Rubber tree early-stage disease intelligent monitoring and prevention system using biological induction complexing agent

Abstract

The invention discloses a rubber tree early-stage disease intelligent monitoring and prevention system using a biological induction complexing agent, and relates to the technical field of agricultural informatization and intelligent agriculture, and the system comprises a risk assessment module which obtains the sensitivity data of different varieties to specific diseases through a pre-established rubber tree variety database, and obtains the sensitivity data of different varieties to the specific diseases; combining regional environment difference information, extracting climate and soil characteristics from the environment data acquisition module, generating an initial disease risk assessment report for each rubber forest, and obtaining preliminary risk grade distribution; according to the rubber tree early-stage disease intelligent monitoring and prevention system using the biological induction complexing agent, the intelligent level, response timeliness and prevention and control economy of rubber tree disease monitoring and prevention are improved, and the stable yield of rubber forests and the sustainable development of agricultural production are effectively guaranteed.

Description

Technical Field

[0001] This invention relates to the field of agricultural informatization and intelligent agriculture technology, specifically to an intelligent monitoring and control system for early-stage diseases of rubber trees using a biosensor compound. Background Technology

[0002] In agricultural production, the prevention and control of diseases in rubber trees is a crucial research topic, directly impacting the sustainable development and economic benefits of the industry. As an important economic crop, the health of rubber trees affects not only yield but also the stability of the entire industry chain. However, disease occurrence is often influenced by a variety of complex factors, and traditional control methods are insufficient to address this challenge, necessitating innovative technological breakthroughs to improve the accuracy of monitoring and management.

[0003] Currently, rubber tree disease monitoring methods largely rely on uniform schemes, neglecting the differences between different varieties, regions, and growing environments. This "one-size-fits-all" approach often leads to uneven resource allocation; some areas suffer from insufficient monitoring and frequent disease outbreaks, while others receive excessive investment with minimal results. A deeper problem lies in the difficulty of adjusting existing methods in real time to dynamically changing environments and plant conditions, lacking comprehensive consideration of risk factors and flexible response capabilities. Against this backdrop, the core technical challenge of this research focuses on how to achieve differentiated design and dynamic optimization of monitoring schemes. The first key factor is the vastly different characteristics and growing environments of rubber tree varieties. For example, some varieties are inherently sensitive to specific diseases, while certain regions are more prone to pathogens due to hot and humid climates. This necessitates that monitoring methods be tailored to local conditions and individual tree species. A deeper challenge arises from this: how to rationally allocate monitoring frequency and intensity with limited resources, such as in high-risk areas or disease-prone seasons, ensuring comprehensive testing while avoiding excessive investment that leads to uncontrolled costs. For a concrete example, when the rainy season arrives, a rubber plantation has a history of fungal infections, as recorded in historical disease data. However, the existing monitoring program cannot temporarily increase nighttime patrols or adjust the focus of testing, resulting in the failure to detect early signs of disease in time, ultimately causing large-scale losses. Summary of the Invention

[0004] The purpose of this invention is to provide an intelligent monitoring and control system for early-stage diseases of rubber trees using a biosensor compound, thereby solving the problems existing in the prior art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: an intelligent monitoring and control system for early-stage rubber tree diseases using a biosensor compound, comprising a risk assessment module, which acquires sensitivity data of different rubber tree varieties to specific diseases through a pre-established rubber tree variety database, extracts climate and soil characteristics from an environmental data acquisition module in conjunction with regional environmental difference information, and generates an initial disease risk assessment report for each rubber forest to obtain a preliminary risk level distribution; and a historical analysis and priority determination module, which, based on the preliminary risk level distribution, performs comparative analysis using a historical disease record database to extract the time and environmental conditions of past disease occurrences, and performs specific analysis on the impact of seasonal changes. The monitoring frequency scheme is determined through a combination of several modules: a matching module to identify high-risk periods and areas; a monitoring adjustment module to acquire real-time sensor network data supporting the identified monitoring priorities, collect data on current environmental humidity and temperature changes, and combine this with preset thresholds of the disease early warning mechanism. If the detected values ​​exceed the safe range, the dynamic scheme design module is triggered to obtain an adjusted monitoring frequency scheme; and a resource allocation optimization module, based on the monitoring frequency scheme output by the dynamic scheme design module, obtains support from a resource allocation optimization algorithm. This module allocates more monitoring equipment and data processing capabilities to high-risk areas and periods, determines whether the resources meet the demand, and if not, allocates resources from low-risk areas to obtain the final resource allocation plan.

[0006] Preferably, the risk assessment module obtains sensitivity data of different rubber tree varieties to specific diseases through a pre-established rubber tree variety database, and extracts climate and soil characteristics from the environmental data acquisition module in conjunction with regional environmental difference information. It then generates an initial disease risk assessment report for each rubber forest, obtaining a preliminary risk level distribution. This includes obtaining disease sensitivity data from the rubber tree variety database and climate and soil characteristic data of the target area; calculating environmental stress factor values ​​based on the climate and soil characteristic data; weighting and correcting the environmental stress factor values ​​with the disease sensitivity data to obtain a dynamic sensitivity coefficient; calculating the initial disease risk value for each rubber forest based on the dynamic sensitivity coefficient; and mapping the initial disease risk value to a continuous risk level distribution map, thereby generating an initial disease risk assessment report for each rubber forest and obtaining a preliminary risk level distribution.

[0007] Preferably, the historical analysis and priority determination module, based on the preliminary risk level distribution, uses a historical disease record database for comparative analysis, extracts the time and environmental conditions of past disease occurrences, performs feature matching for the impact of seasonal changes, and determines the monitoring priority of high-risk periods and areas. This includes acquiring preliminary risk level distribution data and a historical disease record database to construct a historical disease spatiotemporal dataset; processing the historical disease spatiotemporal dataset using time series decomposition to generate a seasonal change feature vector; acquiring real-time environmental monitoring data, matching the seasonal change feature vector with the real-time environmental monitoring data to obtain a similarity score; generating a spatiotemporal distribution map based on the similarity score, parsing the spatiotemporal distribution map to obtain regional monitoring weights, and determining the monitoring priority of high-risk periods and areas based on the regional monitoring weights.

[0008] Preferably, the monitoring adjustment module, for a determined monitoring priority, acquires sensor network data supported by real-time monitoring capabilities, collects current environmental humidity and temperature changes, and combines them with a preset threshold of the disease early warning mechanism. If the detected value exceeds the safe range, it triggers the dynamic scheme design module to obtain an adjusted monitoring frequency scheme, including activating sensor network nodes according to the determined monitoring priority configuration command, acquiring environmental humidity and temperature change values; calculating the absolute value of the deviation of the environmental humidity and temperature change values ​​relative to the preset threshold; generating an abnormal state trigger command if the absolute value of the deviation exceeds the safe range; calculating the shortened acquisition time interval in response to the abnormal state trigger command, and generating the adjusted monitoring frequency scheme based on the acquisition time interval.

