Meteorological disaster intelligent early warning system based on real-time data acquisition and analysis

Abstract

The invention belongs to the technical field of meteorological disaster early warning, and particularly relates to a meteorological disaster intelligent early warning system based on real-time data acquisition and analysis, which comprises a meteorological data monitoring and acquisition module, a meteorological disaster prediction module, an intelligent early warning module, a regional monitoring grade analysis module and a regional meteorological supervision terminal, by collecting and analyzing various meteorological data in real time and finding out meteorological abnormity and disaster precursor in time, the accuracy and timeliness of early warning are improved, corresponding emergency response measures can be automatically triggered according to early warning information, timely rescue and protection measures are provided for related departments and the public, the influence and loss of disasters are effectively reduced, and the safety and reliability of the system are improved. The meteorological monitoring grade of the corresponding area is analyzed through the area monitoring grade analysis module, and the area meteorological monitoring management is enhanced when the corresponding area is marked as a high-grade area, so that it is ensured that meteorological disasters of the corresponding area can be rapidly and effectively handled subsequently; and subsequent damage to corresponding areas due to meteorological disasters is further reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of meteorological disaster early warning technology, and in particular to an intelligent meteorological disaster early warning system based on real-time data collection and analysis. Background Art

[0002] Meteorological disasters such as typhoons, rainstorms, droughts, and lightning pose a serious threat to human society and economic activities. Chinese invention patent publication number CN115601928A discloses a combined meteorological disaster monitoring and early warning device. This device utilizes intelligent meteorological monitoring stations to collect multiple environmental and road surface parameters, and uses these parameters to generate meteorological disaster alerts. This device integrates multiple environmental factors to improve the accuracy of meteorological disaster alerts. However, in actual application, the above-mentioned technical solution can only realize the monitoring and analysis of various meteorological data in the corresponding area and the early warning of meteorological disasters. It cannot accurately assess the monitoring and management level and the degree of monitoring and management risks in the corresponding area while realizing meteorological disaster early warning. It is not conducive to formulating reasonable and scientific monitoring and management plans and targeted improvement measures for the corresponding area, and the degree of intelligence is low. In view of the above technical defects, a solution is now proposed. Summary of the Invention

[0003] The purpose of the present invention is to provide an intelligent early warning system for meteorological disasters based on real-time data collection and analysis, which solves the problem that the existing technology cannot accurately evaluate the monitoring and management level and the degree of monitoring and management risks in the corresponding area while realizing meteorological disaster early warning, which is not conducive to making reasonable and scientific monitoring and management plans and targeted improvement measures for the corresponding area, and has a low level of intelligence.

[0004] To achieve the above object, the present invention provides the following technical solutions: An intelligent meteorological disaster early warning system based on real-time data collection and analysis, including a meteorological data monitoring and collection module, a meteorological disaster prediction module, an intelligent early warning module, a regional monitoring level analysis module, and a regional meteorological supervision terminal; The meteorological data monitoring and collection module deploys meteorological monitoring equipment to collect various meteorological data of the corresponding area in real time, packages the collected meteorological data into meteorological packages, and sends the meteorological packages to the meteorological disaster prediction module; The meteorological disaster prediction module uses big data processing technology to clean, integrate, store and analyze meteorological data packages in real time. It also uses machine learning algorithms to establish a meteorological disaster prediction model, conduct in-depth mining of meteorological data packages, and predict the probability, intensity and potential impact range of meteorological disasters. The meteorological disaster prediction results are then sent to the intelligent early warning module. The intelligent early warning module automatically generates early warning information based on meteorological disaster forecast results, including warning level, warning area, and expected impact time, and sends the warning information to relevant departments, enterprises, and the public via SMS, email, APP push, or social media channels; The regional monitoring level analysis module analyzes the meteorological monitoring level of the corresponding area, and marks the corresponding area as a high-level area or a low-level area accordingly, and sends the meteorological monitoring level marking information of the corresponding area to the regional meteorological supervision end, and strengthens regional meteorological monitoring management when a high-level area is received.

