Integrated control system for tomato leafminer pest in protected vegetable cultivation

Abstract

The application discloses a comprehensive prevention and control system for pests of tomato leaf-roller in facility vegetables, relates to the technical field of disease and pest control in facility agriculture, and comprises a spatial distribution acquisition module, which acquires spatial distribution data of a pest invasion path in a facility agricultural environment and determines the protection level requirement intensity of different regions; and a protection parameter calculation module, which calculates the specification parameters and installation density of a pest prevention grid in each region according to the protection level requirement intensity, adjusts the aperture of the pest prevention grid to the minimum specification if the pest density of a peripheral region exceeds a preset threshold, and obtains a configuration scheme of a first layer of electrically-controlled isolation net protection barriers; the comprehensive prevention and control system for pests of tomato leaf-roller in facility vegetables can effectively cope with the complexity and variability of pest invasion, and significantly improves the pest prevention and control effect and sustainability of the facility agricultural environment.

Description

Technical Field

[0001] This invention relates to the field of pest and disease control technology in facility agriculture, specifically to an integrated pest management system for tomato leafminer pests in facility vegetables. Background Technology

[0002] As a crucial pillar of modern agricultural development, the level of pest and disease control in facility agriculture directly impacts the quality and safety of agricultural products and the sustainable development of the industry. With the increasing consumer demand for green agricultural products, establishing an efficient pest control system has become a key aspect of the transformation and upgrading of facility agriculture.

[0003] Current pest control programs exhibit significant limitations in practical application. While chemical control methods are fast-acting, their effectiveness often declines sharply when faced with increasing pest resistance and changing environmental conditions. Biological control, though environmentally friendly, suffers from limited overall control capacity due to a lack of effective coordination among different biological agents in complex facility environments. Electrically controlled isolation nets offer relatively stable protection, but their coverage and depth are limited when used alone. More critically, existing programs generally lack a systematic integration approach; the synergistic mechanisms between various control methods are unclear, making it difficult to achieve stable and reliable protective effects. The core challenge of pest control in facility agriculture lies in optimizing the spatial layout of protective layers. In facility agriculture environments, pest invasion paths are diverse and concealed, requiring the establishment of protective barriers of varying strengths and characteristics from the periphery to the core area. The selection of insect-proof net specifications, the configuration of repellent plant species, and the determination of the release locations of natural enemy insects all require precise matching based on pest behavioral characteristics and the facility's spatial structure. This complexity of spatial layout further exacerbates the technical challenges of the coordinated configuration of protective elements. When the three elements of electrical control isolation net protection, plant repulsion, and biological control work simultaneously in the same space, their interrelationships are complex. They may produce synergistic effects or interfere with each other. Achieving precise coordination between different protective elements in time and space to ensure the stability and continuity of the entire protection system is extremely technically challenging. Summary of the Invention

[0004] The purpose of this invention is to provide an integrated pest management system for tomato leafminer pests in greenhouse vegetables, constructing a multi-level pest protection system based on spatial stratification and element synergy, and achieving an organic integration of electrical control isolation net defense and biological defense.

[0005] To achieve the above objectives, the present invention provides the following technical solution: an integrated pest management system for tomato leafminer pests in greenhouse vegetables, comprising: a spatial distribution acquisition module, which deploys multi-point monitoring devices in the outer area, intermediate buffer zone, and inner core area of ​​greenhouse agriculture through a sensor network, periodically collects frequency data and species information of pest activities, generates pest activity record tables for monitoring points, obtains preliminary distribution of pest activities in each area, classifies and organizes pest species in different areas based on the pest activity record tables using data classification tools, and determines the activity patterns of pests in each area by combining a pre-established pest behavior characteristic database. If the frequency of pests in the outer area is higher than a preset threshold, it is marked as high. The system categorizes pest risks and obtains a classified pest risk list. Based on this list, it tracks the spatial distribution of high-risk pests along their invasion paths, using geographic information systems (GIS) tools to map the movement paths of pests from the outer areas to the core areas. This identifies key invasion nodes in each area and acquires spatial distribution data of pest invasion paths in the facility agriculture environment, determining the required intensity of protection levels for different areas. The protection parameter calculation module uses the protection level and required intensity data, employing a spatial stratification algorithm to initially divide the pest control grid distribution in each area. It compares the pest density information in the outer areas; if the pest density exceeds a preset threshold, it generates a preliminary adjustment plan for the pest control grid. Basic grid distribution data for each region is obtained. Based on this data, the specifications of the insect-proof grid are analyzed. Data processing tools are used to match and calculate the grid aperture and minimum specification to obtain the configuration scheme for the insect-proof grid in each region. The specifications and installation density of the insect-proof grid in each region are calculated according to the required intensity of protection. If the pest density in the outer area exceeds a preset threshold, the aperture of the insect-proof grid is adjusted to the minimum specification to obtain the first-layer electrically controlled isolation net protective barrier configuration scheme. The biological repellency configuration module analyzes the coverage of the electrically controlled isolation net protective barrier and increases the density of repellent plants in areas with deficiencies in the electrically controlled isolation net protection to obtain the second-layer biological repellency protection configuration. (Compatibility) The analysis module, based on plant growth cycle data in the biological protection configuration, obtains the attenuation pattern of the repellency effect of each plant from a pre-established plant information database. It generates a comparison list of the intensity of the interaction between plants and pests, considering differences in pest sensitivity, and obtains preliminary details of the protection attenuation distribution. Using these preliminary details, it analyzes the differences in pest sensitivity to repellency factors using data comparison tools. Combining this with the predatory characteristics of natural enemy insects, it filters suitable natural enemy species from a pre-established database, determines a list of target natural enemy species, obtains the plant growth cycle and attenuation pattern of the repellency effect in the biological repellency protection configuration, and judges the compatibility between natural enemies and repellent plants based on the differences in pest sensitivity to different repellency factors.The temporal activation control module adjusts the activation sequence of three protective elements—electrically controlled isolation netting, repellent plants, and natural enemy insects—over time based on compatibility analysis results. If the effect of a previous protective element decreases to a critical value, the next protective element is activated. The spatial collaborative monitoring module monitors the interaction intensity of different protective elements within the same area, obtaining the synergistic effect coefficients. If the synergistic effect coefficient is lower than a preset standard, the spatial distribution density of the protective elements is redistributed. The effect evaluation and feedback module, based on the spatial distribution density adjustment results, continuously monitors pest population changes and protective effect feedback to obtain a multi-layered pest protection system.

