteorological similarity, the resources of the meteorological base station and the early warning meteorological warning platform can be better utilized. In this way, when the meteorological disaster risk in a certain target area is high, more resources can be concentrated to monitor and warn the area to ensure that corresponding disaster prevention and mitigation measures are taken in time. The method allows the boundaries of the target area to be dynamically adjusted according to changes in meteorological data. When meteorological conditions change, the meteorological similarity values ​​of the intersecting areas may change accordingly, which may cause changes in the target area to which they belong. This flexibility enables the early warning meteorological warning platform to better adapt to the complexity and variability of meteorological disasters. For users, they are more concerned about the meteorological disaster risks in their area. By dividing the intersecting areas into target areas with higher meteorological similarity, it is possible to ensure that users receive more accurate and relevant early warning information, thereby improving user experience. The method supports more refined division and management of target areas. By calculating the meteorological similarity values ​​and determining the ownership of the intersecting areas, a more accurate analysis and evaluation of the meteorological data in the target area can be achieved, thus supporting more refined early warnings.

[0017] Optionally, calculating the first meteorological similarity value between the intersection area and the first target area according to the historical meteorological data includes:

[0018] Obtaining a first average temperature, a first average precipitation, a first average wind speed, and a first average air pollution index of the first target area from the historical meteorological data, and obtaining a second average temperature, a second average precipitation, a second average wind speed, and a second average air pollution index of the intersection area from the historical meteorological data;

[0019] calculating a first difference between the first average temperature and the second average temperature, calculating a second difference between the first average precipitation and the second average precipitation, calculating a third difference between the first average wind speed and the second average wind speed, and calculating a fourth difference between the first average air pollution index and the second average air pollution index;

[0020] The temperature, precipitation, wind speed and air pollution index are respectively assigned a first weight, a second weight, a third weight and a fourth weight, and the first meteorological similarity is calculated by weighted summing the first difference, the second difference, the third difference and the fourth difference, wherein the first weight is equal to the second weight, the third weight is equal to the fourth weight, and the first weight is greater than the third weight.

[0021] By adopting the above technical solution, by comparing the average values ​​of multiple meteorological indicators of the first target area and the intersection area, the similarity of the meteorological conditions of the two areas can be more comprehensively understood. This method can more accurately reflect the meteorological similarity of the two areas than considering only a single meteorological indicator. Different weights are assigned to meteorological indicators such as temperature, precipitation, wind speed, and air pollution index, which reflects the difference in importance of these indicators in the calculation of meteorological similarity. For example, temperature and precipitation usually have a greater impact on meteorological disasters, so it is reasonable to assign higher weights. This weight distribution method makes the meteorological similarity calculation more in line with the actual situation. By calculating the meteorological similarity, the intersection area can be divided into target areas with more similar meteorological conditions, thereby realizing the refined division of the warning area. This helps to more accurately predict and assess the risks of meteorological disasters and provide more targeted guidance for disaster prevention and mitigation. Since meteorological conditions may change over time, the meteorological similarity of the intersection area may also change accordingly. By regularly updating historical meteorological data and recalculating meteorological similarity, the division of warning areas can be flexibly adjusted according to actual conditions to improve the adaptability of the warning system. By finely dividing the warning area, the resources of the warning system can be more reasonably allocated. For areas with similar meteorological conditions, early warning resources and information can be shared to improve resource utilization efficiency.

[0022] Optionally, determining a target type of meteorological disasters in a target area according to historical meteorological data, and determining a meteorological disaster warning indicator for the target area according to the target type includes:

[0023] Statistics on the types of meteorological disasters that have occurred in the target area;

[0024] When the meteorological disaster type is unique, determining the meteorological disaster type as the target type;

[0025] When the meteorological disaster type is not unique, the first meteorological disaster type is determined as the target type, the first meteorological disaster type and the second meteorological disaster type are any two meteorological disaster types that have occurred in the target area, and the number of occurrences of the first meteorological disaster type is greater than the number of occurrences of the second meteorological disaster type;

[0026] When the target type is drought or flood, determining the meteorological disaster warning indicator of the target area to be precipitation;

[0027] When the target type is high temperature or cold wave, determining that the meteorological disaster warning indicator of the target area is temperature;

[0028] When the target type is haze or sandstorm, the meteorological disaster warning indicator for the target area is determined to be the air pollution index.

[0029] By adopting the above technical solution, the types of meteorological disasters that have occurred in the target area are counted, and the target types of warnings are determined based on these types, making the warning more targeted and accurate. This can avoid aimless shooting and ensure that warning resources can be concentrated on the disaster types that need the most attention. When the types of meteorological disasters that have occurred in the target area are not unique, the target type is determined according to the number of disasters that have occurred. This frequency-based priority determination method can identify the most common meteorological disasters in the target area, so as to give priority warnings to them and improve the effectiveness of the warning. According to the target type, setting corresponding warning indicators, such as precipitation, temperature and air pollution index, can ensure that the warning content is closely related to the target disaster type. This reasonably set warning indicator helps to improve the pertinence and accuracy of the warning and make the warning information more in line with the actual situation. By setting warning indicators according to the types of meteorological disasters in the target area, the refinement of the warning can be achieved. The types of meteorological disasters in different regions may be different, so setting warning indicators according to regional characteristics can better reflect the meteorological disaster risks in the region and improve the pertinence and effectiveness of the warning. By setting reasonable warning indicators, the configuration of warning resources can be optimized according to the actual situation of the target area. For common meteorological disaster types, more resources can be invested in monitoring and early warning; for less common meteorological disaster types, resources can be appropriately reduced. This resource optimization allocation method helps to improve the efficiency and effectiveness of early warning.

[0030] Optionally, determining the warning thresholds corresponding to each risk level of the meteorological disaster warning indicator according to the influencing factors of the target area includes:

[0031] Acquire the number of communication base stations and historical traffic flow in the target area, predict the traffic flow at a preset time according to the historical traffic flow, and perform weighted summation of the number of communication base stations and the traffic flow at the preset time to obtain a judgment value;

[0032] When the judgment value is less than the first threshold, the basic warning threshold of each risk level is determined according to the historical meteorological data;

[0033] When the judgment value is greater than or equal to the first threshold and less than the second threshold, adjusting the basic warning threshold according to the vegetation coverage rate, the number of buildings and the type of buildings;

[0034] When the judgment value is greater than or equal to the second threshold, the basic warning threshold is adjusted according to the number and type of enterprises.

[0035] By adopting the above technical solution, not only the number of communication base stations, which indirectly reflects the population density, is considered, but also the historical traffic flow is introduced, and the traffic flow at the preset time is predicted. The combined use of these two indicators can more comprehensively reflect the population mobility and activity of the target area, and provide a more accurate basis for meteorological disaster warning. The judgment value obtained by weighted summation can dynamically adjust the warning threshold according to the population mobility and activity of the area. When the judgment value is low, it means that the population in the area is sparse or the activity is low. At this time, a loose warning threshold can be set based on historical meteorological data; when the judgment value is high, it means that the population in the area is dense or the activities are frequent, and a more stringent warning threshold needs to be set to ensure the timeliness and accuracy of the warning. According to the different ranges of the judgment value, the method can finely adjust the warning threshold. In areas with a small number of communication base stations and low traffic flow, the warning threshold may rely more on historical meteorological data; while in areas with a large number of communication base stations or high traffic flow, the setting of the warning threshold will consider more factors such as vegetation coverage, the number and type of buildings, and the number and type of enterprises to achieve more accurate warnings. By comprehensively considering multiple factors and dynamically adjusting the warning threshold, this method can more accurately predict the probability of occurrence and impact range of meteorological disasters, thereby improving the efficiency and accuracy of early warning. This will help relevant departments and personnel take preventive measures in advance and reduce the threat of meteorological disasters to the safety of life and property of the people.

