A real-time monitoring and early warning system for agricultural product diseases

Abstract

The present invention relates to the field of agricultural technology, and specifically to a real-time monitoring and early warning system for agricultural product diseases, comprising an environmental monitoring module, a crop growth monitoring module, a disease detection module, a data analysis module, and an early warning generation module. The system comprises: an environmental monitoring module for real-time monitoring of farmland environmental parameters; a crop growth monitoring module for collecting crop growth status data; a disease detection module for real-time detection of crop disease information; a data analysis module for comprehensive analysis of monitored data, assessment of current disease risks, and prediction of future disease development trends; and an early warning generation module for generating corresponding disease early warning information. The present invention integrates environmental monitoring, crop growth status monitoring, and disease detection, and combines a decision tree algorithm for precise disease risk assessment and prediction, achieving real-time and accurate disease early warnings, thereby assisting farm managers in providing early warnings.

Description

Technical Field

[0001] The present invention relates to the field of agricultural technology, and in particular to a real-time monitoring and early warning system for agricultural product diseases. Background Art

[0002] With the development of agricultural modernization, the prevention and control of crop diseases has become an important link in ensuring crop yield and quality. Traditional disease monitoring and prevention methods usually rely on manual inspections and empirical judgments, which have low work efficiency and slow response speed, and it is difficult to achieve real-time monitoring and accurate early warning of diseases. At the same time, farmland environmental factors such as temperature, humidity, and light intensity have a significant impact on the occurrence and development of diseases. Traditional methods find it difficult to fully consider these factors, resulting in disease prevention and control measures often not being taken in a timely manner, which in turn affects the healthy growth and yield of crops.

[0003] However, most existing agricultural product disease monitoring and early warning systems rely on a single monitoring data source, and the data processing and early warning algorithms are relatively simple. They fail to fully utilize multiple sensor data and advanced analysis algorithms for comprehensive evaluation and prediction; this results in low accuracy in disease monitoring and a lack of accurate early warning of disease risks under different climates, environments and crop growth conditions. Summary of the Invention

[0004] Based on the above objectives, the present invention provides a real-time monitoring and early warning system for agricultural product diseases.

[0005] A real-time monitoring and early warning system for agricultural product diseases includes an environmental monitoring module, a crop growth monitoring module, a disease detection module, a data analysis module, and an early warning generation module; wherein:

[0006] Environmental monitoring module: used to monitor farmland environmental parameters in real time, including temperature and humidity, soil pH, and light intensity;

[0007] Crop growth monitoring module: used to collect crop growth status data, including leaf area, plant height and growth rate;

[0008] Disease detection module: used to detect crop disease information in real time through infrared imaging technology, including surface lesions, rot or insect pests;

[0009] Data Analysis Module: This module receives data from the environmental monitoring module, crop growth monitoring module, and disease detection module, uses a decision tree algorithm to conduct a comprehensive analysis of the received data, and assesses current disease risks and predicts future disease development trends based on multiple conditions including environmental parameters, growth status data, and disease information.

[0010] Early warning generation module: Generates corresponding disease early warning information based on the disease risk assessment results provided by the data analysis module, and transmits the early warning information to the terminal device of the farm manager.

[0011] Optionally, the environmental monitoring module includes a temperature and humidity sensing unit, a soil pH sensing unit, a light intensity sensing unit, and a data processing unit; wherein:

[0012] Temperature and humidity sensing unit: used to collect temperature and humidity data in farmland air in real time. The sensing unit includes a temperature sensor and a humidity sensor, which are used to measure ambient temperature and relative humidity respectively.

[0013] Soil pH sensing unit: used to monitor the pH of farmland soil in real time. The sensing unit includes a pH sensor that can accurately measure the pH value in the soil;

[0014] Light intensity sensing unit: used to detect the light intensity of the farmland in real time. The sensing unit includes a light sensor capable of measuring light intensity;

[0015] Data processing unit: used to receive the raw data from the temperature and humidity sensing unit, soil pH sensing unit and light intensity sensing unit, perform preprocessing, including data filtering, calibration and format conversion, and send the processed data to the data analysis module.

[0016] Optionally, the crop growth monitoring module includes a leaf area monitoring unit, a plant height monitoring unit, and a growth rate monitoring unit; wherein:

[0017] Leaf area monitoring unit: used to collect crop leaf area data in real time. The monitoring unit includes a high-resolution image acquisition device that takes images of crop leaves and uses image processing algorithms to calculate the crop leaf area. The leaf area calculation formula is: ,in, is the leaf area, and Respectively The length and width of the leaves, is the number of leaves;

[0018] Plant height monitoring unit: used to measure the height of crop plants in real time. This monitoring unit includes a laser rangefinder or ultrasonic sensor, which accurately determines the height of crops by transmitting signals and measuring the time difference between reflected signals. The formula for calculating crop height is: ,in, is the height of the crop, is the propagation speed of sound waves or light signals, is the round trip time of the signal;

[0019] Growth rate monitoring unit: used to monitor the growth rate of crops in real time. The monitoring unit periodically collects the growth data of crop height and leaf area, and calculates the growth rate of crops based on the collected time information. The growth rate calculation formula is: ,in, is the growth rate of crops, and For crops at time and The leaf area, is the time interval.

