Forestry new technology intelligent disease and pest prevention and control system and method

Abstract

The invention discloses a forestry new technology intelligent disease and pest prevention and control system and method, and relates to the technical field of disease and pest prevention and control, and the system comprises a data collection module which collects the real-time data of diseases and pests in a forest; the pest and disease damage identification and analysis module is used for analyzing the collected real-time data, carrying out pest and disease damage identification by utilizing an artificial intelligence algorithm and calculating the threat level of the pest and disease damage; the pest and disease early warning module sends out pest and disease early warning signals and provides prevention and control suggestions according to recognition and calculation results; the prevention and control measure recommendation module intelligently recommends prevention and control measures according to the early warning result and the specific disease and pest species; and the execution module is used for performing automatic prevention and control operation through intelligent equipment according to the recommended prevention and control measures. Dynamic monitoring of diseases and insect pests is provided, the recognition module based on deep learning automatically analyzes data, the diseases and insect pests are accurately recognized, threat levels are evaluated, personalized prevention and control measures are recommended, the prevention and control efficiency is effectively improved, and the ecological environment is protected.

Description

Technical Field

[0001] The present invention relates to the technical field of pest control, and in particular to a new forestry technology intelligent pest control system and method. Background Art

[0002] Pest and disease prevention and control in forestry has always been a key issue affecting forest ecological health and production. Traditional pest and disease prevention and control methods usually rely on manual monitoring and empirical judgment, resulting in low prevention and control efficiency, poor accuracy, and susceptibility to human factors. In addition, there is often no early warning mechanism for the outbreak of pests and diseases, and prevention and control measures are delayed, affecting the sustainable use of forest resources. In order to improve prevention and control effects and reduce ecological and economic losses, the use of advanced intelligent technologies has become an inevitable trend.

[0003] In recent years, with the rapid development of the Internet of Things, sensor technology, artificial intelligence, and big data analysis, intelligent pest and disease control systems have gradually become a new solution. These systems can collect forest environmental data in real time, use deep learning algorithms to identify and analyze pests and diseases, accurately assess threat levels, and intelligently recommend prevention and control measures, thereby improving the timeliness, accuracy, and automation level of pest and disease control. Summary of the Invention

[0004] In order to solve the above technical problems, a new forestry technology intelligent pest control system and method is provided. This technical solution solves the above problems.

[0005] In order to achieve the above objects, the technical solution adopted by the present invention is:

[0006] New forestry technology intelligent pest control systems and methods, including:

[0007] Data collection module, used to collect real-time data on forest pests and diseases, including climate conditions, soil moisture, vegetation health index, pest species and numbers;

[0008] The pest and disease identification and analysis module is used to analyze the collected real-time data, use artificial intelligence algorithms to identify pests and diseases, and calculate their threat level;

[0009] The pest and disease early warning module issues pest and disease early warning signals based on identification and calculation results, and provides specific prevention and control suggestions;

[0010] The prevention and control measures recommendation module intelligently recommends prevention and control measures based on early warning results and specific pest and disease types, including chemical control, physical control, and biological control plans;

[0011] The execution module performs automated prevention and control operations through intelligent equipment based on recommended prevention and control measures.

[0012] Preferably, the pest identification and analysis module specifically includes:

[0013] Feature extraction unit: extracts key features from the data acquired by the data acquisition module, extracts the features of the diseased area of ​​plant pests and diseases through image processing technology, and extracts the environmental related features of pests and diseases through sensor data;

[0014] Pest and disease identification unit: Based on deep learning algorithms, it analyzes image data and sensor data to identify the types of pests and diseases;

[0015] Threat level calculation unit: Based on the identification results, combined with the type and quantity of pests and diseases, as well as environmental conditions, a pest and disease threat level assessment model is established to calculate the threat level of pests and diseases;

[0016] Threat level prediction unit: predicts the threat level through regression analysis model, outputs mild, moderate and severe levels, and outputs identification results and threat level assessment report.

