Low-temperature cloudy and rainy early warning method and system based on big data

Abstract

The invention relates to the technical field of disaster early warning, and discloses a low-temperature cloudy and rainy early warning method and system based on big data, and the system comprises a collection module which collects the meteorological data of a current time period and the meteorological data of a previous time period in a meteorological-time series data set, obtaining a meteorological fluctuation value according to the meteorological data of the current time period and the meteorological data of the previous time period; the judgment module is used for screening out abnormal feature data in the current time period when it is determined that low-temperature cloudy and rainy early warning is carried out on the to-be-monitored area; comparing the abnormal feature data with historical feature data, and judging an initial early warning level according to a comparison result; the adjusting module is used for judging whether to adjust the initial early warning level or not according to the traffic data and the crop growth stage so as to obtain a final early warning level; the storage module is configured to store the abnormal feature data; and the early warning module is configured to perform early warning according to the final early warning level. According to the invention, effective early warning can be carried out on low-temperature cloudy and rainy weather, and loss caused by disasters is reduced.

Description

Technical Field

[0001] The present invention relates to the field of disaster warning technology, and in particular to a low temperature and rainy weather warning method and system based on big data. Background Art

[0002] Low temperature rainy weather refers to continuous rainy days with a drop in temperature. Under this weather condition, the precipitation is not large, but the temperature is low, and sometimes it lasts for a month. This weather phenomenon is particularly common in the middle and lower reaches of the Yangtze River and in southern my country.

[0003] The main purpose of issuing low temperature and rain warning is to provide early warning to ensure the safety of people's lives and property and the normal production and living order. Low temperature and rainy weather may bring many adverse effects, including safety hazards caused by slippery roads, snow and ice, as well as impacts on agriculture, transportation, human health and other aspects. By issuing early warning information, effective prevention and response measures can be taken to reduce losses and risks.

[0004] However, the existing low temperature and rainy methods have problems such as low warning accuracy and lack of timeliness.

[0005] Therefore, how to effectively improve the accuracy and timeliness of the low temperature and rain warning system has become a technical problem that technical personnel in this field urgently need to solve. Summary of the invention

[0006] In view of this, the present invention proposes a low temperature and rainy weather warning method and system based on big data, aiming to effectively improve the accuracy and timeliness of the low temperature and rainy weather warning system.

[0007] In one aspect, the present invention proposes a low temperature and rainy early warning system based on big data, comprising: The acquisition module is configured to acquire meteorological data of the area to be monitored and establish a meteorological-time series data set according to the time series; it is also configured to acquire meteorological data of the current time period and meteorological data of the previous time period in the meteorological-time series data set, and obtain a meteorological fluctuation value according to the meteorological data of the current time period and the meteorological data of the previous time period; wherein the meteorological data includes temperature data, humidity data, precipitation and sunshine duration; The judgment module is configured to compare the meteorological fluctuation value with the meteorological fluctuation threshold, and judge whether to issue a low temperature and rainy warning to the monitored area according to the comparison result; when it is determined that a low temperature and rainy warning is issued to the monitored area, filter out abnormal feature data in the current time period; compare the abnormal feature data with the historical feature data, and judge the initial warning level according to the comparison result; an adjustment module, configured to, after determining the initial warning level, control the acquisition module to acquire traffic data and crop growth stage of the monitored area, and determine whether to adjust the initial warning level according to the traffic data and crop growth stage to obtain a final warning level; A storage module, configured to store the abnormal characteristic data; The early warning module is configured to issue an early warning according to the final early warning level.

[0008] Further, when obtaining the meteorological fluctuation value according to the meteorological data of the current time period and the meteorological data of the previous time period, it includes: Collecting first temperature data in a current time period, establishing a first temperature data set according to the first temperature data, and calculating a first average temperature value; Collecting second temperature data of a previous time period, establishing a second temperature data set according to the second temperature data, and calculating a second average temperature value; Subtracting the first average temperature value from the second average temperature value to obtain a temperature difference value, comparing the temperature difference value with a temperature difference threshold value, and determining a temperature change trend according to the comparison result; When the temperature change trend is a temperature increase, it is determined that low temperature and rainy weather conditions do not occur; When the temperature change trend is a decrease in temperature, it is determined that low temperature and rainy weather conditions occur, and a weather fluctuation value is obtained based on the weather data of the current time period and the weather data of the previous time period.