[0006] Preferably, the spatial distribution acquisition module acquires spatial distribution data of pest invasion paths in the facility agriculture environment and determines the protection level requirements for different areas by: deploying multi-point monitoring devices in the outer, intermediate buffer, and inner core areas of the facility agriculture using a sensor network; periodically collecting frequency data and species information of pest activities; generating pest activity record tables for each monitoring point to obtain a preliminary distribution of pest activities in each area; and, based on the pest activity record tables, using data classification tools to categorize and organize the pest species in different areas, and combining this with a pre-established pest behavior characteristic database to determine the presence of pests in each area. In the activity mode, if the frequency of pests in the outer area exceeds a preset threshold, they are marked as high-risk species, resulting in a classified pest risk list. Using this pest risk list, the spatial distribution of high-risk species along the invasion path is tracked, and geographic information tools are used to draw a map of the pests' movement path from the outer area to the inner core area, identifying key nodes for pest invasion in each area. Based on these key nodes and the pest risk list, combined with the protection level classification criteria, a data comparison tool is used to calculate the demand intensity value of the area. If the demand intensity value exceeds a preset threshold, a protection plan is generated, providing a basis for adjusting the protection level of different areas.

[0007] Preferably, the protection parameter calculation module calculates the specification parameters and installation density of the insect-proof grid in each area based on the protection level requirement intensity. If the pest density in the outer area exceeds a preset threshold, the aperture of the insect-proof grid is adjusted to the minimum specification. The configuration scheme for the first layer of electrically controlled isolation net protection barrier includes: using the protection level and requirement intensity data, a spatial layering algorithm is used to initially divide the distribution of the insect-proof grid in each area; the pest density information in the outer area is compared; if the pest density exceeds a preset threshold, a preliminary adjustment scheme for the insect-proof grid is generated, and basic data of the grid distribution in each area is obtained; based on the basic data of the grid distribution, the specification parameters of the insect-proof grid are analyzed, and data processing tools are used to match and calculate the grid aperture and minimum specification to obtain the specification configuration scheme of the insect-proof grid in each area; based on the specification configuration scheme, combined with the installation density and the pest density data in the outer area, if the installation density is lower than the preset threshold corresponding to the pest density, the distribution density of the insect-proof grid is dynamically adjusted to determine the optimized grid density result in each area.

[0008] Preferably, the protection parameter calculation module calculates the specification parameters and installation density of the insect-proof grid in each area according to the required intensity of the protection level. If the pest density in the outer area exceeds a preset threshold, the aperture of the insect-proof grid is adjusted to the minimum specification. The configuration scheme for the first layer of electrically controlled isolation net protective barrier also includes: based on the grid density optimization results, and considering the construction requirements of the electrically controlled isolation net barrier, using an information integration tool to fuse the specification parameters and installation density data to obtain a complete configuration scheme for the first layer of electrically controlled isolation net barrier; and using the complete configuration scheme, using a data verification tool to verify the coverage of the insect-proof grid according to the protection level requirements of the outer area. If the coverage area does not reach the preset threshold, an adjustment instruction for supplementary grid distribution is generated to determine the final deployment data of the electrically controlled isolation net barrier. Based on the final deployment data, combined with pest density and preset threshold information, a protection intensity distribution map for each area is generated using a data mapping tool, providing a basis for dynamic adjustment of the protection level. Using the protection intensity distribution map, a logical comparison tool is used to periodically analyze the pest density change trend to ensure the long-term adaptability of the pest control grid and the electrically controlled isolation net barrier. If the change trend exceeds the preset threshold, an update scheme for grid specifications and density is generated to determine the continuous optimization data for the protection level.

