Agricultural product disease real-time monitoring and early warning system

Abstract

The invention relates to the technical field of agriculture, in particular to an agricultural product disease real-time monitoring and early warning system which comprises an environment monitoring module, a crop growth monitoring module, a disease detection module, a data analysis module and an early warning generation module. Wherein the environment monitoring module is used for monitoring environment parameters of a farmland in real time; the crop growth monitoring module is used for collecting growth state data of crops; the disease detection module is used for detecting disease information of crops in real time; the data analysis module is used for comprehensively analyzing the monitored data, evaluating the current disease risk and predicting the future disease development trend; and the early warning generation module is used for generating corresponding disease early warning information. According to the invention, environment monitoring, crop growth state monitoring and disease detection are fused, accurate disease risk assessment and prediction are carried out in combination with a decision tree algorithm, and real-time and accurate disease early warning is realized, so that farm management personnel are helped to carry out early warning.

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 experience-based judgments, with low work efficiency, slow response speed, and difficulty in achieving 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 are 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 of the 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, failing 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 purpose, 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, comprising an environmental monitoring module, a crop growth monitoring module, a disease detection module, a data analysis module and an early warning generation module; wherein: 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; Disease detection module: used to detect crop disease information in real time through infrared imaging technology, including disease spots, rot or insect pests on the surface of crops; Data analysis module: used to receive data from the environmental monitoring module, crop growth monitoring module and disease detection module, use decision tree algorithm to conduct comprehensive analysis on the received data, evaluate the current disease risk based on multiple conditions such as environmental parameters, growth status data and disease information, and predict future disease development trends; 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.

[0006] 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: 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 the light intensity; Data processing unit: used to receive the raw data from the temperature and humidity sensing unit, the soil pH sensing unit and the light intensity sensing unit, perform preprocessing, including data filtering, calibration and format conversion, and send the processed data to the data analysis module.

[0007] Optionally, 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, which takes images of crop leaves and uses image processing algorithms to calculate the leaf area of ​​the crop. 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; Plant height monitoring unit: used to measure the height of crop plants in real time. The monitoring unit includes a laser rangefinder or an ultrasonic sensor, which accurately determines the height of the crop by transmitting a signal and measuring the time difference of the reflected signal. The calculation formula for the 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 by combining the collected time information. The calculation formula of the growth rate is: ,in, is the growth rate of the crop, and For crops at time and The leaf area at For the time interval.

[0008] Optionally, 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 spots, rotten or pest 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: It is used to classify and identify the disease type according to the extracted characteristic parameters, determine the specific type of lesions, rots or insect pests, and transmit the identification results to the data analysis module.

[0009] 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: 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, build a multi-layer decision tree model using a decision tree algorithm, and evaluate the current disease risk based on multiple conditions such as environmental parameters, crop growth status data, and disease information; Risk assessment unit: used to quantitatively assess the disease risk, calculate the probability of disease occurrence, and generate a risk assessment report based on the output results of the decision tree analysis unit; Trend prediction unit: used to predict the development trend of diseases based on current and historical data, using the branch paths 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.

[0010] Optionally, the decision tree analysis unit includes: Decision tree construction subunit: used to construct a multi-layer decision tree model through a decision tree algorithm based on the farmland data set from the data integration unit. The specific construction process includes the following steps: Select splitting features: Select the best splitting features by calculating the information gain of each environmental parameter, crop growth status data and disease information; the calculation formula of information gain is: ,in, For the data set, Characterized by Features 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, the multi-layer decision tree model is constructed to classify and identify the input data; Disease risk assessment subunit: 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: receiving 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.

[0011] Optionally, 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 the 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 can be 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 reasoning 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.

[0012] Optionally, 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 following formula is used to assess the severity: ,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; specifically apply 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 autoregression coefficient, is the moving average coefficient, is a random error term.

[0013] Optionally, 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 according to the disease risk assessment results provided by the data analysis module. The generation process includes the following steps: Risk level determination: Determine the risk level of the disease based on the disease risk assessment results output by the data analysis module, and generate corresponding warning information based on different risk levels; the format of the warning information is: current disease risk level X, disease type Y, predicted time period Z; Warning type classification: Generate warning messages of corresponding types according to the 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.

[0014] Optionally, 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 the warning information from the warning information generation unit to the target device.

[0015] Beneficial effects of the present invention: 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, a decision tree algorithm is used for disease risk assessment, so that the system can accurately predict disease trends based on multiple factors of environment, crops and disease information, helping farm managers to formulate prevention and control measures in advance.

[0016] 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, take appropriate disease prevention and control measures, and reduce the impact of diseases on crop growth. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1A schematic diagram of a real-time monitoring and early warning system for agricultural product diseases according to an embodiment of the present invention; Figure 2 Schematic diagram of a data analysis module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0020] It should be noted that the references to "one embodiment", "embodiment", "exemplary embodiments", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0021] In general, a term can be understood, at least in part, from its 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.