[0009] Further, when obtaining the meteorological fluctuation value according to the meteorological data of the current time period and the meteorological data of the previous time period, it includes: Calculate the temperature fluctuation value, humidity fluctuation value, precipitation fluctuation value and sunshine duration fluctuation value of the monitored area respectively; The meteorological fluctuation value is calculated according to the temperature fluctuation value, humidity fluctuation value, precipitation fluctuation value and sunshine duration fluctuation value, and the meteorological fluctuation value is obtained by the following formula:

[0010] in, Indicates the weather fluctuation value, represents the jth time node, represents the i-th meteorological variable, β represents the weight coefficient, Indicates the value of the i-th meteorological variable corresponding to the j-th time node in the current time period, Indicates the value of the i-th meteorological variable corresponding to the j-th time node in the previous time period.

[0011] Further, the meteorological fluctuation value is compared with the meteorological fluctuation threshold, and judging whether to issue a low temperature and rainy warning for the monitored area according to the comparison result includes: When the meteorological fluctuation value is less than the meteorological fluctuation threshold, it is determined that no low temperature and rain warning is issued for the monitored area; When the meteorological fluctuation value is greater than or equal to the meteorological fluctuation threshold, it is determined that a low temperature and rainy weather warning is issued for the monitored area.

[0012] Further, when determining to issue a low temperature and rainy early warning to the monitored area, screening out abnormal characteristic data in the current time period includes: Screening out meteorological data corresponding to each meteorological fluctuation value that is greater than or equal to the meteorological fluctuation threshold, and performing abnormal value calculation on the meteorological data to determine the abnormal characteristic data; Calculate the outlier value of each filtered meteorological data based on the Z-Score method;

[0013] in, represents the standard score, represents the meteorological data value after each screening, μ represents the average value of the meteorological data in the current time period, and σ represents the standard deviation of the meteorological data in the current time period; when When it is greater than or equal to 2, the meteorological data is determined to be abnormal characteristic data.

[0014] Furthermore, the abnormal characteristic data is compared with the historical characteristic data, and the initial warning level is determined according to the comparison result, including: Calculating the similarity between the abnormal feature data and the historical feature data, comparing the similarity with a first similarity threshold and a second similarity threshold, and determining the initial warning level according to the comparison result; wherein the first similarity threshold is greater than the second similarity threshold; When the similarity is greater than or equal to the second similarity threshold, determining the initial warning level as a high-level warning; When the similarity is greater than or equal to a first similarity threshold and less than the second similarity threshold, determining that the initial warning level is a low-level warning; When the similarity is less than the first similarity threshold, the abnormal feature data is added to the historical feature database and an alarm is issued to remind manual verification.

[0015] Furthermore, the similarity is obtained by the following formula:

[0016] in, Indicates similarity, The qth characteristic value of the abnormal characteristic data in the current time period, Indicates the average value of abnormal feature data in the current time period. The qth eigenvalue of the historical feature data, represents the average value of historical characteristic data, and n represents the number of meteorological variables.

[0017] Further, judging whether to adjust the initial warning level according to the traffic data and the crop growth stage to obtain the final warning level includes: Extracting traffic flow data, average vehicle speed data, traffic accident quantity data, and delay time data from the traffic data; Calculate early warning indicators based on the traffic flow data, average vehicle speed data, traffic accident quantity data, delay time data and crop growth stage;

[0018] in, Represents an early warning indicator, Indicates traffic flow, represents the average vehicle speed, represents the number of traffic accidents, Indicates the delay time. It represents the crop growth stage index, and α1, α2, α3, α4, α5, and e represent the influence coefficients.

[0019] Further, judging whether to adjust the initial warning level according to the traffic data and the crop growth stage, and obtaining the final warning level, further includes: Comparing the warning indicator with the warning indicator threshold, adjusting the initial warning level according to the comparison result, and obtaining a final warning level; When the warning indicator is greater than or equal to the warning indicator threshold, it is determined to increase the initial warning level, and the increased initial warning level is used as the final warning level; When the warning indicator is less than the warning indicator threshold, it is determined to lower the initial warning level, and the lowered initial warning level is used as the final warning level.

[0020] Compared with the prior art, the invention has the following beneficial effects: the low temperature and rainy early warning system based on big data provided by the invention has high flexibility and adaptability. By real-time monitoring and analysis of meteorological data, the system can detect abnormal fluctuations in a timely manner, and dynamically adjust the early warning level in combination with traffic data and crop growth stages. This early warning method not only improves the accuracy and timeliness of the early warning, but also optimizes the early warning model by continuously learning historical data, reduces false alarms and missed alarms, and thus takes effective countermeasures to protect people's lives and property.