[0020] Optionally, the disease detection module includes an infrared imaging unit, an image processing unit, and a disease identification unit; wherein:

[0021] Infrared imaging unit: includes a high-resolution infrared camera to capture thermal distribution images of the crop surface;

[0022] Image processing unit: used to process the infrared image data from the infrared imaging unit; the unit includes an image enhancement subunit and an image segmentation subunit;

[0023] Image enhancement subunit: used to improve the visibility of the diseased area by adjusting the contrast and brightness;

[0024] Image segmentation subunit: Used to separate the crop surface from the background using edge detection algorithms, extract the contour data of diseased, rotten, or insect-infested areas, and generate a binary image of the diseased area;

[0025] Disease identification unit: used to analyze the binary image data output by the image processing unit, identify and classify crop disease information; the unit includes a feature extraction subunit and a classification subunit;

[0026] Feature extraction subunit: used to extract the characteristic parameters of the area, shape and edge sharpness of the lesion;

[0027] Classification subunit: used to classify and identify disease types based on the extracted characteristic parameters, determine the specific types of lesions, rots or insect pests, and transmit the identification results to the data analysis module.

[0028] Optionally, the data analysis module includes a data integration unit, a decision tree analysis unit, a risk assessment unit, and a trend prediction unit; wherein:

[0029] Data integration unit: used to receive all data from the environmental monitoring module, crop growth monitoring module and disease detection module, and uniformly format and integrate data from different sources to form a comprehensive farmland data set;

[0030] Decision tree analysis unit: used to analyze the integrated farmland data set, using the decision tree algorithm to build a multi-layer decision tree model to assess the current disease risk based on multiple conditions such as environmental parameters, crop growth status data, and disease information;

[0031] Risk assessment unit: used to quantitatively assess disease risks based on the output results of the decision tree analysis unit, calculate the probability of disease occurrence, and generate a risk assessment report;

[0032] Trend prediction unit: used to predict the development trend of diseases based on current and historical data, using the branch path of the multi-layer decision tree model to analyze the potential development direction and severity of diseases under different environments and crop growth conditions, and provide disease development forecasts for a period of time in the future.

[0033] Optionally, the decision tree analysis unit includes:

[0034] Decision tree construction subunit: This subunit is used to construct a multi-layer decision tree model using a decision tree algorithm based on the farmland dataset from the data integration unit. The specific construction process includes the following steps:

[0035] Select splitting features: The best splitting features are selected by calculating the information gain of various environmental parameters, crop growth status data, and disease information. The information gain calculation formula is:

[0036] ,in, For the dataset, Characterized by Features The subset corresponding to a certain value of For the dataset Information entropy of

[0037] Node splitting: based on the selected features and their thresholds , the dataset Split into subsets and , so that the value of each subset on this feature satisfies or ;

[0038] Recursive construction: for each subset and Recursively perform feature selection and node splitting steps until the stopping condition is met;

[0039] Model generation: After completing the above steps, a multi-layer decision tree model is constructed to classify and identify the input data;

[0040] Disease risk assessment subunit: This subunit is used to assess the current disease risk based on the constructed decision tree model, combined with current environmental parameters, crop growth status data, and disease information. The assessment steps include:

[0041] Input data: Receive current environmental parameters, crop growth status data and disease information as input features;

[0042] Path traversal: Based on the input features, the decision tree model starts from the root node, determines the splitting conditions of each node in turn, and traverses downward along the path that meets the conditions until it reaches the leaf node;

[0043] Risk level output: At the leaf node, the disease risk level is output according to the category label, including low risk, medium risk or high risk, and the assessment result is passed to the risk assessment unit.