[0036] Optionally, adjusting the basic warning threshold according to vegetation coverage, number of buildings and building types includes:

[0037] Determine the fifth weight, the sixth weight and the seventh weight corresponding to the vegetation coverage rate, the number of buildings and the type of buildings according to the meteorological disaster warning indicators;

[0038] Converting a first impact of vegetation coverage on the meteorological disaster warning index into a first value, converting a second impact of the number of buildings on the meteorological disaster warning index into a second value, and converting a third impact of building type on the meteorological disaster warning index into a third value;

[0039] A weighted sum is performed on the first value, the second value, and the third value to obtain a first adjustment value, and the basic warning threshold is adjusted according to the first adjustment value.

[0040] By adopting the above technical scheme, considering geographical and environmental factors such as vegetation coverage, number of buildings and building types, the meteorological disaster risk in the target area can be more accurately reflected. These factors have an important impact on the occurrence, development and impact of meteorological disasters, so incorporating them into the adjustment process of the warning threshold can improve the accuracy and reliability of the warning. Different regions have different vegetation coverage, number of buildings and building types, which will affect the impact and propagation speed of meteorological disasters. By adjusting the warning threshold according to these factors, a more refined warning can be achieved to ensure that different regions can obtain warning information that conforms to their actual conditions. According to the adjusted warning threshold, warning resources and emergency resources can be allocated more reasonably. For areas with lower warning thresholds, more resources and manpower may need to be invested in monitoring and warning; while for areas with higher warning thresholds, resource investment can be appropriately reduced to improve resource utilization efficiency. Incorporating factors such as vegetation coverage, number of buildings and building types into the adjustment process of the warning threshold can promote the development of multi-factor comprehensive evaluation. This method can not only improve the accuracy and reliability of warnings, but also provide a more scientific basis for disaster risk assessment and disaster management. It has certain flexibility and adaptability, and can be adjusted and optimized according to the actual conditions of different regions. Regardless of the type of area, such as cities, rural areas or mountainous areas, the warning threshold can be adjusted according to this method to adapt to the meteorological disaster risk characteristics of different regions.

[0041] Optionally, adjusting the basic warning threshold according to the number and type of enterprises includes:

[0042] Set the first adjustment factor based on the number of enterprises;

[0043] Determining target enterprise types associated with the meteorological disaster warning indicators, and setting a second adjustment coefficient according to the number of target enterprise types;

[0044] The first adjustment coefficient is multiplied by the second adjustment coefficient to obtain an adjustment coefficient, and the adjustment coefficient is multiplied by the basic warning threshold to obtain an adjusted warning threshold.

[0045] By adopting the above technical solution, the first adjustment coefficient is set considering the number of enterprises, and the second adjustment coefficient is set according to the target enterprise type associated with the meteorological disaster warning indicator, so that the warning threshold can be more in line with the actual situation of the target area. This targeted adjustment makes the warning information more practical and helps guide enterprises to take corresponding disaster prevention and mitigation measures. Enterprises are important subjects of social and economic activities and one of the main objects affected by meteorological disasters. By adjusting the warning threshold according to the number and type of enterprises, the impact of meteorological disasters on enterprises can be more accurately assessed, thereby optimizing resource allocation. For enterprises with greater impact, rescue resources and emergency materials can be allocated preferentially to ensure the normal operation of the enterprise and the safety of employees. Meteorological disaster warning not only involves the meteorological department, but also requires close cooperation with relevant departments such as emergency management departments and enterprises. By adjusting the warning threshold considering the number and type of enterprises, the coordination and cooperation between the meteorological department and other departments can be promoted. Relevant departments can take corresponding response measures in a timely manner according to the warning information to jointly respond to the challenges brought by meteorological disasters. By setting the adjustment coefficient to dynamically adjust the warning threshold, the warning system is more flexible. As the number and type of enterprises change, the warning threshold can be adjusted accordingly to meet the warning needs in different situations. This flexibility helps to improve the adaptability and reliability of the warning system. The adjusted warning threshold can provide more accurate and comprehensive information support for decision makers. Decision makers can judge the risk level and potential impact range of meteorological disasters based on the warning threshold, and then formulate corresponding response strategies and measures. This support helps decision makers make more scientific and reasonable decisions.

[0046] In a second aspect of the present application, a meteorological disaster risk early warning system is provided, comprising a classification module, a threshold module, a data module and an early warning module, wherein:

[0047] A classification module configured to determine a target type of meteorological disasters in a target area according to historical meteorological data, and determine a meteorological disaster warning indicator for the target area according to the target type;

[0048] A threshold module is configured to determine the warning threshold corresponding to each risk level of the meteorological disaster warning indicator according to the influencing factors of the target area, wherein the influencing factors include population density, vegetation coverage, building information and enterprise information;

[0049] A data module configured to obtain current meteorological data of the target area, predict the predicted meteorological data within a preset time in the future in combination with the historical meteorological data of the target area, and extract target data corresponding to the meteorological disaster warning indicator from the predicted meteorological data;

[0050] The early warning module is configured to determine the meteorological disaster risk level of the target area based on the comparison result of the target data and the early warning threshold, and when the meteorological disaster risk level is greater than the risk threshold, generate early warning information for the target area according to the meteorological disaster risk level.

[0051] In the third aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes any one of the methods described above.

[0052] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, any of the methods described above is executed.

[0053] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0054] 1. Determine the target type of meteorological disasters in the target area based on historical meteorological data, and set early warning indicators accordingly. This targeted setting makes the early warning more accurate and can accurately reflect the unique meteorological disaster risks in the target area;

[0055] 2. By comprehensively considering influencing factors such as population density, vegetation coverage, building information and enterprise information, the warning threshold of meteorological disaster warning indicators can be dynamically adjusted. This dynamic adjustment makes the warning threshold more in line with the actual situation and improves the accuracy and effectiveness of the warning;

[0056] 3. Not only obtain current meteorological data, but also combine historical meteorological data to predict the predicted meteorological data within a preset time in the future, and extract target data from it. This method of combining prediction and early warning can detect potential meteorological disaster risks in advance and provide sufficient preparation time for disaster prevention and emergency response;

[0057] 4. When the meteorological disaster risk level exceeds the set risk threshold, personalized warning information for the target area can be generated according to the meteorological disaster risk level. This personalized warning information can more accurately reflect the meteorological disaster risk situation in the target area and provide more accurate warning services for relevant departments and the public. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 It is a flow chart of the early warning method for meteorological disaster risk disclosed in the embodiment of the present application;

[0059] Figure 2It is a schematic diagram of dividing the monitoring area in an embodiment of the present application;

[0060] Figure 3 It is a schematic diagram of a module of a meteorological disaster risk early warning system disclosed in an embodiment of the present application;

[0061] Figure 4 It is a structural schematic diagram of an electronic device disclosed in an embodiment of the present application.

[0062] Explanation of the accompanying drawings: 301, classification module; 302, threshold module; 303, data module; 304, warning module; 401, processor; 402, communication bus; 403, user interface; 404, network interface; 405, memory. DETAILED DESCRIPTION

[0063] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0064] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0065] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0066] This embodiment discloses a meteorological disaster risk early warning method, which is applied to a meteorological early warning platform. Figure 1 is a flow chart of the meteorological disaster risk early warning method disclosed in the embodiment of the present application, such as Figure 1 As shown, the early warning method includes the following steps:

[0067] S110, determining a target type of meteorological disasters in a target area according to historical meteorological data, and determining a meteorological disaster warning indicator for the target area according to the target type;