[0021] In another aspect, the present invention also proposes a low temperature rain warning method based on big data, comprising the following steps: S100: Collecting meteorological data of the area to be monitored, and establishing a meteorological-time series data set according to the time series; collecting meteorological data of the current time period and meteorological data of the previous time period in the meteorological-time series data set, and obtaining a meteorological fluctuation value according to the meteorological data of the current time period and the meteorological data of the previous time period; wherein the meteorological data includes temperature data, humidity data, precipitation and sunshine duration; S200: comparing the meteorological fluctuation value with the meteorological fluctuation threshold, and judging whether to issue a low temperature and rainy warning to the monitored area according to the comparison result; when it is determined that a low temperature and rainy warning is issued to the monitored area, screening out abnormal characteristic data in the current time period; comparing the abnormal characteristic data with the historical characteristic data, and judging the initial warning level according to the comparison result; S300: After the initial warning level is determined, the collection module is controlled to collect traffic data and crop growth stage of the monitored area, and whether to adjust the initial warning level is determined according to the traffic data and crop growth stage to obtain a final warning level; S400: storing the abnormal characteristic data; S500: issuing an early warning according to the final early warning level.

[0022] It is understandable that the above-mentioned low temperature and rain warning method and system based on big data have the same beneficial effects and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings: Figure 1 A structural block diagram of a low temperature and rainy early warning system based on big data provided by an embodiment of the present invention; Figure 2A flowchart of a low temperature and rainy weather warning method based on big data provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0024] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, in the absence of conflict, the embodiments of the present invention and the features described in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0025] See also Figure 1 As shown, in some embodiments of the present application, this embodiment provides a low temperature and rain warning system based on big data, including: The acquisition module is configured to acquire meteorological data of the area to be monitored and establish a meteorological-time series data set according to the time series; it is also configured to acquire meteorological data of the current time period and meteorological data of the previous time period in the meteorological-time series data set, and obtain a meteorological fluctuation value according to the meteorological data of the current time period and the meteorological data of the previous time period; wherein the meteorological data includes temperature data, humidity data, precipitation and sunshine duration; In this embodiment, the weather-time series data set is constructed using a time series model based on weather satellite data, ground weather station data, radar data, and a historical weather database.

[0026] The judgment module is configured to compare the meteorological fluctuation value with the meteorological fluctuation threshold, and judge whether to issue a low temperature and rainy warning to the monitored area according to the comparison result; when it is determined that a low temperature and rainy warning is issued to the monitored area, filter out abnormal feature data in the current time period; compare the abnormal feature data with the historical feature data, and judge the initial warning level according to the comparison result; an adjustment module, configured to, after determining the initial warning level, control the acquisition module to acquire traffic data and crop growth stage of the monitored area, and determine whether to adjust the initial warning level according to the traffic data and crop growth stage to obtain a final warning level; In this embodiment, the crop growth stage refers to a specific period of crop growth, such as sowing period, germination period, tillering period, jointing period, heading period, flowering period, filling period and maturity period, etc. These stages have different sensitivities to low temperature and rain.

[0027] A storage module, configured to store the abnormal characteristic data; The early warning module is configured to issue an early warning according to the final early warning level.

[0028] It is understandable that the low temperature and rainy weather warning system based on big data provided by this embodiment can effectively integrate multi-source data to improve the accuracy and timeliness of warnings. By real-time monitoring and analysis of meteorological changes, combined with traffic data and crop growth stages, the system can effectively warn of low temperature and rainy weather and reduce losses caused by disasters.

[0029] Specifically, when obtaining the meteorological fluctuation value according to the meteorological data of the current time period and the meteorological data of the previous time period, it includes: Collecting first temperature data in a current time period, establishing a first temperature data set according to the first temperature data, and calculating a first average temperature value; Collecting second temperature data of a previous time period, establishing a second temperature data set according to the second temperature data, and calculating a second average temperature value; Subtracting the first average temperature value from the second average temperature value to obtain a temperature difference value, comparing the temperature difference value with a temperature difference threshold value, and determining a temperature change trend according to the comparison result; When the temperature change trend is a temperature increase, it is determined that low temperature and rainy weather conditions do not occur; When the temperature change trend is a decrease in temperature, it is determined that low temperature and rainy weather conditions occur, and a weather fluctuation value is obtained based on the weather data of the current time period and the weather data of the previous time period.

[0030] In this embodiment, when the temperature difference is less than or equal to the temperature difference threshold, it indicates that the current temperature change trend is temperature rise or temperature stability, and does not constitute a warning condition for low temperature and rainy weather; when the temperature difference is greater than the temperature difference threshold, it indicates that the temperature has dropped significantly, and it is necessary to further analyze the changes in other meteorological factors such as humidity, air pressure and wind speed.

[0031] In this embodiment, the temperature difference threshold is obtained based on the statistical analysis of historical meteorological data. For example, the temperature difference threshold is set to 3°C, which means that if the average temperature of the current time period drops by more than 3°C compared with the previous time period, the system will consider that there are low temperature and rainy weather conditions.