[0044] Optionally, the risk assessment unit includes:

[0045] Historical disease pattern analysis subunit: used to calculate the conditional probability value of the corresponding disease occurrence by counting the frequency and occurrence conditions of historical diseases;

[0046] Real-time meteorological information analysis subunit: used to receive real-time meteorological information, including temperature, humidity, precipitation, and wind speed, and combine meteorological information with historical disease pattern data for analysis; by calculating the correlation coefficient between real-time meteorological factors and historical disease patterns, the impact of meteorological factors on disease occurrence is quantified;

[0047] Disease risk calculation subunit: used to calculate the comprehensive probability value of disease occurrence based on the conditional probability values and correlation coefficients of meteorological factors provided by the historical disease pattern analysis subunit and the real-time meteorological information analysis subunit, combined with the Bayesian inference algorithm;

[0048] Risk assessment report generation subunit: used to generate a disease risk assessment report based on the calculated comprehensive probability value of disease occurrence, including disease risk level, affected area and disease type.

[0049] Optionally, the trend prediction unit includes:

[0050] Branch path analysis subunit: used to use the branch paths of the multi-layer decision tree model to analyze the potential development direction of the disease under the combination of different environmental parameters, crop growth status data and disease information;

[0051] Development direction assessment subunit: Based on the output results of the branch path analysis unit, the severity of different disease development directions is assessed. The severity assessment is performed using the following formula: ,in, Score the overall severity of disease development, For the The weight of the path, For the The disease severity score corresponding to each path, is the number of paths involved;

[0052] Trend prediction generation subunit: Based on the severity score of the development direction assessment unit, predict the development trend of the disease in the future period; specifically, use the time series prediction model to predict the development trend of the disease in the future. The formula is: ,in, For time The predicted value of disease severity, is a constant term, is the autoregressive coefficient, is the moving average coefficient, is the random error term.

[0053] Optionally, the warning generation module includes a warning information generation unit and an information transmission unit; wherein:

[0054] Warning information generation unit: used to generate corresponding disease warning information based on the disease risk assessment results provided by the data analysis module. The generation process includes the following steps:

[0055] Risk level determination: Based on the disease risk assessment results output by the data analysis module, the disease risk level is determined and corresponding warning information is generated according to different risk levels. The format of the warning information is: current disease risk level X, disease type Y, and predicted time period Z;

[0056] Warning type classification: Generate corresponding warning messages based on disease type, current environment, and crop status;

[0057] Information transmission unit: used to transmit the generated disease warning information to the terminal equipment of farm managers through the communication network.

[0058] Optionally, the information transmission unit includes a network communication interface subunit and a data transmission subunit; wherein:

[0059] Network communication interface subunit: used to transmit warning information to the terminal equipment of farm managers, supporting wireless communication technologies including Wi-Fi, 4G, 5G or LoRa;

[0060] Data transmission subunit: used to send warning information from the warning information generation unit to the target device.

[0061] Beneficial effects of the present invention:

[0062] The present invention uses a variety of sensors to collect farmland environmental parameters, crop growth status and disease information in real time, thereby realizing comprehensive monitoring of diseases. By integrating environmental monitoring, crop growth monitoring and disease detection modules, the system can accurately assess the risk of disease occurrence under different monitoring conditions, avoiding the neglect of environmental factors in traditional methods, thereby improving the accuracy and real-time performance of disease risk assessment. In addition, the decision tree algorithm is used for disease risk assessment, enabling the system to accurately predict disease trends based on multiple factors of environment, crop and disease information, helping farm managers to formulate prevention and control measures in advance.

[0063] The present invention can generate corresponding disease warning information in a timely manner based on the disease risk assessment results through the warning generation module, and transmit it to the terminal equipment of the farm manager through the communication network, ensuring that the farm manager can receive the warning information in the first time; this real-time and accurate warning mechanism enables farm managers to adjust crop management strategies in a timely manner and take appropriate disease prevention and control measures, reducing the impact of diseases on crop growth. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0065] Figure 1 Schematic diagram of a real-time monitoring and early warning system for agricultural product diseases according to an embodiment of the present invention;

[0066] Figure 2 Schematic diagram of a data analysis module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0067] The present invention is described in detail below with reference to the accompanying drawings and specific embodiments. It is also noted that, to provide a more detailed description, the following embodiments are best and preferred embodiments, and those skilled in the art may employ alternative methods for implementing certain known technologies. Furthermore, the accompanying drawings are intended only to provide a more detailed description of the embodiments and are not intended to limit the present invention.

[0068] It should be noted that references in the specification to "one embodiment," "an embodiment," "exemplary embodiments," "some embodiments," etc. indicate that the described embodiments may include specific features, structures, or characteristics, but not necessarily every embodiment will include such specific features, structures, or characteristics. Furthermore, when specific features, structures, or characteristics are described in conjunction with an embodiment, it is within the knowledge of persons skilled in the relevant art to implement such features, structures, or characteristics in conjunction with other embodiments (whether or not explicitly described).