[0005] Furthermore, the specific analysis process of the regional monitoring level analysis module includes: Obtain all meteorological disasters that occurred in the corresponding area during the detection period, mark the affected area and disaster losses of the corresponding meteorological disasters as meteorological disaster coverage value and meteorological disaster loss value respectively, compare the meteorological disaster coverage value and meteorological disaster loss value with the preset meteorological disaster coverage threshold and preset meteorological disaster loss threshold respectively, and if the meteorological disaster coverage value or meteorological disaster loss value exceeds the corresponding preset threshold, mark the corresponding meteorological disaster as an abnormal disaster; The number of abnormal disasters occurring during the detection period is obtained and marked as the disaster risk frequency value, and the meteorological disaster coverage values of all meteorological disasters occurring during the detection period are averaged to obtain the disaster coverage value, and the meteorological disaster losses of all meteorological disasters occurring during the detection period are averaged to obtain the disaster loss table value; the regional disaster characteristic value is obtained by numerically calculating the disaster risk frequency value, disaster coverage value and disaster loss table value; And obtain the personnel economic characteristic values of the corresponding area, perform numerical calculations on the regional disaster characteristic values and the personnel economic characteristic values to obtain the regional grade judgment value, perform numerical comparison on the regional grade judgment value and the preset regional grade judgment threshold value, if the regional grade judgment value exceeds the corresponding preset regional grade judgment threshold value, the corresponding area is marked as a high-grade area; if the regional grade judgment value does not exceed the corresponding preset regional grade judgment threshold value, the corresponding area is marked as a low-grade area.

[0006] Furthermore, the regional monitoring level analysis module is communicated with the personnel economic evaluation module, which analyzes the personnel activities and economic conditions of the corresponding area, obtains the personnel economic characteristic values of the corresponding area through analysis, and sends the personnel economic characteristic values to the regional level monitoring and analysis module.

[0007] Furthermore, the specific analysis process of the personnel economic evaluation module is as follows: The average value of the population size in the corresponding area over the past five years is collected and marked as the population detection value, and the average value of the economic output value in the corresponding area over the past five years is collected and marked as the economic detection value. The population detection value and the economic detection value are respectively assigned corresponding preset weight values, and the population detection value and the economic detection value are respectively multiplied by the corresponding preset weight values, and the sum of the two sets of multiplication results is marked as the personnel economic characteristic value.

[0008] Furthermore, the regional monitoring level analysis module is communicatively connected to the meteorological regulatory hidden danger assessment module. The regional monitoring level analysis module sends the meteorological monitoring level mark information of the corresponding area to the meteorological regulatory hidden danger assessment module. The meteorological regulatory hidden danger assessment module analyzes the degree of regulatory hidden dangers in the corresponding area, generates a high regulatory hidden danger signal or a low regulatory hidden danger signal through analysis, and sends the high regulatory hidden danger signal or the low regulatory hidden danger signal to the regional meteorological regulatory end. When the regional meteorological regulatory end receives the high regulatory hidden danger signal, it issues a corresponding warning.

[0009] Furthermore, the specific analysis process of the meteorological supervision hidden danger assessment module includes: Obtain the meteorological monitoring equipment that needs to be managed in the corresponding area, mark the corresponding meteorological monitoring equipment as monitoring object i, where i is a natural number greater than 1; collect the usage time of monitoring object i and calculate the ratio of it to the life span threshold to obtain the usage coefficient, set a target time period, collect the number of failures and the total failure duration of monitoring object i within the target time period and mark them as the target failure value and target asynchronous value, and mark the average delay time of data collection and transmission of monitoring object i within the target time period as the data transmission delay value; The monitoring characteristic value is obtained by numerically calculating the usage coefficient, target failure value, target asynchronous value and data delay value, and the monitoring characteristic value is numerically compared with the corresponding preset monitoring characteristic threshold. If the monitoring characteristic value exceeds the corresponding preset monitoring characteristic threshold, the monitored object i is marked as an unavailable device; if an unavailable device exists, a high-risk supervision signal is generated.