[0032] Specifically, when obtaining the meteorological fluctuation value according to the meteorological data of the current time period and the meteorological data of the previous time period, it includes: Calculate the temperature fluctuation value, humidity fluctuation value, precipitation fluctuation value and sunshine duration fluctuation value of the monitored area respectively; The meteorological fluctuation value is calculated according to the temperature fluctuation value, humidity fluctuation value, precipitation fluctuation value and sunshine duration fluctuation value, and the meteorological fluctuation value is obtained by the following formula:

[0033] in, Indicates the weather fluctuation value, represents the jth time node, represents the i-th meteorological variable, β represents the weight coefficient, Indicates the value of the i-th meteorological variable corresponding to the j-th time node in the current time period, Indicates the value of the i-th meteorological variable corresponding to the j-th time node in the previous time period.

[0034] In this embodiment, the current time period and the previous time period both include the same number of time nodes (m), the meteorological data of the jth time node in the current time period and the meteorological data of the jth time node in the previous time period are corresponding (j=1, 2, 3...m), and the temperature change fluctuation value is the difference between the temperature value of the jth time node in the current time period and the temperature value of the jth time node in the previous time period. The calculation method of the humidity change fluctuation value, the precipitation change fluctuation value and the sunshine duration change fluctuation value is similar to that of the temperature change fluctuation value, corresponding to the changes in humidity, precipitation and sunshine duration respectively.

[0035] In this embodiment, the meteorological variables are temperature data, humidity data, precipitation and sunshine duration.

[0036] Specifically, the meteorological fluctuation value is compared with the meteorological fluctuation threshold, and judging whether to issue a low temperature and rainy warning for the monitored area according to the comparison result includes: When the meteorological fluctuation value is less than the meteorological fluctuation threshold, it is determined that no low temperature and rain warning is issued for the monitored area; When the meteorological fluctuation value is greater than or equal to the meteorological fluctuation threshold, it is determined that a low temperature and rainy weather warning is issued for the monitored area.

[0037] In this embodiment, determining whether to issue a low temperature and rainy early warning for the monitored area based on the comparison result of the meteorological fluctuation value and the meteorological fluctuation threshold is an effective method, because the meteorological fluctuation value can comprehensively reflect the changes in multiple meteorological factors such as temperature, humidity, air pressure and wind speed. By setting a reasonable meteorological fluctuation threshold, the system can accurately identify potential low temperature and rainy weather, and issue an early warning.

[0038] Specifically, when determining to issue a low temperature and rain warning for the monitored area, screening out abnormal characteristic data in the current time period includes: Screening out meteorological data corresponding to each meteorological fluctuation value that is greater than or equal to the meteorological fluctuation threshold, and performing abnormal value calculation on the meteorological data to determine the abnormal characteristic data; Calculate the outlier value of each filtered meteorological data based on the Z-Score method;

[0039] in, represents the standard score, represents the meteorological data value after each screening, μ represents the average value of the meteorological data in the current time period, and σ represents the standard deviation of the meteorological data in the current time period; when When it is greater than or equal to 2, the meteorological data is determined to be abnormal characteristic data.

[0040] In this embodiment, the Z-Score (Standard Score) method is an outlier detection method widely used in statistical analysis, which determines whether a data point is an outlier by calculating the deviation of the data point from the mean. Specifically, the Z-Score method evaluates the degree of abnormality of a data point by comparing each data point with the mean (μ) and standard deviation (σ) of the data set. When the standard score Z is greater than or equal to 2, it indicates that the deviation of the data point from the mean exceeds two standard deviations, so the data point can be considered abnormal. In this system, by using the Z-Score method, abnormal characteristic data can be effectively screened out from meteorological data, which may indicate potential low temperature and rainy weather conditions. In this way, the system can promptly identify and warn of possible low temperature and rainy events, thereby providing important meteorological information to residents and decision makers in relevant areas.

[0041] In this embodiment, the calculation method of the meteorological data value is: extract the temperature data, humidity data, precipitation and sunshine duration of the jth time node in the current time period; assign weights to the temperature data, humidity data, precipitation and sunshine duration respectively; and then add these data to obtain the meteorological data value of each time node. In this way, it can be ensured that each meteorological factor is reasonably considered according to its importance in the formation of low temperature and rain. The purpose of weight allocation is to highlight those meteorological factors that have a greater impact on the formation of low temperature and rain, thereby improving the accuracy and efficiency of the early warning system. For example, if humidity and precipitation play a key role in the formation of low temperature and rain, their weight coefficients βi can be set higher. On the contrary, if the influence of temperature and sunshine duration is relatively small, their weight coefficients can be set accordingly lower. In this way, the system can dynamically adjust the weights of various meteorological factors according to actual meteorological conditions, so as to more accurately predict and warn low temperature and rainy weather.