[0068] Collect long-term historical meteorological data of the target area. Historical meteorological data usually include multiple meteorological parameters such as temperature, humidity, wind speed, wind direction, rainfall, snowfall, lightning activity, air pressure, etc., and need to cover different seasons and weather patterns. Conduct in-depth analysis of the collected historical meteorological data. This process usually includes: observing the changing trend of meteorological parameters on a long-term scale, such as the annual increase in temperature or the seasonal change in rainfall; finding extreme weather events in historical records, such as heavy rain, blizzard, typhoon, etc.; identifying the association and pattern between meteorological parameters through statistical methods and machine learning algorithms. For example, a combination of certain meteorological parameters may indicate the occurrence of a certain meteorological disaster. Based on the results of the above data analysis, common meteorological disaster types in the target area can be identified. These types may include: heavy rain, drought, typhoon, blizzard, freezing, and lightning. A preset number of target types can be selected from the common meteorological disaster types in the target area. For example, in the embodiment of the present application, a most important target type can be selected for focus, and other target types also need to be appropriately concerned. After determining the target type of meteorological disasters in the target area, it is necessary to set corresponding early warning indicators for the target type. These indicators are usually based on meteorological parameters and are directly related to the likelihood or severity of the disaster. For example, for rainstorm disasters, early warning indicators may include rainfall, rainfall duration, and basin water level. If the rainfall in a specific time period (such as 1 hour, 6 hours, 24 hours) reaches or exceeds a certain threshold, it indicates that the rainfall indicator is abnormal. If the length of continuous rainfall exceeds a certain threshold, it indicates that the rainfall duration indicator is abnormal. If the water level of a river or lake exceeds the flood warning line, it indicates that the basin water level indicator is abnormal. For other types of disasters, such as typhoons, droughts, blizzards, etc., there will also be corresponding early warning indicators, which are usually set according to the characteristics of the disaster and historical data.

[0069] Optionally, the early warning method includes:

[0070] Divide the monitoring area into multiple target areas according to the monitoring range of the meteorological base station;

[0071] When there is an intersecting area between adjacent target areas, the intersecting area refers to an area where the first target area and the second target area intersect each other, the first target area and the second target area are adjacent target areas, and a first meteorological similarity value between the intersecting area and the first target area is calculated based on the historical meteorological data, and a second meteorological similarity value between the intersecting area and the second target area is calculated;

[0072] When the first meteorological similarity value is greater than the second meteorological similarity value, the intersection area is divided into the first target area.

[0073] The monitoring area is divided into target areas of different levels according to the size, topography, climate characteristics and other factors of the monitoring area to ensure that each target area can receive accurate meteorological monitoring. Each target area should be able to represent the meteorological characteristics and environmental conditions of the area in which it is located, so as to provide accurate data support for subsequent meteorological analysis and forecasting.

[0074] First, determine the center point of the monitoring area (which can be the geographic center or an area with typical meteorological conditions). Then, based on the center point, draw multiple concentric circles with different radii, and use the intersection of the concentric circles and the radial lines as the potential location of the meteorological base station. Based on the above steps, the monitoring area can be further subdivided into multiple grids, and the center or intersection of each grid is used as the potential location of the meteorological base station. The size of the grid can be adjusted according to the monitoring range and monitoring needs of the meteorological base station. The setting of the meteorological base station must first consider its monitoring range to ensure that each meteorological base station can cover most of the target area where it is located, while avoiding duplicate coverage and blind spots. Topography has an important impact on meteorological conditions. The setting of meteorological base stations should fully consider the topographic features, such as mountains, rivers, lakes, etc., to ensure that the meteorological base stations can accurately monitor the meteorological changes in these areas. The climate characteristics of different regions may vary greatly. The setting of meteorological base stations should fully consider these factors, such as precipitation, temperature, humidity, wind speed, etc., in order to provide more accurate data support for meteorological analysis and prediction. Population distribution is also an important consideration for the setting of meteorological base stations. In densely populated areas, the number and density of meteorological base stations should be appropriately increased to provide more timely and accurate meteorological services to local residents. Before setting up a meteorological base station, a full field survey should be conducted to understand the topography, climate characteristics, population distribution, etc. of the monitoring area, so as to provide a scientific basis for the setting of meteorological base stations. Using GIS (Geographic Information System) and other technical means, simulate and analyze the potential locations of meteorological base stations, evaluate their monitoring range, coverage area, data quality and other indicators, and provide decision support for the setting of meteorological base stations. After the meteorological base station is set up, it should be optimized and adjusted according to the actual monitoring situation, such as increasing or decreasing the number of meteorological base stations, adjusting the location of meteorological base stations, etc., to ensure the accuracy and reliability of meteorological monitoring data.

[0075] The existing division methods are to divide the monitoring area into regular rectangular grids, while the present application divides the monitoring area into multiple circles according to the monitoring range of the meteorological base station. The monitoring range of the meteorological base station is usually circular, so the circular grid based on the monitoring range of the meteorological base station can more accurately reflect the distribution and changes of meteorological data. This division method can ensure that the meteorological data in each grid is collected by the same meteorological base station, thereby reducing data differences and errors and improving the accuracy of early warning. Regular rectangular grids may not be able to fully adapt to complex terrain and landforms, such as mountainous areas and rivers, when divided. The circular grid can flexibly adjust the size and shape according to the monitoring range of the meteorological base station to better adapt to the changes in terrain and landforms. This means that in complex terrain areas, circular grid division can provide more accurate meteorological disaster warning information. In the regular rectangular grid division, there may be some grids without meteorological base stations or insufficient number of meteorological base stations, resulting in a lack of meteorological data or low quality in these grids. Dividing into circular grids according to the monitoring range of the meteorological base station can ensure that there is at least one meteorological base station in each grid, thereby optimizing the configuration of meteorological resources and improving the coverage and quality of meteorological data. Circular grid division makes the transmission and processing of meteorological data more efficient. The circular grid division method makes the early warning system more flexible and scalable. When a new meteorological base station is added or the monitoring range of a meteorological base station changes, the grid division can be easily adjusted to adapt to the new distribution and changes of meteorological data.

[0076] According to the monitoring range of the meteorological base station, the entire monitoring area is divided into multiple target areas. These target areas are usually determined based on the monitoring radius or coverage range of the meteorological base station with the meteorological base station as the center. This division method can ensure that each target area has sufficient meteorological data support while covering the entire monitoring area. After the target area division is completed, it is necessary to identify the intersection areas between adjacent target areas. These intersection areas are the parts where adjacent target areas intersect with each other. They may be affected by multiple meteorological base stations at the same time, so they need special attention during early warning. In order to determine the ownership of the intersection area, it is necessary to calculate the meteorological similarity value between the intersection area and the adjacent target area respectively. The meteorological similarity value can be calculated based on historical meteorological data, usually including the similarity of multiple meteorological parameters such as temperature, humidity, rainfall, wind speed, etc. The specific calculation method can be determined according to actual needs and data characteristics, for example, methods such as correlation coefficient and distance measurement can be used. After calculating the meteorological similarity value, the intersection area can be divided into a target area with a higher meteorological similarity value. Specifically, if the first meteorological similarity value between the intersection area and the first target area is greater than the second meteorological similarity value with the second target area, the intersection area is divided into the first target area. This ensures that the meteorological characteristics of the intersecting area are more consistent with the target area, thereby improving the accuracy of the early warning.

[0077] Figure 2 is a schematic diagram of dividing the monitoring area in the embodiment of the present application, such as Figure 2 As shown, according to the monitoring range of the meteorological base station, the entire monitoring area 201 is divided into a first target area 202, a second target area 203, and a third target area 204 (for the sake of simplicity of description, Figure 2 Only the above three target areas are shown in FIG. 2 ), there is a first intersection area 205 between the first target area 202 and the second target area 203, there is a second intersection area 206 between the first target area 202 and the third target area 204, the area of ​​the first target area 202 minus the first intersection area 205 and the second intersection area 206 is called A, the area of ​​the second target area 203 minus the first intersection area 205 is called B, and the area of ​​the third target area 204 minus the second intersection area 206 is called C. Assuming that the two meteorological parameters of temperature and rainfall are selected to calculate the similarity value, the temperature correlation coefficient between the first intersection area 205 and A is 0.85, and the rainfall correlation coefficient is 0.7; the temperature correlation coefficient between the first intersection area 205 and B is 0.7, and the rainfall correlation coefficient is 0.65. Since the meteorological similarity value (the sum of the correlation coefficients of temperature and rainfall) between the first intersection area 205 and A is higher, the first intersection area 205 can be divided into A, that is, the first intersection area 205 is divided into the first target area 202. Based on the same method, the ownership of 206 can be determined.