[0010] Furthermore, if there is no unavailable equipment, the monitoring characteristic value of the monitoring object i is calculated by comparing it with the corresponding preset monitoring characteristic threshold to obtain the monitoring analysis value, and the monitoring analysis values of all meteorological monitoring equipment that need to be managed in the corresponding area are averaged to obtain the supervision hidden danger coefficient; If the corresponding area is a high-level area, the preset regulatory hidden danger coefficient threshold LP1 is assigned; if the corresponding area is a low-level area, the preset regulatory hidden danger coefficient threshold LP2 is assigned, and LP2>LP1>0; the regulatory hidden danger coefficient is numerically compared with the corresponding preset regulatory hidden danger coefficient threshold. If the regulatory hidden danger coefficient exceeds the corresponding preset regulatory hidden danger coefficient threshold, a high regulatory hidden danger signal is generated.

[0011] Furthermore, if the supervisory hidden danger coefficient does not exceed the corresponding preset supervisory hidden danger coefficient threshold, the real-time number of emergency personnel on duty responsible for meteorological disaster emergency response in the corresponding area is obtained and marked as the emergency personnel inspection value, and the post time of the corresponding emergency personnel is compared with the preset post time threshold. If the post time exceeds the preset post time threshold, the corresponding emergency personnel is marked as an excellent personnel; The real-time number of excellent personnel on duty is obtained and marked as the excellent personnel inspection value. The emergency personnel inspection value and the excellent personnel inspection value are compared with the preset emergency personnel inspection threshold and the preset excellent personnel inspection threshold respectively. If the emergency personnel inspection value or the excellent personnel inspection value does not exceed the corresponding preset threshold, it is determined that the current emergency potential danger state is in place; When it is determined that the emergency hazard state is in place, the time is counted until the emergency hazard state ends, and the emergency hazard duration is obtained based on the sum of all emergency hazard durations within the target period to obtain the total emergency hazard duration value. The number of emergency hazard durations exceeding the preset emergency hazard duration threshold within the target period is marked as the emergency hazard frequency table value, and the emergency hazard duration with the largest value within the target period is marked as the emergency hazard duration amplitude value. The emergency hazard coefficient is obtained by numerically calculating the total time value of emergency hazards, the emergency hazard frequency table value and the emergency hazard amplitude value. If the corresponding area is a high-level area, the preset emergency hazard coefficient threshold TP1 is assigned; if the corresponding area is a low-level area, the preset emergency hazard coefficient threshold TP2 is assigned, and TP2>TP1>0; the emergency hazard coefficient is numerically compared with the corresponding preset emergency hazard coefficient threshold. If the emergency hazard coefficient exceeds the corresponding preset emergency hazard coefficient threshold, a high-hazard signal for supervision is generated; if the emergency hazard coefficient does not exceed the corresponding preset emergency hazard coefficient threshold, a low-hazard signal for supervision is generated.

[0012] Compared with the prior art, the present invention has the following beneficial effects: 1. In the present invention, by real-time collection and analysis of various meteorological data, meteorological anomalies and disaster precursors are discovered in a timely manner, the accuracy and timeliness of early warnings are improved, and corresponding emergency response measures can be automatically triggered according to the early warning information, effectively reducing the impact and losses of disasters. The regional monitoring level analysis module analyzes the meteorological monitoring level of the corresponding area, and strengthens regional meteorological monitoring management when the corresponding area is marked as a high-level area, ensuring that the subsequent meteorological disasters in the corresponding area can be responded to quickly and effectively, further reducing the damage caused by meteorological disasters in the corresponding area. 2. In the present invention, the meteorological monitoring level mark information of the corresponding area is sent to the meteorological supervision hidden danger assessment module through the regional monitoring level analysis module. The meteorological supervision hidden danger assessment module analyzes the supervision hidden danger degree of the corresponding area and makes corresponding improvement measures when generating a high supervision hidden danger signal. It is conducive to making reasonable and scientific monitoring and management plans for the corresponding area, reducing the level of regional meteorological monitoring and management hidden dangers, and further reducing the damage caused to the corresponding area by meteorological disasters. It has a high degree of intelligence. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings; Figure 1 This is a system block diagram of Embodiment 1 of the present invention; Figure 2 This is a system block diagram of Example 2 of the present invention. DETAILED DESCRIPTION