[0042] In this embodiment, in the current time period, each meteorological fluctuation value that is greater than or equal to the meteorological fluctuation threshold has corresponding meteorological data. The above method is used to calculate the outlier value. For example, the meteorological data values ​​corresponding to the 1st to 5th time nodes in the current time period are 15, 16, 13, 30, 16, and 14. Then the average value of the meteorological data in the current time period is 17, and the value of the standard deviation σ is approximately 5.88. For the meteorological data X=30, its standard score value is calculated to be approximately 2.21, so the meteorological data corresponding to the meteorological data value 30 is the abnormal characteristic data.

[0043] Specifically, the abnormal feature data is compared with the historical feature data, and the initial warning level is determined according to the comparison result, including: Calculating the similarity between the abnormal feature data and the historical feature data, comparing the similarity with a first similarity threshold and a second similarity threshold, and determining the initial warning level according to the comparison result; wherein the first similarity threshold is greater than the second similarity threshold; When the similarity is greater than or equal to the second similarity threshold, determining the initial warning level as a high-level warning; When the similarity is greater than or equal to a first similarity threshold and less than the second similarity threshold, determining that the initial warning level is a low-level warning; When the similarity is less than the first similarity threshold, the abnormal feature data is added to the historical feature database and an alarm is issued to remind manual verification.

[0044] In this embodiment, the historical feature data includes meteorological data recorded in a certain period in the past, which covers a variety of meteorological factors such as temperature, humidity, precipitation and sunshine duration. Through the continuous updating and expansion of the historical feature database, the system can learn and adapt to more meteorological patterns and improve the accuracy and timeliness of early warning. A large amount of historical meteorological data and its corresponding early warning level are stored in the historical feature database. After processing and analysis, these data can be used as a reference for future early warning judgment. When new abnormal feature data appears, the system will compare it with the historical feature data and judge the early warning level by calculating the similarity. If the similarity is high, it means that the current meteorological fluctuation is similar to some known low temperature and rainy weather patterns in history, and the system will determine the early warning level according to the similarity. If the similarity is low, it means that the current meteorological fluctuation may be a new pattern, and the system will remind manual verification to ensure the accuracy of the early warning. Through such a mechanism, the system can not only automatically warn, but also continuously learn and optimize, so as to be more accurate in future early warnings.

[0045] In this embodiment, the first similarity threshold and the second similarity threshold are determined based on the statistical analysis of historical meteorological data. The first similarity threshold is set relatively high to ensure that the system will only determine it as a high-level warning when the similarity between the abnormal feature data and the historical feature data is very high. The second similarity threshold is relatively low and is used to identify those situations that have a certain similarity with the historical data but are not enough to be determined as a high-level warning. Through such a setting, the system can distinguish between different levels of warning situations, thereby providing decision makers with more accurate reference information. In addition, the system can also automatically adjust the threshold according to the warning results to adapt to changes in meteorological patterns and ensure the continued effectiveness and adaptability of the warning system.

[0046] In this embodiment, in the meteorological warning system, a high-level warning usually means that emergency measures need to be taken to deal with possible low-temperature rainy weather. Even if the similarity is high but the risk level is not high, it may be because the current meteorological conditions are similar to some historical low-temperature rainy events that have caused significant impacts. Therefore, the system tends to conservatively issue a high-level warning to avoid underestimation of potential risks. This strategy helps to ensure the reliability of the warning system and ensure that timely warnings can be provided at critical moments.

[0047] Specifically, the similarity is obtained by the following formula:

[0048] in, Indicates similarity, The qth characteristic value of the abnormal characteristic data in the current time period, Indicates the average value of abnormal feature data in the current time period. The qth eigenvalue of the historical feature data, represents the average value of historical characteristic data, and n represents the number of meteorological variables.

[0049] In this embodiment, n=1,2,3,4, and by calculating the similarity S value, the system can evaluate the similarity between the current abnormal feature data and the historical feature data. If the S value is high, it indicates that the current weather fluctuation is similar to some known patterns in history, and the system will determine the warning level based on the similarity. If the S value is low, it indicates that the current weather fluctuation may be a new pattern, and the system will remind manual verification to ensure the accuracy of the warning. Through such a mechanism, the system can not only automatically warn, but also continuously learn and optimize, so as to be more accurate in future warnings.

