Disease and pest outbreak process mining risk prediction method and system based on multi-source factors

Abstract

The invention relates to the technical field of pest control, in particular to a pest outbreak process mining risk prediction method and system based on multi-source factors. The method comprises the following steps: measuring regional meteorological data, regional crop soil fertility degree and regional disease and pest occurrence data corresponding to crop disease and pest monitoring points in real time; the corresponding pesticide spraying usage amount is obtained through the crop disease and insect pest monitoring points, and regional occurrence density accounting and disease and insect pest outbreak mining analysis are carried out on regional disease and insect pest occurrence data based on the pesticide spraying usage amount. Obtaining a corresponding regional pest and disease outbreak characteristic mode under the meteorological condition and a correlation characteristic relation between regional soil fertility and pest and disease outbreak; and performing multi-source factor risk prediction and control decision support analysis on the crop disease and pest monitoring points to generate a disease and pest outbreak area control suggestion scheme. According to the invention, scientific and accurate disease and pest risk early warning can be provided for agricultural production.

Description

Technical Field

[0001] The present invention relates to the technical field of pest and disease control, and particularly to a method and system for mining risk prediction of pest and disease outbreaks based on multi-source factors. Background Art

[0002] Pests and diseases pose a serious threat to agricultural production, not only affecting the growth and yield of crops, but also potentially causing large-scale economic losses. The outbreak patterns of pests and diseases are becoming increasingly complex, and the monitoring and prediction of single factors can no longer meet the requirements of modern agricultural production for pest and disease prevention and control. At present, most traditional pest and disease prediction methods rely on the analysis of single factors such as empirical data, meteorological conditions, and crop planting patterns, and use statistical models, expert systems, or meteorological models for prediction. However, traditional methods do not fully consider the comprehensive impact of various factors such as environment, climate, and soil quality on pest and disease outbreaks, resulting in poor accuracy and reliability of prediction results and difficulty in responding to various sudden factors in real time. Summary of the Invention

[0003] Based on this, it is necessary for the present invention to provide a method and system for mining risk prediction of pest and disease outbreaks based on multi-source factors to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for mining risk prediction of pest and disease outbreaks based on multi-source factors includes the following steps: Step S1: Measure in real time the regional meteorological data, the regional crop soil fertility degree, and the regional pest and disease occurrence data corresponding to the pest and disease monitoring points of crops, where the regional pest and disease occurrence data includes the number of pest and disease occurrences, the time of pest and disease occurrences, and the locations of pest and disease occurrences; Step S2: Obtain the corresponding pesticide spraying usage amount through the pest and disease monitoring points of crops, and calculate the regional occurrence density of the regional pest and disease occurrence data based on the pesticide spraying usage amount to obtain the regional pest and disease occurrence density; Step S3: Conduct mining analysis of pest and disease outbreaks on the regional pest and disease occurrence density based on the regional meteorological data and the regional crop soil fertility degree to obtain the corresponding regional pest and disease outbreak characteristic patterns under meteorological conditions and the correlation characteristic relationship between regional soil fertility and pest and disease outbreaks; Step S4: Conduct multi-source factor risk prediction on the pest and disease monitoring points of crops based on the corresponding regional pest and disease outbreak characteristic patterns under meteorological conditions and the correlation characteristic relationship between regional soil fertility and pest and disease outbreaks to obtain the regional pest and disease outbreak risk prediction results; conduct prevention and control decision support analysis based on the regional pest and disease outbreak risk prediction results, and generate a prevention and control suggestion plan for the pest and disease outbreak area.

[0005] Further, Step S1 includes the following steps: Step S11: Real-time measure the regional meteorological data corresponding to the crop pest and disease monitoring points through the meteorological monitoring station network, including the temperature, humidity, precipitation, and light intensity corresponding to the monitoring point area; Step S12: Real-time monitor and collect the regional soil conditions corresponding to the crop pest and disease monitoring points through soil sensors to obtain the regional crop soil condition data, including the regional crop soil pH value, the regional crop soil fertility content index, and the regional crop soil microbial prosperity degree; Step S13: Conduct a regional soil fertility accounting for the crop pest and disease monitoring points based on the regional crop soil condition data to obtain the regional crop soil fertility level; Step S14: Real-time measure the regional pest and disease occurrence data corresponding to the crop pest and disease monitoring points through the daily pest and disease reporting records, including the number of pest and disease occurrences, the time of pest and disease occurrences, and the location of pest and disease occurrences.

[0006] Further, the regional crop soil fertility content index described in Step S12 specifically includes the regional soil nitrogen, phosphorus, and potassium content indexes.

[0007] Further, Step S13 includes the following steps: Step S131: Conduct a fertility decay analysis of the regional soil conditions corresponding to the crop pest and disease monitoring points based on the regional crop soil pH value to obtain the regional soil pH fertility decay index; Step S132: Obtain the corresponding regional crop vegetation coverage through the crop pest and disease monitoring points, and calculate the vegetation coverage area index for the crop pest and disease monitoring points based on the regional crop vegetation coverage to obtain the regional crop vegetation coverage area index; Step S133: Conduct a regional soil fertility accounting for the crop pest and disease monitoring points based on the regional soil pH fertility decay index, the regional crop vegetation coverage area index, the regional crop soil fertility content index, and the regional crop soil microbial prosperity degree using the regional soil fertility calculation formula to obtain the regional crop soil fertility level.

[0008] Further, the regional soil fertility calculation formula described in Step S133 is specifically: ; In the formula, is the regional crop soil fertility level, is the area of the crop pest and disease monitoring point area, is the spatial position parameter corresponding to the crop pest and disease monitoring point, is the regional soil pH fertility decay index, is the regional soil nitrogen content, is the nitrogen content fertility influence coefficient, is the regional soil phosphorus content, is the phosphorus content fertility influence coefficient, is the regional soil potassium content, is the potassium content fertility influence coefficient, is at the spatial position corresponding regional crop soil microbial prosperity degree, is the regional microbial prosperity contribution coefficient, is the regional crop vegetation coverage area index, is the vegetation coverage influence coefficient, is the correction coefficient of the regional crop soil fertility degree.

[0009] Further, step S2 includes the following steps: Step S21: Collect the corresponding pesticide usage records through the crop pest and disease monitoring points, and obtain the corresponding pesticide spraying usage amount according to the pesticide usage records; Step S22: Based on the pesticide spraying usage amount, conduct a pest and disease distribution attenuation assessment analysis on the corresponding pest and disease occurrence quantity in the regional pest and disease occurrence data to obtain the regional pest and disease distribution pesticide usage attenuation factor; Step S23: Based on the corresponding pest and disease occurrence locations in the regional pest and disease occurrence data, conduct a statistical analysis of the occurrence range area of the corresponding area of the crop pest and disease monitoring points to obtain the size of the regional pest and disease occurrence range area; Step S24: Based on the pesticide spraying usage amount, the regional pest and disease distribution pesticide usage attenuation factor, and the size of the regional pest and disease occurrence range area, use the regional occurrence density calculation formula to calculate the regional occurrence density of the pest and disease occurrence quantity and the pest and disease occurrence time to obtain the regional pest and disease occurrence density; Among them, the regional occurrence density calculation formula is specifically: ; In the formula, is the regional pest and disease occurrence density, is the pest and disease occurrence time, is the time variable parameter, is the size of the regional pest and disease occurrence range area, is the pesticide spraying usage amount, is at the time corresponding pest and disease occurrence quantity, is the regional pest and disease distribution pesticide usage attenuation factor, is the correction coefficient of the regional pest and disease occurrence density.

[0010] Further, step S3 includes the following steps: Step S31: Uniformly grid the spatial area corresponding to the crop pest and disease monitoring points to obtain a uniformly gridded pest and disease occurrence area; Step S32: Based on the uniformly gridded pest and disease occurrence area, conduct a regional time-series outbreak analysis of the regional pest and disease occurrence density to obtain the grid diffusion outbreak development pattern corresponding to the change of regional pest and disease occurrence over time; Step S33: Design meteorological conditions through the temperature, humidity, precipitation, and light intensity corresponding to the regional meteorological data to generate the regional meteorological distribution conditions; Step S34: Based on the regional meteorological distribution conditions, conduct a pest and disease outbreak mining analysis on the grid diffusion outbreak development pattern corresponding to the change of regional pest and disease occurrence over time to obtain the regional pest and disease outbreak characteristic pattern corresponding to the meteorological conditions; Step S35: Based on the uniformly gridded pest and disease occurrence area, conduct a soil fertility correlation analysis of the regional crop soil fertility degree and the regional pest and disease occurrence density to obtain the correlation characteristic relationship between the regional soil fertility and the pest and disease outbreak.

[0011] Furthermore, step S35 includes the following steps: Step S351: Based on the uniformly gridded pest and disease occurrence area, conduct grid division on the regional crop soil fertility degree and the regional pest and disease occurrence density to obtain the crop soil fertility degree and the pest and disease occurrence density values corresponding to the same uniform grid; Step S352: According to the crop soil fertility degree and the pest and disease occurrence density values corresponding to the same uniform grid, conduct a correlation metric calculation to obtain the correlation coefficient between the crop soil fertility and the pest and disease occurrence density within each uniform grid; Step S353: Based on the correlation coefficient between the crop soil fertility and the pest and disease occurrence density within each uniform grid, conduct a soil fertility correlation analysis of the regional crop soil fertility degree and the regional pest and disease occurrence density to obtain the correlation characteristic relationship between the regional soil fertility and the pest and disease outbreak.