[0069] In general, terms can be understood, at least in part, from their use in context. For example, depending at least in part on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending at least in part on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0070] like Figure 1-Figure 2 As shown, a real-time monitoring and early warning system for agricultural product diseases includes an environmental monitoring module, a crop growth monitoring module, a disease detection module, a data analysis module, and an early warning generation module; wherein:

[0071] Environmental monitoring module: used to monitor farmland environmental parameters in real time, including temperature and humidity, soil pH, and light intensity;

[0072] Crop growth monitoring module: used to collect crop growth status data, including leaf area, plant height and growth rate;

[0073] Disease detection module: used to detect crop disease information in real time through infrared imaging technology, including surface lesions, rot or insect pests;

[0074] Data Analysis Module: This module receives data from the Environmental Monitoring Module, the Crop Growth Monitoring Module, and the Disease Detection Module. It uses a decision tree algorithm to comprehensively analyze the received data. Based on multiple conditions, including environmental parameters, crop growth status data, and disease information, it assesses current disease risks and predicts future disease trends. The decision tree algorithm constructs a multi-layer decision tree model, using farmland environmental parameters and crop growth status as input variables. Through node splitting and path selection, it outputs the corresponding disease risk level and provides accurate input information for the Early Warning Generation Module.

[0075] Early warning generation module: Based on the disease risk assessment results provided by the data analysis module, it generates corresponding disease early warning information and transmits the early warning information to the terminal equipment of farm managers as the basis for disease prevention and control decisions.

[0076] The environmental monitoring module includes a temperature and humidity sensing unit, a soil pH sensing unit, a light intensity sensing unit, and a data processing unit; wherein:

[0077] Temperature and humidity sensing unit: used to collect temperature and humidity data in farmland air in real time. The sensing unit includes a temperature sensor and a humidity sensor, which are used to measure ambient temperature and relative humidity respectively.

[0078] Soil pH sensing unit: used to monitor the pH of farmland soil in real time. The sensing unit includes a pH sensor that can accurately measure the pH value in the soil;

[0079] Light intensity sensing unit: used to detect the light intensity of the farmland in real time. The sensing unit includes a light sensor that can measure the light intensity;

[0080] Data processing unit: used to receive the raw data from the temperature and humidity sensing unit, soil pH sensing unit and light intensity sensing unit, perform preprocessing, including data filtering, calibration and format conversion, and send the processed data to the data analysis module; through the coordinated work of the above units, the environmental monitoring module can comprehensively and real-time monitor the environmental conditions of the farmland, providing high-quality input data for the data analysis module.

[0081] The crop growth monitoring module includes a leaf area monitoring unit, a plant height monitoring unit, and a growth rate monitoring unit; wherein:

[0082] Leaf area monitoring unit: used to collect crop leaf area data in real time. The monitoring unit includes a high-resolution image acquisition device, such as a digital camera or video camera, which takes images of crop leaves and uses image processing algorithms to calculate the crop leaf area. The calculation formula for leaf area is: ,in, is the leaf area, and Respectively The length and width of the leaves, is the number of leaves; the collected leaf area data is transmitted to the data analysis module after image processing for disease risk assessment;

[0083] Plant height monitoring unit: used to measure the height of crop plants in real time. This monitoring unit includes a laser rangefinder or ultrasonic sensor, which accurately determines the height of crops by transmitting signals and measuring the time difference between reflected signals. The formula for calculating crop height is: ,in, is the height of the crop, is the propagation speed of sound waves or light signals, The time it takes for the signal to go back and forth; the measured height data is transmitted to the data analysis module for further analysis;

[0084] Growth rate monitoring unit: used to monitor the growth rate of crops in real time. The monitoring unit periodically collects the growth data of crop height and leaf area, and calculates the growth rate of crops based on the collected time information. The growth rate calculation formula is: ,in, is the growth rate of crops, and For crops at time and The leaf area, is the time interval; the same calculation method is applicable to the growth rate calculation of plant height and other growth parameters; the calculated growth rate data is transmitted to the data analysis module for further analysis of crop growth status; through the collaborative work of the above units, the crop growth monitoring module can accurately and real-timely provide crop growth status data, providing an accurate basis for subsequent disease risk assessment.