[0009] Preferably, the biological avoidance configuration module, by analyzing the coverage area of ​​the electrically controlled isolation net protective barrier, increases the density of avoidant plants in areas where the electrically controlled isolation net protection has defects, to obtain a second layer of biological avoidance protection configuration. This includes: based on the coverage area data of the electrically controlled isolation net barrier, using a data comparison tool to detect the protection strength of each area; if it is found that the protection strength in the coverage area is lower than a preset threshold, then an adjustment requirement list for the corresponding area is generated, obtaining the distribution details of the area; based on the distribution details of the area, for the selection of avoidant plant species, a pre-established plant database is used for matching to obtain plant species adapted to the regional environment, determining a preliminary plant species list; based on the preliminary plant species list and combined with the spatial layout requirements, geographic information tools are used to divide the area into locations, generating a plant planting distribution map, obtaining an optimized spatial layout scheme; based on the optimized spatial layout scheme, for the adjustment of plant density, if the protection strength of a certain area is lower than a preset threshold, then a specific instruction to increase the density is generated, determining the final protection configuration data.

[0010] Preferably, the compatibility analysis module acquires the plant growth cycle and the decay pattern of the repellency effect in the biological repellency protection configuration. Based on the differences in pest sensitivity to different repellency factors, determining the compatibility between natural enemies and repellent plants includes: acquiring the decay pattern of the repellency effect of each plant from a pre-established plant database based on the plant growth cycle data in the biological protection configuration; generating a comparison list of the intensity of the interaction between plants and pests based on the differences in pest sensitivity, obtaining preliminary details of the protection decay distribution; and using data comparison tools to analyze the differences in pest sensitivity to repellency factors, combined with the predatory characteristics of natural enemy insects. The system first selects suitable natural enemy species from a pre-established database to determine a list of target natural enemy species. If there is a time conflict between the natural enemy insects in the target natural enemy species list and the plant growth cycle, an optimized plan for the release time node is generated using a time node adjustment tool. For the release quantity, a density distribution calculation tool is used to generate an allocation plan to obtain the final natural enemy release arrangement. Based on the final natural enemy release arrangement, a compatibility assessment tool is used to determine the adaptability of the natural enemy insects and repellent plants in spatial distribution. If the environmental adaptability of a certain area is lower than a preset threshold, an adjusted distribution plan is generated to determine the final protective configuration combination.

[0011] Preferably, the timing activation control module adjusts the activation sequence of the three protective elements—electrically controlled isolation net protection, repellent plants, and predatory insects—in the time dimension based on compatibility analysis results. The mode for activating the next protective element if the effect of the previous protective element decreases to a critical value includes: obtaining the initial activation sequence data of the electrically controlled isolation net protection, repellent plants, and predatory insects in the time dimension from a pre-established protective element database; continuously tracking the current effect of the electrically controlled isolation net protection using a real-time monitoring tool; comparing the specific value of the effect decrease with a preset critical value to determine whether the triggering condition has been met; if the specific value of the effect decrease reaches the preset critical value, then... The sequence adjustment tool dynamically updates the activation sequence, optimizes the configuration parameters of repellent plants, obtains the adjusted time dimension data, and determines whether it meets the preset collaborative optimization criteria. Based on the adjusted time dimension data, the collaborative optimization tool matches and calculates the mode parameters of repellent plants with the activation parameters of natural enemy insects to obtain the collaborative activation sequence of the two in the time dimension, and determines the specific start time of the mode. The sequence execution tool loads the collaborative activation sequence data into the protection element control module, preloads the mode of natural enemy insects, obtains the final protection element activation scheme, and determines whether its execution order in the time dimension meets the optimization target.

[0012] Preferably, the spatial collaborative monitoring module monitors the interaction intensity of different protective elements within the same area, obtains the synergistic effect coefficient of different protective elements, and, if the synergistic effect coefficient is lower than a preset standard, reallocates the spatial distribution density of protective elements, including: obtaining specific spatial distribution parameters from pre-established regional division data; tracking the location information of different protective elements within the same area in real time; continuously recording the interaction intensity between elements using data acquisition tools to obtain corresponding raw data records; standardizing the raw data records using data processing tools to calculate the synergistic effect coefficient between protective elements; if the synergistic effect coefficient is lower than a preset threshold, generating distribution optimization instructions using parameter update tools to determine the area to be adjusted; dynamically adjusting the spatial distribution parameters within the area to be adjusted using distribution optimization tools to obtain the adjusted density distribution information and determine whether it meets the preset standard comparison requirements; and continuously tracking the adjusted interaction intensity using regional monitoring tools based on the adjusted density distribution information to obtain new synergistic effect data and determine whether the preset target value has been reached.

[0013] Preferably, the effect evaluation and feedback module, based on the spatial distribution density adjustment results, obtains a multi-level pest protection system by continuously monitoring pest population changes and protection effect feedback, including: classifying and storing data on spatial distribution and density adjustment through a pre-established dynamic configuration database to obtain the distribution status of protection elements in different areas and determine initial configuration information; continuously collecting pest population fluctuation data using monitoring tools based on the initial configuration information, and combining it with protection feedback information to obtain real-time performance data of protection elements in each area; analyzing the correlation between pest population fluctuation and protection feedback using logical judgment tools based on the real-time performance data, and generating parameter adjustment instructions if the fluctuation exceeds a preset threshold to determine the protection parameters that need to be optimized.