[0009] Preferably, the resource allocation optimization module obtains support from the resource allocation optimization algorithm through the monitoring frequency scheme output by the dynamic scheme design module. It allocates more monitoring equipment and data processing capabilities to high-risk areas and time periods, determines whether resources meet the demand, and if insufficient, allocates resources from low-risk areas. The final resource allocation plan includes: obtaining the monitoring frequency dataset output by the dynamic scheme design module; constructing a high-risk area resource demand matrix based on the monitoring frequency dataset; calculating the difference between the high-risk area resource demand matrix and the collected real-time operating status of the equipment to obtain a resource gap vector; generating a resource replenishment request tag if the resource gap vector is greater than zero; retrieving a list of idle resources in low-risk areas based on the resource replenishment request tag; redirecting resources in the list to generate resource allocation instructions; executing the resource allocation instructions to complete resource migration; and outputting the final resource allocation plan.

[0010] Preferably, the system also includes a disease data analysis module. Based on the final resource allocation plan, it uses a real-time monitoring data stream to continuously collect disease-related indicators of the rubber plantation. It performs multi-dimensional analysis on abnormal data points to determine if any disease is emerging. Specifically, this includes acquiring a real-time data stream containing leaf spectral reflectance values ​​and environmental humidity values, which is collected by activated sensor monitoring nodes; using an isolated forest algorithm to detect outliers in the real-time data stream to obtain abnormal data points; extracting the geospatial location information of the abnormal data points and combining it with historical disease database records to construct a multi-dimensional feature matrix; inputting the multi-dimensional feature matrix into a support vector machine model to calculate a similarity value; and if the similarity value exceeds an alarm threshold, outputting the potential risk type corresponding to the abnormal data point to determine if any disease is emerging in the rubber plantation.

[0011] Preferably, the system also includes an early warning and response optimization module. For identified disease early warning information, the module pushes an alarm signal to the system through a disease early warning mechanism. It then performs a secondary verification of the monitoring frequency adjustment scheme based on a cost control strategy. If the alarm level is high, additional resources are allocated preferentially to obtain an optimized prevention and control response scheme. Specifically, this includes acquiring crop multispectral image data to extract disease feature vectors, and calculating a disease early warning confidence level representing the probability of disease occurrence based on the disease feature vectors. If the early warning confidence level is greater than a preset threshold, an alarm signal strength is output, and the frequency adjustment coefficient generated based on the alarm signal strength is further verified in conjunction with the cost consumption rate.

[0012] Preferably, the early warning and response optimization module, upon identifying early signs of disease, pushes an alarm signal to the system through a disease early warning mechanism. It then performs a secondary verification of the monitoring frequency adjustment scheme in conjunction with a cost control strategy. If the alarm level is high, additional resources are allocated preferentially. The optimized prevention and control response scheme further includes calculating resource allocation weights based on the remaining resources and the alarm signal strength if the secondary verification result indicates a high-risk level. Finally, it integrates the resource allocation weights with the frequency adjustment coefficient to generate a prevention and control execution command, thereby achieving the optimized prevention and control response scheme.

[0013] Preferably, it also includes a dynamic tracking and updating module, which, based on the optimized prevention and control response plan, obtains the latest feedback from the environmental data acquisition module, continuously tracks the dynamic development of the disease, updates the data according to the changing trends, determines whether further adjustments to the monitoring strategy are needed, and obtains the final dynamic monitoring results. Specifically, it includes acquiring the real-time feedback data stream uploaded by the environmental data acquisition module, which is collected based on the optimized prevention and control response plan; parsing the real-time feedback data stream to extract disease feature values; and constructing a dynamic map of disease development based on the disease feature values.

[0014] Preferably, the dynamic tracking and updating module, based on the optimized prevention and control response plan, obtains the latest feedback from the environmental data acquisition module, continuously tracks the dynamic development of the disease, updates the data according to the changing trend, determines whether further adjustments to the monitoring strategy are needed, and obtains the final dynamic monitoring result. This also includes calculating the trend change rate of the disease development dynamic map; if the trend change rate exceeds a threshold, a strategy adjustment instruction is generated; parameters are reset according to the strategy adjustment instruction, and multi-dimensional environmental data is aggregated to form a dynamic monitoring set to output the final dynamic monitoring result.

[0015] As can be seen from the above technical solution, the present invention has the following beneficial effects: This intelligent monitoring and control system for early-stage rubber tree diseases, utilizing a biosensor compound, introduces a risk assessment mechanism based on the sensitivity of rubber tree varieties and regional environmental differences. This transforms disease monitoring from a traditional, uniform approach to refined management tailored to different varieties, regions, and environmental conditions, significantly improving the targeting and accuracy of disease risk identification. By dynamically determining monitoring priorities based on historical disease records and seasonal variation characteristics, the system can identify high-incidence periods and key areas in advance, preventing disease spread due to monitoring blind spots or delayed responses. An adaptive adjustment mechanism based on real-time environmental humidity and temperature changes enables consistent monitoring intensity with actual risk levels, allowing for timely increases in data collection density during periods of rising disease risk. Furthermore, resource allocation optimization strategies further enhance the system's effectiveness. Given limited monitoring equipment and data processing capabilities, resources are prioritized for high-risk areas and critical periods, effectively avoiding both resource waste and insufficient monitoring. Real-time analysis and anomaly identification of multi-source disease-related indicators enable the system to identify and warn of diseases in their early stages, significantly reducing the probability of large-scale outbreaks. Furthermore, cost control constraints are introduced through an early warning and response optimization mechanism, ensuring that control measures maintain reasonable resource consumption levels while guaranteeing effectiveness. Finally, a dynamic tracking and updating mechanism forms a continuous feedback loop, allowing monitoring strategies to be continuously revised and optimized as disease development progresses. This comprehensively improves the intelligence, timeliness, and economic efficiency of rubber tree disease monitoring and control, effectively guaranteeing stable rubber plantation yields and sustainable agricultural production. Attached Figure Description