[0022] 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: 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; Disease detection module: used to detect crop disease information in real time through infrared imaging technology, including disease spots, rot or insect pests on the surface of crops; Data analysis module: used to receive data from the environmental monitoring module, crop growth monitoring module and disease detection module, and use the decision tree algorithm to conduct a comprehensive analysis of the received data. Based on multiple conditions such as environmental parameters, growth status data and disease information, the current disease risk is evaluated and the future disease development trend is predicted. The decision tree algorithm constructs a multi-layer decision tree model, takes the environmental parameters of the farmland and the crop growth status as input variables, outputs the corresponding disease risk level through node splitting and path selection, and provides accurate input information for the early warning generation module. 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 equipment of farm managers as the basis for disease prevention and control decisions.

[0023] 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 that can measure the light intensity; Data processing unit: used to receive the raw data from the temperature and humidity sensing unit, the soil pH sensing unit and the 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, and provide high-quality input data for the data analysis module.

[0024] 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, such as a digital camera or a video camera, which takes images of crop leaves and calculates the crop leaf area using an image processing algorithm. 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; Plant height monitoring unit: used to measure the height of crop plants in real time. The monitoring unit includes a laser rangefinder or an ultrasonic sensor, which accurately determines the height of the crop by transmitting a signal and measuring the time difference of the reflected signal. The calculation formula for the 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; the measured height data is transmitted to the data analysis module for further analysis; 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 by combining the collected time information. The calculation formula of the growth rate is: ,in, is the growth rate of the crop, and For crops at time and The leaf area at 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-time provide crop growth status data, providing an accurate basis for subsequent disease risk assessment.

[0025] The disease detection module includes an infrared imaging unit, an image processing unit and a disease recognition 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 spots, rotten or pest areas, and generate a binary image of the diseased area; Disease recognition 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 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 pests, and transmit accurate disease information to the data analysis module to support disease risk assessment and early warning.

[0026] 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: 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, build a multi-layer decision tree model using a decision tree algorithm, and evaluate the current disease risk based on multiple conditions such as environmental parameters, crop growth status data, and disease information; Risk assessment unit: used to quantitatively assess the disease risk, calculate the probability of disease occurrence, and generate a risk assessment report based on the output results of the decision tree analysis unit; Trend prediction unit: used to predict the development trend of diseases based on current and historical data, using the branch paths 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.

[0027] The decision tree analysis unit includes: Decision tree construction subunit: used to construct a multi-layer decision tree model through a decision tree algorithm based on the farmland data set from the data integration unit. The specific construction process includes the following steps: Select splitting features: Select the best splitting features by calculating the information gain (IG) of each environmental parameter, crop growth status data and disease information; the calculation formula of information gain is: ,in, For the data set, Characterized by Features 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; through information gain calculation, the feature that can best reduce uncertainty is selected for node splitting; 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 (such as the maximum depth of the tree, the minimum number of samples in the leaf node, or the information gain is lower than a preset threshold); Model generation: After completing the above steps, the multi-layer decision tree model is constructed to classify and identify the input data; Disease risk assessment subunit: 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 (such as temperature and humidity, soil pH, light intensity), crop growth status data (such as leaf area, plant height, growth rate) and disease information (such as lesions, rot or insect pests) 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; 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, combined 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.

[0028] The risk assessment unit includes: 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. Suppose the conditional probability value of the disease occurrence is , the specific calculation formula is: ,in, Indicates that under given historical conditions Lower Disease The probability of occurrence, Represents historical conditions The joint probability of the disease occurring is Represents historical conditions The probability of occurrence; Real-time meteorological information analysis subunit: used to receive real-time meteorological information, including temperature, humidity, precipitation and wind speed, and combine the meteorological information with historical disease pattern data for analysis; by calculating the correlation coefficient between real-time meteorological factors and historical disease patterns, the influence of meteorological factors on the occurrence of diseases is quantified. The calculation formula of 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; 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; 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 conditions of disease occurrence, is the prior probability of historical disease occurrence, is the total probability of real-time weather information; Risk assessment report generation subunit: used to generate the comprehensive probability value of the disease occurrence according to the calculated value , generate a disease risk assessment report, including disease risk level, affected area and disease type; the risk level in the report can be classified according to the following standards: when , which is high risk; when , which is a medium risk; 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.