[0078] By calculating the meteorological similarity values ​​between the intersecting area and the adjacent target area, and dividing the intersecting area into target areas with higher meteorological similarity, the accuracy and pertinence of the warning information can be ensured. In this way, the meteorological warning for each target area can be based on data that is more consistent with its meteorological characteristics, thereby improving the accuracy of the warning. Dividing the intersecting area into target areas with higher meteorological similarity can avoid repeated meteorological data analysis and warning judgments between multiple target areas. This can significantly improve the efficiency of warnings and enable relevant departments to make decisions and respond more quickly. There may be large differences in meteorological characteristics and disaster risks in different regions. By dividing the monitoring area into multiple target areas and dividing the intersecting areas based on meteorological similarity values, it can better adapt to the diversity of geography and climate and provide more accurate meteorological disaster warning services for different regions.

[0079] Optionally, calculating the first meteorological similarity value between the intersection area and the first target area according to the historical meteorological data includes:

[0080] Obtaining a first average temperature, a first average precipitation, a first average wind speed, and a first average air pollution index of the first target area from the historical meteorological data, and obtaining a second average temperature, a second average precipitation, a second average wind speed, and a second average air pollution index of the intersection area from the historical meteorological data;

[0081] calculating a first difference between the first average temperature and the second average temperature, calculating a second difference between the first average precipitation and the second average precipitation, calculating a third difference between the first average wind speed and the second average wind speed, and calculating a fourth difference between the first average air pollution index and the second average air pollution index;

[0082] The temperature, precipitation, wind speed and air pollution index are respectively assigned a first weight, a second weight, a third weight and a fourth weight, and the first meteorological similarity is calculated by weighted summing the first difference, the second difference, the third difference and the fourth difference, wherein the first weight is equal to the second weight, the third weight is equal to the fourth weight, and the first weight is greater than the third weight.

[0083] Continuing with the above example, the first average temperature (TA), the first average precipitation (PA), the first average wind speed (VA), and the first average air pollution index (AQIA) are extracted from the historical meteorological data of the first target area 202. The second average temperature (TB), the second average precipitation (PB), the second average wind speed (VB), and the second average air pollution index (AQIB) are extracted from the historical meteorological data of the first intersection area 205. The first difference between the first average temperature and the second average temperature is calculated (ΔT=|TA-TB|). The second difference between the first average precipitation and the second average precipitation is calculated (ΔP=|PA-PB|). The third difference between the first average wind speed and the second average wind speed is calculated (ΔV=|VA-VB|). The fourth difference between the first average air pollution index and the second average air pollution index is calculated (ΔAQI=|AQIA-AQIB|). According to the importance of meteorological factors and the degree of influence on early warning, weights are assigned to temperature, precipitation, wind speed, and air pollution index respectively. In the embodiment of the present application, it is assumed that temperature and precipitation have a greater impact on meteorological similarity, so they are assigned higher weights (first weight and second weight), while wind speed and air pollution index have less impact, so they are assigned lower weights (third weight and fourth weight). Assume that the first weight and the second weight are both 0.3, and the third weight and the fourth weight are both 0.2 (that is, the first weight = the second weight > the third weight = the fourth weight). In order to ensure that the larger the similarity value, the more similar the meteorology, the weighted summation of the first difference, the second difference, the third difference and the fourth difference refers to taking the reciprocal of each difference for weighted summation. The four differences are weighted summed using the above weights to calculate the first meteorological similarity value (Similarity). Similarity=0.3×1 / ΔT+0.3×1 / ΔP+0.2×1 / ΔV+0.2×1 / ΔAQI.

[0084] By comparing the differences in key meteorological parameters such as average temperature, average precipitation, average wind speed, and average air pollution index between the first target area and the intersection area, and assigning reasonable weights to different parameters, the meteorological similarity between the two can be more accurately evaluated. This refined evaluation method makes the division of the intersection area more accurate, thereby improving the accuracy of meteorological disaster warnings. There may be large differences in meteorological conditions in different regions. For example, the range and importance of parameters such as temperature, precipitation, wind speed, and air pollution index may vary. By assigning different weights to different meteorological parameters, these differences can be better reflected, so that the warning method can adapt to complex and changeable meteorological conditions. Not only traditional meteorological parameters such as temperature and precipitation are considered, but also more factors such as wind speed and air pollution index are incorporated. This comprehensive consideration of multiple factors can more comprehensively evaluate the meteorological similarity between different regions, making the warning results more comprehensive and reliable. By accurately dividing the ownership of the intersection area, the resources for meteorological warning and emergency response can be more reasonably allocated. Dividing the intersection area into a target area that is closer to its meteorological conditions can ensure the effective use of resources and avoid waste and redundancy of resources.

[0085] Optionally, determining a target type of meteorological disasters in a target area according to historical meteorological data, and determining a meteorological disaster warning indicator for the target area according to the target type includes:

[0086] Statistics on the types of meteorological disasters that have occurred in the target area;

[0087] When the meteorological disaster type is unique, determining the meteorological disaster type as the target type;

[0088] When the meteorological disaster type is not unique, the first meteorological disaster type is determined as the target type, the first meteorological disaster type and the second meteorological disaster type are any two meteorological disaster types that have occurred in the target area, and the number of occurrences of the first meteorological disaster type is greater than the number of occurrences of the second meteorological disaster type;

[0089] When the target type is drought or flood, determining the meteorological disaster warning indicator of the target area to be precipitation;

[0090] When the target type is high temperature or cold wave, determining that the meteorological disaster warning indicator of the target area is temperature;

[0091] When the target type is haze or sandstorm, the meteorological disaster warning indicator for the target area is determined to be the air pollution index.

[0092] If the target area has only experienced one type of meteorological disaster in the past historical records, such as drought, then drought is directly determined as the target type of meteorological disasters in the target area. If the target area has experienced multiple meteorological disasters, further analysis is required. For example, it is found in statistics that drought has occurred 10 times, floods have occurred 5 times, high temperatures have occurred 8 times, cold waves have occurred 3 times, haze has occurred 6 times, and sandstorms have occurred 2 times. Since drought occurs the most times, drought is first taken as the first meteorological disaster type and is considered as the target type. However, if it is necessary to pay attention to multiple disasters at the same time, multiple target types can also be set, or the severity and impact range of the disasters can be sorted to select the most important ones as the target types. In the embodiment of the present application, it is assumed that only one of the most important target types is selected, so drought is determined as the target type. According to the determined target type, the corresponding meteorological disaster warning indicators need to be further determined. For drought disasters, precipitation is a key warning indicator. Therefore, the meteorological disaster warning indicator of the target area is determined to be precipitation. When the precipitation continues to be lower than a certain threshold, a drought warning needs to be issued. If the target type is high temperature or cold wave, temperature becomes the main warning indicator. For high temperatures, when the temperature continues to be higher than a certain high temperature threshold, a high temperature warning needs to be issued; for cold waves, when the temperature drops rapidly and falls below a certain low temperature threshold, a cold wave warning needs to be issued. For air pollution-related disasters such as haze or sandstorms, the air pollution index is a key warning indicator. When the air pollution index continues to be higher than a certain threshold, a corresponding air pollution warning needs to be issued.