[0012] Furthermore, step S4 includes the following steps: Step S41: Based on the regional pest and disease outbreak characteristic pattern corresponding to the meteorological conditions, conduct a meteorological pest and disease impact analysis on the distribution law of the corresponding pests and diseases at the crop pest and disease monitoring points in the geographical space to obtain the regional pest and disease outbreak meteorological impact factors; Step S42: Based on the correlation characteristic relationship between the regional soil fertility and the pest and disease outbreak, conduct a soil fertility pest and disease correlation analysis on the distribution law of the corresponding pests and diseases at the crop pest and disease monitoring points in the geographical space to obtain the regional soil fertility pest and disease outbreak correlation factors; Step S43: Perform multi-source factor risk prediction on the crop pest and disease monitoring points based on the meteorological impact factors of regional pest and disease outbreaks and the associated factors of regional soil fertility and pest and disease outbreaks, so as to obtain the regional pest and disease outbreak risk prediction results, including the predicted outbreak risk levels of pests and diseases corresponding to the monitoring point areas; Step S44: Conduct prevention and control decision-making support analysis based on the regional pest and disease outbreak risk prediction results, and generate a prevention and control suggestion plan for the pest and disease outbreak area, including the selection of pesticides for pests and diseases, the dosage and duration of use, and the implementation of biological control measures.

[0013] Furthermore, the present invention also provides a risk prediction system for the process mining of pest and disease outbreaks based on multi-source factors, which is used to execute the risk prediction method for the process mining of pest and disease outbreaks based on multi-source factors as described above. The risk prediction system for the process mining of pest and disease outbreaks based on multi-source factors includes: A real-time monitoring module for crop regions, which is used to measure in real time the regional meteorological data, the degree of regional crop soil fertility, and the regional pest and disease occurrence data corresponding to the crop pest and disease monitoring points, where the regional pest and disease occurrence data includes the number of pest and disease occurrences, the time of pest and disease occurrences, and the locations of pest and disease occurrences; A pest and disease occurrence density calculation module, which is used to obtain the corresponding pesticide spraying usage amount through the crop pest and disease monitoring points, and calculate the regional occurrence density of the regional pest and disease occurrence data based on the pesticide spraying usage amount to obtain the regional pest and disease occurrence density; A pest and disease outbreak feature mining module, which is used to conduct pest and disease outbreak mining analysis on the regional pest and disease occurrence density based on the regional meteorological data and the degree of regional crop soil fertility, so as to obtain the corresponding regional pest and disease outbreak feature patterns under meteorological conditions and the associated feature relationships between regional soil fertility and pest and disease outbreaks; A multi-source factor risk prediction module for pests and diseases, which is used to perform multi-source factor risk prediction on the crop pest and disease monitoring points based on the corresponding regional pest and disease outbreak feature patterns under meteorological conditions and the associated feature relationships between regional soil fertility and pest and disease outbreaks, so as to obtain the regional pest and disease outbreak risk prediction results; conduct prevention and control decision-making support analysis based on the regional pest and disease outbreak risk prediction results, and thus generate a prevention and control suggestion plan for the pest and disease outbreak area.

[0014] Advantages of the present invention: 1. The risk prediction method for pest and disease outbreak process mining based on multi-source factors proposed by the present invention, compared with the prior art, the beneficial effects of the present application are that by measuring in real time the meteorological data, soil fertility degree and pest and disease occurrence data corresponding to the pest and disease monitoring points of crops, it can provide important basic information for subsequent pest and disease monitoring and early warning. The meteorological data includes factors such as temperature, humidity, precipitation and light intensity, which directly affect the occurrence and development of pests and diseases; the soil fertility data reflects the nutritional status of the soil, such as acidity and alkalinity, nitrogen, phosphorus, potassium content, and the prosperity degree of the microbial community, etc. And through the statistical analysis of the occurrence quantity, time and location of pests and diseases, the occurrence law and regional characteristics of pests and diseases can be understood, providing accurate reference for subsequent prediction and prevention. In this way, the timeliness of monitoring can be ensured through the collection of real-time data, enabling farmers and farm managers to take prevention and control measures in a timely manner at the initial stage of pest and disease occurrence, reducing potential economic losses. It provides data support for subsequent pest and disease prevention and control and agricultural production management, helping agricultural management departments and farmers to make more scientific and accurate decisions. Secondly, by obtaining the corresponding pesticide spraying usage amount through the pest and disease monitoring points of crops, and based on the pesticide spraying usage amount, the regional occurrence density of the pest and disease occurrence data in the area is calculated. The relationship between pesticide use and pest and disease occurrence can be further analyzed. The key to this step is to infer the severity of pest and disease occurrence through the pesticide use situation, so as to achieve a more accurate calculation of the pest and disease occurrence density. If the pesticide use amount in a region is too high, it means that the pest and disease occurrence density in that region is large, and vice versa, it means that the pest and disease occurrence is relatively mild. Through the calculation of the regional occurrence density, it can be more clearly identified which areas have more frequent pest and disease occurrences, and thus provide a basis for the next prevention and control decision. The data of the pesticide spraying amount helps to determine the spatio-temporal distribution characteristics of pest and disease occurrence, helps to evaluate the effect of the current pest and disease prevention and control measures. This data calculation also helps to provide a more accurate risk assessment for agricultural production and prevention and control work, ensuring the timeliness and effectiveness of pest and disease prevention and control measures. Then, through the outbreak mining analysis of the pest and disease occurrence density based on the regional meteorological data and the crop soil fertility degree, the outbreak law of pests and diseases under different climatic conditions and soil environments can be revealed. The beneficial effect of this analysis is that by analyzing the relationship between these factors and the pest and disease occurrence density, a characteristic pattern of regional pest and disease outbreaks can be constructed, further predicting the future pest and disease outbreak trend, so as to fully consider the comprehensive impact of various factors such as environment, climate, and soil fertility quality on pest and disease outbreaks.Finally, by conducting a multi-source factor risk prediction on crop pest and disease monitoring points based on the corresponding regional pest and disease outbreak characteristic patterns under meteorological conditions and the correlation characteristic relationship between regional soil fertility and pest and disease outbreaks, a multi-dimensional risk assessment model can be constructed. This model can comprehensively predict the occurrence risks of pests and diseases for different agricultural production regions, provide early warning information for farmers in advance, improve the accuracy and reliability of prediction results, effectively reduce the damage of pests and diseases to crops, and avoid yield losses caused by pest and disease outbreaks. By generating regional control suggestion plans, personalized control strategies can be provided to help farmers take appropriate pesticide spraying, irrigation, fertilization and other measures at the most suitable time, thereby effectively reducing the occurrence of pests and diseases.

[0015] 2. The risk prediction system for pest and disease outbreak process mining based on multi-source factors proposed by the present invention is generally composed of a real-time monitoring module for crop regions, a calculation module for pest and disease occurrence density, a mining module for pest and disease outbreak characteristics, and a risk prediction module for multi-source factors of pests and diseases. It can implement any risk prediction method for pest and disease outbreak process mining based on multi-source factors of the present invention, and is used to realize the risk prediction method for pest and disease outbreak process mining based on multi-source factors through the operation between computer programs running on each module. The internal structure of the system cooperates with each other, which can greatly reduce repetitive work and manpower input, quickly and effectively provide a more accurate and efficient risk prediction process for pest and disease outbreak process mining based on multi-source factors, thereby simplifying the operation process of the risk prediction system for pest and disease outbreak process mining based on multi-source factors. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Other features, objects, and advantages of the present invention will become more apparent by reading the detailed description of non-limiting embodiments with reference to the following drawings: Figure 1 It is a schematic flowchart of the steps of the risk prediction method for pest and disease outbreak process mining based on multi-source factors of the present invention; Figure 2 For Figure 1 a detailed schematic flowchart of step S1 in Figure 3 For Figure 2 a detailed schematic flowchart of step S13 in DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] The technical method of the present invention will be clearly and completely described below with reference to the drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative work fall within the scope of protection of the present invention.

[0018] In addition, the drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities may be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0019] It should be understood that although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0020] To achieve the above object, please refer to Figures 1 to 2 , the present invention provides a risk prediction method for pest and disease outbreak process mining based on multi-source factors, and the method includes the following steps: Step S1: By measuring in real time the regional meteorological data, the regional crop soil fertility degree, and the regional pest and disease occurrence data corresponding to the pest and disease monitoring points of the crops, wherein the regional pest and disease occurrence data includes the number of pest and disease occurrences, the time of pest and disease occurrences, and the location of pest and disease occurrences; Step S2: Obtain the corresponding pesticide spraying usage amount through the pest and disease monitoring points of the crops, and calculate the regional occurrence density of the regional pest and disease occurrence data based on the pesticide spraying usage amount to obtain the regional pest and disease occurrence density; Step S3: Based on the regional meteorological data and the regional crop soil fertility degree, conduct pest and disease outbreak mining analysis on the regional pest and disease occurrence density to obtain the corresponding regional pest and disease outbreak characteristic pattern under the meteorological conditions and the correlation characteristic relationship between the regional soil fertility and the pest and disease outbreak; Step S4: Based on the corresponding regional pest and disease outbreak characteristic pattern under the meteorological conditions and the correlation characteristic relationship between the regional soil fertility and the pest and disease outbreak, conduct multi-source factor risk prediction on the pest and disease monitoring points of the crops to obtain the regional pest and disease outbreak risk prediction result; conduct prevention and control decision support analysis according to the regional pest and disease outbreak risk prediction result, and generate a prevention and control suggestion plan for the pest and disease outbreak area.