[0017] Preferably, the analysis of image data and sensor data based on a deep learning algorithm to identify the types of pests and diseases specifically includes:

[0018] Use convolutional neural network deep learning algorithms to analyze the collected pest and disease image data and extract feature information from the pest and disease images, including the morphological and color characteristics of the diseased area, to identify the type of pest and disease;

[0019] Combined with data from environmental sensors, deep learning algorithms are used to process sensor data, extracting environmental factors that cause pests and diseases, and combining this with image data to comprehensively determine the type of pests and diseases.

[0020] Combining the extracted image features and sensor features, a pest threat level assessment model is established to identify pest types;

[0021] The pest threat level assessment model formula is:

[0022]

[0023] Where x is the input data, including features of image and sensor data, w1 and w2 are weight matrices, b1 and b2 are bias terms, σ is the activation function, θ is all network parameters, and f θ (x) is the output pest and disease category prediction value, is the true label.

[0024] Preferably, the threat level calculation unit specifically includes:

[0025] Based on the identified pest and disease types and quantities, combined with environmental factors such as climate conditions, soil moisture, and vegetation health index, the threat level of pests and diseases to the forest ecosystem is calculated using a multivariate regression model machine learning method. The threat level calculation formula is:

[0026] L=β0+β1C+β2Q+β3E

[0027] Where C is the severity of the pest type, Q is the number of pests, E is the danger level of environmental conditions, β0, β1, β3 are the coefficients of the regression model, and L is the threat level;

[0028] Based on the calculation results and combined with the specific ecological and economic impacts, the threat level of pests and diseases is output. By updating environmental data and pest and disease data in real time, the threat level assessment model is dynamically adjusted.

[0029] Preferably, the prediction of threat level by using a regression analysis model, outputting mild, moderate and severe levels, and outputting the identification result and threat level assessment report specifically include:

[0030] A linear regression model is used to predict the threat level of pests and diseases, with the pest type, quantity, and environmental data as inputs and the output as the predicted value of the threat level;

[0031] Among them, the linear regression model formula is:

[0032]

[0033] Where, is the predicted value of threat level, K0 is the intercept term, K1, K2, K3, K n are regression coefficients, X1, X2, X3, X n is the input feature of the model, ∈ is the error term;

[0034] Based on the output of the regression model, the threat level is classified as mild, moderate, and severe;

[0035] A threat level assessment report will be generated based on the output of the regression model, which will include the types, quantity, threat level and possible impact of pests and diseases, and output corresponding prevention and control recommendations based on the threat level.

[0036] Preferably, the pest warning module specifically includes:

[0037] Warning signal generation unit: issues warning signals based on the calculated threat level and identification results. If the threat level reaches the threshold, the system automatically generates an alarm and notifies you to take timely prevention and control measures.

[0038] Prevention and control suggestion generation unit: Based on the type and threat level of pests and diseases, the system will provide specific prevention and control suggestions, including chemical control, physical control, and biological control;

[0039] Prevention and control measures evaluation and recommendation unit: Based on the characteristics of different pests and diseases, environmental conditions and local management needs, intelligently recommend prevention and control measures, evaluate the effectiveness and cost of different prevention and control measures, and provide the optimal solution;

[0040] Recording and reporting unit: records the process of identification, analysis, early warning and prevention and control recommendations of all pests and diseases, and generates corresponding reports.

[0041] New forestry technology and intelligent pest control methods include:

[0042] S1: Collect real-time data of the forest area through the data collection module, including climate, soil and vegetation health information;

[0043] S2: The collected data is transmitted to the pest and disease identification and analysis module, which uses artificial intelligence algorithms to perform real-time pest and disease detection and analysis;

[0044] S3: Based on the analysis results, the pest and disease early warning module issues a warning signal and predicts the upcoming outbreak of pests and diseases;

[0045] S4: The prevention and control measures recommendation module recommends prevention and control measures based on the prediction results, including chemical control, physical control, and biological control methods;

[0046] S5: The execution module performs automated prevention and control operations according to the recommended measures and uses the intelligent spraying system for prevention and control.