[0014] Preferably, the effect evaluation and feedback module, based on the spatial distribution density adjustment results and through continuous monitoring of pest population changes and protection effect feedback, obtains a multi-level pest protection system, which further includes: dynamically updating the protection parameters using an adaptive adjustment algorithm according to parameter adjustment instructions, obtaining the adjusted multi-level system configuration information, and determining whether it meets the requirements of stable configuration; performing secondary calibration on the spatial distribution of protection elements using the adjusted multi-level system configuration information, obtaining updated density distribution data, and determining the protection coverage of each area; continuously tracking the matching degree between protection feedback and pest population fluctuations based on the updated density distribution data, obtaining new monitoring data, and determining whether the multi-level system has reached a stable configuration state; and updating the adjusted spatial distribution and density adjustment information to the dynamic configuration database using a data storage tool using the new monitoring data to obtain a complete protection element configuration record.

[0015] As can be seen from the above technical solution, the present invention has the following beneficial effects:

[0016] This integrated pest management system for tomato leafminer pests in greenhouse agriculture collects pest invasion data through a sensor network, designs an electrically controlled isolation net protective barrier using a spatial hierarchical algorithm, deploys biological repellency protection using a plant avoidance factor matching algorithm, and constructs a biological control layer using a natural enemy insect release strategy algorithm. The invention also employs an element-coordinated optimization algorithm to adjust the activation sequence of each protective element, monitors the interactions between elements through a spatial dimension coordination mechanism, and continuously updates protective parameters using an adaptive adjustment algorithm. This multi-layered, dynamically coordinated protective system effectively addresses the complexity and variability of pest invasions, significantly improving pest control effectiveness and sustainability in greenhouse agriculture environments. Attached Figure Description

[0017] Figure 1 This is a system connection diagram of the present invention. Detailed Implementation

[0018] 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.

[0019] like Figure 1As shown, this invention provides a technical solution: an integrated pest management system for tomato leafminer pests in greenhouse vegetables, comprising: a spatial distribution acquisition module, which deploys multi-point monitoring devices in the outer area, intermediate buffer zone, and inner core area of ​​greenhouse agriculture through a sensor network, periodically collects frequency data and species information of pest activities, generates a pest activity record table for each monitoring point, obtains the preliminary distribution of pest activities in each area, classifies and organizes the pest species in different areas according to the pest activity record table using a data classification tool, and determines the activity patterns of pests in each area by combining with a pre-established pest behavior characteristic database. If the frequency of pests in the outer area is higher than a preset threshold, it is marked as a high-risk species, resulting in a classified pest risk list. The system tracks the spatial distribution of high-risk pests along their invasion paths, using geographic information systems (GIS) tools to map the movement paths of pests from the outer areas to the core areas, identifying key invasion nodes in each region, and acquiring spatial distribution data of pest invasion paths in the facility agriculture environment to determine the required intensity of protection levels for different regions. The protection parameter calculation module, based on the protection level and required intensity data, uses a spatial stratification algorithm to initially divide the pest control grid distribution in each region. It compares the pest density information in the outer areas; if the pest density exceeds a preset threshold, it generates a preliminary adjustment plan for the pest control grid, obtaining basic grid distribution data for each region. Based on this basic grid distribution data, it analyzes the specifications and parameters of the pest control grid, using... The data processing tool matches and calculates the mesh aperture and minimum size to obtain the specification configuration scheme of the insect-proof mesh in each area. Based on the required intensity of protection layers, it calculates the specification parameters and installation density of the insect-proof mesh in each area. If the pest density in the outer area exceeds a preset threshold, the mesh aperture is adjusted to the minimum size to obtain the first-layer electrically controlled isolation net protective barrier configuration scheme. The biological repulsion configuration module analyzes the coverage of the electrically controlled isolation net protective barrier and increases the density of repellent plants in areas with deficiencies in the electrically controlled isolation net protection to obtain the second-layer biological repulsion protection configuration. The compatibility analysis module, based on the plant growth cycle data in the biological protection configuration, obtains the attenuation law of the repulsion effect of each plant from a pre-established plant information database, and addresses the differences in pest sensitivity. A comparative list of the effects of plants and pests was compiled to obtain preliminary details of the protection attenuation distribution. Based on these details, data comparison tools were used to analyze the differences in pests' sensitivity to repellent factors. Combined with the predatory characteristics of natural enemy insects, suitable natural enemy species were screened from a pre-established database to determine the target natural enemy species list. The plant growth cycle and the attenuation pattern of the repellency effect in the biological repellency protection configuration were obtained. Based on the differences in pests' sensitivity to different repellent factors, the compatibility between natural enemies and repellent plants was determined. The time-series activation control module adjusted the activation sequence of the three protection elements—electrically controlled isolation net protection, repellent plants, and natural enemy insects—in the time dimension based on the compatibility analysis results. If the effect of the previous protection element decreased to a critical value, the mode of the next protection element was activated.The spatial collaborative monitoring module monitors the interaction intensity of different protective elements within the same area, obtaining the synergistic effect coefficient of different protective elements. If the synergistic effect coefficient is lower than a preset standard, the spatial distribution density of protective elements is redistributed. The effect evaluation and feedback module, based on the spatial distribution density adjustment results, continuously monitors pest population changes and protection effect feedback to obtain a multi-level pest protection system.