[0085] The disease detection module includes an infrared imaging unit, an image processing unit, and a disease identification unit; wherein:

[0086] Infrared imaging unit: includes a high-resolution infrared camera to capture thermal distribution images of the crop surface;

[0087] Image processing unit: used to process the infrared image data from the infrared imaging unit; the unit includes an image enhancement subunit and an image segmentation subunit;

[0088] Image enhancement subunit: used to improve the visibility of the diseased area by adjusting the contrast and brightness;

[0089] Image segmentation subunit: Used to separate the crop surface from the background using edge detection algorithms, extract the contour data of diseased, rotten, or insect-infested areas, and generate a binary image of the diseased area;

[0090] Disease identification unit: used to analyze the binary image data output by the image processing unit, identify and classify crop disease information; the unit includes a feature extraction subunit and a classification subunit;

[0091] Feature extraction subunit: used to extract the characteristic parameters of the area, shape and edge sharpness of the lesion;

[0092] Classification subunit: used to classify and identify disease types based on the extracted characteristic parameters, determine the specific type of lesions, rots or insect pests, and transmit the identification results to the data analysis module; through the collaborative work of the above units, the disease detection module can efficiently and accurately detect and identify crop lesions, rots or insect pests, and transmit precise disease information to the data analysis module to support disease risk assessment and early warning.

[0093] The data analysis module includes a data integration unit, a decision tree analysis unit, a risk assessment unit, and a trend prediction unit; among which:

[0094] Data integration unit: used to receive all data from the environmental monitoring module, crop growth monitoring module and disease detection module, and uniformly format and integrate data from different sources to form a comprehensive farmland data set;

[0095] Decision tree analysis unit: used to analyze the integrated farmland data set, using the decision tree algorithm to build a multi-layer decision tree model to assess the current disease risk based on multiple conditions such as environmental parameters, crop growth status data, and disease information;

[0096] Risk assessment unit: used to quantitatively assess disease risks based on the output results of the decision tree analysis unit, calculate the probability of disease occurrence, and generate a risk assessment report;

[0097] Trend prediction unit: used to predict the development trend of diseases based on current and historical data, using the branch path of the multi-layer decision tree model to analyze the potential development direction and severity of diseases under different environments and crop growth conditions, and provide disease development forecasts for a period of time in the future.

[0098] The decision tree analysis unit includes:

[0099] Decision tree construction subunit: This subunit is used to construct a multi-layer decision tree model using a decision tree algorithm based on the farmland dataset from the data integration unit. The specific construction process includes the following steps:

[0100] Select splitting features: The best splitting features are selected by calculating the information gain (IG) of various environmental parameters, crop growth status data, and disease information. The information gain calculation formula is:

[0101] ,in, For the dataset, Characterized by Characterized by The subset corresponding to a certain value of For the dataset The information entropy of is defined as: ,in, For category The probability of is the number of categories; by calculating the information gain, the feature that can best reduce uncertainty is selected for node splitting;

[0102] Node splitting: based on the selected features and their thresholds , the dataset Split into subsets and , so that the value of each subset on this feature satisfies or ;

[0103] Recursive construction: for each subset and Recursively perform feature selection and node splitting steps until a stopping condition is met (such as the maximum depth of the tree, the minimum number of samples in a leaf node, or the information gain is lower than a preset threshold);

[0104] Model generation: After completing the above steps, a multi-layer decision tree model is constructed to classify and identify the input data;

[0105] Disease risk assessment subunit: This subunit is used to assess the current disease risk based on the constructed decision tree model, combined with current environmental parameters, crop growth status data, and disease information. The assessment steps include:

[0106] Input data: Receive current environmental parameters (such as temperature and humidity, soil pH, and light intensity), crop growth status data (such as leaf area, plant height, and growth rate), and disease information (such as lesions, rot, or insect infestation) as input features;

[0107] Path traversal: Based on the input features, the decision tree model starts from the root node, determines the splitting conditions of each node in turn, and traverses downward along the path that meets the conditions until it reaches the leaf node;

[0108] Risk level output: At the leaf node, the disease risk level is output according to the category label, including low risk, medium risk or high risk, and the assessment result is passed to the risk assessment unit; the above-mentioned decision tree construction unit selects the best feature for node splitting through information gain, and recursively constructs a multi-layer decision tree model to achieve effective classification of complex data sets. The disease risk assessment unit uses the constructed decision tree model and combines it with the multi-dimensional data collected in real time to accurately assess the current disease risk level and ensure the accuracy and reliability of the early warning information.

[0109] The risk assessment unit includes:

[0110] Historical disease pattern analysis subunit: It is used to calculate the conditional probability value of the corresponding disease occurrence by counting the frequency and occurrence conditions of historical diseases. The conditional probability value of the disease occurrence is , the specific calculation formula is: ,in, Indicates that under given historical conditions Lower diseases The probability of occurrence, Represents historical conditions The joint probability of the disease occurring is Represents historical conditions probability of occurrence;

[0111] Real-time meteorological information analysis subunit: used to receive real-time meteorological information, including temperature, humidity, precipitation and wind speed, and combine meteorological information with historical disease pattern data for analysis; by calculating the correlation coefficient between real-time meteorological factors and historical disease patterns, the impact of meteorological factors on disease occurrence is quantified. The calculation formula for the correlation coefficient is: ,in, is the correlation coefficient, and are the sample values of meteorological factors and disease occurrence data, and is the mean of meteorological factors and disease occurrence data, is the number of samples;