[0047] Preferably, the step of transmitting the collected data to the pest and disease identification and analysis module and performing real-time pest and disease detection and analysis using an artificial intelligence algorithm specifically includes:

[0048] Image processing technology is used to analyze the image data of pests and diseases collected in the forest area, and the morphological and color characteristics of the diseased area are extracted;

[0049] Based on the convolutional neural network deep learning algorithm, the extracted image features are combined with data from environmental sensors to identify the types of pests and diseases in real time;

[0050] Use artificial intelligence algorithms to conduct multidimensional analysis of image and sensor data, and through comprehensive assessment, determine the types, severity and potential threats of pests and diseases to forest ecosystems.

[0051] Preferably, the pest warning module issues a warning signal based on the analysis results and predicts the upcoming pest outbreak, specifically including:

[0052] Assess the threat level based on the identified pest and disease types and numbers, as well as environmental factors, and predict the future development of pests and diseases by combining historical data and trend analysis;

[0053] Based on the threat level and prediction results of pests and diseases, the pest and disease warning module generates a warning signal. When the threat level exceeds the set threshold, the system will automatically trigger an alarm and notify relevant personnel.

[0054] Preferably, the control measures recommendation module recommends control measures based on the prediction results, including chemical control, physical control, and biological control methods, specifically including:

[0055] The prevention and control measures recommendation module provides specific prevention and control measures based on the type and threat level of different pests and diseases, including:

[0056] Chemical control: Recommend chemical agents and pesticides based on the type of pests and diseases;

[0057] Physical prevention: Based on prevention and control needs, it is recommended to install physical barriers and trapping devices;

[0058] Biological control: Control of pests and diseases by releasing natural enemies and using biological pesticides.

[0059] Compared with the prior art, the present invention has the following beneficial effects:

[0060] This invention proposes to collect climate, soil moisture, vegetation health and other data in real time through a sensor network to achieve dynamic monitoring of pests and diseases. A recognition module based on deep learning automatically analyzes the data, accurately identifies pests and diseases, assesses the threat level, and recommends personalized prevention and control measures. The system can automatically execute prevention and control operations and dynamically adjust strategies based on real-time data, effectively improving prevention and control efficiency, protecting the ecological environment by reducing the use of chemical pesticides, and improving forest health and sustainability. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 It is a system framework diagram of the present invention;

[0062] Figure 2 It is a step flow framework diagram of the present invention. DETAILED DESCRIPTION

[0063] The following description is intended to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are merely examples, and those skilled in the art may conceive of other obvious variations.

[0064] Reference Figure 1 As shown, the new forestry technology intelligent pest control system and method includes:

[0065] Data collection module, used to collect real-time data on forest pests and diseases, including climate conditions, soil moisture, vegetation health index, pest species and numbers;

[0066] The pest and disease identification and analysis module is used to analyze the collected real-time data, use artificial intelligence algorithms to identify pests and diseases, and calculate their threat level;

[0067] The pest and disease early warning module issues pest and disease early warning signals based on identification and calculation results, and provides specific prevention and control suggestions;

[0068] The prevention and control measures recommendation module intelligently recommends prevention and control measures based on early warning results and specific pest and disease types, including chemical control, physical control, and biological control plans;

[0069] The execution module performs automated prevention and control operations through intelligent equipment based on recommended prevention and control measures.

[0070] The pest and disease identification and analysis module specifically includes:

[0071] Feature extraction unit: extracts key features from the data acquired by the data acquisition module, extracts the features of the diseased area of ​​plant pests and diseases through image processing technology, and extracts the environmental related features of pests and diseases through sensor data;

[0072] Pest and disease identification unit: Based on deep learning algorithms, it analyzes image data and sensor data to identify the types of pests and diseases;

[0073] Threat level calculation unit: Based on the identification results, combined with the type and quantity of pests and diseases, as well as environmental conditions, a pest and disease threat level assessment model is established to calculate the threat level of pests and diseases;

[0074] Threat level prediction unit: predicts the threat level through regression analysis model, outputs mild, moderate and severe levels, and outputs identification results and threat level assessment report;

[0075] Through deep learning and image processing technologies within artificial intelligence algorithms, not only can pest and disease species be accurately identified, but also their threat levels can be analyzed in real time. This identification and calculation results are combined to provide accurate predictions for the early warning module. This module combines deep learning, image processing, sensor data, and regression analysis to achieve automated and intelligent pest and disease identification and threat assessment.