[0014] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0015] Example 1: Figure 1 As shown, the meteorological disaster intelligent early warning system based on real-time data collection and analysis proposed by the present invention includes a meteorological data monitoring and collection module, a meteorological disaster prediction module, an intelligent early warning module, a regional monitoring level analysis module and a regional meteorological supervision terminal; The meteorological data monitoring and collection module deploys meteorological monitoring equipment to collect various meteorological data of the corresponding area in real time (including temperature, humidity, air pressure, wind speed, wind direction, lightning activity, precipitation, and other meteorological data), packages the collected meteorological data into meteorological packages, and sends the meteorological packages to the meteorological disaster prediction module; The meteorological disaster prediction module uses big data processing technology to clean, integrate, store and analyze meteorological data packages in real time. It also combines machine learning algorithms (such as neural networks, support vector machines, decision trees, etc.) to establish a meteorological disaster prediction model, conduct in-depth mining of meteorological data packages, and predict the probability, intensity and potential impact range of meteorological disasters. The meteorological disaster prediction results are then sent to the intelligent early warning module. The intelligent early warning module automatically generates early warning information based on the results of meteorological disaster forecasts, including the warning level, warning area and expected impact time, and sends the warning information to relevant departments, enterprises and the public via SMS, email, APP push or social media channels; through real-time collection and analysis of various meteorological data, the system can promptly detect meteorological anomalies and disaster precursors, improve the accuracy and timeliness of early warnings, and automatically trigger corresponding emergency response measures based on early warning information, providing timely rescue and protection measures for relevant departments and the public, effectively reducing the impact and losses of disasters.

[0016] The regional monitoring level analysis module analyzes the meteorological monitoring level of the corresponding area, marks the corresponding area as a high-level area or a low-level area based on the analysis, and sends the meteorological monitoring level mark information of the corresponding area to the regional meteorological supervision end. When a high-level area is received, regional meteorological monitoring management is strengthened, which is conducive to ensuring that the meteorological disasters in the corresponding area can be responded to quickly and effectively in the future, and reducing the damage caused by meteorological disasters in the corresponding area. The specific analysis process of the regional monitoring level analysis module is as follows: Obtain all meteorological disasters that occurred in the corresponding area during a detection period (preferably, the detection period is forty days), mark the affected area and disaster losses of the corresponding meteorological disasters as meteorological disaster coverage values and meteorological disaster loss values, respectively, and compare the meteorological disaster coverage values and meteorological disaster loss values with preset meteorological disaster coverage thresholds and preset meteorological disaster loss thresholds, respectively; If the meteorological disaster coverage value or meteorological disaster loss value exceeds the corresponding preset threshold, it indicates that the damage caused by the corresponding meteorological disaster is more serious, and the corresponding meteorological disaster will be marked as an abnormal disaster; The number of abnormal disasters occurring during the detection period is obtained and marked as the disaster risk frequency value, and the meteorological disaster coverage values of all meteorological disasters occurring during the detection period are averaged to obtain the disaster coverage value, and the meteorological disaster losses of all meteorological disasters occurring during the detection period are averaged to obtain the disaster loss table value; The regional disaster characteristic value QS is obtained by numerically calculating the disaster risk frequency value XR, the disaster coverage value TF, and the disaster loss table value YP using the formula QS=re*XR+(hy*TF+es*YP) / re. Among them, re, hy, and es are preset proportional coefficients with values greater than zero. The larger the value of the regional disaster characteristic value QS, the greater the overall natural disaster risk of the corresponding area. And obtain the personnel economic characteristic value QL of the corresponding area, and numerically calculate the regional disaster characteristic value QS and the personnel economic characteristic value QL through the formula QW=k1*QS+k2*QL to obtain the regional level judgment value QW; wherein k1 and k2 are preset proportional coefficients with values greater than zero, and the larger the value of the regional level judgment value QW, the higher the monitoring and management level required for the corresponding area; The regional level judgment value QW is numerically compared with the preset regional level judgment threshold. If the regional level judgment value QW exceeds the corresponding preset regional level judgment threshold, it indicates that the monitoring importance level of the corresponding area is high and it is necessary to continuously strengthen the monitoring and management of meteorological disasters, then the corresponding area is marked as a high-level area; if the regional level judgment value QW does not exceed the corresponding preset regional level judgment threshold, it indicates that the monitoring importance level of the corresponding area is low, then the corresponding area is marked as a low-level area.