[0112] Disease risk calculation subunit: It is used to calculate the comprehensive probability value of disease occurrence based on the conditional probability values and correlation coefficients of meteorological factors provided by the historical disease pattern analysis subunit and the real-time meteorological information analysis subunit, combined with the Bayesian inference algorithm; the Bayesian formula is: ,in, Given real-time weather information The posterior probability of the disease occurring is is the likelihood of observing meteorological information under the condition of disease occurrence, is the prior probability of historical disease occurrence, is the total probability of real-time weather information;

[0113] Risk assessment report generation subunit: used to generate the comprehensive probability value of disease occurrence based on the calculated value , generate a disease risk assessment report, including the disease risk level, affected area and disease type; the risk level in the report can be classified according to the following standards:

[0114] when , which is high risk;

[0115] when , which is medium risk;

[0116] when , which is a low risk; through the above steps, the risk assessment unit can quantitatively assess the disease risk of farmland based on historical data and real-time meteorological information, and provide a detailed assessment report to provide farm managers with timely and effective decision-making basis.

[0117] The trend forecasting unit includes:

[0118] The branch path analysis subunit is used to analyze the potential development direction of diseases under the combination of different environmental parameters, crop growth status data, and disease information using the branch paths of the multi-layer decision tree model. By traversing all relevant branch paths of the decision tree model, the development path of the disease under the predetermined combination of conditions is identified. The calculation steps of the branch path analysis include:

[0119] Input data matching: Based on current environmental parameters, crop growth status data and disease information, determine the corresponding branch path in the decision tree model;

[0120] Path traversal: Starting from the root node of the decision tree model, according to the characteristic value of the input data, the branches that meet the conditions are selected layer by layer until the leaf node is reached, and the conditions of all nodes on the path are recorded;

[0121] Path weight calculation: For each traversed path, calculate its weight , the weight calculation formula is: ,in, is the weight of the path, For the path The probability of the node condition, is the number of nodes on the path;

[0122] Development direction assessment subunit: Based on the output results of the branch path analysis unit, the severity of different disease development directions is assessed. The severity assessment is performed using the following formula: ,in, Score the overall severity of disease development, For the The weight of the path, For the The disease severity score corresponding to each path, is the number of paths involved;

[0123] Trend prediction generation subunit: Based on the severity score of the development direction assessment unit, the development trend of the disease in the future is predicted; specifically, a time series prediction model (such as the autoregressive moving average model, ARIMA) is used to predict the development trend of the disease in the future. The formula is: ,in, For time The predicted value of disease severity, is a constant term, is the autoregressive coefficient, is the moving average coefficient, is a random error term; the above subunits identify the development direction of the disease under different combinations of conditions through path traversal of the multi-layer decision tree model; the development direction assessment unit quantifies the development severity of the disease based on the path weight and disease severity score; the trend prediction generation unit uses the time series analysis model to combine historical and current data to predict the future development trend of the disease.

[0124] The warning generation module includes a warning information generation unit and an information transmission unit; wherein:

[0125] Warning information generation unit: used to generate corresponding disease warning information based on the disease risk assessment results provided by the data analysis module. The generation process includes the following steps:

[0126] Risk level determination: Based on the disease risk assessment results output by the data analysis module, the disease risk level (such as low, medium, or high) is determined, and corresponding warning information is generated based on the different risk levels. The format of the warning information is: current disease risk level X, disease type Y, and predicted time period Z;

[0127] Warning type classification: Generate corresponding warning messages based on the disease type (such as lesions, rot, insect pests, etc.) and the current environment and crop status, such as "Increased risk of leaf lesions, please check carefully" and "Increasing risk of rot due to the approaching high temperature and high humidity conditions";

[0128] Information transmission unit: used to transmit the generated disease warning information to the terminal equipment of farm managers through the communication network.

[0129] The information transmission unit includes a network communication interface subunit and a data transmission subunit; wherein:

[0130] Network communication interface subunit: used to transmit warning information to the terminal equipment of farm managers, supporting wireless communication technologies including Wi-Fi, 4G, 5G or LoRa;

[0131] Data transmission subunit: used to send warning information from the warning information generation unit to the target device; through the organic combination of the above units, it ensures that all links of the system are closely connected to achieve the purpose of efficient and accurate warning transmission.

[0132] The present invention encompasses any alternatives, modifications, equivalents, and solutions that fall within the spirit and scope of the present invention. To provide a thorough understanding of the present invention, specific details are described in detail below in connection with the preferred embodiments of the present invention, but those skilled in the art will be able to fully understand the present invention without these detailed descriptions. Furthermore, to avoid unnecessary confusion regarding the essence of the present invention, well-known methods, processes, procedures, components, and circuits have not been described in detail.