[0020] This system adopts a layered control concept, constructing an integrated control pathway for tomato leafminer pests through the collaborative operation of multiple modules. First, the spatial distribution acquisition module uses image recognition and pest monitoring sensors to determine the pest's activity paths and density, providing foundational data for subsequent protection layers. The protection parameter calculation module, combining regional pest density and risk level, calculates and adjusts the aperture and density of the insect-proof mesh to achieve the first layer of electrical control isolation. If the electrical control isolation barrier is found to be insufficient to completely block pests, the biological repulsion configuration module plants specific repellent plants, such as marigolds, in the vulnerable areas, using their volatile compounds to repel pests, thus achieving the second layer of biological defense. The compatibility analysis module analyzes the life cycle of repellent plants and the time decay of their repellency effect through database analysis, while also considering the adaptability of natural enemy insects to the same ecological environment, thereby determining the coexistence possibility of protective factors. Subsequently, the time-series activation control module formulates a time-series activation strategy based on the compatibility analysis results, ensuring that the next protection stage automatically intervenes when the protection intensity is insufficient. The spatial collaborative monitoring module adjusts the spatial distribution of each element by monitoring the ecological interaction intensity between various protection elements in real time, improving the collaborative effect. Finally, the effectiveness evaluation and feedback module assesses the protection efficiency based on changes in the actual number of pests, dynamically optimizes the overall system parameters, and forms a closed-loop, multi-layered protection system.

[0021] This system establishes a three-pronged protection strategy—electrically controlled isolation netting, biological repellency, and natural enemy intervention—through coordinated spatial-temporal control, significantly improving protection accuracy and system response flexibility. The electrically controlled isolation netting barrier, while ensuring basic isolation, can dynamically adjust mesh size to cope with high-density pests and reduce protection gaps. Biological repellency measures utilize the natural characteristics of plants to provide a green barrier, eliminating the need for chemical intervention and enhancing the system's environmental friendliness and sustainability. Compatibility analysis of natural enemy insects and repellent plants improves ecological security and avoids negative effects between protection elements. Through dynamic activation mechanisms and synergistic effect regulation, the system can intelligently respond to different pest infestation changes, achieving optimal allocation of control resources and improving overall control efficiency and cost-effectiveness.

[0022] The spatial distribution acquisition module acquires spatial distribution data of pest invasion paths in the facility agriculture environment, and determines the protection level requirements for different areas. This includes deploying multi-point monitoring devices in the outer, intermediate buffer, and inner core areas of the facility agriculture using a sensor network to periodically collect frequency and species information of pest activities. A pest activity record table is generated for each monitoring point to obtain a preliminary distribution of pest activities in each area. Based on the pest activity record table, a data classification tool is used to categorize and organize the pest species in different areas. Combined with a pre-established pest behavior characteristic database, the activity patterns of pests in each area are determined. If the frequency of pests in the outer area exceeds a preset threshold, they are marked as high-risk species, resulting in a classified pest risk list. Using the pest risk list, the spatial distribution of high-risk species along the invasion path is tracked. A geographic information system (GIS) tool is used to draw a path map of pest movement from the outer area to the inner core area, identifying key nodes for pest invasion in each area. Based on the key nodes and the pest risk list, combined with the protection level classification criteria, a data comparison tool is used to calculate the demand intensity value for each area. If the demand intensity value exceeds a preset threshold, a protection plan is generated, providing a basis for adjusting the protection level for different areas.

[0023] The operation of this spatial distribution acquisition module is based on the spatial division principles of facility agriculture areas and the need for high-precision insect monitoring. First, the agricultural production area is divided into three spatial levels: the outer area, the intermediate buffer zone, and the inner core area. The division method is based on actual geographical boundaries, crop planting density, and environmental enclosure. For example, the outer area refers to the 10-meter radius closest to the outer wall, the intermediate buffer zone is the area extending 10 to 30 meters inward from the outer wall, and the inner core area is the area within 30 meters of the outer wall. Then, sensor nodes are deployed in a fixed grid within each area, with a spacing of 5 meters between nodes to ensure comprehensive coverage. Each sensor node includes an insect trap with light attraction capabilities, a high-definition camera module with image recognition capabilities, a temperature and humidity measurement component, and a data upload module supporting wireless communication. All nodes are uniformly numbered and scheduled by the main controller.

[0024] The system uses a 5-minute sampling cycle to periodically trigger nodes to initiate the insect infestation identification process. Insect traps attract pests using a 365-nanometer ultraviolet light source. Once an insect falls into the identification window area, a camera takes a picture. The image is transmitted to the central server, where image analysis algorithms identify the insect species and quantity. The identification results are recorded in the activity data log table in the format of "time, location, insect species, frequency". For example, if a node photographs 3 tomato leafminers between 8:00 AM and 8:05 AM, the data is recorded as: 08:00, Node No. 1, Tomato Leafminer, Frequency 3. All data is transmitted to the central server in real time and aggregated.

[0025] The system performs preliminary statistics on the collected data every hour. First, it summarizes the total frequency of insect species occurrences by region, then it conducts horizontal comparisons by insect species to create frequency distribution maps for each insect species in each region. If an insect species' cumulative occurrence frequency in the outer areas exceeds 30 times, the risk identification mechanism is triggered. This 30-times threshold is determined by the following method: combining historical insect infestation data for the same region over the past three years, the average daily occurrence frequency of the insect species in the seven days prior to the invasion outbreak is calculated. If the occurrence frequency is greater than 1.5 times this historical average, it is set as a high-risk threshold. Therefore, if the tomato leafminer's frequency exceeds 30 times in the outer areas for two consecutive days, it is marked as a high-risk insect species and added to the pest risk list. The list includes the insect species name, identification time period, frequency statistics, and identification area.