[0093] By analyzing the types of meteorological disasters that have occurred in the target area in history and determining the main target types of meteorological disasters based on this, the early warning work can be made more targeted. This method can avoid blind early warnings, reduce unnecessary waste of resources, and improve the accuracy of early warnings. After determining the target type, selecting appropriate early warning indicators according to different types of disasters, such as precipitation, temperature, air pollution index, etc., can make the early warning strategy more scientific and reasonable. This targeted early warning strategy can more effectively guide disaster prevention and mitigation work and reduce the losses caused by disasters. The types and characteristics of meteorological disasters in different regions may be different. It can fully consider the characteristics of the target area, determine its main meteorological disaster types based on historical data, and formulate corresponding early warning strategies accordingly. This highly adaptable method can improve the flexibility and practicality of the early warning system. Through automated data analysis and type determination processes, the main types of meteorological disasters in the target area can be quickly and accurately identified, and targeted early warning indicators can be provided to decision makers. This helps to speed up the decision-making process, improve decision-making efficiency, and ensure that effective responses can be made in a timely manner when disasters occur. According to the types of meteorological disasters and early warning indicators, disaster prevention and mitigation resources, such as human, material, and financial resources, can be more reasonably allocated. This optimization of resource allocation can ensure that rescue and recovery work can be carried out quickly and effectively when a disaster occurs, reducing the impact of the disaster on society and the economy.

[0094] S120, determining the warning thresholds corresponding to each risk level of the meteorological disaster warning indicator according to the influencing factors of the target area, wherein the influencing factors include population density, vegetation coverage, building information, and enterprise information;

[0095] Population density is one of the important factors in assessing the potential impact of meteorological disasters. Densely populated areas face a higher risk of casualties and property losses when facing meteorological disasters. Analyze the relationship between population density and disaster losses in historical meteorological disaster events. Adjust the warning thresholds at different risk levels based on the analysis results. For example, in areas with high population density, the warning threshold may need to be set lower to issue warnings earlier. The impact of vegetation coverage on meteorological disasters is mainly reflected in soil conservation and water regulation. High vegetation coverage may help mitigate the impact of soil erosion and floods. Analyze the relationship between vegetation coverage and meteorological disaster losses. Adjust the warning thresholds based on the analysis results. For example, in areas with high vegetation coverage, the warning threshold for floods can be appropriately increased. Information such as the structure, type, and density of buildings will affect the degree of damage and the difficulty of rescue in meteorological disasters. For example, old buildings may be more vulnerable to damage in strong winds. Analyze the damage of different types of buildings in meteorological disasters. Set different warning thresholds for different types of buildings based on the analysis results of building information. Enterprise information includes the type, size, and location of the enterprise, which will affect the degree of impact of meteorological disasters on enterprise operations. For example, chemical companies may face the risk of leakage when facing heavy rain. Analyze the potential risks of different types of enterprises in meteorological disasters. According to the analysis results of enterprise information, set different warning thresholds for different types of enterprises. At the same time, for high-risk enterprises, more stringent warning thresholds may need to be set. After determining the warning thresholds corresponding to each influencing factor, a comprehensive analysis is required to ensure the rationality and effectiveness of the warning thresholds. This includes considering the mutual influence between different factors and the differences between different regions. According to the analysis results, the warning thresholds can be adjusted and optimized as necessary.

[0096] Optionally, determining the warning thresholds corresponding to each risk level of the meteorological disaster warning indicator according to the influencing factors of the target area includes:

[0097] Acquire the number of communication base stations and historical traffic flow in the target area, predict the traffic flow at a preset time according to the historical traffic flow, and perform weighted summation of the number of communication base stations and the traffic flow at the preset time to obtain a judgment value;

[0098] When the judgment value is less than the first threshold, the basic warning threshold of each risk level is determined according to the historical meteorological data;

[0099] When the judgment value is greater than or equal to the first threshold and less than the second threshold, adjusting the basic warning threshold according to the vegetation coverage rate, the number of buildings and the type of buildings;

[0100] When the judgment value is greater than or equal to the second threshold, the basic warning threshold is adjusted according to the number and type of enterprises.

[0101] The number of communication base stations can indeed indirectly reflect the population density of a region. In densely populated areas, the number of communication base stations is often large due to the large demand for communication; while in sparsely populated areas, the number of communication base stations is relatively small. Therefore, the number of communication base stations can be used as an important reference for assessing the population density of a region and the scope of potential meteorological disasters. The introduction of historical traffic flow data adds another dimension to the assessment. Traffic flow data can directly reflect the activity and mobility of a region, and then reflect the distribution of population and resources in the region and the potential impact of disasters. By analyzing historical traffic flow data, the traffic flow at a preset time can be predicted, so as to more accurately assess the potential risk of the region at that time. A judgment value is obtained by weighted summing the number of communication base stations and the traffic flow at the preset time. This judgment value comprehensively considers the two factors of population density and regional activity, and provides a more accurate basis for the subsequent adjustment of the warning threshold. Different warning threshold adjustment strategies are adopted according to the size of the judgment value. When the judgment value is small, it indicates that the population density and activity level in the area are low, and the sensitivity to meteorological disasters is relatively low. Therefore, the warning threshold can be mainly determined by historical meteorological data; when the judgment value is large, it indicates that the population density and activity level in the area are high, and it is necessary to consider other influencing factors, such as vegetation coverage, number and type of buildings, number and type of enterprises, etc., to fine-tune the warning threshold. High vegetation coverage may help reduce the impact of soil erosion and floods, so in areas with rich vegetation, the warning threshold for floods can be appropriately increased. The structure, density and type of buildings will affect the degree of damage and the difficulty of rescue in meteorological disasters. For example, old buildings may be more vulnerable to strong winds. Therefore, in areas with a large number of buildings and a high proportion of old buildings, the warning threshold for related meteorological disasters (such as strong winds) needs to be set lower. When the number of communication base stations is greater than or equal to the second threshold: In densely populated large or megacities, the consequences of meteorological disasters may be more serious. In addition to the above factors, special attention should be paid to enterprise information. Number and type of enterprises: Different types of enterprises may face different risks in meteorological disasters. For example, chemical companies may face the risk of leakage during heavy rain. Therefore, in high-density enterprise areas, especially areas where high-risk enterprises (such as chemical companies) are concentrated, it is necessary to set more stringent warning thresholds for related meteorological disasters (such as heavy rain and strong winds).

[0102] By considering the number of communication base stations (indirectly reflecting population density), the system can more accurately assess population distribution and density, and thus more accurately predict the impact of meteorological disasters on the population. This helps ensure that warnings are issued in a timely manner when necessary to reduce the potential impact of disasters on the population. Factors such as population density, traffic flow, vegetation coverage, number of buildings and type of enterprises vary greatly in different regions, all of which affect the potential impact of meteorological disasters. Therefore, dynamically adjusting the warning threshold can ensure the pertinence and effectiveness of the warning and avoid excessive or insufficient warnings. By adjusting the warning threshold to adapt to different risk levels according to different ranges of judgment values ​​(based on the number of communication base stations and traffic flow), this method can more accurately reflect the risk level of the target area when facing different meteorological disasters. In addition to considering the number of communication base stations (population density), multiple factors such as traffic flow, vegetation coverage, number of buildings and type of enterprises are also combined, which helps to more comprehensively assess the vulnerability and risk level of the target area in the face of meteorological disasters. Optionally, the adjustment of the basic warning threshold according to vegetation coverage, number of buildings and type of buildings includes:

[0103] Determine the fifth weight, the sixth weight and the seventh weight corresponding to the vegetation coverage rate, the number of buildings and the type of buildings according to the meteorological disaster warning indicators;

[0104] Converting a first impact of vegetation coverage on the meteorological disaster warning index into a first value, converting a second impact of the number of buildings on the meteorological disaster warning index into a second value, and converting a third impact of building type on the meteorological disaster warning index into a third value;

[0105] A weighted sum is performed on the first value, the second value, and the third value to obtain a first adjustment value, and the basic warning threshold is adjusted according to the first adjustment value.