[0050] In this embodiment, The qth eigenvalue of the abnormal characteristic data of the current time period. For example, in meteorological data, the eigenvalue is specific data such as temperature, humidity, precipitation or sunshine duration in a certain time period. When q=1, D1 represents the first eigenvalue of the abnormal characteristic data of the current time period - temperature data; when q=2, D2 represents the second eigenvalue of the abnormal characteristic data of the current time period - humidity data; when q=3, D3 represents the third eigenvalue of the abnormal characteristic data of the current time period - precipitation; when q=4, D4 represents the fourth eigenvalue of the abnormal characteristic data of the current time period - sunshine duration. Similarly, Hq represents the qth eigenvalue of the historical characteristic data, where H1, H2, H3 and H4 correspond to historical temperature data, historical humidity data, historical precipitation and historical sunshine duration respectively. Through this correspondence, the system can perform detailed analysis of different meteorological variables, so as to more accurately evaluate the similarity between the current meteorological conditions and historical data.

[0051] Specifically, judging whether to adjust the initial warning level according to the traffic data and the crop growth stage, and obtaining the final warning level includes: Extracting traffic flow data, average vehicle speed data, traffic accident quantity data, and delay time data from the traffic data; Calculate early warning indicators based on the traffic flow data, average vehicle speed data, traffic accident quantity data, delay time data and crop growth stage;

[0052] in, Represents an early warning indicator, Indicates traffic flow, represents the average vehicle speed, represents the number of traffic accidents, Indicates the delay time. It represents the crop growth stage index, and α1, α2, α3, α4, α5, and e represent the influence coefficients.

[0053] In this embodiment, by setting different influence coefficients α1, α2, α3, α4, α5, and e, the degree of influence of different traffic conditions and crop growth stages on the early warning index can be adjusted. For example, when the crop is in a critical growth period, the value of G will increase, thereby increasing the value of the early warning index WI to reflect the sensitivity of crop growth to traffic conditions. On the contrary, if the traffic flow Tf is high, the average vehicle speed Vs is low, the number of traffic accidents A is large, and the delay time D is long, then the early warning index WI will also increase accordingly, indicating that the traffic conditions are poor and the early warning level needs to be increased. Through this calculation method that comprehensively considers traffic data and crop growth stages, the system can provide more accurate and personalized early warning information to help relevant departments and farmers make more reasonable decisions.

[0054] In this embodiment, traffic flow data can reflect the current traffic conditions. For example, if the traffic flow data suddenly increases, it may indicate that a large number of vehicles are stranded on the road due to weather reasons, which will directly affect the smoothness and safety of traffic. The average speed data is the average value of the vehicle's driving speed, which can reflect the traffic efficiency of the road. If the average speed decreases, it may mean that the road conditions have deteriorated, for example, due to the slippery road surface caused by low temperature and rainy weather, the vehicle slows down. The data on the number of traffic accidents is directly related to the impact of weather conditions on traffic safety. The increased number of accidents may indicate that the weather conditions pose a threat to driving safety. The delay time data reflects the impact of traffic conditions on transportation efficiency. Long delays may affect the timely delivery of agricultural products, thereby affecting market supply and prices. Through the comprehensive analysis of these traffic data, the system can more accurately assess the potential impact of weather changes on transportation and agricultural production, thereby providing decision makers with more comprehensive and timely early warning information.

[0055] Specifically, judging whether to adjust the initial warning level according to the traffic data and the crop growth stage, and obtaining the final warning level also includes: Comparing the warning indicator with the warning indicator threshold, adjusting the initial warning level according to the comparison result, and obtaining a final warning level; When the warning indicator is greater than or equal to the warning indicator threshold, it is determined to increase the initial warning level, and the increased initial warning level is used as the final warning level; When the warning indicator is less than the warning indicator threshold, it is determined to lower the initial warning level, and the lowered initial warning level is used as the final warning level.

[0056] In this embodiment, the warning indicator threshold is set based on historical data and actual warning effects to ensure the timeliness and accuracy of the warning. For example, if the warning indicator threshold is set to 10, when the calculated warning indicator WI is greater than or equal to 10, the system will automatically increase the warning level to remind relevant departments and the public to take corresponding preventive measures. On the contrary, if the warning indicator WI is less than 10, the system will lower the warning level to reduce unnecessary alarms and avoid causing public panic and waste of resources. In this way, the system can dynamically adjust the warning level according to real-time traffic data and crop growth stage to ensure the practicality and effectiveness of the warning information.

[0057] In this embodiment, if the initial warning level is a high-level warning, then when the initial warning level is increased, the high-level warning will be upgraded to the highest-level warning to ensure that the most stringent preventive measures can be taken in extreme weather conditions. On the contrary, if the initial warning level is a low-level warning, the low-level warning level will be reduced to the lowest-level warning. If the initial level is the highest-level warning, then when the initial warning level is lowered, the high-level warning will be reduced to a low-level warning; if the initial level is a low-level warning, then when the initial warning level is increased, the low-level warning will be upgraded to a high-level warning; it can be seen that the final warning level is the highest-level warning, the high-level warning, the low-level warning, and the lowest-level warning, and the highest-level warning>high-level warning>low-level warning>lowest-level warning.