[0021] In the embodiments of the present invention, please refer to Figure 1As shown in the figure, it is a schematic diagram of the step flow of the risk prediction method for pest and disease outbreak process mining based on multi-source factors according to the present invention. In this example, the risk prediction method for pest and disease outbreak process mining based on multi-source factors includes the following steps: Step S1: Real-time measure the regional meteorological data, regional crop soil fertility degree, and regional pest and disease occurrence data corresponding to the crop pest and disease monitoring points, where the regional pest and disease occurrence data includes the number of pest and disease occurrences, the time of pest and disease occurrences, and the locations of pest and disease occurrences; In the embodiment of the present invention, by obtaining the meteorological data corresponding to different pest and disease monitoring points in this region, the meteorological data includes, but is not limited to, information such as temperature, humidity, wind speed, precipitation, and light duration. The collection of meteorological data can be achieved through meteorological stations installed in farmland or by obtaining historical meteorological records through network platforms. Immediately afterwards, it is necessary to collect the soil fertility data of regional crops, including indicators such as the organic matter content of the soil, the concentrations of main fertilizer elements such as nitrogen, phosphorus, and potassium, and the pH value. These soil data can be obtained by on-site sampling and sent to a soil analysis laboratory for testing, or can be monitored and recorded in real time through farmland sensors. In addition, it is also necessary to collect the pest and disease occurrence data in the region, which includes information such as the number of pest and disease occurrences, the specific time of occurrence, and the occurrence locations. Usually, it is obtained through pest and disease monitoring networks, remote sensing data collection, or manual inspections. The number of pests and diseases is usually counted based on sample plot surveys. The real-time acquisition of these data ensures the timeliness of subsequent data processing and provides the necessary basic information for subsequent analysis.

[0022] Step S2: Obtain the corresponding pesticide spraying usage amount through the crop pest and disease monitoring points, and calculate the regional occurrence density of the regional pest and disease occurrence data based on the pesticide spraying usage amount to obtain the regional pest and disease occurrence density; In the embodiment of the present invention, through the crop pest and disease monitoring points, obtain the pesticide spraying usage amount data of this region. The acquisition of the pesticide spraying amount can be achieved through the monitoring device installed on the pesticide spraying equipment. The spraying amount data recorded by the equipment can be transmitted to the cloud platform in real time for storage and processing. Based on the amount of pesticide spraying, it is necessary to calculate the density of the pest and disease occurrence data in the region. The calculation of the regional pest and disease occurrence density is determined based on the size of the pest and disease occurrence range and the attenuation of the pest and disease distribution by the sprayed pesticide. When calculating, first define the spatial distribution range of the pests and diseases, and combine the actual effect of the sprayed pesticide to calculate the pest and disease density in different regions. In some special cases, the GIS (Geographic Information System) technology can be used to calculate the spatial distribution of the pest and disease occurrence density at different monitoring points through the spatial analysis function to obtain a more accurate pest and disease density distribution map, and finally obtain the regional pest and disease occurrence density.

[0023] Step S3: Based on the regional meteorological data and the regional crop soil fertility degree, conduct pest and disease outbreak mining analysis on the regional pest and disease occurrence density to obtain the corresponding regional pest and disease outbreak characteristic patterns under meteorological conditions and the correlation characteristic relationship between regional soil fertility and pest and disease outbreaks; In the embodiments of the present invention, by statistically analyzing historical pest and disease occurrence data and meteorological data, a regression model or a machine learning model can be established to reveal how meteorological factors (such as temperature, humidity, precipitation, etc.) affect the outbreak of pests and diseases. For example, certain pests and diseases are prone to break out under high-temperature and humid climate conditions, while certain pests break out more severely under drought conditions. By mining these correlation patterns, a prediction model of meteorological conditions and pest and disease occurrence can be established, so as to predict and analyze the corresponding regional pest and disease outbreak characteristic patterns under meteorological conditions. At the same time, it is also necessary to analyze the impact of soil fertility in the region on pest and disease outbreaks. The concentration of fertilizer elements in the soil will affect the growth of crops, and thus affect the incidence of pests and diseases. High-fertility soil will promote the reproduction of certain pests and diseases, while certain soils inhibit the growth of pests and diseases. By comparing and analyzing the soil fertility levels and pest and disease occurrence data in different regions, the specific impact of different soil fertility levels on pest and disease outbreaks can be revealed, and finally the correlation characteristic relationship between soil fertility and pest and disease outbreaks can be clearly obtained.

[0024] Step S4: Based on the corresponding regional pest and disease outbreak characteristic patterns under meteorological conditions and the correlation characteristic relationship between regional soil fertility and pest and disease outbreaks, conduct multi-source factor risk prediction on crop pest and disease monitoring points to obtain the regional pest and disease outbreak risk prediction results; conduct prevention and control decision support analysis according to the regional pest and disease outbreak risk prediction results, and generate a prevention and control suggestion plan for the pest and disease outbreak area.

[0025] In the embodiments of the present invention, based on the regional pest and disease outbreak characteristic patterns under the meteorological conditions obtained in the foregoing steps and the correlation characteristic relationship between soil fertility and pest and disease outbreaks, the risk of pest and disease outbreaks is predicted. Based on these data, a multi-source data fusion model can be constructed, considering multiple factors such as meteorological factors, soil fertility, and the density of historical pest and disease occurrences. Statistical models or deep learning algorithms (such as neural networks, decision trees, etc.) are used to predict the risk of pest and disease outbreaks. This process requires weighting multiple factors to obtain the final risk assessment value. After the risk prediction is completed, a pest and disease control advice plan for different regions is further generated through data analysis. The advice plan includes specific control measures, such as suggesting an increase in the amount of pesticides used or adjusting the spraying time, or taking other non-chemical control measures (such as planting pest-resistant crop varieties). At the same time, based on the short-term prediction of meteorological forecast data, timely warnings can be made for upcoming pest and disease events in the next few days or weeks, and a dynamically adjusted control plan is provided. These decision support analyses will help farmers or agricultural managers respond more precisely to pest and disease outbreaks, thereby minimizing crop losses and finally generating a pest and disease control advice plan for the outbreak area.

[0026] Further, step S1 includes the following steps: Step S11: Real-time measure the regional meteorological data corresponding to the crop pest and disease monitoring points through a meteorological monitoring station network, including the temperature, humidity, precipitation, and light intensity corresponding to the monitoring point area; Step S12: Real-time monitor and collect the regional soil conditions corresponding to the crop pest and disease monitoring points through soil sensors to obtain regional crop soil condition data, including the soil pH value of regional crops, the soil fertility content index of regional crops, and the prosperity degree of regional crop soil microorganisms; Step S13: Calculate the regional soil fertility of the crop pest and disease monitoring points based on the regional crop soil condition data to obtain the degree of regional crop soil fertility; Step S14: Real-time measure the regional pest and disease occurrence data corresponding to the crop pest and disease monitoring points through daily pest and disease reporting records, including the number of pest and disease occurrences, the time of pest and disease occurrences, and the location of pest and disease occurrences.

[0027] As an embodiment of the present invention, refer to Figure 2 shown, for Figure 1 the detailed step flow diagram of step S1 in Step S11: Real-time measure the regional meteorological data corresponding to the crop pest and disease monitoring points through a meteorological monitoring station network, including the temperature, humidity, precipitation, and light intensity corresponding to the monitoring point area; In the embodiments of the present invention, meteorological data of the area corresponding to the crop pest and disease monitoring point is measured in real time through a meteorological monitoring station network. In this step, multiple meteorological monitoring stations are deployed in the crop planting area to continuously collect meteorological parameters such as temperature, humidity, precipitation, and light intensity. Temperature and humidity are monitored in real time by sensors in the meteorological station and uploaded to the central database to record accurate temperature changes and humidity fluctuations. Precipitation is automatically sensed by a rain gauge and the intensity and duration of precipitation are calculated, and the data is transmitted to the cloud in a timely manner for analysis. Light intensity is collected by a light sensor, and the data is uploaded to the monitoring system through a wireless network, and finally the meteorological data of the area corresponding to the crop pest and disease monitoring point is obtained.