[0076] Based on deep learning algorithms, image data and sensor data are analyzed to identify pest and disease types, including:

[0077] Use convolutional neural network deep learning algorithms to analyze the collected pest and disease image data and extract feature information from the pest and disease images, including the morphological and color characteristics of the diseased area, to identify the type of pest and disease;

[0078] Combined with data from environmental sensors, deep learning algorithms are used to process sensor data, extracting environmental factors that cause pests and diseases, and combining this with image data to comprehensively determine the type of pests and diseases.

[0079] Combining the extracted image features and sensor features, a pest threat level assessment model is established to identify pest types;

[0080] The pest threat level assessment model formula is:

[0081]

[0082] Where x is the input data, including features of image and sensor data, w1 and w2 are weight matrices, b1 and b2 are bias terms, σ is the activation function, θ is all network parameters, and f θ (x) is the output pest and disease category prediction value, is the true label;

[0083] The convolutional neural network deep learning algorithm can extract effective features from a large amount of pest and disease image data, accurately identify the type of pest and disease, and combine it with environmental sensor data to comprehensively judge the occurrence factors of pests and diseases and their harmfulness. This multi-dimensional analysis method greatly improves the accuracy and real-time performance of pest and disease identification.

[0084] The threat level calculation unit specifically includes:

[0085] Based on the identified pest and disease types and quantities, combined with environmental factors such as climate conditions, soil moisture, and vegetation health index, the threat level of pests and diseases to the forest ecosystem is calculated using a multivariate regression model machine learning method. The threat level calculation formula is:

[0086] L=β0+β1C+β2Q+β3E

[0087] Where C is the severity of the pest type, Q is the number of pests, E is the danger level of environmental conditions, β0, β1, β3 are the coefficients of the regression model, and L is the threat level;

[0088] Based on the calculation results and combined with the specific ecological and economic impacts, the threat level of pests and diseases is output. The threat level assessment model is dynamically adjusted by updating environmental data and pest and disease data in real time.

[0089] By combining environmental factors with the types and numbers of pests and diseases through a multivariate regression model, the degree of threat posed by pests and diseases to forests can be dynamically assessed. By updating environmental data and pest and disease data in real time, the threat level model is continuously adjusted to ensure that the system can accurately provide response plans based on current actual conditions.

[0090] The threat level is predicted through a regression analysis model, and the output is a mild, moderate, and severe level. The output identification results and threat level assessment report include:

[0091] A linear regression model is used to predict the threat level of pests and diseases, with the pest type, quantity, and environmental data as inputs and the output as the predicted value of the threat level;

[0092] Among them, the linear regression model formula is:

[0093]

[0094] Where, is the predicted value of threat level, K0 is the intercept term, K1, K2, K3, K n are regression coefficients, X1, X2, X3, X n is the input feature of the model, ∈ is the error term;

[0095] Based on the output of the regression model, the threat level is classified as mild, moderate, and severe;

[0096] A threat level assessment report will be generated based on the output of the regression model. The report will include the type, quantity, threat level and possible impact of pests and diseases, and output corresponding prevention and control recommendations based on the threat level;

[0097] The module's early warning mechanism makes predictions based on threat levels, identification results, and historical data, automatically generates alerts based on set thresholds, and promptly notifies relevant personnel. Prevention and control recommendation generation is combined with the prevention and control measures evaluation system to provide users with the most appropriate prevention and control strategies to minimize losses.