[0017] Furthermore, the regional monitoring level analysis module is connected to the personnel economic assessment module. The personnel economic assessment module analyzes the personnel activities and economic conditions of the corresponding area, obtains the personnel economic characteristic value QL of the corresponding area through analysis, and sends the personnel economic characteristic value QL to the regional level monitoring and analysis module, providing data support for the analysis process of the regional level monitoring and analysis module and ensuring the accuracy of its analysis results. The specific analysis process of the personnel economic assessment module is as follows: The average value of the population of the corresponding area in the past five years is collected and marked as the population detection value, and the average value of the economic output value of the corresponding area in the past five years is collected and marked as the economic detection value, and the population detection value and the economic detection value are respectively assigned corresponding preset weight values, and the values of the assigned preset weight values are all positive numbers; The population detection value and the economic detection value are multiplied by the corresponding preset weight values respectively, and the sum of the two sets of product results is marked as the personnel economic characteristic value QL; it should be noted that the larger the value of the personnel economic characteristic value QL, the higher the importance level of the corresponding area.

[0018] Example 2: Figure 2 As shown, the difference between this embodiment and the first embodiment is that the regional monitoring level analysis module is communicatively connected to the meteorological supervision hidden danger assessment module. The regional monitoring level analysis module sends the meteorological monitoring level mark information of the corresponding area to the meteorological supervision hidden danger assessment module. The meteorological supervision hidden danger assessment module analyzes the supervision hidden danger degree of the corresponding area and generates a high supervision hidden danger signal or a low supervision hidden danger signal through analysis. The high-risk signal or low-risk signal is sent to the regional meteorological supervision terminal. When the regional meteorological supervision terminal receives the high-risk signal, it issues a corresponding warning so that corresponding improvement measures can be taken in time, thereby reducing the risk level of regional meteorological monitoring and management, and further reducing the damage caused by meteorological disasters in the corresponding area. The specific analysis process of the meteorological supervision risk assessment module is as follows: Obtain the meteorological monitoring equipment that needs to be managed in the corresponding area, mark the corresponding meteorological monitoring equipment as monitoring object i, where i is a natural number greater than 1; The usage time of the monitored object i is collected and compared with the life time threshold to calculate the usage coefficient; and a target period is set, preferably, the target period is ten days; the number of failures and the total failure duration of the monitored object i during the target period are collected and marked as the target failure value and the target asynchronous value, and the average delay time of the data collection and transmission of the monitored object i during the target period is marked as the data transmission delay value; The monitoring characteristic value ZFi is obtained by numerically calculating the coefficient SYi, the target fault value NPi, the target asynchronous value HMi, and the data delay value FXi using the formula ZFi=cg*SYi+ew*NPi+hu*HMi+ry*FXi. Here, cg, ew, hu, and ry are preset proportional coefficients with values greater than zero. A larger value of the monitoring characteristic value ZFi indicates a worse quality condition of the monitored object i and a greater operational risk. Compare the monitoring characteristic value ZFi with the corresponding preset monitoring characteristic threshold. If the monitoring characteristic value ZFi exceeds the corresponding preset monitoring characteristic threshold, it indicates that the quality of the monitoring object i is poor and the operation risk is large. The monitoring object i is marked as unavailable equipment. If there is an unavailable equipment, it indicates that there is a large safety risk in regional meteorological monitoring. A high-risk supervision signal is generated. If there is no unavailable equipment, the monitoring characteristic value of the monitoring object i is calculated by comparing it with the corresponding preset monitoring characteristic threshold to obtain the monitoring analysis value, and the monitoring analysis values of all meteorological monitoring equipment that need to be managed in the corresponding area are averaged to obtain the supervision hidden danger coefficient. It should be noted that the larger the value of the supervision hidden danger coefficient, the greater the overall safety hazard of regional meteorological monitoring. If the corresponding area is a high-level area, the preset regulatory hidden danger coefficient threshold LP1 is assigned; if the corresponding area is a low-level area, the preset regulatory hidden danger coefficient threshold LP2 is assigned, and LP2>LP1>0. By assigning the appropriate preset regulatory hidden danger coefficient threshold to the corresponding area based on the monitoring management level, the accuracy and rationality of the meteorological monitoring safety hidden danger analysis results can be significantly improved; The regulatory hidden danger coefficient is numerically compared with the corresponding preset regulatory hidden danger coefficient threshold. If the regulatory hidden danger coefficient exceeds the corresponding preset regulatory hidden danger coefficient threshold, it indicates that the safety hazards existing in regional meteorological monitoring are generally large, and a high regulatory hidden danger signal is generated.