[0028] Step S12: The soil condition of the area corresponding to the crop pest and disease monitoring point is monitored and collected in real time through a soil sensor to obtain the soil condition data of the regional crops, including the soil pH value of the regional crops, the soil fertility content index of the regional crops, and the prosperity degree of soil microorganisms in the regional crops. In the embodiments of the present invention, the soil condition of the area corresponding to the crop pest and disease monitoring point is monitored in real time by using a soil sensor. In this step, multiple soil sensors are installed in the crop planting area. These sensors can accurately detect the soil pH value, fertility content, and the prosperity degree of microorganisms. The soil pH value is measured by a pH monitoring sensor to monitor whether the soil environment is suitable for crop growth and the occurrence of pests and diseases that may be affected. The soil fertility content is realized through a series of chemical sensors, specifically monitoring the content of the three main nutrient elements of nitrogen, phosphorus, and potassium in the soil, and the data is uploaded to the cloud in real time. The prosperity degree of soil microorganisms is captured by a specific microorganism sensor. The sensor feeds back the soil biological activity data by detecting the number and activity of the microorganism population in the soil. The real-time data will be integrated and analyzed to obtain the specific performance of the soil condition of the regional crops, and finally the soil condition data of the regional crops is obtained.

[0029] Step S13: Based on the soil condition data of the regional crops, the regional soil fertility of the crop pest and disease monitoring point is calculated to obtain the degree of regional soil fertility of the crops. In the embodiments of the present invention, through the obtained soil condition data of the regional crops, soil fertility calculation is carried out, and the soil fertility of each monitoring point in the region is evaluated through an algorithm. First, the content of elements such as nitrogen, phosphorus, and potassium in the soil is weighted and calculated to obtain a fertility index. In addition, combined with the soil pH value and the prosperity degree of microorganisms, the soil health is further evaluated, so as to obtain the comprehensive degree of soil fertility. This process is automatically calculated through a data model to ensure the scientificity and accuracy of the evaluation results. If the soil fertility index is lower than the set standard threshold, the system will generate a warning message, indicating that the area may face the risk of soil infertility, affecting the growth environment of crops, and finally the degree of regional soil fertility of the crops is obtained.

[0030] Step S14: Measure the occurrence data of pests and diseases in the area corresponding to the crop pests and diseases monitoring points in real time through the daily report records of pests and diseases, including the occurrence quantity of pests and diseases, the occurrence time of pests and diseases, and the occurrence location of pests and diseases.

[0031] In the embodiment of the present invention, through the daily report records of pests and diseases, the occurrence data of pests and diseases in the area corresponding to the crop pests and diseases monitoring points is measured in real time. In this step, by using mobile terminal devices (such as smart phones, tablets, etc.), agricultural workers upload the daily observation and report data of pests and diseases to the system. The occurrence quantity, occurrence time, and occurrence location of pests and diseases will be recorded in detail. The system identifies the high-incidence areas, time periods, and types of pests and diseases by regularly summarizing the uploaded pest and disease report records. For example, if a certain pest and disease is reported continuously for several days in a specific area, the system will automatically mark this area as a high-incidence area of pests and diseases. The system performs correlation analysis on this information with meteorological data and soil conditions to further infer the potential risk of pest and disease outbreaks. All records will be stored in the database for future training of pest and disease prediction models, and finally, the occurrence data of pests and diseases in the area corresponding to the crop pests and diseases monitoring points is obtained.

[0032] Further, the regional crop soil fertility content indicators described in step S12 specifically include regional soil nitrogen, phosphorus, and potassium content indicators.

[0033] Further, step S13 includes the following steps: Step S131: Perform fertility attenuation analysis on the soil conditions in the area corresponding to the crop pests and diseases monitoring points based on the regional crop soil pH value to obtain the regional soil pH fertility attenuation index; Step S132: Obtain the regional crop vegetation coverage corresponding to the crop pests and diseases monitoring points, and calculate the vegetation coverage area index for the crop pests and diseases monitoring points based on the regional crop vegetation coverage to obtain the regional crop vegetation coverage area index; Step S133: Based on the regional soil pH fertility attenuation index, the regional crop vegetation coverage area index, the regional crop soil fertility content indicators, and the regional crop soil microbial prosperity degree, use the regional soil fertility calculation formula to calculate the regional soil fertility of the crop pests and diseases monitoring points to obtain the degree of regional crop soil fertility.

[0034] As an embodiment of the present invention, referring to Figure 3 shown, for Figure 2 the detailed step flow schematic diagram of step S13 in Step S131: Based on the soil pH of regional crops, conduct a fertility attenuation analysis on the soil conditions of the areas corresponding to the crop pest and disease monitoring points to obtain the regional soil pH fertility attenuation index; In the embodiments of the present invention, according to the positions of the crop pest and disease monitoring points, soil samples are obtained through the Geographic Information System (GIS). For each soil sample, a soil pH detector is used to measure the pH and obtain its pH value. Then, the pH data of each soil sample is combined with the soil fertility attenuation model to calculate the influence degree of soil pH on soil fertility. At this time, by considering the influence of pH on soil nutrient elements and combining factors such as soil texture, fertility level, and nutrient loss rate, the corresponding fertility attenuation index is obtained. Specifically, if the soil pH is lower than 5.5 (acidic soil), its attenuation index will increase significantly, indicating difficulties in maintaining soil fertility and crop growth; if the soil pH is higher than 7.5 (alkaline soil), it will also have an adverse effect on soil fertility maintenance. On this basis, by analyzing the pH and fertility attenuation conditions of different regions, the soil fertility attenuation index of this region is evaluated, and finally the regional soil pH fertility attenuation index is obtained.

[0035] Step S132: Obtain the corresponding regional crop vegetation coverage through the crop pest and disease monitoring points, and calculate the vegetation coverage area index for the crop pest and disease monitoring points based on the regional crop vegetation coverage to obtain the regional crop vegetation coverage area index; In the embodiments of the present invention, image data of the crops around the monitoring points are obtained through remote sensing satellite images or drone photography. Image processing software (such as ENVI or ArcGIS) is used to process the image data to extract the vegetation information of the crop areas. During the calculation of vegetation coverage, the Normalized Difference Vegetation Index (NDVI) is used to evaluate the growth of ground vegetation. The calculation formula of NDVI is: NDVI = (NIR - RED) / (NIR + RED), where NIR represents the reflectance of the near-infrared band and RED is the reflectance of the red light band. The NDVI value calculated by this formula can be used to evaluate the growth density and health status of crops, thereby reflecting the corresponding regional crop vegetation coverage. Further, spatial analysis of the images is carried out in combination with the Geographic Information System (GIS) to determine the vegetation coverage area index of the area corresponding to the monitoring points. The specific operation is to combine the vegetation coverage distribution with land use conditions, crop types, etc. to obtain the vegetation coverage area index of this region, that is, NDVI × land use area. If the NDVI value of the area corresponding to the monitoring point is high, it indicates that the vegetation coverage of this area is good and the probability of pest and disease occurrence is relatively low; if the NDVI value is low, it indicates poor vegetation coverage and a high risk of pest and disease outbreaks. Finally, the regional crop vegetation coverage area index is obtained.

[0036] Step S133: Based on the regional soil acidity-alkalinity fertility attenuation index, the regional crop vegetation coverage area index, the regional crop soil fertility content index, and the regional crop soil microbial prosperity degree, use the regional soil fertility calculation formula to calculate the regional soil fertility of the crop pest and disease monitoring points, so as to obtain the regional crop soil fertility degree.

[0037] In the embodiment of the present invention, by combining the regional area of the crop pest and disease monitoring points, the spatial position parameters, the regional soil acidity-alkalinity fertility attenuation index, the regional soil nitrogen content, the nitrogen content fertility influence coefficient, the regional soil phosphorus content, the phosphorus content fertility influence coefficient, the regional soil potassium content, the potassium content fertility influence coefficient, the regional crop soil microbial prosperity degree, the regional microbial prosperity contribution coefficient, the regional crop vegetation coverage area index, the vegetation coverage influence coefficient, and related parameters, a suitable regional soil fertility calculation formula is constructed for statistical calculation of soil fertility, so as to quantitatively calculate the specific value of the regional crop soil fertility degree, and finally obtain the regional crop soil fertility degree.

[0038] Further, the regional soil fertility calculation formula described in step S133 is specifically: ; In the formula, is the regional crop soil fertility degree, is the regional area of the crop pest and disease monitoring points, is the spatial position parameter corresponding to the crop pest and disease monitoring points, is the regional soil acidity-alkalinity fertility attenuation index, is the regional soil nitrogen content, is the nitrogen content fertility influence coefficient, is the regional soil phosphorus content, is the phosphorus content fertility influence coefficient, is the regional soil potassium content, is the potassium content fertility influence coefficient, is the corresponding regional crop soil microbial prosperity degree at the spatial position , is the regional microbial prosperity contribution coefficient, is the regional crop vegetation coverage area index, is the vegetation coverage influence coefficient, is the correction coefficient of the regional crop soil fertility degree.