[0106] Set the first quantitative relationship between vegetation coverage and meteorological disaster risk. For example, assume that for every 10% increase in vegetation coverage, the risk of meteorological disasters decreases by 1 unit (the unit here can be any set risk quantitative index). For example: if the vegetation coverage of the target area is 60%, then the risk of meteorological disasters may decrease by 6 units (first value) relative to the case of 0% vegetation coverage. Set the second quantitative relationship between the number of buildings and the risk of meteorological disasters. This may require a comprehensive analysis based on historical disaster data, building types, and local terrain conditions. For example, assume that for every 1,000 buildings added, the risk of meteorological disasters increases by 1 unit. If there are 1,700 buildings in the target area, then the risk of meteorological disasters may increase by 1.7 units (second value) relative to areas without buildings. Classify buildings according to their type (such as residential, commercial, industrial, etc.) and their vulnerability to meteorological disasters. Set a vulnerability index or risk level for each type of building. Based on the type and number of buildings, calculate a comprehensive value to represent the impact of building types on meteorological disasters. For example, assume that the vulnerability index of residential buildings is 0.001, that of commercial buildings is 0.002, and that of industrial buildings is 0.003. If there are 1,000 residential buildings, 500 commercial buildings, and 200 industrial buildings in the target area, the impact of building types on meteorological disasters can be: 1000*0.001+500*0.002+200*0.003=2.6 (third value). Therefore, when the vegetation coverage rate of the target area is 60%, there are 1,000 residential buildings, 500 commercial buildings, and 200 industrial buildings in the target area, then the first adjustment value for the meteorological disaster warning indicator of precipitation is: first value*fifth weight+second value*sixth weight+third value*seventh weight. Assuming that the fifth weight, sixth weight, and seventh weight are 0.5, 0.3, and 0.2, respectively, the first adjustment value is -6*0.5+1.7*0.3+2.6*0.2=-1.97. That is, the risk of meteorological disasters is reduced by 1.97 units relative to the basic value. The "unit" here can be a percentage. Since the lower the risk, the larger the threshold, the current warning threshold can be increased by 1.97% relative to the basic warning threshold. For example, the basic warning threshold for precipitation is 50mm / 3h, 50*(1+1.97%)=50.99, then the current warning threshold can be 50.99mm / 3h.

[0107] By introducing vegetation coverage, the number of buildings and the type of buildings as early warning indicators, the meteorological early warning system can be made more refined. These factors can directly affect the impact of meteorology on the ground and human society. Therefore, considering these factors can make the early warning closer to the actual situation. Different regions and cities have different responses and tolerance to meteorology due to differences in vegetation coverage, building distribution and types. By determining the fifth weight, the sixth weight and the seventh weight, and calculating the corresponding first value, second value and third value, the basic early warning threshold can be adjusted individually. This adjustment can ensure that the early warning system can provide accurate and timely early warning information in different regions and cities. Considering factors such as vegetation coverage, the number of buildings and the type of buildings can more comprehensively assess the risks that may be brought by meteorology. Vegetation can reduce the risk of soil erosion and floods, while the number and type of buildings directly affect the drainage capacity and disaster response capacity. Therefore, incorporating these factors into the early warning system can improve the accuracy and reliability of the early warning. Through refined and personalized early warning adjustments, relevant departments and units can be more effectively guided in resource allocation and disaster response. After the warning is issued, relevant departments can promptly activate emergency plans, allocate emergency resources, and organize emergency teams based on the warning information to ensure personnel safety and social stability.

[0108] Optionally, adjusting the basic warning threshold according to the number and type of enterprises includes:

[0109] Set the first adjustment factor based on the number of enterprises;

[0110] Determining target enterprise types associated with the meteorological disaster warning indicators, and setting a second adjustment coefficient according to the number of target enterprise types;

[0111] The first adjustment coefficient is multiplied by the second adjustment coefficient to obtain an adjustment coefficient, and the adjustment coefficient is multiplied by the basic warning threshold to obtain an adjusted warning threshold.

[0112] Regions with a large number of enterprises usually have more frequent economic activities, higher demands for infrastructure such as energy and transportation, and correspondingly higher sensitivity to meteorological disasters. When the number of enterprises exceeds a certain threshold, a more sensitive and timely early warning mechanism is needed. Different types of enterprises have different sensitivities and tolerances to meteorological disasters. For example, agricultural enterprises may be more sensitive to droughts and floods, while energy enterprises may be more concerned about storms and power outages. When adjusting the early warning threshold, it is necessary to consider the characteristics and needs of the enterprise type. Set a basic adjustment coefficient (such as 1.0) to represent the early warning threshold without the influence of the number and type of enterprises. Set the corresponding first adjustment coefficient according to the number of enterprises. For example, when the number of enterprises exceeds 1,000, set the first adjustment coefficient to 0.9; when the number of enterprises exceeds 5,000, set the first adjustment coefficient to 0.8. Set different second adjustment coefficients according to the characteristics and needs of the enterprise type. For example, for areas where agricultural enterprises are concentrated, set the precipitation adjustment coefficient for drought warning to 0.9; for areas where energy enterprises are concentrated, set the wind speed adjustment coefficient for storm warning to 0.8. Assuming that the original warning threshold is X, the adjusted warning threshold is: Y=X*(basic adjustment coefficient*first adjustment coefficient*second adjustment coefficient).

[0113] Assume that the original warning threshold X is 100 mm / month of precipitation for drought warning, and there are 3,000 enterprises in the target area, of which agricultural enterprises account for a large proportion. The basic adjustment coefficient is 1.0. Because the number of enterprises exceeds 1,000 but does not reach 5,000, the first adjustment coefficient is set to 0.9. Considering that agricultural enterprises account for a large proportion, the second adjustment coefficient of precipitation for drought warning is set to 0.9. The adjusted warning threshold: Y = 100 mm / month * (1.0 * 0.9 * 0.9) = 81 mm / month.

[0114] By comprehensively considering the impact of the number and type of enterprises on meteorological disaster risks, the meteorological disaster risks in the target area can be assessed more accurately. This personalized adjustment enables the early warning system to be closer to the actual situation, reduce the possibility of false alarms and missed alarms, and improve the accuracy and reliability of early warnings. Based on the adjustment of the number and type of enterprises, the early warning system can more accurately guide relevant departments to allocate resources and respond to disasters. Before a meteorological disaster occurs, relevant departments can dispatch resources in advance based on the early warning information to ensure that rescue teams and materials can quickly reach the disaster-stricken areas and minimize disaster losses. By analyzing the number and type of enterprises, those types of enterprises that are particularly sensitive or vulnerable to meteorological disasters can be identified. This helps enterprises take risk management measures in advance, such as strengthening facility maintenance and formulating emergency plans, to improve their ability to resist meteorological disasters. At the same time, this also provides a scientific basis for the government to formulate relevant policies and standards, and promotes the prevention and management of meteorological disaster risks by the entire society. The adjusted early warning threshold can provide more scientific decision-making support for the government, enterprises and the public. The government can formulate more reasonable disaster prevention and mitigation measures based on the early warning information, enterprises can adjust production plans and resource allocation based on the early warning information, and the public can take protective measures in advance based on the early warning information to reduce personal and family losses.

[0115] S130, obtaining the current meteorological data of the target area, predicting the predicted meteorological data within a preset time in the future in combination with the historical meteorological data of the target area, and extracting the target data corresponding to the meteorological disaster warning indicator from the predicted meteorological data;

[0116] The current meteorological data of the target area are obtained through the meteorological base station. These data usually include basic parameters such as temperature, humidity, wind speed, wind direction, air pressure, precipitation, and real-time monitoring information of possible meteorological phenomena (such as thunderstorms, typhoons, sandstorms, etc.). These data reflect the current meteorological conditions in the target area and are the basis for meteorological disaster warning. After obtaining the current meteorological data, these data and the historical meteorological data of the target area are used to predict the meteorological changes in the future through the meteorological prediction model. The historical meteorological data contains the laws and characteristics of past meteorological changes in the target area, which has important reference value for predicting future weather. The meteorological prediction model usually adopts the numerical weather forecast method, which simulates atmospheric dynamics, thermal dynamics, microphysics and other processes, combines observation data and initial conditions, and calculates the changes in meteorological elements in the future. The prediction time range can be set as needed, such as a few hours, a few days or a few weeks. After obtaining the future predicted meteorological data, it is necessary to extract the target data related to the meteorological disaster warning indicators from these data. Meteorological disaster warning indicators usually include key parameters such as precipitation, wind speed, visibility, and temperature. Changes in these parameters may trigger or aggravate meteorological disasters. By comparing the forecast data with the preset meteorological disaster warning threshold, it is possible to determine whether a meteorological disaster is likely to occur in the future, and take corresponding warning and response measures accordingly. For example, if it is predicted that the precipitation in the next few hours will exceed the preset rainstorm threshold, it is necessary to issue a rainstorm warning in a timely manner and remind the public and relevant departments to take precautions.