[0029] The trend forecasting unit includes: Branch path analysis subunit: used to analyze the potential development direction of the disease under the combination of different environmental parameters, crop growth status data and disease information by 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: Input data matching: According to the current environmental parameters, crop growth status data and disease information, determine the corresponding branch path in the decision tree model; Path traversal: Starting from the root node of the decision tree model, according to the characteristic value of the input data, select the branches that meet the conditions layer by layer until reaching the leaf node, and record the conditions of all nodes on the path; 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; 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 following formula is used to assess the severity: ,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; specifically apply the time series prediction model (such as the autoregressive moving average model, ARIMA) 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 autoregression 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 evaluation unit quantifies the development severity of the disease according to the path weight and the disease severity score; the trend prediction generation unit uses the time series analysis model, combined with historical and current data, to predict the future development trend of the disease.

[0030] 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 according to the disease risk assessment results provided by the data analysis module. The generation process includes the following steps: Risk level determination: According to the disease risk assessment results output by the data analysis module, determine the risk level of the disease (such as low, medium, high), and generate corresponding warning information according to different risk levels; the format of the warning information is: current disease risk level X, disease type Y, predicted time period Z; Warning type classification: Generate warning messages of corresponding types according to the disease type (such as lesions, rot, insect pests, etc.) and the current environment and crop status, such as "The risk of leaf lesions is increasing, please check carefully", "High temperature and high humidity conditions are approaching, and the risk of rot diseases is increasing", etc. Information transmission unit: used to transmit the generated disease warning information to the terminal equipment of farm managers through the communication network.

[0031] 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 the 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 efficient and accurate warning transmission.

[0032] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0033] 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 principle of the present invention. These improvements and modifications should also be regarded as 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; Disease detection module: used to detect crop disease information in real time through infrared imaging technology, including disease spots, rot or insect pests on the surface of crops; Data analysis module: used to evaluate current disease risks and predict future disease 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 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, build a multi-layer decision tree model using the decision tree algorithm, and evaluate the current disease risk; Risk assessment unit: used to quantitatively assess the disease risk, calculate the probability of disease occurrence, and generate a risk assessment report based on the output results of the decision tree analysis unit; Trend prediction unit: used to predict the development trend of diseases based on current and historical data, and provide disease development forecasts for a period of time in the future; Early warning generation module: Generates corresponding disease early warning information based on the disease risk assessment results, and transmits the early warning information to the terminal devices of farm managers.

2. The real-time monitoring and early warning system for agricultural product diseases according to claim 1 is 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 the light intensity; Data processing unit: used to receive the raw data from the temperature and humidity sensing unit, the soil pH sensing unit and the 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 is characterized in that: 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, which takes images of crop leaves and uses image processing algorithms to calculate the leaf area of ​​the crop. 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; Plant height monitoring unit: used to measure the height of crop plants in real time. The monitoring unit includes a laser rangefinder or an ultrasonic sensor, which accurately determines the height of the crop by transmitting a signal and measuring the time difference of the reflected signal. The calculation formula for the 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 by combining the collected time information. The calculation formula of the growth rate is: ,in, is the growth rate of the crop, and For crops at time and The leaf area at is the time interval.

4. The real-time monitoring and early warning system for agricultural product diseases according to claim 1, characterized in that: 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 spots, rotten or pest 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 feature parameters of the area, shape and edge sharpness of the lesion; Classification subunit: It is used to classify and identify the disease type according to the extracted characteristic parameters, determine the specific type of lesions, rots or insect pests, and transmit the identification results to the data analysis module.

5. The real-time monitoring and early warning system for agricultural product diseases according to claim 1, characterized in that: The decision tree analysis unit comprises: Decision tree construction subunit: used to construct a multi-layer decision tree model through a decision tree algorithm based on the farmland data set from the data integration unit. The specific construction process includes the following steps: Select splitting features: Select the best splitting features by calculating the information gain of each environmental parameter, crop growth status data and disease information; the calculation formula of information gain is: ,in, For the data set, Characterized by Features 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 data set 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, the multi-layer decision tree model is constructed to classify and identify the input data; Disease risk assessment subunit: 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: receiving 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.

6. A real-time monitoring and early warning system for agricultural product diseases according to claim 5, characterized in that: The risk assessment unit comprises: 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 the 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 can be 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 reasoning 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.

7. A real-time monitoring and early warning system for agricultural product diseases according to claim 6, characterized in that: The trend prediction unit comprises: 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 following formula is used to assess the severity: ,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; specifically apply 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 autoregression coefficient, is the moving average coefficient, is a random error term.

8. 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 according to the disease risk assessment results provided by the data analysis module. The generation process includes the following steps: Risk level determination: Determine the risk level of the disease based on the disease risk assessment results output by the data analysis module, and generate corresponding warning information based on different risk levels; the format of the warning information is: current disease risk level X, disease type Y, predicted time period Z; Warning type classification: Generate warning messages of corresponding types according to the 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.

9. The real-time monitoring and early warning system for agricultural product diseases according to claim 1, 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 the warning information from the warning information generation unit to the target device.

Images