[0039] The present invention has obtained a regional soil fertility calculation formula through the use of a specific mathematical model and verification, which is used to calculate the regional soil fertility of crop pest and disease monitoring points. This regional soil fertility calculation formula quantifies the degree of regional soil fertility by combining multiple factors, including soil pH, nitrogen, phosphorus, and potassium content, microbial prosperity, and vegetation coverage area. This multi-dimensional evaluation method is more comprehensive than single soil component detection and can more accurately reflect the overall health status of the soil. For example, the soil pH fertility decay index reflects the impact of soil acidity and alkalinity on soil fertility. Different crops adapt to different acid-base environments, and the decay index in the formula can reflect its negative impact on soil fertility. The fertility influence coefficients of nitrogen, phosphorus, and potassium reflect the direct impact of the concentrations of these basic nutrient elements on soil fertility, helping to reflect the growth support effect of the chemical composition of regional soil on crops. Soil microbial prosperity is related to the biological activity of the soil. Microbial prosperity can affect soil fertility and the occurrence of pests and diseases because microbial activities contribute to nutrient cycling and pathogen inhibition. The vegetation coverage area index reflects the role of vegetation coverage on soil fertility. When the coverage is relatively high, soil erosion and loss are less, and the fertility is relatively high. The spatial position parameter is introduced into the formula, reflecting the spatial heterogeneity of soil fertility within the region. In practical applications, the fertility level of the soil is often not evenly distributed. Therefore, it is very important to consider spatial variability when evaluating regional fertility. In this way, precise agricultural management and pest and disease prevention and control measures can be implemented according to different soil conditions. The important role of soil microorganisms in soil fertility is particularly emphasized. Microorganisms not only contribute to nutrient decomposition and cycling but also help prevent and control pests and diseases. The microbial prosperity in this formula is listed separately and reflects its contribution to fertility through a contribution coefficient. The diversity and quantity of the microbial community affect the health of the soil, so their role also has an important indirect effect on pest and disease control. In addition, the correction coefficients in this formula can further adjust the calculation results to make the soil fertility evaluation more in line with the actual situation. These correction coefficients can be calibrated through on-site monitoring data to ensure that the calculation of soil fertility is closer to the actual situation and avoid the deviation that may be brought by a single theoretical model. In summary, this formula fully considers the degree of regional crop soil fertility , the area of the regional crop pest and disease monitoring point , the spatial position parameter corresponding to the crop pest and disease monitoring point , the regional soil pH fertility decay index , the regional soil nitrogen content , the nitrogen content fertility influence coefficient , the regional soil phosphorus content , the phosphorus content fertility influence coefficient , the regional soil potassium content , the potassium content fertility influence coefficient , the prosperity degree of crop soil microorganisms in the corresponding area at the spatial position , the regional microorganism prosperity contribution coefficient , the regional crop vegetation coverage area index , the vegetation coverage influence coefficient , the correction coefficient of the regional crop soil fertility degree , according to the regional crop soil fertility degree , the mutual correlation relationship between the regional crop soil fertility degree and the above parameters constitutes a functional relationship , this formula can realize the process of calculating the regional soil fertility of the crop pest and disease monitoring point. At the same time, through the correction coefficient of the regional crop soil fertility degree , the introduction of which can be adjusted according to the error situation in the calculation process, so as to improve the accuracy and applicability of the regional soil fertility calculation formula.

[0040] Further, step S2 includes the following steps: Step S21: Collect the corresponding pesticide usage records through the crop pest and disease monitoring points, and obtain the corresponding pesticide spraying usage amount according to the pesticide usage records; In the embodiment of the present invention, the pesticide usage records are collected through the set crop pest and disease monitoring points. First, using the agricultural Internet of Things technology, the monitoring point devices are connected to the data center to collect pesticide spraying records in real time. Each monitoring point will regularly record the types, spraying amounts, spraying times of pesticides, and the regional information of pesticide usage. By using geographic information system (GIS) and remote sensing technology, combined with the agricultural data management system, the area and specific spraying amount of pesticide spraying can be accurately identified. In addition, combined with the growth stage of crops, meteorological data, and soil characteristic information, the pesticide usage situation is supplemented and verified to ensure the accuracy and integrity of the data. The data is uniformly stored and processed through the data center, and finally the corresponding pesticide spraying usage amount is obtained.

[0041] Step S22: Based on the pesticide spraying usage amount, conduct a pest distribution attenuation assessment analysis on the corresponding pest occurrence quantity in the regional pest and disease occurrence data to obtain the regional pest distribution pesticide usage attenuation factor; In an embodiment of the present invention, based on the pesticide spraying usage amount, a pest distribution attenuation evaluation and analysis is carried out on the corresponding pest occurrence quantity in the regional pest occurrence data. First, a spatial distribution model of the pest occurrence data in the region is established by using a spatial interpolation algorithm (such as Kriging interpolation method). Based on the pesticide spraying amount data, combined with meteorological conditions (temperature, humidity, wind speed, etc.) and terrain characteristics (slope, terrain height, etc.), an attenuation evaluation is carried out on the distribution range and occurrence intensity of pests. The attenuation factor is determined by the combined action of multiple factors, including the amount of spraying, the degradation rate of pesticides, the influence of environmental conditions, etc. Using multivariate regression analysis, by establishing a relationship model between pesticide use and pest occurrence, the distribution of pests is quantitatively attenuated, and the pesticide use attenuation factor is calculated to evaluate the difference between the pesticide use effects in different regions on pest outbreaks. Finally, the pesticide use attenuation factor for regional pest distribution is obtained.

[0042] Step S23: Based on the corresponding pest occurrence locations in the regional pest occurrence data, the area of the occurrence range corresponding to the crop pest monitoring points is statistically calculated to obtain the size of the regional pest occurrence range area. In an embodiment of the present invention, based on the pest occurrence data in the region, the area of the regional occurrence range is statistically calculated for different pest occurrence locations. First, the pest occurrence locations are spatially marked through a Geographic Information System (GIS), and on-site monitoring and image acquisition are carried out using remote sensing images or unmanned aerial vehicle (UAV) aerial photography technology to obtain the precise geographical coordinates of pest occurrences. Then, combined with the specific boundary information of the crop planting area, through spatial analysis tools (such as buffer analysis, area calculation, etc.), the size of the occurrence range of pests is statistically calculated. Using a standardized area calculation method, combined with the historical occurrence data of crop pests, the pest occurrence area is detailedly divided to ensure the accuracy and reliability of the measurement. And by combining environmental monitoring data (such as soil humidity, rainfall, etc.), the regional distribution of pest occurrences is dynamically adjusted to further optimize the estimation of the pest occurrence range area. Finally, the size of the regional pest occurrence range area is obtained.

[0043] Step S24: Based on the pesticide spraying usage amount, the pesticide use attenuation factor for regional pest distribution, and the size of the regional pest occurrence range area, the regional occurrence density of the pest occurrence quantity and the pest occurrence time is calculated using the regional occurrence density calculation formula to obtain the regional pest occurrence density. In the embodiments of the present invention, a suitable regional occurrence density calculation formula is constructed by combining the pesticide spraying usage amount, the pesticide usage attenuation factor for regional pest and disease distribution, the area size of the regional pest and disease occurrence range, the number of pest and disease occurrences, the pest and disease occurrence time, the time variable parameter, and relevant parameters to perform the quantitative calculation of the occurrence density, so as to quantitatively determine the corresponding occurrence situation of pests and diseases in the monitoring point area, and finally obtain the regional pest and disease occurrence density.

[0044] Among them, the specific formula for the regional occurrence density is: ; In the formula, is the regional pest and disease occurrence density, is the pest and disease occurrence time, is the time variable parameter, is the area size of the regional pest and disease occurrence range, is the pesticide spraying usage amount, is at time the corresponding number of pest and disease occurrences, is the regional pest and disease distribution pesticide usage attenuation factor, is the correction coefficient of the regional pest and disease occurrence density.

[0045] The present invention has obtained a regional occurrence density calculation formula through the use of a specific mathematical model and verification, which is used to calculate the regional occurrence density of the number and time of occurrence of pests and diseases. This regional occurrence density calculation formula comprehensively considers multiple key factors (such as the occurrence area of pests and diseases, the amount of pesticide spraying, the number of pests and diseases, the pest and disease distribution attenuation factor, the occurrence time of pests and diseases, etc.), and can comprehensively reflect the occurrence density of pests and diseases in the region. By integrating these factors, the formula helps to accurately describe the spread and development trend of pests and diseases in the region. The time variable and the exponential decay term in the formula can dynamically reflect the impact of pesticide spraying on the occurrence of pests and diseases. As time goes by, the effect of pesticides gradually decays, thus affecting the number of pests and diseases. This dynamic modeling method enables detailed analysis of the occurrence of pests and diseases at different time periods, rather than just providing static results. By introducing the pesticide use attenuation factor, the formula can model the long-term effect of pesticide spraying. The attenuation factor takes into account the gradual weakening of the pesticide effect over time and helps to evaluate the continuous efficacy after pesticide use. This enables accurate measurement of the control effect of pesticides on pests and diseases at different time points, thereby more effectively optimizing pesticide use strategies. Each parameter in the formula, such as the occurrence area of pests and diseases, the amount of pesticide spraying, and the number of pests and diseases, can be specifically quantified. These quantified factors help with actual data analysis, can provide precise decision-making support for agricultural managers, optimize resource allocation, and reduce the risks of overuse of pesticides and environmental pollution. In addition, the correction coefficient in the formula provides the ability to flexibly adjust the calculation results, which means that in case of special situations (such as weather conditions, changes in farmland environment, etc.), the calculation results can be supplemented and corrected by adjusting this correction coefficient, making the prediction results more accurate and in line with the actual situation. In this way, reasonable pesticide spraying strategies, pest and disease control timing, and regional prevention and control measures can be determined based on the prediction results of the regional occurrence density, thereby improving agricultural production efficiency. In summary, this formula fully considers the regional occurrence density of pests and diseases , the occurrence time of pests and diseases , the time variable parameter , the size of the occurrence area of regional pests and diseases , the amount of pesticide spraying , at time , the corresponding number of pests and diseases occurring , the pesticide use attenuation factor for regional pest and disease distribution , the correction coefficient of the regional occurrence density of pests and diseases , according to the regional occurrence density of pests and diseases and the mutual correlation relationship between the above parameters constitutes a functional relationship , this formula can achieve the process of calculating the regional occurrence density of the number and occurrence time of pests and diseases. At the same time, through the correction coefficient of the regional pest and disease occurrence density introduced, it can be adjusted according to the error situation in the calculation process, thereby improving the accuracy and applicability of the regional occurrence density calculation formula.