[0019] Furthermore, if the supervisory hidden danger coefficient does not exceed the corresponding preset supervisory hidden danger coefficient threshold, the real-time number of emergency personnel on duty responsible for meteorological disaster emergency response in the corresponding area is obtained and marked as the emergency personnel inspection value, and the post time of the corresponding emergency personnel is compared with the preset post time threshold. If the post time exceeds the preset post time threshold, it indicates that the corresponding emergency personnel has rich post experience, and the corresponding emergency personnel is marked as excellent personnel; The real-time number of excellent personnel on duty is obtained and marked as the excellent personnel inspection value. The emergency personnel inspection value and the excellent personnel inspection value are compared with the preset emergency personnel inspection threshold and the preset excellent personnel inspection threshold respectively. If the emergency personnel inspection value or the excellent personnel inspection value does not exceed the corresponding preset threshold, it indicates that the current emergency preparedness status is poor, and it is judged that the current emergency potential risk state is in place; When it is determined that the emergency hazard state is in place, the time is counted until the emergency hazard state ends, and the emergency hazard duration is obtained based on the sum of all emergency hazard durations within the target period to obtain the total emergency hazard duration value. The number of emergency hazard durations exceeding the preset emergency hazard duration threshold within the target period is marked as the emergency hazard frequency table value, and the emergency hazard duration with the largest value within the target period is marked as the emergency hazard duration amplitude value. The emergency hazard coefficient TN is obtained by numerically calculating the total time value QP of the emergency hazard, the frequency table value LX of the emergency hazard, and the amplitude value MS of the emergency hazard using the formula TN=n*LX+(t*QP+c*MS) / 2. Among them, t, n, and c are preset proportional coefficients with values greater than zero. The larger the value of the emergency hazard coefficient TN, the greater the overall emergency response hazard for meteorological disasters in the corresponding area. If the corresponding area is a high-level area, a preset emergency hidden danger coefficient threshold TP1 is assigned; if the corresponding area is a low-level area, a preset emergency hidden danger coefficient threshold TP2 is assigned, and TP2>TP1>0; by assigning the corresponding preset emergency hidden danger coefficient threshold to the corresponding area based on the monitoring and management level, the accuracy and rationality of the emergency handling hidden danger analysis results can be significantly improved; The emergency hazard coefficient TN is numerically compared with the corresponding preset emergency hazard coefficient threshold. If the emergency hazard coefficient TN exceeds the corresponding preset emergency hazard coefficient threshold, it indicates that the emergency response hazards for meteorological disasters in the corresponding area are generally large, and a high-hazard signal for supervision is generated; if the emergency hazard coefficient TN does not exceed the corresponding preset emergency hazard coefficient threshold, it indicates that the emergency response hazards for meteorological disasters in the corresponding area are generally small, and a low-hazard signal for supervision is generated.