[0026] Subsequently, the system invokes the trajectory tracking module. For insect species identified as high-risk, a node connection analysis is performed in the spatial dimension. Starting from the node where the insect first appears in the outer area, the system progressively searches inwards for its reappearance records in the middle and core areas, connecting each appearance point according to the time sequence. For example, if an insect species first appears at node 1 (outer area) in the 1st hour, then reappears at node 5 (middle buffer zone) in the 3rd hour, and finally appears at node 9 (core area) in the 6th hour, then the insect species' path is node 1 to node 5 to node 9. The activity path is marked in this order. The system invokes the geographic information mapping module to depict this path on an electronic map with a red line, marking node 5 as a key node in the invasion path.

[0027] After the path is determined, the system enters the regional intensity demand assessment phase. The intensity value of each region is a weighted sum, with weighting factors set according to the insect species risk level classification: high-risk insect species have a weight of 5, medium-risk insect species have a weight of 3, and low-risk insect species have a weight of 1. The frequency of occurrence of each insect species is multiplied by its weight to obtain the contribution value of that insect species. The contribution values ​​of all insect species are then summed to obtain the regional intensity value. For example, if a region has 30 high-risk insect species, 40 medium-risk insect species, and 50 low-risk insect species, then the regional intensity value is 30 multiplied by 5 plus 40 multiplied by 3 plus 50 multiplied by 1, resulting in 150 plus 120 plus 50, and the final intensity value is 320.

[0028] The system's intensity threshold is set at 200, determined based on the following logic: The system analyzes the distribution of insect intensity values ​​in various regions during past years of high pest infestation, takes the average of all historical intensity values ​​as a baseline, and then adds 50% as the strengthening threshold. Therefore, when the intensity value of a certain area exceeds 200, the system identifies it as a protection upgrade area and automatically generates protection enhancement measures, including: increasing the density of insect-proof mesh from 20 meshes per square meter to 40 meshes per square meter; adjusting the mesh size from 0.6 mm to 0.3 mm; adding repellent plants and increasing the planting density from 1 plant per 10 square meters to 2 plants per 5 square meters; and installing high-frequency trapping devices at 10-meter intervals. The parameter settings are derived from industry standards and verification results from experimental demonstration bases to ensure the measures are scientifically effective.

[0029] The protection parameter calculation module calculates the specifications and installation density of the insect-proof grid in each area based on the protection level requirements. If the pest density in the outer area exceeds a preset threshold, the mesh size of the insect-proof grid is adjusted to the minimum specification. The configuration scheme for the first layer of electrically controlled isolation netting protection barrier includes: using protection level and requirement intensity data, a spatial layering algorithm is used to initially divide the distribution of the insect-proof grid in each area; comparing the pest density information in the outer area, if the pest density exceeds a preset threshold, a preliminary adjustment scheme for the insect-proof grid is generated, obtaining the basic data for the grid distribution in each area; based on the basic data for the grid distribution, the specifications of the insect-proof grid are analyzed, and data processing tools are used to match and calculate the mesh size and minimum specification, obtaining the specification configuration scheme for the insect-proof grid in each area; based on the specification configuration scheme, combined with the installation density and pest density data in the outer area, if the installation density is lower than the preset threshold corresponding to the pest density, the distribution density of the insect-proof grid is dynamically adjusted to determine the grid in each area. Density optimization results: Based on the grid density optimization results, and considering the construction requirements of the electrically controlled isolation barrier, an information integration tool is used to merge the specification parameters and installation density data to obtain a complete configuration scheme for the first layer of the electrically controlled isolation barrier. Using this complete configuration scheme, and considering the protection level requirements of the outer area, a data verification tool is used to detect the coverage of the insect-proof grid. If the coverage does not reach a preset threshold, an adjustment instruction for supplementary grid distribution is generated to determine the final deployment data of the electrically controlled isolation barrier. Based on the final deployment data of the electrically controlled isolation barrier, combined with pest density and preset threshold information, a protection intensity distribution map for each area is generated using a data mapping tool, providing a basis for dynamic adjustment of the protection level. Using the protection intensity distribution map, and considering the long-term adaptability of the insect-proof grid and the electrically controlled isolation barrier, a logical comparison tool is used to periodically analyze the pest density change trend. If the change trend exceeds a preset threshold, an update scheme for grid specifications and density is generated to determine the continuous optimization data for the protection level.

[0030] This protection parameter calculation module constructs a stable and effective first-layer electrically controlled isolation net protective barrier system that meets the dynamic changes of pests through seven consecutive and closely related steps. The first step is area division and intensity analysis. The system acquires data from the spatial distribution acquisition module, including area number, historical pest density statistics, and protection level intensity values, and divides the target facility area into multiple numbered units, each 5 meters by 5 meters, with an area of ​​25 square meters. The numbering format is area code plus row and column number, such as A01 to A64. Each unit is assigned a protection level requirement intensity value, which is obtained by multiplying the number of high-risk pest species by their weight value and adding the weighted scores of medium- and low-risk pest species. For example, if a high-risk insect species appears 25 times with a weight of 5, a medium-risk insect species appears 30 times with a weight of 3, and a low-risk insect species appears 40 times with a weight of 1, then the calculation formula is 25 multiplied by 5 plus 30 multiplied by 3 plus 40 multiplied by 1. The total score is 125 plus 90 plus 40, which is 255. This value is the protection requirement intensity of unit A03.