[0046] Furthermore, step S3 includes the following steps: Step S31: Perform regional uniform grid division on the spatial area corresponding to the crop pest and disease monitoring points to obtain a uniform grid of the pest and disease occurrence area; In the embodiment of the present invention, by performing regional uniform grid division on the spatial area corresponding to the crop pest and disease monitoring points, during the implementation process, first, the data of the crop pest and disease monitoring points need to be collected to obtain the spatial coordinates of each monitoring point and the relevant information of the pest and disease occurrence. Then, use GIS (Geographic Information System) tools to perform spatial distribution analysis on the monitoring point data, divide the monitoring area into uniform grids, and the size of the grids should be set according to the scale of the specific area and the distribution density of the monitoring points to ensure that each grid contains an appropriate number of monitoring points and can comprehensively represent the spatial distribution of the pest and disease occurrence. The pest and disease monitoring data can be converted into the pest and disease occurrence situation of each grid in the area, and finally a uniform grid of the pest and disease occurrence area is obtained.

[0047] Step S32: Perform regional time-series outbreak analysis on the regional pest and disease occurrence density based on the uniform grid of the pest and disease occurrence area to obtain the grid diffusion outbreak development mode corresponding to the change of the regional pest and disease occurrence over time; In the embodiment of the present invention, by performing regional time-series outbreak analysis on the regional pest and disease occurrence density based on the uniform grid of the pest and disease occurrence area, the time-series data provided by the pest and disease monitoring points are used to analyze the pest and disease occurrence situation in each grid, and classify and sort them in terms of time. Based on historical data, use time-series analysis methods (such as ARIMA model, seasonal decomposition, etc.) to model the time-series characteristics of the pest and disease occurrence, identify the outbreak cycle, outbreak time point and outbreak intensity of the pest and disease. Through this process, the time evolution trend and spatial diffusion mode of the pest and disease can be obtained, and the occurrence and spread of the pest and disease in the future period can be predicted. The model analysis results will show the outbreak development mode of the pest and disease in each grid over a period of time, and finally obtain the grid diffusion outbreak development mode corresponding to the change of the regional pest and disease occurrence over time.

[0048] Step S33: Design meteorological conditions through the temperature, humidity, precipitation and light intensity corresponding to the regional meteorological data to generate regional meteorological distribution conditions; In the embodiments of the present invention, meteorological condition design is carried out through the temperature, humidity, precipitation, and light intensity corresponding to regional meteorological data. The acquisition of meteorological data can be through meteorological stations, satellite remote sensing data, or meteorological simulation systems to obtain the specific meteorological data of the corresponding area of each monitoring grid. The core of meteorological condition design is to conduct a detailed modeling of the meteorological conditions at different geographical locations and different time periods within the region. Using meteorological modeling methods, such as interpolation algorithms (e.g., Kriging interpolation or inverse distance weighting method), spatial interpolation is performed on the regional meteorological data to fill the meteorological blank points between monitoring stations. Through this process, the specific meteorological distribution corresponding to each grid point within the region is obtained, including the spatio-temporal distribution characteristics of elements such as temperature, humidity, precipitation, and light intensity, and finally, the regional meteorological distribution conditions are generated.

[0049] Step S34: Based on the regional meteorological distribution conditions, conduct pest and disease outbreak mining and analysis on the grid diffusion outbreak development pattern corresponding to the change of regional pest and disease occurrence over time, and obtain the corresponding regional pest and disease outbreak characteristic pattern under meteorological conditions; In the embodiments of the present invention, through conducting pest and disease outbreak mining and analysis on the grid diffusion outbreak development pattern corresponding to the change of regional pest and disease occurrence over time based on the regional meteorological distribution conditions, the implementation of this step requires in-depth analysis by combining meteorological data with the spatio-temporal change patterns of pests and diseases. Multifactor analysis methods, such as multiple regression analysis, random forest, support vector machine, etc., are used to explore the influence law of meteorological conditions on pest and disease outbreaks. First, match the meteorological data of each grid with the corresponding pest and disease occurrence situation, construct a relationship model between pest and disease outbreaks and meteorological conditions, and identify the specific influence of meteorological factors on pest and disease occurrence by analyzing historical data, such as whether the changes in temperature and humidity promote the reproduction and spread of pests and diseases, and whether precipitation leads to the rapid spread of pests and diseases. Through this analysis, the meteorological characteristic pattern of pest and disease outbreaks can be obtained, and finally, the corresponding regional pest and disease outbreak characteristic pattern under the corresponding meteorological conditions can be obtained.

[0050] Step S35: Based on the uniform grid of the pest and disease occurrence area, conduct soil fertility correlation analysis on the degree of regional crop soil fertility and the density of regional pest and disease occurrence, and obtain the correlation characteristic relationship between regional soil fertility and pest and disease outbreaks.

[0051] In the embodiments of the present invention, through soil fertility correlation analysis of the soil fertility degree of regional crops and the occurrence density of regional pests and diseases based on a uniform grid of the pest and disease occurrence area, in this step, first, it is necessary to collect the soil fertility data of crops in the area, including indicators such as the nutrient content, pH value, and soil type of the soil. Using soil sampling techniques, soil data is obtained through laboratory analysis or sensor monitoring. Then, combined with the density data of the occurrence of pests and diseases in the area, correlation analysis methods such as Pearson correlation coefficient or Granger causality test are used to quantitatively analyze the relationship between soil fertility and the occurrence of pests and diseases. By analyzing the impact of soil fertility changes on the outbreak of pests and diseases, it is possible to identify whether the lack or excess of certain specific nutrient elements in the soil promotes the occurrence and spread of pests and diseases. For example, low nitrogen or excessive phosphorus content in certain soils leads to the outbreak of specific pests. Finally, the correlation characteristic relationship between regional soil fertility and the outbreak of pests and diseases is obtained, that is, whether there is a positive or negative correlation between the corresponding soil fertility and the outbreak of pests and diseases in the monitoring point area.

[0052] Further, step S35 includes the following steps: Step S351: Based on a uniform grid of the pest and disease occurrence area, divide the soil fertility degree of regional crops and the occurrence density of regional pests and diseases to obtain the corresponding crop soil fertility degree and pest and disease occurrence density values under the same uniform grid; In the embodiments of the present invention, by selecting a research area and dividing it into uniform grids, the division of this area should be based on the spatial characteristics of the pest and disease occurrence area and the distribution of crop soil fertility, ensuring that the boundaries of the grids can better cover the pest and disease occurrence density and soil fertility data in the area. The size of each grid should be suitable for the agricultural planting structure in this area. Usually, the scale of the grid is determined according to the density of crop planting and the distribution range of pests and diseases. Remote sensing technology and geographic information system (GIS) tools are used to collect the crop planting information and soil sample fertility data in the area. Through satellite images and ground sampling, the soil fertility data in each grid is extracted, including the organic matter content of the soil, the concentration of nutrient elements such as nitrogen, phosphorus, and potassium, and the specific data of the occurrence of pests and diseases. The soil fertility degree and pest and disease occurrence density values of each grid are recorded in the grid and used for subsequent correlation analysis. Finally, the corresponding crop soil fertility degree and pest and disease occurrence density values under the same uniform grid are obtained.

[0053] Step S352: Calculate the correlation metric according to the corresponding crop soil fertility degree and pest and disease occurrence density values under the same uniform grid to obtain the correlation coefficient between the crop soil fertility and the pest and disease occurrence density in each uniform grid; In the embodiments of the present invention, by selecting an appropriate statistical analysis method for correlation measurement according to the soil fertility degree and the occurrence density value of pests and diseases of each grid obtained previously, in order to accurately calculate the correlation coefficient between soil fertility and the occurrence density of pests and diseases, classic correlation analysis methods such as Pearson correlation coefficient and Spearman rank correlation coefficient can be selected. According to the soil fertility value and the occurrence density value of pests and diseases in each uniform grid, pair them one by one and calculate their correlation. In this process, first, standardize the data of each grid to eliminate the influence between different dimensions. Subsequently, use computer software (such as the SciPy library in Python or the correlation analysis tool in R language) to calculate the correlation, and obtain the correlation coefficient within each grid. Through the calculation results, the positive or negative correlation relationship between soil fertility and the occurrence density of pests and diseases can be identified, and finally, the correlation coefficient between the soil fertility of crops and the occurrence density of pests and diseases within each uniform grid is obtained.