[0016] Figure 1 This is a connection diagram of the intelligent monitoring and control system for early-stage diseases of rubber trees using biosensor compound agents, as described in this invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] like Figure 1 As shown, this invention provides a technical solution: an intelligent monitoring and control system for early-stage rubber tree diseases using a biosensor compound, comprising a risk assessment module, which acquires sensitivity data of different rubber tree varieties to specific diseases through a pre-established rubber tree variety database, extracts climate and soil characteristics from an environmental data acquisition module in conjunction with regional environmental difference information, and generates an initial disease risk assessment report for each rubber forest to obtain a preliminary risk level distribution; a historical analysis and priority determination module, which, based on the preliminary risk level distribution, compares and analyzes historical disease record databases to extract the time and environmental conditions of past disease occurrences, performs feature matching for seasonal changes, and determines the monitoring priority for high-risk periods and areas; a monitoring adjustment module, which, based on the determined monitoring priority, acquires sensor network data supported by real-time monitoring capabilities, collects current environmental humidity and temperature changes, and, combined with a preset threshold of the disease early warning mechanism, triggers a dynamic scheme design module if the detected value exceeds the safe range to obtain an adjusted monitoring frequency scheme; and a resource allocation optimization module, which, through... The monitoring frequency scheme output by the dynamic scheme design module is used to obtain support from the resource allocation optimization algorithm. More monitoring equipment and data processing capabilities are allocated to high-risk areas and time periods to determine whether the resources meet the needs. If insufficient, resources are transferred from low-risk areas to obtain the final resource allocation plan. The disease data analysis module, based on the final resource allocation plan, uses real-time monitoring data streams to continuously collect disease-related indicators of rubber forests. It performs multi-dimensional analysis on abnormal data points to determine whether there are disease outbreaks. The early warning and response optimization module pushes alarm signals to the system through the disease early warning mechanism for the identified disease outbreaks. Combined with cost control strategies, the monitoring frequency adjustment scheme is re-verified. If the alarm level is high, additional resources are allocated first to obtain an optimized prevention and control response scheme. The dynamic tracking and updating module, based on the optimized prevention and control response scheme, obtains the latest feedback from the environmental data acquisition module, continuously tracks the development of diseases, updates the data based on the changing trends, and determines whether further adjustments to the monitoring strategy are needed to obtain the final dynamic monitoring results.

[0019] In the above implementation, the system is based on the multi-factor coupling mechanism of rubber tree diseases, comprehensively modeling the differences in rubber tree varieties, changes in environmental conditions, and historical disease evolution patterns. First, the risk assessment module quantifies the disease susceptibility of different varieties using a rubber tree variety database, and integrates these characteristics with regional climate and soil parameters to form a risk level distribution that reflects the actual regional conditions at the initial monitoring stage. Subsequently, the historical analysis and priority determination module uses the time nodes of diseases that have occurred in the historical disease record database and their corresponding environmental conditions to match the current risk distribution with temporal and seasonal characteristics, identifying key periods and spatial areas where diseases are prevalent. Based on this, the monitoring and adjustment module receives real-time environmental humidity and temperature data collected by the sensor network and compares it with the threshold model in the disease early warning mechanism to quickly identify abnormal environmental conditions; when environmental parameters deviate from the safe range, the dynamic scheme design module adaptively adjusts the monitoring frequency. The resource allocation optimization module further introduces a resource scheduling algorithm, prioritizing the use of limited monitoring equipment and data processing capabilities for high-risk areas and high-risk periods. The disease data analysis module identifies potential disease precursors through multi-dimensional correlation analysis of real-time monitoring data. The early warning and response optimization module dynamically adjusts the intensity of control resource allocation based on a comprehensive alarm level and cost control strategy. Finally, the dynamic tracking and updating module forms a closed-loop feedback mechanism, enabling the system to continuously adjust monitoring and control strategies as disease trends develop.

[0020] In the above implementation, the system, through the collaborative work of multiple modules, realizes a shift from "passive discovery" to "proactive prediction and intervention" of early-stage rubber tree diseases. On the one hand, the risk assessment mechanism based on variety sensitivity and regional environmental characteristics improves the pertinence and accuracy of disease risk judgment; on the other hand, by introducing historical disease data and matching it with seasonal characteristics, the probability of misjudgment is effectively reduced. The dynamic monitoring frequency adjustment and resource allocation optimization mechanism enables monitoring resources to be concentrated on high-risk areas and key periods, thereby improving overall monitoring efficiency under limited resource volume. At the same time, the multi-dimensional disease data analysis and hierarchical early warning response mechanism help to take timely control measures when diseases are still in their nascent stage, reducing the risk of disease spread and control costs, and improving the intelligence level and stability of rubber forest disease management.

[0021] The risk assessment module, through a pre-established rubber tree variety database, acquires sensitivity data of different varieties to specific diseases. Combined with regional environmental differences, it extracts climate and soil characteristics from the environmental data acquisition module. For each rubber plantation, it generates an initial disease risk assessment report, obtaining a preliminary risk level distribution. This includes acquiring disease sensitivity data from the rubber tree variety database and climate and soil characteristic data of the target area; calculating environmental stress factor values ​​based on the climate and soil characteristic data; weighting and correcting the environmental stress factor values ​​with the disease sensitivity data to obtain a dynamic sensitivity coefficient; calculating the initial disease risk value for each rubber plantation based on the dynamic sensitivity coefficient; and mapping the initial disease risk value to a continuous risk level distribution map, thereby generating an initial disease risk assessment report and obtaining a preliminary risk level distribution for each rubber plantation.