[0031] The second step is insect density analysis. Data is continuously collected for 7 days in each unit using the insect monitoring module, and the cumulative number of insects in that unit is extracted. For example, if a total of 375 insects are recorded in unit A03 over 7 days, the insect density is calculated as 375 divided by 25, resulting in 15 insects per square meter. The system then compares this to the pest density threshold standard to determine if it exceeds the limit. Here, the threshold is set at 10 insects per square meter. This value is derived from the field damage level classification criteria, and is determined with reference to insect control standards and the results of multiple field surveys. When the insect density exceeds 10 insects per square meter, the system marks the unit as a "density exceeding limit area" and triggers subsequent processing procedures.

[0032] The third step is matching the mesh size of the insect-proof net. The system reads the mesh size parameters of the currently installed insect-proof net in the unit, for example, 0.5 mm, made of polyester. The system calls the pest database to obtain the body length information of the current main pest, such as the tomato leafminer, which has a body length of 1 mm. According to experimental verification, when the mesh size is greater than 0.4 mm, the interception rate is less than 85%. To ensure a 90% interception effect, the mesh size must be less than or equal to 0.3 mm. This data comes from insect passage tests and interception performance curves. Therefore, the system determines that the 0.5 mm mesh size does not meet the requirements, and the system automatically outputs an update command: replace the current mesh size with 0.3 mm high-density polyethylene material, and write it into the unit configuration draft.

[0033] The fourth step is the installation density analysis. The system reads the actual coverage area of ​​the existing grid within the unit. For example, if the total area of ​​unit A03 is 25 square meters and the measured coverage is 20 square meters, then the installation density is 20 divided by 25, resulting in 80%. According to the insect density and coverage rate standard comparison table, when the insect density is 15 insects per square meter, the recommended grid coverage rate should not be less than 90%, based on the relationship between electrical control isolation netting blockage and density ratio in historical control cases. Since 80% is lower than the standard, the system generates an adjustment measure: the supplementary coverage area is 25 multiplied by 90% minus 20, resulting in 2.5 square meters. The system records this data and integrates it into the final deployment plan.

[0034] The fifth step is to integrate the complete configuration plan. The system uses an information integration tool to combine the aperture specification adjustment results with the installation density replenishment data to form a complete protection parameter configuration plan and generate a structured table format. The content includes: unit number, target aperture, target coverage, current coverage, required replenishment area, materials, and implementation priority level. This table also serves as the deployment basis for the construction unit and as reference data for subsequent inspections.

[0035] The sixth step involves verifying the deployment results and generating supplementary adjustment instructions. After deployment, the system re-acquires images of the area, uses image recognition algorithms to calculate the actual grid coverage area, and compares it with the theoretical values ​​in the table. For example, if the target is 22.5 square meters and the actual detected area is 21 square meters, the difference is 1.5 square meters. If the actual coverage rate is less than the threshold of 95%, the system immediately generates a supplementary installation instruction, specifying the grid number and corresponding location coordinates. This data is simultaneously stored in the protection resource scheduling platform for allocating construction materials.

[0036] The seventh step involves generating an intensity map and establishing a trend warning mechanism. The system integrates all configuration data with insect density data and uses a data mapping tool to create a protection intensity distribution map. Different intensity areas are displayed in the map using color coding, and parameters such as pore size and coverage are labeled in each unit. The system is set to a 7-day cycle and implements a trend warning function by comparing changes in insect density. The change is calculated as the absolute value of the difference between the current 7-day average insect density and the average insect density of the previous 7 days. For example, if the current cycle is 16 insects per square meter and the previous cycle was 10 insects, the change is 6 insects per square meter. If the change exceeds 5 insects per square meter, or the change rate exceeds 30%, the system generates a trend exceeding limit alarm and initiates a new round of pore size and coverage density assessment. This mechanism ensures the entire protection system has continuous adaptability, avoiding protection blind spots and delays in failure.

[0037] The first layer of electrically controlled protective barrier consists of a double-layer staggered sliding mesh assembly and a linear stepper motor. Each layer of the double-layer staggered sliding mesh assembly uses the same material and structure, with the mesh openings arranged in a regular array (such as squares or rhombuses). The material can be high-strength nylon, PET, or stainless steel filaments. The two layers of mesh are installed side by side within a support frame, with one layer fixed and the other sliding in a parallel direction. When the mesh openings of the two layers are fully aligned, the mesh openings are at their maximum (e.g., 2mm). After sliding a certain displacement, a partial overlap area is formed, reducing the effective aperture (e.g., 0.1mm-1mm) and providing more stringent protection.

[0038] A linear stepper motor is used to drive the movable mesh to slide on the guide rail. The drive control can achieve millimeter-level position adjustment, thereby precisely controlling the aperture size. The linear stepper motor is arranged at the edge of the frame and drives the mesh through rack, synchronous belt or guide rod.