[0117] S140. Determine the meteorological disaster risk level of the target area according to the comparison result of the target data and the warning threshold, and when the meteorological disaster risk level is greater than the risk threshold, generate warning information for the target area according to the meteorological disaster risk level.

[0118] According to the comparison results, the meteorological disaster risk in the target area is divided into different levels. The level division can be set according to actual needs and specific circumstances, usually including low risk, medium risk, high risk, etc. For example, when the predicted precipitation is close to or exceeds the rainstorm warning threshold, it can be judged as a high risk level. After determining the meteorological disaster risk level, it is necessary to conduct a risk assessment on the target area. The risk assessment can comprehensively consider factors such as the geographical location, topography, population distribution, economic conditions, and the impact and frequency of historical meteorological disasters in the target area to more accurately judge the impact that meteorological disasters may have on the target area. According to the risk assessment results, generate personalized warning information. The warning information should include the meteorological disaster risk level of the target area, the predicted meteorological conditions, the possible scope and time of impact, and the recommended response measures. At the same time, the warning information also needs to consider the characteristics and actual conditions of the target area, such as language, culture, and communication methods, to ensure the effective communication and acceptance of the information. The generated personalized warning information needs to be released through appropriate channels. Common release channels include television, radio, the Internet, and mobile phone text messages. When releasing information, attention should be paid to its accuracy and timeliness to ensure that the public and relevant departments can obtain it in a timely manner and take appropriate response measures.

[0119] This embodiment also discloses a meteorological disaster risk early warning system. Figure 3 Schematic diagram of a module of a meteorological disaster risk warning system disclosed in an embodiment of the present application. Figure 3 As shown, the early warning system includes a classification module, a threshold module, a data module and an early warning module, wherein:

[0120] A classification module configured to determine a target type of meteorological disasters in a target area according to historical meteorological data, and determine a meteorological disaster warning indicator for the target area according to the target type;

[0121] A threshold module is configured to determine the warning threshold corresponding to each risk level of the meteorological disaster warning indicator according to the influencing factors of the target area, wherein the influencing factors include population density, vegetation coverage, building information and enterprise information;

[0122] A data module configured to obtain current meteorological data of the target area, predict the predicted meteorological data within a preset time in the future in combination with the historical meteorological data of the target area, and extract target data corresponding to the meteorological disaster warning indicator from the predicted meteorological data;

[0123] The early warning module is configured to determine the meteorological disaster risk level of the target area based on the comparison result of the target data and the early warning threshold, and when the meteorological disaster risk level is greater than the risk threshold, generate early warning information for the target area according to the meteorological disaster risk level.

[0124] Optionally, the early warning system includes a partition module, and the partition module is configured to:

[0125] Divide the monitoring area into multiple target areas according to the monitoring range of the meteorological base station;

[0126] When there is an intersecting area between adjacent target areas, the intersecting area refers to an area where the first target area and the second target area intersect each other, the first target area and the second target area are adjacent target areas, and a first meteorological similarity value between the intersecting area and the first target area is calculated based on the historical meteorological data, and a second meteorological similarity value between the intersecting area and the second target area is calculated;

[0127] When the first meteorological similarity value is greater than the second meteorological similarity value, the intersection area is divided into the first target area.

[0128] Optionally, the partition module is configured to:

[0129] Obtaining a first average temperature, a first average precipitation, a first average wind speed, and a first average air pollution index of the first target area from the historical meteorological data, and obtaining a second average temperature, a second average precipitation, a second average wind speed, and a second average air pollution index of the intersection area from the historical meteorological data;

[0130] calculating a first difference between the first average temperature and the second average temperature, calculating a second difference between the first average precipitation and the second average precipitation, calculating a third difference between the first average wind speed and the second average wind speed, and calculating a fourth difference between the first average air pollution index and the second average air pollution index;

[0131] The temperature, precipitation, wind speed and air pollution index are respectively assigned a first weight, a second weight, a third weight and a fourth weight, and the first meteorological similarity is calculated by weighted summing the first difference, the second difference, the third difference and the fourth difference, wherein the first weight is equal to the second weight, the third weight is equal to the fourth weight, and the first weight is greater than the third weight.

[0132] Optionally, the classification module is configured to:

[0133] Statistics on the types of meteorological disasters that have occurred in the target area;

[0134] When the meteorological disaster type is unique, determining the meteorological disaster type as the target type;

[0135] When the meteorological disaster type is not unique, the first meteorological disaster type is determined as the target type, the first meteorological disaster type and the second meteorological disaster type are any two meteorological disaster types that have occurred in the target area, and the number of occurrences of the first meteorological disaster type is greater than the number of occurrences of the second meteorological disaster type;

[0136] When the target type is drought or flood, determining the meteorological disaster warning indicator of the target area to be precipitation;

[0137] When the target type is high temperature or cold wave, determining that the meteorological disaster warning indicator of the target area is temperature;

[0138] When the target type is haze or sandstorm, the meteorological disaster warning indicator for the target area is determined to be the air pollution index.

[0139] Optionally, the threshold module is configured to:

[0140] Acquire the number of communication base stations and historical traffic flow in the target area, predict the traffic flow at a preset time according to the historical traffic flow, and perform weighted summation of the number of communication base stations and the traffic flow at the preset time to obtain a judgment value;

[0141] When the judgment value is less than the first threshold, the basic warning threshold of each risk level is determined according to the historical meteorological data;

[0142] When the judgment value is greater than or equal to the first threshold and less than the second threshold, adjusting the basic warning threshold according to the vegetation coverage rate, the number of buildings and the type of buildings;

[0143] When the judgment value is greater than or equal to the second threshold, the basic warning threshold is adjusted according to the number and type of enterprises.

[0144] Optionally, the threshold module is further configured to:

[0145] Determine the fifth weight, the sixth weight and the seventh weight corresponding to the vegetation coverage rate, the number of buildings and the type of buildings according to the meteorological disaster warning indicators;

[0146] Converting a first impact of vegetation coverage on the meteorological disaster warning index into a first value, converting a second impact of the number of buildings on the meteorological disaster warning index into a second value, and converting a third impact of building type on the meteorological disaster warning index into a third value;

[0147] A weighted sum is performed on the first value, the second value, and the third value to obtain a first adjustment value, and the basic warning threshold is adjusted according to the first adjustment value.

[0148] Optionally, the threshold module is configured to:

[0149] Set the first adjustment factor based on the number of enterprises;

[0150] Determining target enterprise types associated with the meteorological disaster warning indicators, and setting a second adjustment coefficient according to the number of target enterprise types;

[0151] The first adjustment coefficient is multiplied by the second adjustment coefficient to obtain an adjustment coefficient, and the adjustment coefficient is multiplied by the basic warning threshold to obtain an adjusted warning threshold.

[0152] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0153] This embodiment also discloses an electronic device, referring to Figure 4 , the electronic device may include: at least one processor, at least one communication bus, a user interface, a network interface, and at least one memory.

[0154] The communication bus is used to realize the connection and communication between these components.

[0155] The user interface may include a display screen (Display) and a camera (Camera), and the optional user interface may also include a standard wired interface and a wireless interface.