[0098] The pest and disease early warning module specifically includes:

[0099] Warning signal generation unit: issues warning signals based on the calculated threat level and identification results. If the threat level reaches the threshold, the system automatically generates an alarm and notifies you to take timely prevention and control measures.

[0100] Prevention and control suggestion generation unit: Based on the type and threat level of pests and diseases, the system will provide specific prevention and control suggestions, including chemical control, physical control, and biological control;

[0101] Prevention and control measures evaluation and recommendation unit: Based on the characteristics of different pests and diseases, environmental conditions and local management needs, intelligently recommend prevention and control measures, evaluate the effectiveness and cost of different prevention and control measures, and provide the optimal solution;

[0102] Recording and reporting unit: records the process of identification, analysis, early warning and prevention and control recommendations of all pests and diseases, and generates corresponding reports.

[0103] Reference Figure 2 As shown, new forestry technology intelligent pest control methods include:

[0104] S1: Collect real-time data of the forest area through the data collection module, including climate, soil and vegetation health information;

[0105] S2: The collected data is transmitted to the pest and disease identification and analysis module, which uses artificial intelligence algorithms to perform real-time pest and disease detection and analysis;

[0106] S3: Based on the analysis results, the pest and disease early warning module issues a warning signal and predicts the upcoming outbreak of pests and diseases;

[0107] S4: The prevention and control measures recommendation module recommends prevention and control measures based on the prediction results, including chemical control, physical control, and biological control methods;

[0108] S5: The execution module performs automated prevention and control operations according to the recommended measures and uses the intelligent spraying system for prevention and control.

[0109] The collected data is transmitted to the pest and disease identification and analysis module, and artificial intelligence algorithms are used to perform real-time pest and disease detection and analysis. Specifically, the following steps are involved:

[0110] Image processing technology is used to analyze the image data of pests and diseases collected in the forest area, and the morphological and color characteristics of the diseased area are extracted;

[0111] Based on the convolutional neural network deep learning algorithm, the extracted image features are combined with data from environmental sensors to identify the types of pests and diseases in real time;

[0112] Use artificial intelligence algorithms to conduct multidimensional analysis of image and sensor data, and through comprehensive assessment, determine the types, severity and potential threats of pests and diseases to forest ecosystems.

[0113] Based on the analysis results, the pest and disease early warning module issues a warning signal and predicts the upcoming outbreak of pests and diseases, including:

[0114] Assess the threat level based on the identified pest and disease types and numbers, as well as environmental factors, and predict the future development of pests and diseases by combining historical data and trend analysis;

[0115] Based on the threat level and prediction results of pests and diseases, the pest and disease warning module generates a warning signal. When the threat level exceeds the set threshold, the system will automatically trigger an alarm and notify relevant personnel.

[0116] The prevention and control measures recommendation module recommends prevention and control measures based on the prediction results, including chemical control, physical control, and biological control methods. Specifically,

[0117] The prevention and control measures recommendation module provides specific prevention and control measures based on the type and threat level of different pests and diseases, including:

[0118] Chemical control: Recommend chemical agents and pesticides based on the type of pests and diseases;

[0119] Physical prevention: Based on prevention and control needs, it is recommended to install physical barriers and trapping devices;

[0120] Biological control: Control of pests and diseases by releasing natural enemies and using biological pesticides.

[0121] In summary, the advantages of the present invention are:

[0122] The system uses an efficient sensor network to collect real-time environmental data such as climate, soil moisture, and vegetation health within the forest area, enabling dynamic monitoring of pests and diseases, and providing real-time data support for prevention and control.

[0123] The deep learning-based pest and disease identification module can automatically extract features from image and sensor data, accurately identify pest and disease types through multi-dimensional analysis, and assess their potential threats to forests, effectively improving the accuracy and efficiency of diagnosis.