[0133] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A real-time monitoring and early warning system for agricultural product diseases, characterized in that: It includes environmental monitoring module, crop growth monitoring module, disease detection module, data analysis module and early warning generation module; among which: Environmental monitoring module: used to monitor farmland environmental parameters in real time, including temperature and humidity, soil pH, and light intensity; Crop growth monitoring module: used to collect crop growth status data, including leaf area, plant height and growth rate; The crop growth monitoring module includes a leaf area monitoring unit, a plant height monitoring unit, and a growth rate monitoring unit; wherein: Leaf area monitoring unit: used to collect crop leaf area data in real time. The monitoring unit includes a high-resolution image acquisition device that takes images of crop leaves and uses image processing algorithms to calculate the crop leaf area. The leaf area calculation formula is: ,in, is the leaf area, and Respectively The length and width of the leaves, is the number of leaves; Plant height monitoring unit: used to measure the height of crop plants in real time. This monitoring unit includes a laser rangefinder or ultrasonic sensor, which accurately determines the height of crops by transmitting signals and measuring the time difference between reflected signals. The formula for calculating crop height is: ,in, is the height of the crop, is the propagation speed of sound waves or light signals, is the round trip time of the signal; Growth rate monitoring unit: used to monitor the growth rate of crops in real time. The monitoring unit periodically collects the growth data of crop height and leaf area, and calculates the growth rate of crops based on the collected time information. The growth rate calculation formula is: ,in, is the growth rate of the crop, and For crops at time and The leaf area, is the time interval; Disease detection module: used to detect crop disease information in real time through infrared imaging technology, including surface lesions, rot or insect pests; The disease detection module includes an infrared imaging unit, an image processing unit, and a disease identification unit; wherein: Infrared imaging unit: includes a high-resolution infrared camera to capture thermal distribution images of the crop surface; Image processing unit: used to process the infrared image data from the infrared imaging unit; the unit includes an image enhancement subunit and an image segmentation subunit; Image enhancement subunit: used to improve the visibility of the diseased area by adjusting the contrast and brightness; Image segmentation subunit: Used to separate the crop surface from the background using edge detection algorithms, extract the contour data of diseased, rotten, or insect-infested areas, and generate a binary image of the diseased area; Disease identification unit: used to analyze the binary image data output by the image processing unit, identify and classify crop disease information; the unit includes a feature extraction subunit and a classification subunit; Feature extraction subunit: used to extract the characteristic parameters of the area, shape and edge sharpness of the lesion; Classification subunit: used to classify and identify disease types based on the extracted characteristic parameters, determine the specific types of lesions, rots or insect pests, and transmit the identification results to the data analysis module; Data Analysis Module: This module receives data from the environmental monitoring module, crop growth monitoring module, and disease detection module, uses a decision tree algorithm to conduct a comprehensive analysis of the received data, and assesses current disease risks and predicts future disease development trends based on multiple conditions including environmental parameters, growth status data, and disease information. The data analysis module includes a data integration unit, a decision tree analysis unit, a risk assessment unit, and a trend prediction unit; wherein: Data integration unit: used to receive all data from the environmental monitoring module, crop growth monitoring module and disease detection module, and uniformly format and integrate data from different sources to form a comprehensive farmland data set; Decision tree analysis unit: used to analyze the integrated farmland data set, using the decision tree algorithm to build a multi-layer decision tree model to assess the current disease risk based on multiple conditions such as environmental parameters, crop growth status data, and disease information; The decision tree analysis unit includes: Decision tree construction subunit: This subunit is used to construct a multi-layer decision tree model using a decision tree algorithm based on the farmland dataset from the data integration unit. The specific construction process includes the following steps: Select splitting features: The best splitting features are selected by calculating the information gain of various environmental parameters, crop growth status data, and disease information. The information gain calculation formula is: ,in, For the dataset, Characterized by Characterized by The subset corresponding to a certain value of For the dataset Information entropy of Node splitting: based on the selected features and their thresholds , the dataset Split into subsets and , so that the value of each subset on this feature satisfies or ; Recursive construction: for each subset and Recursively perform feature selection and node splitting steps until the stopping condition is met; Model generation: After completing the above steps, a multi-layer decision tree model is constructed to classify and identify the input data; Disease risk assessment subunit: This subunit is used to assess the current disease risk based on the constructed decision tree model, combined with current environmental parameters, crop growth status data, and disease information. The assessment steps include: Input data: Receive current environmental parameters, crop growth status data and disease information as input features; Path traversal: Based on the input features, the decision tree model starts from the root node, determines the splitting conditions of each node in turn, and traverses downward along the path that meets the conditions until it reaches the leaf node; Risk level output: At the leaf node, the disease risk level is output according to the category label, including low risk, medium risk or high risk, and the assessment result is passed to the risk assessment unit; Risk assessment unit: used to quantitatively assess disease risks based on the output results of the decision tree analysis unit, calculate the probability of disease occurrence, and generate a risk assessment report; The risk assessment unit includes: Historical disease pattern analysis subunit: used to calculate the conditional probability value of the corresponding disease occurrence by counting the frequency and occurrence conditions of historical diseases; Real-time meteorological information analysis subunit: used to receive real-time meteorological information, including temperature, humidity, precipitation, and wind speed, and combine meteorological information with historical disease pattern data for analysis; by calculating the correlation coefficient between real-time meteorological factors and historical disease patterns, the impact of meteorological factors on disease occurrence is quantified; Disease risk calculation subunit: used to calculate the comprehensive probability value of disease occurrence based on the conditional probability values and correlation coefficients of meteorological factors provided by the historical disease pattern analysis subunit and the real-time meteorological information analysis subunit, combined with the Bayesian inference algorithm; Risk assessment report generation subunit: used to generate a disease risk assessment report based on the calculated comprehensive probability value of disease occurrence, including disease risk level, affected area and disease type; Trend prediction unit: used to predict the development trend of diseases based on current and historical data. It uses the branch paths of the multi-layer decision tree model to analyze the potential development direction and severity of diseases under different environmental and crop growth conditions, and provide disease development forecasts for a period of time in the future. The trend prediction unit includes: Branch path analysis subunit: used to use the branch paths of the multi-layer decision tree model to analyze the potential development direction of the disease under the combination of different environmental parameters, crop growth status data and disease information; Development direction assessment subunit: Based on the output results of the branch path analysis unit, the severity of different disease development directions is assessed. The severity assessment is performed using the following formula: ,in, Score the overall severity of disease development, For the The weight of the path, For the The disease severity score corresponding to each path, is the number of paths involved; Trend prediction generation subunit: Based on the severity score of the development direction assessment unit, predict the development trend of the disease in the future period; specifically, use the time series prediction model to predict the development trend of the disease in the future. The formula is: ,in, For time The predicted value of disease severity, is a constant term, is the autoregressive coefficient, is the moving average coefficient, is the random error term; Early warning generation module: Generates corresponding disease early warning information based on the disease risk assessment results provided by the data analysis module, and transmits the early warning information to the terminal device of the farm manager.