[0022] In this embodiment, during actual operation, the risk assessment module first reads the spatial identification information of the target rubber plantation to determine the corresponding rubber tree variety category. It then retrieves the disease sensitivity data of that variety against the target disease from the rubber tree variety database. This disease sensitivity data is a single, definitive value, determined by statistically analyzing the number of disease occurrences, disease coverage area, and yield reduction percentage caused by the disease over at least three complete growth cycles. This data is then standardized before being stored in the database. After obtaining the disease sensitivity data, the system retrieves climate and soil characteristic data corresponding to the spatial location of the rubber plantation through the environmental data acquisition module. The climate characteristic data is obtained from continuous data collected within the assessment period. The collected data consist of temperature, humidity, and rainfall data. Soil characteristic data comprises soil moisture content, soil aeration, and soil nutrient status data collected continuously within the same period. All environmental data are sampled at fixed time intervals, and the final input values ​​are obtained by averaging after removing outliers. Subsequently, the system compares each of the above climate and soil characteristic data with its corresponding safety threshold. The safety threshold is determined by selecting sample years with disease occurrence frequencies higher than a set proportion from the historical disease record database, statistically analyzing the concentrated distribution range of the corresponding environmental data in those years, and using the upper and lower boundaries of this range as the safety threshold for that environmental parameter. When the actual collected values... When the threshold range is exceeded, the system clearly determines that the environmental parameter constitutes environmental stress on the rubber tree. After completing the threshold determination for all environmental parameters, the system assigns a corresponding stress impact value to each parameter determined to constitute environmental stress. This value is determined by the correlation strength between the magnitude of change of the environmental parameter and the severity of disease occurrence in historical data, and is stored in the system with a fixed weight. Subsequently, the system accumulates all weighted stress impact values ​​to obtain a unique environmental stress factor value. This environmental stress factor value is used to fully characterize the degree to which current environmental conditions promote the occurrence of diseases in the target rubber forest. After obtaining the environmental stress factor value, the system performs a weighted correction process with disease sensitivity data, where the disease sensitivity data... Using the base value as the baseline and environmental stress factor values ​​as correction values, these values ​​are superimposed at a pre-set fixed ratio to form a dynamic sensitivity coefficient. This dynamic sensitivity coefficient is a single, fixed value used to reflect the true susceptibility of the rubber plantation to the target disease under the current specific environmental conditions. Subsequently, the system uses the dynamic sensitivity coefficient as the core input parameter, combined with the actual planting area data, planting quantity data per unit area, and historical disease occurrence ratio data in the same region for comprehensive calculation. The planting area data and planting quantity data are both derived from the basic rubber plantation archives, and the historical disease occurrence ratio data are derived from the statistical results of the same region in the historical disease record database. The initial disease risk value corresponding to the rubber plantation is obtained through a fixed weight superposition method.After obtaining the initial disease risk values, the system maps these values ​​to intervals according to a pre-set risk level classification standard. This standard is also based on historical disease occurrence results. By statistically correlating historical risk values ​​with actual disease occurrence results, multiple continuous and non-overlapping risk level intervals are formed. Finally, the system integrates the risk level results of each rubber plantation according to its spatial location, generating a continuously distributed risk level distribution map. This distribution map, along with the corresponding numerical descriptions, is output as an initial disease risk assessment report, thus obtaining a quantifiable, reproducible, and directly applicable preliminary risk level distribution result for subsequent monitoring and decision-making.

[0023] The historical analysis and priority determination module, based on the preliminary risk level distribution, uses a historical disease record database for comparative analysis to extract the time and environmental conditions of past disease occurrences. It performs feature matching to account for seasonal variations and determines the monitoring priorities for high-risk periods and areas. This includes acquiring preliminary risk level distribution data and the historical disease record database to construct a historical disease spatiotemporal dataset; processing the historical disease spatiotemporal dataset using time series decomposition to generate seasonal variation feature vectors; acquiring real-time environmental monitoring data and matching the seasonal variation feature vectors with the real-time environmental monitoring data to obtain a similarity score; generating a spatiotemporal distribution map based on the similarity score; parsing the spatiotemporal distribution map to obtain regional monitoring weights; and determining the monitoring priorities for high-risk periods and areas based on the regional monitoring weights.

[0024] In this embodiment, when the historical analysis and priority determination module is running, the system first receives preliminary risk level distribution data output by the risk assessment module. This data clearly records the risk level result and spatial location identifier of each rubber plantation within the current assessment period. Simultaneously, the system retrieves historical disease occurrence records from the historical disease record database that correspond to the spatial location of the aforementioned rubber plantations. These historical disease occurrence records include the specific date information of the disease occurrence and the corresponding environmental condition data during the disease occurrence period. The system aligns the preliminary risk level distribution data and the historical disease occurrence records according to a unified spatial coordinate and time scale, thereby constructing a historical disease spatiotemporal dataset. The time scale uses the natural day as the smallest unit, and the spatial scale uses a single rubber plantation as the smallest unit. After constructing the historical disease spatiotemporal dataset, the system chronologically arranges the disease occurrence frequency of each rubber plantation over multiple historical years. Based on this arrangement, it performs periodic analysis on the disease occurrence data. Specifically, it statistically analyzes the disease occurrence time points over consecutive years, identifies recurring high-incidence disease situations within the same time interval, and extracts periodic variation characteristics reflecting seasonal changes in diseases. Finally, it transforms these periodic variation characteristics into a seasonal variation feature vector, which consists of multiple defined values. These values ​​are determined by considering at least three historical data points. The seasonal variation feature vector is obtained by averaging the number of disease occurrences and the extent of disease impact within the same time interval throughout the year. After obtaining the seasonal variation feature vector, the system further acquires real-time environmental monitoring data for the current assessment period. This real-time environmental monitoring data includes temperature data, air humidity data, and rainfall data consistent with the environmental conditions recorded in historical disease occurrence records. All real-time environmental monitoring data originates from continuous sampling results of the environmental data acquisition module within fixed time intervals, and stable input values ​​are formed through averaging after removing outliers. Subsequently, the system compares the real-time environmental monitoring data with the seasonal variation feature vector item by item according to the corresponding time interval and environmental condition type. The system calculates the similarity score by comparing the real-time environmental status with the seasonal variation feature vector in terms of numerical trend and fluctuation amplitude. This similarity score is a single, definite value, and its magnitude is directly determined by the degree of overlap between the real-time environmental monitoring data and the environmental data of historical high-incidence seasons of diseases. After obtaining the similarity score, the system uses it as a basis, combined with the risk level results and spatial distribution relationships of each rubber forest in the preliminary risk level distribution data, to generate a corresponding spatiotemporal distribution map. This spatiotemporal distribution map marks high similarity time intervals on the time axis and marks the locations of high-risk rubber forests in the spatial dimension, thus realizing a centralized expression of disease risk in time and space.Subsequently, the system statistically summarizes the similarity scores of each rubber plantation in different time intervals within the spatiotemporal distribution map. The similarity scores are then weighted according to a pre-set fixed ratio with the corresponding risk level values ​​of the rubber plantations to obtain regional monitoring weights. Each regional monitoring weight is a single, fixed value, directly reflecting the overall risk level of disease occurrence in that region during the current time period. Finally, the system sorts regions based on their regional monitoring weights, clearly identifying time intervals and spatial areas with regional monitoring weights exceeding a preset priority threshold as high-risk periods and high-risk areas. The priority threshold is determined by statistically analyzing the distribution of regional monitoring weights before the actual occurrence of diseases in the historical disease record database, and selecting a lower limit value that covers the vast majority of disease occurrence scenarios as the judgment criterion, thus ultimately determining the monitoring priority.

[0025] The monitoring and adjustment module, based on a determined monitoring priority, acquires real-time monitoring data from sensor networks supported by the monitoring capabilities, collects current environmental humidity and temperature changes, and combines this with a preset threshold of the disease early warning mechanism. If the detected values ​​exceed the safe range, the dynamic scheme design module is triggered to obtain an adjusted monitoring frequency scheme. This includes activating sensor network nodes according to the determined monitoring priority configuration command, acquiring environmental humidity and temperature change values; calculating the absolute value of the deviation of the environmental humidity and temperature change values ​​relative to the preset threshold; generating an abnormal state trigger command if the absolute value of the deviation exceeds the safe range; and calculating a shortened acquisition time interval in response to the abnormal state trigger command, and generating the adjusted monitoring frequency scheme based on the acquisition time interval.