[0020] The working principle of the present invention is as follows: when in use, the meteorological data monitoring and collection module deploys meteorological monitoring equipment to collect various meteorological data of the corresponding area in real time. The meteorological disaster prediction module analyzes and processes the meteorological package and predicts the probability, intensity and potential impact range of meteorological disasters. The intelligent early warning module automatically generates early warning information according to the meteorological disaster prediction results and sends it to relevant departments, enterprises and the public. It can timely detect meteorological anomalies and disaster precursors and automatically trigger corresponding emergency response measures, improve the accuracy and timeliness of early warnings, and effectively reduce the impact and losses of disasters. The meteorological monitoring level of the corresponding area is analyzed by the regional monitoring level analysis module. When the corresponding area is marked as a high-level area, the regional meteorological monitoring management is strengthened, which is conducive to ensuring that the subsequent meteorological disasters in the corresponding area can be responded to quickly and effectively, and further reducing the subsequent damage to the corresponding area due to meteorological disasters.

[0021] The above formulas are all dimensionless and calculated by taking their numerical values. The formula is a formula for the latest real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions. The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made based on the contents of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that technicians in the relevant technical field can well understand and use the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. The intelligent early warning system for meteorological disasters based on real-time data collection and analysis is characterized by: It includes meteorological data monitoring and collection module, meteorological disaster prediction module, intelligent early warning module, regional monitoring level analysis module and regional meteorological supervision terminal; The meteorological data monitoring and collection module deploys meteorological monitoring equipment to collect various meteorological data of the corresponding area in real time, packages the collected meteorological data into meteorological packages, and sends the meteorological packages to the meteorological disaster prediction module; The meteorological disaster prediction module uses big data processing technology to clean, integrate, store and analyze meteorological data packages in real time. It also uses machine learning algorithms to establish a meteorological disaster prediction model, conduct in-depth mining of meteorological data packages, and predict the probability, intensity and potential impact range of meteorological disasters. The meteorological disaster prediction results are then sent to the intelligent early warning module. The intelligent early warning module automatically generates early warning information based on meteorological disaster forecast results, including warning level, warning area, and expected impact time, and sends the warning information to relevant departments, enterprises, and the public via SMS, email, APP push, or social media channels; The regional monitoring level analysis module analyzes the meteorological monitoring level of the corresponding area, and marks the corresponding area as a high-level area or a low-level area accordingly, and sends the meteorological monitoring level marking information of the corresponding area to the regional meteorological supervision end, and strengthens regional meteorological monitoring management when a high-level area is received.

2. The meteorological disaster intelligent early warning system based on real-time data collection and analysis according to claim 1 is characterized in that: The specific analysis process of the regional monitoring level analysis module includes: All meteorological disasters that occurred in the corresponding area during the detection period are obtained. If the meteorological disaster coverage value or meteorological disaster loss value exceeds the corresponding preset threshold, the corresponding meteorological disaster is marked as an abnormal disaster; the number of abnormal disasters that occurred during the detection period is obtained and marked as the disaster risk frequency value. The regional disaster characteristic value is obtained by numerically calculating the disaster risk frequency value, disaster coverage value and disaster loss value; And obtain the personnel economic characteristic values of the corresponding area, perform numerical calculations on the regional disaster characteristic values and the personnel economic characteristic values to obtain the regional grade judgment value. If the regional grade judgment value exceeds the corresponding preset regional grade judgment threshold, the corresponding area will be marked as a high-grade area; if the regional grade judgment value does not exceed the corresponding preset regional grade judgment threshold, the corresponding area will be marked as a low-grade area.

3. The meteorological disaster intelligent early warning system based on real-time data collection and analysis according to claim 2 is characterized in that: The regional monitoring level analysis module is communicated with the personnel economic evaluation module. The personnel economic evaluation module analyzes the personnel activities and economic conditions of the corresponding area, obtains the personnel economic characteristic values of the corresponding area through analysis, and sends the personnel economic characteristic values to the regional level monitoring and analysis module.