[0058] See also Figure 2 As shown, in some embodiments of the present application, this embodiment provides a low temperature and rainy early warning method based on big data, comprising the following steps: S100: Collecting meteorological data of the area to be monitored, and establishing a meteorological-time series data set according to the time series; collecting meteorological data of the current time period and meteorological data of the previous time period in the meteorological-time series data set, and obtaining a meteorological fluctuation value according to the meteorological data of the current time period and the meteorological data of the previous time period; wherein the meteorological data includes temperature data, humidity data, precipitation and sunshine duration; S200: comparing the meteorological fluctuation value with the meteorological fluctuation threshold, and judging whether to issue a low temperature and rainy warning to the monitored area according to the comparison result; when it is determined that a low temperature and rainy warning is issued to the monitored area, screening out abnormal characteristic data in the current time period; comparing the abnormal characteristic data with the historical characteristic data, and judging the initial warning level according to the comparison result; S300: After the initial warning level is determined, the collection module is controlled to collect traffic data and crop growth stage of the monitored area, and whether to adjust the initial warning level is determined according to the traffic data and crop growth stage to obtain a final warning level; S400: storing the abnormal characteristic data; S500: issuing an early warning according to the final early warning level.

[0059] It is understandable that the low temperature and rain warning method based on big data provided by this embodiment has high flexibility and adaptability. By real-time monitoring and analysis of meteorological data, the system can detect abnormal fluctuations in a timely manner, and dynamically adjust the warning level in combination with traffic data and crop growth stages. This warning method not only improves the accuracy and timeliness of the warning, but also optimizes the warning model by continuously learning historical data, reduces false alarms and missed alarms, and thus takes effective response measures to protect people's lives and property.

[0060] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0061] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0062] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0063] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0064] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A low temperature and rainy early warning system based on big data, characterized in that: include: The acquisition module is configured to acquire meteorological data of the area to be monitored and establish a meteorological-time series data set according to the time series; it is also configured to acquire meteorological data of the current time period and meteorological data of the previous time period in the meteorological-time series data set, and obtain a meteorological fluctuation value according to the meteorological data of the current time period and the meteorological data of the previous time period; wherein the meteorological data includes temperature data, humidity data, precipitation and sunshine duration; The judgment module is configured to compare the meteorological fluctuation value with the meteorological fluctuation threshold, and judge whether to issue a low temperature and rainy warning to the monitored area according to the comparison result; when it is determined that a low temperature and rainy warning is issued to the monitored area, filter out abnormal feature data in the current time period; compare the abnormal feature data with the historical feature data, and judge the initial warning level according to the comparison result; an adjustment module, configured to, after determining the initial warning level, control the acquisition module to acquire traffic data and crop growth stage of the monitored area, and determine whether to adjust the initial warning level according to the traffic data and crop growth stage to obtain a final warning level; A storage module, configured to store the abnormal characteristic data; An early warning module, configured to issue an early warning according to the final early warning level; When obtaining the meteorological fluctuation value according to the meteorological data of the current time period and the meteorological data of the previous time period, it includes: Collecting first temperature data in a current time period, establishing a first temperature data set according to the first temperature data, and calculating a first average temperature value; Collecting second temperature data of a previous time period, establishing a second temperature data set according to the second temperature data, and calculating a second average temperature value; Subtracting the first average temperature value from the second average temperature value to obtain a temperature difference value, comparing the temperature difference value with a temperature difference threshold value, and determining a temperature change trend according to the comparison result; When the temperature change trend is a temperature increase, it is determined that low temperature and rainy weather conditions do not occur; When the temperature change trend is a temperature drop, it is determined that low temperature and rainy weather conditions occur, and a weather fluctuation value is obtained based on the weather data of the current time period and the weather data of the previous time period; When obtaining the meteorological fluctuation value according to the meteorological data of the current time period and the meteorological data of the previous time period, it includes: Calculate the temperature fluctuation value, humidity fluctuation value, precipitation fluctuation value and sunshine duration fluctuation value of the monitored area respectively; The meteorological fluctuation value is calculated according to the temperature fluctuation value, humidity fluctuation value, precipitation fluctuation value and sunshine duration fluctuation value, and the meteorological fluctuation value is obtained by the following formula: in, Indicates the weather fluctuation value, represents the jth time node, represents the i-th meteorological variable, β represents the weight coefficient, Indicates the value of the i-th meteorological variable corresponding to the j-th time node in the current time period, Indicates the value of the i-th meteorological variable corresponding to the j-th time node in the previous time period; The meteorological fluctuation value is compared with the meteorological fluctuation threshold, and judging whether to issue a low temperature and rain warning for the monitored area according to the comparison result, including: When the meteorological fluctuation value is less than the meteorological fluctuation threshold, it is determined that no low temperature and rain warning will be issued for the monitored area; When the meteorological fluctuation value is greater than or equal to the meteorological fluctuation threshold, it is determined that a low temperature and rainy weather warning is issued for the monitored area; When determining to issue a low temperature and rain warning for the monitored area, screening out abnormal characteristic data in the current time period includes: Screening out meteorological data corresponding to each meteorological fluctuation value that is greater than or equal to the meteorological fluctuation threshold, and performing abnormal value calculation on the meteorological data to determine the abnormal characteristic data; Calculate the outlier value of each filtered meteorological data based on the Z-Score method; in, represents the standard score, represents the meteorological data value after each screening, μ represents the average value of the meteorological data in the current time period, and σ represents the standard deviation of the meteorological data in the current time period; when When it is greater than or equal to 2, the meteorological data is determined to be abnormal characteristic data; Comparing the abnormal characteristic data with the historical characteristic data and determining the initial warning level according to the comparison result includes: Calculating the similarity between the abnormal feature data and the historical feature data, comparing the similarity with a first similarity threshold and a second similarity threshold, and determining the initial warning level according to the comparison result; wherein the first similarity threshold is greater than the second similarity threshold; When the similarity is greater than or equal to the second similarity threshold, determining the initial warning level as a high-level warning; When the similarity is greater than or equal to a first similarity threshold and less than the second similarity threshold, determining that the initial warning level is a low-level warning; When the similarity is less than the first similarity threshold, the abnormal feature data is added to the historical feature database and an alarm is issued to remind manual verification.