[0026] In this embodiment, during execution, the monitoring and adjustment module first receives the monitoring priority result output by the historical analysis and priority determination module. This monitoring priority result identifies the monitoring importance of different rubber plantation areas in the current time period in a defined numerical form. Based on this monitoring priority result, the system generates a corresponding configuration instruction. This configuration instruction explicitly includes the sensor network node number to be activated and the corresponding working status parameters. Subsequently, the system issues the configuration instruction to the sensor network nodes deployed in the target rubber plantation area, causing the sensor network nodes corresponding to high monitoring priorities to enter a continuous data acquisition state. After the sensor network nodes are activated, the system acquires environmental humidity values ​​and temperature change data according to a preset basic data acquisition time interval. The system calculates the values, where the ambient humidity value is directly output by the humidity sensor within a single acquisition cycle, and the temperature change value is calculated by subtracting the temperature sampling results from two consecutive acquisition cycles. All acquired data undergoes consistency verification before entering the calculation process to eliminate abnormal values ​​caused by communication anomalies or sensor failures. Subsequently, the system calls the pre-set environmental safety threshold parameters in the disease early warning mechanism to compare the current ambient humidity value and temperature change value against the thresholds. The ambient humidity threshold is determined by selecting humidity data samples corresponding to the period before disease occurrence from the historical disease record database, statistically analyzing their concentrated distribution range, and taking the upper and lower boundary values ​​as the safety range. The temperature change threshold is determined by statistically analyzing the humidity data samples before disease occurrence... Historical data on temperature fluctuations over a continuous time period are used to determine the maximum permissible range of temperature changes before disease outbreaks, which is then defined as a safety threshold. After determining the threshold, the system calculates the deviations between the current ambient humidity and its corresponding safety threshold, as well as the deviations between the current temperature change and its corresponding safety threshold. The absolute values ​​of these deviations are processed to ensure that the magnitude of the deviation accurately reflects the intensity of environmental changes. When the absolute value of either deviation exceeds the corresponding safety threshold, the system immediately determines that the environmental state of the monitored area is abnormal and generates an abnormal state trigger command. After the abnormal state trigger command is generated, the monitoring and adjustment module immediately enters the response processing flow, recalculating the current sensor network's acquisition strategy. The calculation involves using the original baseline sampling time interval as an initial parameter, determining the shortening ratio based on the degree to which the absolute value of the deviation exceeds a threshold. The larger the absolute value of the deviation, the higher the corresponding shortening ratio of the sampling time interval, thus calculating the shortened sampling time interval, which is a single, fixed value. Subsequently, the system uniformly adjusts the sampling frequency of the activated sensor network nodes based on this sampling time interval, and solidifies the adjusted sampling frequency parameter into the adjusted monitoring frequency scheme for continuous execution in subsequent monitoring processes. This ensures that environmental humidity and temperature change data can be acquired with higher temporal resolution when environmental conditions significantly deviate from the safe range, providing a sufficient, continuous, and reliable data foundation for further assessment of disease risks.

[0027] The resource allocation optimization module, through the monitoring frequency scheme output by the dynamic scheme design module, obtains support from the resource allocation optimization algorithm. It allocates more monitoring equipment and data processing capabilities to high-risk areas and time periods, determines whether resources meet the demand, and if insufficient, allocates resources from low-risk areas. The final resource allocation plan includes: obtaining the monitoring frequency dataset output by the dynamic scheme design module; constructing a high-risk area resource demand matrix based on the monitoring frequency dataset; calculating the difference between the high-risk area resource demand matrix and the collected real-time operating status of the equipment to obtain a resource gap vector; generating a resource replenishment request tag if the resource gap vector is greater than zero; retrieving a list of idle resources in low-risk areas based on the resource replenishment request tag, and redirecting the resources in the list to generate resource allocation instructions; executing the resource allocation instructions to complete resource migration, and outputting the final resource allocation plan.

[0028] In this embodiment, when the resource allocation optimization module is running, it first receives the monitoring frequency dataset output by the dynamic scheme design module. This monitoring frequency dataset records the monitoring frequency requirements corresponding to different rubber forest areas in the current time period in a defined numerical form. Based on this monitoring frequency dataset, the system reads the monitoring frequency values ​​of each high-risk area one by one, and combines this with the amount of data collection that a single monitoring device can complete per unit time and the data processing capacity required per unit time to calculate the number of monitoring devices and data processing capacity required for each high-risk area in the current monitoring cycle. This constructs a high-risk area resource demand matrix, where each value in the resource demand matrix is ​​a defined value, determined by monitoring... The frequency measurement values ​​are converted to the single device capability parameters. After constructing the resource demand matrix for high-risk areas, the system further collects real-time operating status data of all monitoring devices in the current system. This operating status data includes whether the device is in working condition, the current workload level, and the available data processing capacity margin. The system compares the above real-time operating status data with the resource demand matrix for high-risk areas item by item. By calculating the difference between the demand quantity and the available quantity, a resource gap vector is obtained. Each value in the resource gap vector is used to clearly indicate whether there is a resource shortage in the corresponding high-risk area in the current time period. When any resource gap vector value is greater than zero, the system clearly determines that the area is in short supply. High-risk areas are identified as having insufficient resources, and corresponding resource replenishment request tags are generated accordingly. After the resource replenishment request tag is generated, the system uses the tag as a trigger condition to perform a resource status search on low-risk areas. Specifically, this involves reading the current operating load data of monitoring equipment in low-risk areas and filtering out monitoring equipment in a low-load or idle state, along with their corresponding data processing capabilities, to form a list of idle resources. The criterion for determining idle resources is that their current workload is lower than a preset idle threshold. This idle threshold is determined by statistically analyzing the long-term average load level of equipment under normal system operation and selecting a fixed percentage of loads below this average load level as the criterion. Subsequently, the system, based on the resource shortage indicated in the resource replenishment request tag... The system selects a corresponding number of monitoring devices and data processing resources from the list of idle resources in priority order, and generates a clear resource allocation instruction. This instruction includes specific information such as the resource source area, the target high-risk area, and the allocation quantity. After the resource allocation instruction is generated, the system executes it to complete the migration or reallocation of monitoring devices and data processing capabilities from low-risk areas to high-risk areas. Once the resource allocation is complete, the system performs a complete update of the global resource status and outputs the updated resource configuration results as the final resource allocation plan for continuous execution within the current monitoring cycle. This ensures that high-risk areas receive sufficient and matching monitoring resources during periods of high monitoring demand.