[0124] By combining environmental factors such as climate conditions, soil moisture, and vegetation health, the system uses methods such as multivariate regression models to accurately calculate the threat level of pests and diseases, thereby providing a basis for recommending subsequent prevention and control measures;

[0125] The system can issue early warning signals based on the calculated threat level, helping relevant personnel take preventive measures in advance to prevent the spread of pests and diseases;

[0126] The prevention and control measures recommendation module provides personalized prevention and control plans based on the type and threat level of different pests and diseases, and combines intelligent devices to automatically execute prevention and control operations, greatly improving prevention and control efficiency and accuracy;

[0127] By updating data in real time, the system can continuously adjust threat levels and control strategies based on the latest environmental changes and pest and disease conditions, ensuring that control measures are always effective;

[0128] Through precise, efficient and intelligent prevention and control, the use of chemical pesticides has been reduced, the ecological environment has been protected, and the utilization efficiency and sustainability of forest resources have been improved.

[0129] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions merely illustrate the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. The new forestry technology intelligent pest control system is characterized by: include: Data collection module, used to collect real-time data on forest pests and diseases, including climate conditions, soil moisture, vegetation health index, pest species and numbers; The pest and disease identification and analysis module is used to analyze the collected real-time data, use artificial intelligence algorithms to identify pests and diseases, and calculate their threat level; The pest and disease early warning module issues pest and disease early warning signals based on identification and calculation results, and provides specific prevention and control suggestions; The prevention and control measures recommendation module intelligently recommends prevention and control measures based on early warning results and specific pest and disease types, including chemical control, physical control, and biological control plans; The execution module performs automated prevention and control operations through intelligent equipment based on recommended prevention and control measures.

2. The new forestry technology intelligent pest control system and method according to claim 1 is characterized in that: The pest and disease identification and analysis module specifically includes: Feature extraction unit: extracts key features from the data acquired by the data acquisition module, extracts the features of the diseased area of ​​plant pests and diseases through image processing technology, and extracts the environmental related features of pests and diseases through sensor data; Pest and disease identification unit: Based on deep learning algorithms, it analyzes image data and sensor data to identify the types of pests and diseases; Threat level calculation unit: Based on the identification results, combined with the type and quantity of pests and diseases, as well as environmental conditions, a pest and disease threat level assessment model is established to calculate the threat level of pests and diseases; Threat level prediction unit: predicts the threat level through regression analysis model, outputs mild, moderate and severe levels, and outputs identification results and threat level assessment report.

3. The new forestry technology intelligent pest control system according to claim 2 is characterized in that: The analysis of image data and sensor data based on deep learning algorithms to identify pest and disease types specifically includes: Use convolutional neural network deep learning algorithms to analyze the collected pest and disease image data and extract feature information from the pest and disease images, including the morphological and color characteristics of the diseased area, to identify the type of pest and disease; Combined with data from environmental sensors, deep learning algorithms are used to process sensor data, extracting environmental factors that cause pests and diseases, and combining this with image data to comprehensively determine the type of pests and diseases. Combining the extracted image features and sensor features, a pest threat level assessment model is established to identify pest types; The pest threat level assessment model formula is: Where x is the input data, including features of image and sensor data, w1 and w2 are weight matrices, b1 and b2 are bias terms, σ is the activation function, θ is all network parameters, and f θ (x) is the output pest and disease category prediction value, is the true label.

4. The new forestry technology intelligent pest control system according to claim 2 is characterized in that: The threat level calculation unit specifically includes: Based on the identified pest and disease types and quantities, combined with environmental factors such as climate conditions, soil moisture, and vegetation health index, the threat level of pests and diseases to the forest ecosystem is calculated using a multivariate regression model machine learning method. The threat level calculation formula is: L=β0+β1C+β2Q+β3E Where C is the severity of the pest type, Q is the number of pests, E is the danger level of environmental conditions, β0, β1, β3 are the coefficients of the regression model, and L is the threat level; Based on the calculation results and combined with the specific ecological and economic impacts, the threat level of pests and diseases is output. By updating environmental data and pest and disease data in real time, the threat level assessment model is dynamically adjusted.