[0054] Step S353: Based on the correlation coefficients between the soil fertility of crops and the occurrence density of pests and diseases within each uniform grid, conduct soil fertility correlation analysis on the soil fertility degree of regional crops and the occurrence density of regional pests and diseases, and obtain the association characteristic relationship between regional soil fertility and pest and disease outbreaks.

[0055] In the embodiments of the present invention, by selecting an appropriate clustering algorithm to analyze the association characteristics of soil fertility and the occurrence density of pests and diseases in the region according to the correlation coefficients obtained by previous quantitative calculations in each uniform grid, hierarchical clustering or K-means clustering methods can be used to classify the correlation coefficients of different grids, and the grids with similar correlation coefficients are grouped into the same category. Analyze the association relationship between the soil fertility characteristics and the occurrence density of pests and diseases of these grids. Through further analysis of the clustering results, the potential relationship between soil fertility and pest and disease outbreaks in different regions can be revealed. For example, some high-fertility regions are related to a higher occurrence density of pests and diseases, while some low-fertility regions show a lower occurrence density of pests and diseases. Combining factors such as regional climate and crop type, use regression analysis or neural network models to further establish a non-linear relationship model between soil fertility and the occurrence density of pests and diseases, and finally obtain the association characteristic relationship between regional soil fertility and pest and disease outbreaks, that is, whether there is a positive or negative correlation between the corresponding soil fertility and pest and disease outbreaks in the monitoring point region.

[0056] Further, step S4 includes the following steps: Step S41: Based on the characteristic pattern of regional pest and disease outbreaks corresponding to meteorological conditions, conduct meteorological pest and disease impact analysis on the distribution law of corresponding pests and diseases of crop pest and disease monitoring points in geographical space, and obtain regional pest and disease outbreak meteorological impact factors; In the embodiments of the present invention, by collecting and collating historical meteorological data of pest and disease monitoring points, including factors such as temperature, humidity, precipitation, wind speed, light intensity, etc., and through statistical analysis methods (such as regression analysis and principal component analysis), the correlation between different meteorological conditions and the outbreak of pests and diseases is identified. Using Geographic Information System (GIS) to conduct spatial analysis on meteorological data and monitoring point data, and matching the meteorological data with the outbreak patterns of different pest and disease types to reveal the distribution characteristics of various pests and diseases under different meteorological conditions. Then, according to the analysis results, meteorological factors affecting the outbreak of pests and diseases (such as temperature fluctuations, humidity changes, precipitation frequency, etc.) are extracted, and their influence degrees on the outbreak of pests and diseases in different regions are quantified. Finally, regional meteorological impact factors for the outbreak of pests and diseases are generated.

[0057] Step S42: Based on the correlation characteristic relationship between regional soil fertility and the outbreak of pests and diseases, conduct soil fertility-pest and disease association analysis on the distribution law of corresponding pests and diseases at crop pest and disease monitoring points in the geographical space to obtain regional soil fertility-pest and disease outbreak association factors; In the embodiments of the present invention, by combining the previously analyzed correlation characteristic relationship between regional soil fertility and the outbreak of pests and diseases, conduct statistical analysis on the distribution law of corresponding pests and diseases in the geographical space, in combination with the historical records of regional pest and disease outbreaks, use multivariate statistical analysis methods (such as multiple linear regression or support vector machine) to analyze the relationship between soil fertility factors and the outbreak of pests and diseases. By comparing and analyzing the outbreak patterns of pests and diseases in different soil type regions, identify which soil fertility characteristics have a significant impact on the outbreak of pests and diseases, and quantify the soil fertility factors according to their influence degrees. Then, combine the analysis results with the geographical distribution of monitoring points using GIS technology to obtain the soil fertility-pest and disease outbreak association factors for specific regions. This factor reveals the possible influence degree of soil fertility in different regions on the outbreak of pests and diseases, and finally obtains regional soil fertility-pest and disease outbreak association factors.

[0058] Step S43: Based on the regional meteorological impact factors for the outbreak of pests and diseases and the regional soil fertility-pest and disease outbreak association factors, conduct multi-source factor risk prediction on crop pest and disease monitoring points to obtain the regional pest and disease outbreak risk prediction results, including the predicted outbreak risk level of pests and diseases corresponding to the monitoring point region; In the embodiment of the present invention, by combining the meteorological impact factors obtained in step S41 with the soil fertility correlation factors obtained in step S42, an input model of multi-source data is constructed. By using machine learning algorithms (such as random forest, decision tree or deep learning network), the historical data of pest and disease outbreaks is trained to predict the risk level of pest and disease occurrence under specific meteorological and soil conditions. The data input into the model includes meteorological data, soil fertility data and historical pest and disease outbreak information of each monitoring point. After the model is trained, for each pest and disease monitoring point, the model will output a risk level indicating the possibility of pest and disease outbreak. The risk level is classified according to the specific distribution area, such as low risk, medium risk and high risk, so as to make targeted decisions for the prevention and control of regional crop pests and diseases, and finally obtain the risk prediction result of regional pest and disease outbreaks.

[0059] Step S44: Conduct prevention and control decision support analysis based on the risk prediction result of regional pest and disease outbreaks, and generate a prevention and control suggestion plan for the pest and disease outbreak area, including the selection of pest and disease pesticides, the dosage and duration of use, and the implementation of biological control measures.

[0060] In the embodiment of the present invention, by combining the previously obtained risk prediction result of pest and disease outbreaks with the growth cycle of crops and the characteristics of different pest and disease types, targeted prevention and control decisions are made. In high-risk areas, pesticides specific to certain pests and diseases are recommended, and specific suggestions on the dosage and duration of use are given. At this time, the selection of pesticides is optimized based on the sensitivity of pests and diseases, the action mechanism of pesticides and the changes in meteorological conditions (such as temperature, humidity, etc.) to improve the prevention and control effect. For medium- and low-risk areas, biological control measures such as the introduction of natural enemies and the release of parasites can be recommended to reduce the use of chemical pesticides and the environmental burden. At the same time, in order to improve the prevention and control effect, dynamic adjustment is also required according to the changes in meteorological data and soil fertility. Through these prevention and control suggestions, farmers can take precise measures in actual operations to effectively control the spread of pests and diseases, and finally generate a prevention and control suggestion plan for the pest and disease outbreak area.

[0061] Furthermore, the present invention also provides a risk prediction system for pest and disease outbreak process mining based on multi-source factors, which is used to execute the risk prediction method for pest and disease outbreak process mining based on multi-source factors as described above. The risk prediction system for pest and disease outbreak process mining based on multi-source factors includes: A real-time monitoring module for crop areas, which is used to measure in real time the regional meteorological data, the degree of regional crop soil fertility and the regional pest and disease occurrence data corresponding to the pest and disease monitoring points of crops, where the regional pest and disease occurrence data includes the number of pest and disease occurrences, the time of pest and disease occurrences and the location of pest and disease occurrences; The pest and disease occurrence density calculation module is used to obtain the corresponding pesticide spraying usage amount through the crop pest and disease monitoring points, and calculate the regional occurrence density of the regional pest and disease occurrence data based on the pesticide spraying usage amount to obtain the regional pest and disease occurrence density; The pest and disease outbreak characteristic mining module is used to conduct pest and disease outbreak mining analysis on the regional pest and disease occurrence density based on the regional meteorological data and the regional crop soil fertility degree, so as to obtain the corresponding regional pest and disease outbreak characteristic pattern under the meteorological conditions and the correlation characteristic relationship between the regional soil fertility and the pest and disease outbreak; The pest and disease multi-source factor risk prediction module is used to conduct multi-source factor risk prediction on the crop pest and disease monitoring points based on the corresponding regional pest and disease outbreak characteristic pattern under the meteorological conditions and the correlation characteristic relationship between the regional soil fertility and the pest and disease outbreak to obtain the regional pest and disease outbreak risk prediction result; conduct prevention and control decision-making support analysis according to the regional pest and disease outbreak risk prediction result, so as to generate a prevention and control suggestion plan for the pest and disease outbreak area.

[0062] Therefore, from any perspective, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, it is intended to cover all changes falling within the meaning and scope of the equivalent elements of the application documents within the present invention.

[0063] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for predicting the risk of pest outbreaks based on multi-source factors, characterized in that: The following steps are involved: Step S1: Real-time measurement of regional meteorological data, regional crop soil fertility and regional pest and disease occurrence data corresponding to the crop pest and disease monitoring point, wherein the regional pest and disease occurrence data includes the number of pest and disease occurrences, the time of pest and disease occurrence and the location of pest and disease occurrence; Step S2: obtaining the corresponding pesticide spraying usage through the crop pest monitoring points, and performing regional occurrence density calculation on the regional pest occurrence data based on the pesticide spraying usage to obtain the regional pest occurrence density; Step S3: Based on regional meteorological data and regional crop soil fertility, the regional pest and disease outbreak mining analysis is performed on the regional pest and disease outbreak density to obtain the corresponding regional pest and disease outbreak characteristic pattern under meteorological conditions and the correlation characteristic relationship between regional soil fertility and pest and disease outbreak; Step S4: Based on the regional pest and disease outbreak characteristic patterns corresponding to meteorological conditions and the correlation characteristic relationship between regional soil fertility and pest and disease outbreaks, multi-source factor risk prediction is performed on crop pest and disease monitoring points to obtain regional pest and disease outbreak risk prediction results; prevention and control decision support analysis is performed based on the regional pest and disease outbreak risk prediction results to generate regional pest and disease outbreak prevention and control recommendation plans.