[0029] The disease data analysis module, based on the final resource allocation plan, continuously collects disease-related indicators of the rubber plantation using a real-time monitoring data stream. It performs multi-dimensional analysis on abnormal data points to determine the presence of potential disease outbreaks. This includes acquiring a real-time data stream containing leaf spectral reflectance and environmental humidity values, collected by activated sensor monitoring nodes; using an isolated forest algorithm to detect outliers in the real-time data stream to identify abnormal data points; extracting the geospatial location information of these abnormal data points and combining it with historical disease database records to construct a multi-dimensional feature matrix; inputting this multi-dimensional feature matrix into a support vector machine model to calculate a similarity value; and if the similarity value exceeds an alarm threshold, outputting the potential risk type corresponding to the abnormal data point to determine whether potential disease outbreaks exist within the rubber plantation.

[0030] In this embodiment, when the disease data analysis module is running, it first determines the range of currently activated sensor monitoring nodes and their corresponding data acquisition task configurations based on the final resource allocation plan output by the resource allocation optimization module. Then, the activated sensor monitoring nodes continuously collect disease-related indicators within the rubber plantation and transmit the collection results to the disease data analysis module in the form of a real-time data stream. This real-time data stream includes at least leaf spectral reflectance values ​​and environmental humidity values. The leaf spectral reflectance values ​​are obtained by spectral acquisition sensor nodes deployed within the rubber plantation measuring the reflectance characteristics of the rubber tree leaf surface within a fixed acquisition period. The environmental humidity values ​​are obtained from measurements taken within the same area. Humidity sensor nodes synchronously collect data. All collected data undergoes time alignment and abnormal communication data removal before entering the analysis process to ensure data consistency. After obtaining a stable real-time data stream, the system uses the isolated forest algorithm to detect outliers in the real-time data stream. Specifically, leaf spectral reflectance values ​​and ambient humidity values ​​are used as joint input features. All data samples within the current collection period are randomly subsampled and path lengths are statistically analyzed. The degree of anomaly is calculated based on the isolation level of each data sample in the overall data distribution, thereby clearly identifying data samples that deviate from the normal distribution range as abnormal data points. The anomaly detection threshold is determined by... During the initial system deployment phase, baseline data collected under disease-free conditions is statistically analyzed, and values ​​covering the upper limit of normal fluctuation range are selected as outlier criteria. After identifying abnormal data points, the system further extracts the geospatial location information corresponding to these abnormal data points. This geospatial location information is directly obtained from the fixed coordinate information bound to the sensor monitoring nodes during deployment. This spatial location information is then correlated and matched with historical disease information recorded in the historical disease database, such as disease occurrence location, disease type, and occurrence time. This constructs a multi-dimensional feature matrix containing abnormal spectral features, abnormal environmental humidity features, and spatial location features. All feature parameters are derived from specific fields in the collected data or historical disease record database. After constructing the multi-dimensional feature matrix, the system inputs the multi-dimensional feature matrix into the support vector machine model for calculation. The support vector machine model is a classification model trained using labeled disease sample data in the historical disease database before system deployment. Its training samples include spectral reflectance features, environmental humidity features, and spatial distribution features corresponding to the occurrence of known diseases. The model output is the similarity value between abnormal data points and known disease samples. This similarity value is a single, definite value used to quantify the degree of closeness between the current abnormal state and the historical disease state.After obtaining the similarity value, the system compares it with an alarm threshold. The alarm threshold is determined by statistically analyzing the similarity distribution range of confirmed disease samples during model training and selecting a lower limit that covers the vast majority of real disease samples as the alarm criterion. When the similarity value exceeds this alarm threshold, the system clearly determines that the corresponding abnormal data point has disease-related characteristics and outputs the potential risk type corresponding to the abnormal data point. This indicates potential disease outbreaks within the rubber plantation, providing a direct, clear, and actionable decision-making basis for subsequent early warning and control responses.

[0031] The early warning and response optimization module, upon identifying early signs of disease, pushes alarm signals to the system through a disease early warning mechanism. It then performs a secondary verification of the monitoring frequency adjustment scheme based on cost control strategies. If the alarm level is high, additional resources are allocated preferentially. The optimized prevention and control response scheme includes acquiring crop multispectral image data to extract disease feature vectors and calculating a sign confidence level representing the likelihood of disease occurrence based on these feature vectors. If the sign confidence level is greater than a preset threshold, an alarm signal strength is output, and the frequency adjustment coefficient generated based on the alarm signal strength is further verified using the cost consumption rate. If the secondary verification result indicates a high-risk level, a resource allocation weight is calculated based on the remaining resources and the alarm signal strength. Finally, the resource allocation weight and the frequency adjustment coefficient are fused to generate a prevention and control execution command, thereby achieving the optimized prevention and control response scheme.

[0032] In this embodiment, the early warning and response optimization module first receives disease early warning information output by the disease data analysis module, and then invokes the deployed disease early warning mechanism to enter the alarm assessment process. The system acquires crop multispectral image data through activated sensor monitoring nodes. The multispectral image data is obtained by periodically imaging rubber tree leaves from fixed monitoring locations. During the acquisition process, a predetermined imaging resolution and imaging time window are used to ensure data comparability. Subsequently, the system performs standardization processing on the multispectral image data, including removing light interference and background noise, and on this basis, extracts disease feature vectors reflecting changes in leaf color, texture abnormalities, and reflectance characteristics. The parameters of the disease feature vectors are... All data are derived from image feature indicators confirmed to correspond with disease occurrence in historical disease samples. Their value ranges and weights were fixed during system deployment. After obtaining the disease feature vector, the system calculates the early warning confidence level based on the degree of matching between the disease feature vector and the features of historical disease samples. This early warning confidence level is a single, definite value used to characterize the probability of disease occurrence under the current observation state; its magnitude is directly determined by the degree of feature matching. Subsequently, the system compares the early warning confidence level with a preset threshold. The preset threshold is determined by statistically analyzing the confidence level distribution corresponding to confirmed disease occurrences in the historical disease database and selecting a lower limit value that covers the vast majority of real disease samples as the judgment criterion. When the confidence level of a disease hazard exceeds a preset threshold, the system clearly determines that the current hazard poses a real risk and outputs a corresponding alarm signal strength based on the confidence level. This alarm signal strength is a defined level value used to distinguish different risk levels. After generating the alarm signal strength, the system further introduces a cost control strategy to perform a secondary verification of the monitoring frequency adjustment results generated based on the alarm signal strength. The cost consumption rate is determined by real-time statistical analysis of the resource consumption generated by the current monitoring equipment operation, data processing, and communication, and comparing it with the system's preset acceptable consumption range. When the resource consumption corresponding to the frequency adjustment exceeds the acceptable range, a verification constraint is triggered. If the secondary verification result still clearly indicates a high-risk level... Furthermore, without violating cost control boundaries, the system calculates resource allocation weights based on the remaining available resources and alarm signal strength. These resource allocation weights are fixed values ​​that directly reflect the priority of additional monitoring equipment and data processing capabilities under the current alarm state. Finally, the system integrates these resource allocation weights with the corresponding frequency adjustment coefficients to generate a clear prevention and control execution instruction. This instruction includes specific parameters such as the amount of additional resources required, the adjusted monitoring frequency, and the execution duration. The instruction is then issued for execution, thus forming an optimized prevention and control response plan under the premise of controllable risk and cost, achieving accurate early warning and efficient response to early diseases of rubber trees.