5. The new forestry technology intelligent pest control system according to claim 4 is characterized in that: The prediction of threat level by the regression analysis model, outputting mild, moderate and severe levels, and outputting identification results and threat level assessment reports specifically include: A linear regression model is used to predict the threat level of pests and diseases, with the pest type, quantity, and environmental data as inputs and the output as the predicted value of the threat level; Among them, the linear regression model formula is: Where, is the predicted value of threat level, K0 is the intercept term, K1, K2, K3, K n are regression coefficients, X1, X2, X3, X n is the input feature of the model, ∈ is the error term; Based on the output of the regression model, the threat level is classified as mild, moderate, and severe; A threat level assessment report will be generated based on the output of the regression model, which will include the types, quantity, threat level and possible impact of pests and diseases, and output corresponding prevention and control recommendations based on the threat level.

6. The new forestry technology intelligent pest control system according to claim 1 is characterized in that: The pest and disease early warning module specifically includes: Warning signal generation unit: issues warning signals based on the calculated threat level and identification results. If the threat level reaches the threshold, the system automatically generates an alarm and notifies you to take timely prevention and control measures. Prevention and control suggestion generation unit: Based on the type and threat level of pests and diseases, the system will provide specific prevention and control suggestions, including chemical control, physical control, and biological control; Prevention and control measures evaluation and recommendation unit: Based on the characteristics of different pests and diseases, environmental conditions and local management needs, intelligently recommend prevention and control measures, evaluate the effectiveness and cost of different prevention and control measures, and provide the optimal solution; Recording and reporting unit: records the process of identification, analysis, early warning and prevention and control recommendations of all pests and diseases, and generates corresponding reports.

7. A new forestry technology intelligent pest control method, characterized in that: include: S1: Collect real-time data of the forest area through the data collection module, including climate, soil and vegetation health information; S2: The collected data is transmitted to the pest and disease identification and analysis module, which uses artificial intelligence algorithms to perform real-time pest and disease detection and analysis; S3: Based on the analysis results, the pest and disease early warning module issues a warning signal and predicts the upcoming outbreak of pests and diseases; S4: The prevention and control measures recommendation module recommends prevention and control measures based on the prediction results, including chemical control, physical control, and biological control methods; S5: The execution module performs automated prevention and control operations according to the recommended measures and uses the intelligent spraying system for prevention and control.

8. The method for intelligent pest control using new forestry technology according to claim 7, characterized in that: The method of transmitting the collected data to the pest and disease identification and analysis module and using artificial intelligence algorithms to perform real-time pest and disease detection and analysis specifically includes: Image processing technology is used to analyze the image data of pests and diseases collected in the forest area, and the morphological and color characteristics of the diseased area are extracted; Based on the convolutional neural network deep learning algorithm, the extracted image features are combined with data from environmental sensors to identify the types of pests and diseases in real time; Use artificial intelligence algorithms to conduct multidimensional analysis of image and sensor data, and through comprehensive assessment, determine the types, severity and potential threats of pests and diseases to forest ecosystems.

9. The method for intelligent pest control using new forestry technology according to claim 7, characterized in that: According to the analysis results, the pest warning module issues a warning signal and predicts the upcoming outbreak of pests and diseases, specifically including: Assess the threat level based on the identified pest and disease types and numbers, as well as environmental factors, and predict the future development of pests and diseases by combining historical data and trend analysis; Based on the threat level and prediction results of pests and diseases, the pest and disease warning module generates a warning signal. When the threat level exceeds the set threshold, the system will automatically trigger an alarm and notify relevant personnel.

10. The intelligent pest control method using new forestry technology according to claim 7, characterized in that: The control measures recommendation module recommends control measures based on the prediction results, including chemical control, physical control, and biological control methods, specifically including: The prevention and control measures recommendation module provides specific prevention and control measures based on the type and threat level of different pests and diseases, including: Chemical control: Recommend chemical agents and pesticides based on the type of pests and diseases; Physical prevention: Based on prevention and control needs, it is recommended to install physical barriers and trapping devices; Biological control: Control of pests and diseases by releasing natural enemies and using biological pesticides.

Images