2. The real-time monitoring and early warning system for agricultural product diseases according to claim 1, characterized in that: The environmental monitoring module includes a temperature and humidity sensing unit, a soil pH sensing unit, a light intensity sensing unit, and a data processing unit; wherein: Temperature and humidity sensing unit: used to collect temperature and humidity data in farmland air in real time. The sensing unit includes a temperature sensor and a humidity sensor, which are used to measure ambient temperature and relative humidity respectively. Soil pH sensing unit: used to monitor the pH of farmland soil in real time. The sensing unit includes a pH sensor that can accurately measure the pH value in the soil; Light intensity sensing unit: used to detect the light intensity of the farmland in real time. The sensing unit includes a light sensor capable of measuring light intensity; Data processing unit: used to receive the raw data from the temperature and humidity sensing unit, soil pH sensing unit and light intensity sensing unit, perform preprocessing, including data filtering, calibration and format conversion, and send the processed data to the data analysis module.

3. The real-time monitoring and early warning system for agricultural product diseases according to claim 1, characterized in that: The warning generation module includes a warning information generation unit and an information transmission unit; wherein: Warning information generation unit: used to generate corresponding disease warning information based on the disease risk assessment results provided by the data analysis module. The generation process includes the following steps: Risk level determination: Based on the disease risk assessment results output by the data analysis module, the disease risk level is determined and corresponding warning information is generated according to different risk levels. The format of the warning information is: current disease risk level X, disease type Y, and predicted time period Z; Warning type classification: Generate corresponding warning messages based on disease type, current environment, and crop status; Information transmission unit: used to transmit the generated disease warning information to the terminal equipment of farm managers through the communication network.

4. A real-time monitoring and early warning system for agricultural product diseases according to claim 3, characterized in that: The information transmission unit includes a network communication interface subunit and a data transmission subunit; wherein: Network communication interface subunit: used to transmit warning information to the terminal equipment of farm managers, supporting wireless communication technologies including Wi-Fi, 4G, 5G or LoRa; Data transmission subunit: used to send warning information from the warning information generation unit to the target device.

Images