[0033] The dynamic tracking and updating module, based on the optimized prevention and control response plan, obtains the latest feedback from the environmental data acquisition module, continuously tracks the dynamic development of the disease, updates the data according to the changing trends, determines whether further adjustments to the monitoring strategy are needed, and obtains the final dynamic monitoring results. This includes acquiring the real-time feedback data stream uploaded by the environmental data acquisition module, which is collected based on the optimized prevention and control response plan; parsing the real-time feedback data stream to extract disease feature values; constructing a dynamic disease development map based on the disease feature values; calculating the trend change rate of the dynamic disease development map; generating a strategy adjustment instruction if the trend change rate exceeds a threshold; resetting parameters according to the strategy adjustment instruction and aggregating multi-dimensional environmental data to form a dynamic monitoring set, thus outputting the final dynamic monitoring results.

[0034] In this embodiment, when the dynamic tracking and updating module is running, it first determines the acquisition parameters and acquisition frequency configurations of various sensor nodes under the current monitoring strategy based on the optimized prevention and control response plan output by the early warning and response optimization module. Based on this, it acquires the real-time feedback data stream uploaded by the environmental data acquisition module. The real-time feedback data stream is a set of data continuously collected under the constraints of the optimized prevention and control response plan. Its data content includes environmental parameter data directly related to the occurrence and development of the disease, as well as biosensor feedback data. All data is marked with a unified timestamp to ensure temporal consistency. Subsequently, the system processes the real-time feedback data stream... The system performs analytical processing to extract disease characteristic values ​​that characterize changes in disease status. The specific content of these characteristic values ​​is determined by historical disease analysis results, and all are deterministic indicators showing a stable trend during disease development. After extracting the characteristic values, the system arranges them in chronological order and constructs a dynamic disease development map based on corresponding spatial location information. This dynamic map continuously reflects the overall trend of disease characteristics changing over time within the same rubber plantation area. After constructing the dynamic map, the system statistically calculates the magnitude of disease characteristic changes in adjacent time periods. The system obtains a trend change rate, which is a single, definite value determined by normalizing the increase or decrease of disease characteristic values ​​within a continuous monitoring period. This rate characterizes the speed and direction of disease development. Subsequently, the system compares the trend change rate with a preset threshold. This threshold is determined by statistically analyzing the rate of change intervals corresponding to the transition from a mild to a severe state in historical disease development samples, and selecting a critical value that accurately distinguishes between stable and deteriorating states as the judgment criterion. When the trend change rate exceeds this threshold, the system clearly determines that the current disease development trend has changed significantly and generates a strategy. Adjustment instructions: After generating the strategy adjustment instructions, the system resets the relevant parameters in the current monitoring strategy according to the instructions. These parameters include, but are not limited to, monitoring frequency, key monitoring area identification, and data aggregation cycle. The parameter reset process is strictly executed according to the definite values ​​given in the strategy adjustment instructions to avoid introducing uncertainties. Subsequently, after completing the parameter reset, the system re-aggregates the multidimensional environmental data from different sensor nodes to form a dynamic monitoring set. The dynamic monitoring set fully reflects the current status of rubber forest diseases and their changing trends in both time and space dimensions. Finally, the system outputs the dynamic monitoring set as the final dynamic monitoring result.

[0035] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A smart monitoring and control system for early-stage diseases of rubber trees using a biosensor compound, characterized in that, include: The risk assessment module obtains sensitivity data of different varieties to specific diseases through a pre-established rubber tree variety database. Combined with regional environmental difference information, it extracts climate and soil characteristics from the environmental data acquisition module and generates an initial disease risk assessment report for each rubber forest, obtaining a preliminary risk level distribution. The historical analysis and priority determination module uses a historical disease record database for comparative analysis based on the preliminary risk level distribution. It extracts the time and environmental conditions of past disease occurrences, performs feature matching based on the impact of seasonal changes, and determines the monitoring priority for high-risk periods and areas. The monitoring and adjustment module acquires real-time monitoring network data supported by the sensor network for the determined monitoring priority, collects the current environmental humidity and temperature changes, and combines them with the preset threshold of the disease early warning mechanism. If the detected value exceeds the safe range, the dynamic scheme design module is triggered to obtain the adjusted monitoring frequency scheme. The resource allocation optimization module obtains support from the resource allocation optimization algorithm through the monitoring frequency scheme output by the dynamic scheme design module. It allocates more monitoring equipment and data processing capabilities to high-risk areas and time periods, determines whether the resources meet the needs, and if not, allocates resources from low-risk areas to obtain the final resource allocation plan.

2. The intelligent monitoring and control system for early-stage diseases of rubber trees using a biosensor compound as described in claim 1, characterized in that: The risk assessment module obtains sensitivity data for specific diseases of different rubber tree varieties from a pre-established rubber tree variety database. Combined with regional environmental differences information, it extracts climate and soil characteristics from the environmental data acquisition module to generate an initial disease risk assessment report for each rubber forest, resulting in a preliminary risk level distribution including: Obtain disease sensitivity data from the rubber tree variety database, as well as climate and soil characteristic data for the target area; Calculate the environmental stress factor values ​​based on the climate characteristic data and the soil characteristic data; The dynamic sensitivity coefficient is obtained by weighting and correcting the environmental stress factor values ​​with the disease sensitivity data. The initial disease risk value for each rubber plantation is calculated based on the aforementioned dynamic sensitivity coefficient; The initial disease risk values ​​are mapped to a continuous risk level distribution map, thereby generating an initial disease risk assessment report for each rubber plantation and obtaining a preliminary risk level distribution.