[0156] The network interface may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0157] Among them, the processor may include one or more processing cores. The processor uses various interfaces and lines to connect various parts of the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory, and calling data stored in the memory. Optionally, the processor can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU), and a modem. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; and the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor, but may be implemented separately through a chip.

[0158] Among them, the memory may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory includes a non-transitory computer-readable storage medium. The memory can be used to store instructions, programs, codes, code sets or instruction sets. The memory may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area may store data involved in the above-mentioned method embodiments, etc. The memory may also be optionally at least one storage device located away from the aforementioned processor. As Figure 4 As shown, the memory as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program of a meteorological disaster risk early warning method.

[0159] exist Figure 4In the electronic device shown, the user interface is mainly used to provide an input interface for the user and obtain data input by the user; and the processor can be used to call an application program for the meteorological disaster risk warning method stored in the memory. When executed by one or more processors, the electronic device executes one or more methods in the above-mentioned embodiments.

[0160] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0161] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0162] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0163] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0164] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0165] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0166] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, it will be easy for those skilled in the art to think of other embodiments of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field that are not recorded in the present disclosure. The description and examples are regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A meteorological disaster risk early warning method, characterized in that: Applied to a meteorological early warning platform, the early warning method includes: Determine the target type of meteorological disasters in the target area according to historical meteorological data, and determine the meteorological disaster warning indicators in the target area according to the target type; Determine the warning threshold corresponding to each risk level of the meteorological disaster warning indicator according to the influencing factors of the target area, wherein the influencing factors include population density, vegetation coverage, building information and enterprise information; Acquire the current meteorological data of the target area, predict the predicted meteorological data within a preset time in the future in combination with the historical meteorological data of the target area, and extract the target data corresponding to the meteorological disaster warning indicator from the predicted meteorological data; determining the meteorological disaster risk level of the target area according to the comparison result between the target data and the warning threshold, and generating warning information of the target area according to the meteorological disaster risk level when the meteorological disaster risk level is greater than the risk threshold, The early warning method comprises: Divide the monitoring area into multiple target areas according to the monitoring range of the meteorological base station; When there is an intersecting area between adjacent target areas, the intersecting area refers to an area where the first target area and the second target area intersect each other, the first target area and the second target area are adjacent target areas, and a first meteorological similarity value between the intersecting area and the first target area is calculated based on the historical meteorological data, and a second meteorological similarity value between the intersecting area and the second target area is calculated; When the first meteorological similarity value is greater than the second meteorological similarity value, the intersection area is divided into the first target area.

2. The meteorological disaster risk early warning method according to claim 1, characterized in that: Calculating the first meteorological similarity value between the intersection area and the first target area according to the historical meteorological data includes: Obtaining a first average temperature, a first average precipitation, a first average wind speed, and a first average air pollution index of the first target area from the historical meteorological data, and obtaining a second average temperature, a second average precipitation, a second average wind speed, and a second average air pollution index of the intersection area from the historical meteorological data; calculating a first difference between the first average temperature and the second average temperature, calculating a second difference between the first average precipitation and the second average precipitation, calculating a third difference between the first average wind speed and the second average wind speed, and calculating a fourth difference between the first average air pollution index and the second average air pollution index; The temperature, precipitation, wind speed and air pollution index are respectively assigned a first weight, a second weight, a third weight and a fourth weight, and the first meteorological similarity is calculated by weighted summing the first difference, the second difference, the third difference and the fourth difference, wherein the first weight is equal to the second weight, the third weight is equal to the fourth weight, and the first weight is greater than the third weight.

3. The meteorological disaster risk early warning method according to claim 1, characterized in that: Determining the target type of meteorological disasters in the target area according to historical meteorological data, and determining the meteorological disaster warning index of the target area according to the target type includes: Statistics on the types of meteorological disasters that have occurred in the target area; When the meteorological disaster type is unique, determining the meteorological disaster type as the target type; When the meteorological disaster type is not unique, the first meteorological disaster type is determined as the target type, the first meteorological disaster type and the second meteorological disaster type are any two meteorological disaster types that have occurred in the target area, and the number of occurrences of the first meteorological disaster type is greater than the number of occurrences of the second meteorological disaster type; When the target type is drought or flood, determining the meteorological disaster warning indicator of the target area to be precipitation; When the target type is high temperature or cold wave, determining that the meteorological disaster warning indicator of the target area is temperature; When the target type is haze or sandstorm, the meteorological disaster warning indicator for the target area is determined to be the air pollution index.

4. The meteorological disaster risk early warning method according to claim 1, characterized in that: Determining the warning thresholds corresponding to each risk level of the meteorological disaster warning indicator according to the influencing factors of the target area includes: Acquire the number of communication base stations and historical traffic flow in the target area, predict the traffic flow at a preset time according to the historical traffic flow, and perform weighted summation of the number of communication base stations and the traffic flow at the preset time to obtain a judgment value; When the judgment value is less than the first threshold, the basic warning threshold of each risk level is determined according to the historical meteorological data; When the judgment value is greater than or equal to the first threshold and less than the second threshold, adjusting the basic warning threshold according to the vegetation coverage rate, the number of buildings and the type of buildings; When the judgment value is greater than or equal to the second threshold, the basic warning threshold is adjusted according to the number and type of enterprises.

5. The meteorological disaster risk early warning method according to claim 4, characterized in that: The adjusting the basic warning threshold according to vegetation coverage, number of buildings and building types includes: Determine the fifth weight, the sixth weight and the seventh weight corresponding to the vegetation coverage rate, the number of buildings and the type of buildings according to the meteorological disaster warning indicators; Converting a first impact of vegetation coverage on the meteorological disaster warning index into a first value, converting a second impact of the number of buildings on the meteorological disaster warning index into a second value, and converting a third impact of building type on the meteorological disaster warning index into a third value; A weighted sum is performed on the first value, the second value, and the third value to obtain a first adjustment value, and the basic warning threshold is adjusted according to the first adjustment value.

6. The meteorological disaster risk early warning method according to claim 4, characterized in that: The adjustment of the basic warning threshold according to the number and type of enterprises includes: Set the first adjustment factor based on the number of enterprises; Determining target enterprise types associated with the meteorological disaster warning indicators, and setting a second adjustment coefficient according to the number of target enterprise types; The first adjustment coefficient is multiplied by the second adjustment coefficient to obtain an adjustment coefficient, and the adjustment coefficient is multiplied by the basic warning threshold to obtain an adjusted warning threshold.

7. A meteorological disaster risk early warning system, characterized in that: It includes classification module, threshold module, data module and warning module, among which: A classification module configured to determine a target type of meteorological disasters in a target area according to historical meteorological data, and determine a meteorological disaster warning indicator for the target area according to the target type; A threshold module is configured to determine the warning threshold corresponding to each risk level of the meteorological disaster warning indicator according to the influencing factors of the target area, wherein the influencing factors include population density, vegetation coverage, building information and enterprise information; A data module configured to obtain current meteorological data of the target area, predict the predicted meteorological data within a preset time in the future in combination with the historical meteorological data of the target area, and extract target data corresponding to the meteorological disaster warning indicator from the predicted meteorological data; an early warning module, configured to determine the meteorological disaster risk level of the target area according to a comparison result between the target data and the early warning threshold, and when the meteorological disaster risk level is greater than the risk threshold, generate early warning information of the target area according to the meteorological disaster risk level, The early warning system includes a partition module, and the partition module is configured to: Divide the monitoring area into multiple target areas according to the monitoring range of the meteorological base station; When there is an intersecting area between adjacent target areas, the intersecting area refers to an area where the first target area and the second target area intersect each other, the first target area and the second target area are adjacent target areas, and a first meteorological similarity value between the intersecting area and the first target area is calculated based on the historical meteorological data, and a second meteorological similarity value between the intersecting area and the second target area is calculated; When the first meteorological similarity value is greater than the second meteorological similarity value, the intersection area is divided into the first target area.

8. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 6 is performed.

Images