2. The low temperature and rainy weather warning system based on big data according to claim 1 is characterized in that: The similarity is obtained by the following formula: in, Indicates similarity, The qth characteristic value of the abnormal characteristic data in the current time period, Indicates the average value of abnormal feature data in the current time period. The qth eigenvalue of the historical feature data, represents the average value of historical characteristic data, and n represents the number of meteorological variables.

3. The low temperature and rain early warning system based on big data according to claim 2 is characterized in that: Determining whether to adjust the initial warning level according to the traffic data and the crop growth stage, and obtaining the final warning level includes: Extracting traffic flow data, average vehicle speed data, traffic accident quantity data, and delay time data from the traffic data; Calculate early warning indicators based on the traffic flow data, average vehicle speed data, traffic accident quantity data, delay time data and crop growth stage; in, Represents an early warning indicator. Indicates the traffic flow, represents the average vehicle speed, represents the number of traffic accidents, Indicates the delay time. It represents the crop growth stage index, and α1, α2, α3, α4, α5, and e represent the influence coefficients.

4. The low temperature and rain early warning system based on big data according to claim 3 is characterized in that: When determining whether to adjust the initial warning level according to the traffic data and the crop growth stage and obtaining the final warning level, the method further includes: Comparing the warning indicator with the warning indicator threshold, adjusting the initial warning level according to the comparison result, and obtaining a final warning level; When the warning indicator is greater than or equal to the warning indicator threshold, it is determined to increase the initial warning level, and the increased initial warning level is used as the final warning level; When the warning indicator is less than the warning indicator threshold, it is determined to lower the initial warning level, and the lowered initial warning level is used as the final warning level.

5. A low temperature and rainy early warning method based on big data, applied to the low temperature and rainy early warning system based on big data as claimed in any one of claims 1 to 4, characterized in that: include: Collect meteorological data of the area to be monitored and establish a meteorological-time series data set based on the time series; Collecting meteorological data of the current time period and meteorological data of the previous time period in the meteorological-time series data set, and obtaining a meteorological fluctuation value according to the meteorological data of the current time period and the meteorological data of the previous time period; wherein the meteorological data includes temperature data, humidity data, precipitation and sunshine duration; The meteorological fluctuation value is compared with the meteorological fluctuation threshold, and it is determined whether to issue a low temperature and rainy warning to the monitored area according to the comparison result; when it is determined that a low temperature and rainy warning is issued to the monitored area, abnormal feature data in the current time period is screened out; the abnormal feature data is compared with the historical feature data, and the initial warning level is determined according to the comparison result; After the initial warning level is determined, the acquisition module is controlled to acquire traffic data and crop growth stage of the monitored area, and whether to adjust the initial warning level is determined according to the traffic data and crop growth stage to obtain a final warning level; Storing the abnormal characteristic data; An early warning is issued according to the final early warning level.

Images