3. The intelligent monitoring and control system for early-stage diseases of rubber trees using a biosensor compound as described in claim 1, characterized in that: The historical analysis and priority determination module, based on the preliminary risk level distribution, uses a historical disease record database for comparative analysis, extracts the time and environmental conditions of past disease occurrences, performs feature matching to account for seasonal changes, and determines the monitoring priority for high-risk periods and areas, including: To acquire preliminary risk level distribution data and a historical disease record database to construct a historical disease spatiotemporal dataset; The historical disease spatiotemporal dataset is processed using time series decomposition to generate seasonal variation feature vectors. Acquire real-time environmental monitoring data, and match the seasonal change feature vector with the real-time environmental monitoring data to obtain a similarity score; A spatiotemporal distribution map is generated based on the similarity score. The spatiotemporal distribution map is analyzed to obtain regional monitoring weights. Based on the regional monitoring weights, the monitoring priority of high-risk periods and regions is determined.

4. The intelligent monitoring and control system for early-stage diseases of rubber trees using a biosensor compound as described in claim 1, characterized in that: The monitoring and adjustment module, based on the determined monitoring priority, acquires sensor network data supported by real-time monitoring capabilities, collects current environmental humidity and temperature changes, and combines this with the preset threshold of the disease early warning mechanism. If the detected value exceeds the safe range, the dynamic scheme design module is triggered to obtain the adjusted monitoring frequency scheme, including: Activate sensor network nodes according to the determined monitoring priority configuration instructions to obtain ambient humidity and temperature change values; Calculate the absolute value of the deviation between the ambient humidity value and the temperature change value relative to a preset threshold; If the absolute value of the deviation exceeds the safe range, an abnormal state trigger command is generated. In response to the abnormal state trigger command, the shortened acquisition time interval is calculated, and an adjusted monitoring frequency scheme is generated based on the acquisition time interval.

5. The intelligent monitoring and control system for early-stage diseases of rubber trees using a biosensor compound as described in claim 1, characterized in that: The resource allocation optimization module, through the monitoring frequency scheme output by the dynamic scheme design module, obtains support from the resource allocation optimization algorithm, allocates more monitoring equipment and data processing capabilities to high-risk areas and time periods, determines whether the resources meet the demand, and if insufficient, allocates resources from low-risk areas, resulting in the final resource allocation plan including: Obtain the monitoring frequency dataset output by the dynamic scheme design module, and construct a resource demand matrix for high-risk areas based on the monitoring frequency dataset; The resource gap vector is obtained by calculating the difference between the resource demand matrix of the high-risk area and the collected real-time operating status of the equipment. If the resource gap vector is greater than zero, a resource replenishment request tag is generated. Based on the resource replenishment request tag, retrieve the list of idle resources in low-risk areas, and redirect the resources in the list of idle resources to generate resource allocation instructions; The resource allocation instructions are executed to complete the resource migration and output the final resource allocation plan.

6. The intelligent monitoring and control system for early-stage diseases of rubber trees using a biosensor compound as described in claim 1, characterized in that, It also includes a disease data analysis module, which, based on the final resource allocation plan, uses real-time monitoring data streams to continuously collect disease-related indicators of rubber plantations, and conducts multi-dimensional analysis of abnormal data points to determine whether there are signs of disease. Specifically, this includes: A real-time data stream containing leaf spectral reflectance values ​​and ambient humidity values ​​is acquired, and the real-time data stream is collected by an activated sensing and monitoring node. The isolated forest algorithm is used to detect outliers in the real-time data stream to identify abnormal data points. Extract the geospatial location information of the abnormal data points and combine it with historical disease database records to construct a multi-dimensional feature matrix; The multi-dimensional feature matrix is ​​input into the support vector machine model to calculate the similarity value; If the similarity value exceeds the alarm threshold, the potential risk type corresponding to the abnormal data point is output to determine whether there are signs of disease in the rubber plantation.

7. The intelligent monitoring and control system for early-stage diseases of rubber trees using a biosensor compound as described in claim 6, characterized in that, It also includes an early warning and response optimization module. For identified early signs of disease, it pushes alarm signals to the system through a disease early warning mechanism. Combined with cost control strategies, it performs a secondary verification of the monitoring frequency adjustment plan. If the alarm level is high, it prioritizes the allocation of additional resources to obtain an optimized prevention and control response plan, specifically including: Crop multispectral image data is acquired to extract disease feature vectors, and the early sign confidence level, which characterizes the probability of disease occurrence, is calculated based on the disease feature vectors. If the confidence level of the early warning signal is greater than a preset threshold, an alarm signal strength is output, and the frequency adjustment coefficient generated based on the alarm signal strength is verified a second time in conjunction with the cost consumption rate.

8. The intelligent monitoring and control system for early-stage diseases of rubber trees using a biosensor compound as described in claim 7, characterized in that: The early warning and response optimization module, upon identifying early signs of disease, pushes alarm signals to the system through a disease early warning mechanism. It also performs a secondary verification of the monitoring frequency adjustment plan based on cost control strategies. If the alarm level is high, additional resources are allocated preferentially. The optimized prevention and control response plan further includes: If the secondary verification result indicates a high-risk level, the resource allocation weight is calculated based on the remaining resource quantity and the alarm signal strength. The resource allocation weights and frequency adjustment coefficients are combined to generate prevention and control execution instructions, thereby achieving an optimized prevention and control response scheme.

9. The intelligent monitoring and control system for early-stage diseases of rubber trees using a biosensor compound as described in claim 7, characterized in that, It also includes a dynamic tracking and updating module, which, based on the optimized prevention and control response plan, obtains the latest feedback from the environmental data acquisition module, continuously tracks the dynamics of disease development, updates the data according to the changing trends, determines whether further adjustments to the monitoring strategy are needed, and obtains the final dynamic monitoring results, specifically including: The real-time feedback data stream uploaded by the environmental data acquisition module is obtained, and the real-time feedback data stream is acquired based on the optimized prevention and control response plan; The disease feature values ​​are extracted by parsing the real-time feedback data stream, and a dynamic map of disease development is constructed based on the disease feature values.

10. The intelligent monitoring and control system for early-stage diseases of rubber trees using a biosensor compound as described in claim 9, characterized in that: The dynamic tracking and updating module, based on the optimized prevention and control response plan, obtains the latest feedback from the environmental data acquisition module, continuously tracks the development of the disease, updates the data according to the changing trends, determines whether further adjustments to the monitoring strategy are needed, and obtains the final dynamic monitoring results, which also include: Calculate the trend change rate of the disease development dynamic map; if the trend change rate exceeds a threshold, generate a strategy adjustment instruction. The parameters are reset according to the strategy adjustment instructions, and multi-dimensional environmental data is aggregated to form a dynamic monitoring set to output the final dynamic monitoring results.

Images