4. The meteorological disaster intelligent early warning system based on real-time data collection and analysis according to claim 3 is characterized in that: The specific analysis process of the personnel economic evaluation module is as follows: The average value of the population size in the corresponding area in the past five years is collected and marked as the population detection value, and the average value of the economic output value in the corresponding area in the past five years is collected and marked as the economic detection value. The population detection value and the economic detection value are multiplied with the corresponding preset weight values respectively, and the sum of the two sets of product results is marked as the personnel economic characteristic value.

5. The meteorological disaster intelligent early warning system based on real-time data collection and analysis according to claim 1 is characterized in that: The regional monitoring level analysis module is communicatively connected to the meteorological supervision hidden danger assessment module. The regional monitoring level analysis module sends the meteorological monitoring level mark information of the corresponding area to the meteorological supervision hidden danger assessment module. The meteorological supervision hidden danger assessment module analyzes the degree of supervision hidden dangers in the corresponding area, generates a high supervision hidden danger signal or a low supervision hidden danger signal through analysis, and sends the high supervision hidden danger signal or the low supervision hidden danger signal to the regional meteorological supervision end.

6. The meteorological disaster intelligent early warning system based on real-time data collection and analysis according to claim 5 is characterized in that: The specific analysis process of the meteorological regulatory hazard assessment module includes: Obtain the meteorological monitoring equipment that needs to be managed in the corresponding area, mark the corresponding meteorological monitoring equipment as monitoring object i, where i is a natural number greater than 1; collect the usage time of monitoring object i and calculate the ratio of it to the life span threshold to obtain the usage coefficient, set a target time period, collect the number of failures and the total failure duration of monitoring object i within the target time period and mark them as the target failure value and target asynchronous value, and mark the average delay time of data collection and transmission of monitoring object i within the target time period as the data transmission delay value; The monitoring characteristic value is obtained by numerically calculating the usage coefficient, target failure value, target asynchronous value and data delay value. If the monitoring characteristic value exceeds the corresponding preset monitoring characteristic threshold, the monitored object i is marked as an unavailable device; if an unavailable device exists, a high-risk supervision signal is generated.

7. The meteorological disaster intelligent early warning system based on real-time data collection and analysis according to claim 6 is characterized in that: If there is no unavailable equipment, the monitoring characteristic value of the monitoring object i is calculated by comparing it with the corresponding preset monitoring characteristic threshold to obtain the monitoring analysis value, and the monitoring analysis values of all meteorological monitoring equipment that need to be managed in the corresponding area are averaged to obtain the supervision hidden danger coefficient; If the corresponding area is a high-level area, the preset regulatory hidden danger coefficient threshold LP1 is assigned; if the corresponding area is a low-level area, the preset regulatory hidden danger coefficient threshold LP2 is assigned, and LP2>LP1>0; if the regulatory hidden danger coefficient exceeds the corresponding preset regulatory hidden danger coefficient threshold, a high regulatory hidden danger signal is generated.

8. The meteorological disaster intelligent early warning system based on real-time data collection and analysis according to claim 7 is characterized in that: If the supervisory hidden danger coefficient does not exceed the corresponding preset supervisory hidden danger coefficient threshold, the emergency hidden danger coefficient is obtained by numerically calculating the total time value of emergency hidden dangers, the emergency hidden danger frequency table value, and the emergency hidden danger amplitude value; if the corresponding area is a high-level area, the preset emergency hidden danger coefficient threshold TP1 is assigned; If the corresponding area is a low-level area, a preset emergency hazard coefficient threshold TP2 is assigned, and TP2>TP1>0; if the emergency hazard coefficient exceeds the corresponding preset emergency hazard coefficient threshold, a high-hazard supervision signal is generated; if the emergency hazard coefficient does not exceed the corresponding preset emergency hazard coefficient threshold, a low-hazard supervision signal is generated.

Images