2. The method for predicting the risk of pest outbreaks based on multi-source factors according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Real-time measurement of regional meteorological data corresponding to the crop disease and insect pest monitoring point through a meteorological monitoring station network, including temperature, humidity, precipitation and light intensity corresponding to the monitoring point area; Step S12: Real-time monitoring and collection of regional soil conditions corresponding to the crop disease and insect pest monitoring points are performed using soil sensors to obtain regional crop soil condition data, including regional crop soil pH, regional crop soil fertility content index, and regional crop soil microbial prosperity; Step S13: Calculating the regional soil fertility of the crop pest and disease monitoring points based on the regional crop soil condition data to obtain the regional crop soil fertility level; Step S14: Real-time measurement of regional pest and disease occurrence data corresponding to the crop pest and disease monitoring point through daily pest and disease reporting records, including the number of pest and disease occurrences, the time of pest and disease occurrence, and the location of pest and disease occurrence.

3. The method for predicting the risk of pest outbreaks based on multi-source factors according to claim 2, characterized in that: The regional crop soil fertility content index in step S12 specifically includes regional soil nitrogen, phosphorus and potassium content indexes.

4. The method for predicting the risk of pest and disease outbreaks based on multi-source factors according to claim 3, characterized in that: Step S13 includes the following steps: Step S131: performing fertility decay analysis on the regional soil conditions corresponding to the crop disease and insect pest monitoring points based on the regional crop soil pH to obtain the regional soil pH fertility decay index; Step S132: obtaining the corresponding regional crop vegetation coverage through the crop disease and insect pest monitoring points, and calculating the vegetation coverage area index of the crop disease and insect pest monitoring points based on the regional crop vegetation coverage to obtain the regional crop vegetation coverage area index; Step S133: Based on the regional soil pH fertility attenuation index, the regional crop vegetation coverage area index, the regional crop soil fertility content index and the regional crop soil microbial prosperity, the regional soil fertility calculation formula is used to calculate the regional soil fertility of the crop pest and disease monitoring points to obtain the regional crop soil fertility level.

5. The method for predicting the risk of pest outbreaks based on multi-source factors according to claim 4, characterized in that: The regional soil fertility calculation formula described in step S133 is specifically: ； In the formula, is the fertility of regional crop soil, is the area of ​​crop pest and disease monitoring points, is the spatial location parameter corresponding to the crop pest and disease monitoring point, is the regional soil pH fertility decay index, is the regional soil nitrogen content, is the nitrogen content fertility influence coefficient, is the regional soil phosphorus content, is the phosphorus content fertility influence coefficient, is the regional soil potassium content, is the potassium content fertility influence coefficient, For the spatial position The corresponding regional crop soil microbial prosperity degree, Contribution coefficient for regional microbial prosperity, is the regional crop vegetation coverage index, is the vegetation cover influence coefficient, It is the correction coefficient for the fertility of regional crop soil.

6. The method for predicting the risk of pest outbreaks based on multi-source factors according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: collecting corresponding pesticide use records through crop pest and disease monitoring points, and obtaining corresponding pesticide spraying usage according to the pesticide use records; Step S22: performing pest distribution attenuation evaluation analysis on the number of pests and diseases corresponding to the regional pest and disease occurrence data based on the amount of pesticide spraying, and obtaining a regional pest and disease distribution pesticide use attenuation factor; Step S23: performing statistics on the occurrence range of the area corresponding to the crop pest and disease monitoring point based on the corresponding pest and disease occurrence location in the regional pest and disease occurrence data to obtain the size of the regional pest and disease occurrence range; Step S24: Based on the amount of pesticide spraying, the pesticide use attenuation factor of regional pest distribution, and the size of the regional pest occurrence range, the regional pest occurrence number and the pest occurrence time are calculated using the regional occurrence density calculation formula to obtain the regional pest occurrence density; The specific calculation formula for regional occurrence density is: ； In the formula, is the regional pest and disease occurrence density, The time when pests and diseases occur. is the time variable parameter, is the area of ​​regional pests and diseases, The amount of pesticide spraying used, For in time The corresponding number of pests and diseases is as follows: Pesticide use attenuation factors for regional pest distribution, is the correction coefficient for the regional pest and disease occurrence density.

7. The method for predicting the risk of pest outbreaks based on multi-source factors according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: uniformly gridding the space area corresponding to the crop pest and disease monitoring point to obtain a uniform grid of the pest and disease occurrence area; Step S32: performing regional time series outbreak analysis on the regional pest and disease occurrence density based on the uniform grid of the pest and disease occurrence area, and obtaining a grid diffusion outbreak development model corresponding to the regional pest and disease occurrence changing with time; Step S33: Designing meteorological conditions based on the temperature, humidity, precipitation and light intensity corresponding to the regional meteorological data to generate regional meteorological distribution conditions; Step S34: performing pest and disease outbreak mining and analysis on the grid diffusion outbreak development pattern corresponding to the regional pest and disease occurrence changes over time based on the regional meteorological distribution conditions, and obtaining the regional pest and disease outbreak characteristic pattern corresponding to the meteorological conditions; Step S35: Based on the uniform grid of the pest and disease outbreak area, soil fertility correlation analysis is performed on the regional crop soil fertility level and the regional pest and disease outbreak density to obtain the correlation characteristic relationship between regional soil fertility and pest and disease outbreak.

8. The method for predicting the risk of pest outbreaks based on multi-source factors according to claim 7, characterized in that: Step S35 includes the following steps: Step S351: Gridding the regional crop soil fertility and regional pest and disease occurrence density based on the uniform grid of the pest and disease occurrence area to obtain the corresponding crop soil fertility and pest and disease occurrence density values ​​under the same uniform grid; Step S352: performing correlation measurement calculation according to the corresponding crop soil fertility and pest and disease occurrence density values ​​in the same uniform grid, and obtaining the correlation coefficient between the crop soil fertility and the pest and disease occurrence density in each uniform grid; Step S353: Based on the correlation coefficient between the soil fertility of crops and the density of pests and diseases in each uniform grid, soil fertility correlation analysis is performed on the regional crop soil fertility degree and the regional pest and disease density to obtain the correlation characteristic relationship between regional soil fertility and the outbreak of pests and diseases.

9. The method for predicting the risk of pest outbreaks based on multi-source factors according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: Based on the corresponding regional pest outbreak characteristic pattern under meteorological conditions, the meteorological pest impact analysis is performed on the distribution law of pests and diseases corresponding to the crop pest and disease monitoring points in the geographical space to obtain the meteorological impact factor of the regional pest and disease outbreak; Step S42: Based on the correlation characteristic relationship between regional soil fertility and pest outbreaks, soil fertility and pest outbreak correlation analysis is performed on the distribution law of pests and diseases corresponding to the crop pest and disease monitoring points in geographical space to obtain regional soil fertility and pest and disease outbreak correlation factors; Step S43: performing multi-source risk prediction for crop pest and disease monitoring points based on regional pest and disease outbreak meteorological influencing factors and regional soil fertility pest and disease outbreak correlation factors to obtain regional pest and disease outbreak risk prediction results, including the predicted pest and disease outbreak risk level corresponding to the monitoring point area; Step S44: Perform prevention and control decision support analysis based on the regional pest outbreak risk prediction results to generate a prevention and control recommendation plan for the pest outbreak area, including pest pesticide selection, dosage and duration of use, and implementation of biological control measures.

10. A risk prediction system for pest outbreaks based on multi-source factors, characterized in that: Used to execute the method for predicting the risk of pest outbreaks based on multi-source factors as claimed in claim 1, the system for predicting the risk of pest outbreaks based on multi-source factors comprises: The crop area real-time monitoring module is used to measure the regional meteorological data, regional crop soil fertility and regional pest and disease occurrence data corresponding to the crop pest and disease monitoring points in real time, where the regional pest and disease occurrence data includes the number of pest and disease occurrences, the time of pest and disease occurrence and the location of pest and disease occurrence; The pest and disease occurrence density calculation module is used to obtain the corresponding pesticide spraying usage through the crop pest and disease monitoring points, and calculate the regional pest and disease occurrence density based on the pesticide spraying usage to obtain the regional pest and disease occurrence density; The pest outbreak feature mining module is used to conduct pest outbreak mining and analysis on the regional pest occurrence density based on regional meteorological data and regional crop soil fertility, so as to obtain the corresponding regional pest outbreak feature pattern under meteorological conditions and the correlation feature relationship between regional soil fertility and pest outbreak; The multi-source risk prediction module for pests and diseases is used to predict the multi-source risk of crop pest and disease monitoring points based on the corresponding regional pest and disease outbreak characteristic patterns under meteorological conditions and the correlation characteristic relationship between regional soil fertility and pest and disease outbreaks, so as to obtain regional pest and disease outbreak risk prediction results; prevention and control decision support analysis is carried out based on the regional pest and disease outbreak risk prediction results, thereby generating regional pest and disease outbreak prevention and control recommendation plans.

Images