[0039] The first-layer electrically controlled isolation netting protective barrier also includes a control unit. Its control core can be a programmable logic controller (PLC) or an embedded microcontroller (MCU) to receive inputs such as data collected by the pest monitoring device, environmental temperature and humidity information, and current time parameters. The control unit analyzes and processes this multi-source information to determine the current pest risk level and facility environmental status, thereby intelligently deciding on the adjustment strategy for the mesh size of the pest-proof netting to achieve dynamic control. To improve the flexibility and practicality of the system response, the control strategy supports both local preset and remote configuration. For example, in night mode, the mesh size is automatically tightened to increase the protection density; when tomato leafminer adults are detected to be active, the mesh size is promptly reduced to strengthen isolation; while in hot weather or ventilation-priority mode with low pest threat, the mesh size is automatically widened to enhance air circulation efficiency. This control mechanism effectively balances the dual objectives of pest control and crop growth environment regulation.

[0040] The biological avoidance configuration module analyzes the coverage of the electrically controlled isolation net protective barrier and increases the density of avoidant plants in areas with deficiencies in the barrier's protection, resulting in a second layer of biological avoidance protection configuration. This includes: based on the coverage data of the electrically controlled isolation net barrier, using a data comparison tool to detect the protection strength of each area; if any area is found to have protection strength below a preset threshold, a list of adjustment needs for that area is generated, providing the area's distribution details; based on these details, a pre-established plant database is used to match the selection of avoidant plant species, obtaining plant species adapted to the regional environment and determining a preliminary plant species list; based on this preliminary list and spatial layout requirements, geographic information tools are used to divide the area into geographical regions, generating a plant planting distribution map and obtaining an optimized spatial layout plan; and based on this optimized plan, adjustments to plant density are made. If the protection strength of a certain area is below a preset threshold, a specific instruction to increase the density is generated, determining the final protection configuration data.

[0041] The biological repellency configuration module identifies areas with deficiencies in the electrically controlled isolation netting protection system within a facility agriculture environment through a comprehensive data-driven and logical deduction process. It then uses ecologically adaptable repellent plant configuration schemes to supplement these deficiencies, constructing a second layer of biological protection barrier. The module's operation process includes six steps. The first step is the identification of weak areas where the protection intensity is below a preset threshold. The system first reads the coverage data provided by the electrically controlled isolation netting protection module. Each basic area unit is set at 5 meters by 5 meters, with an area of ​​25 square meters. The coverage rate of each unit is calculated by dividing the actual area of ​​the insect-proof netting installed in that unit by the total area and multiplying by 100. For example, if the actual protected area of ​​a unit is 21 square meters, the coverage rate is 21 divided by 25 multiplied by 100, resulting in 84%. The system's built-in coverage threshold is 95%, determined based on the facility structure design safety margin, insect penetration ability experimental results, and industry standards. If the unit coverage rate is less than 95%, the system identifies it as a "weak area in the electrically controlled isolation netting protection," recording the unit number, coordinates, missing area, and the status of the electrically controlled isolation netting in adjacent areas, forming a "weak area distribution table."

[0042] The second step is the screening of repellent plant species. The system queries the plant database for environmental adaptation parameters of each plant, including sunshine duration, soil type, humidity range, and growth cycle, to screen plant species that meet the environmental conditions of the current vulnerable area. Taking area B08 as an example, the test results show that the area has 6 hours of sunshine per day, an average humidity of 70%, and a soil pH of 6.2, classifying it as slightly acidic loam. The database records marigolds as adaptable to more than 5 hours of sunshine per day, a humidity range of 60% to 80%, and suitable for soils with a pH of 5.5 to 7.5; therefore, marigolds are identified as suitable plants. Similarly, vetiver and rosemary also meet the environmental requirements. The system includes these three plants in the preliminary species list and records their respective repellency indices: marigold 65, vetiver 55, and rosemary 60. The repellency index refers to the unit repellency intensity of each plant against the target insect species; the data comes from the statistical data of repellency behavior experiments at the agricultural experimental station.

[0043] The third step is spatial location division. The system calls the geographic information processing module to perform graphic reconstruction of each weak area, dividing the 25-square-meter area into 6 graphic regions of 2 meters by 2 meters, each with an area of ​​4 square meters. The system plans the layout of plants to avoid or avoid the weak areas within each graphic region. The minimum spacing of each plant is determined based on its canopy width and ventilation requirements. For example, marigolds are spaced 40 centimeters apart, vetiver 30 centimeters apart, and rosemary 45 centimeters apart. The system fills each square meter with the corresponding plants at the maximum density. Taking marigolds as an example, a spacing of 40 centimeters means 2 plants per row, or 4 plants per square meter. Therefore, 16 plants can be planted in a 4-square-meter area. If the layout ratio is set at 60% marigolds and 40% vetiver 40%, then 10 marigolds and 6 vetiver stalks will be placed in this graphic region.

[0044] The fourth step is the calculation of protection intensity and density adjustment. The system calculates the protection intensity value for each area. The method is to multiply the quantity of each plant by its avoidance index and then sum them. For example, if 10 marigolds and 6 vetiver plants are planted in an area, the total intensity value is 10 multiplied by 65 plus 6 multiplied by 55, which is 650 plus 330, resulting in 980. The system sets a protection intensity threshold of 1200, which is derived from empirical data on the total intensity required for the target insect to achieve a 50% avoidance rate in a avoidance environment and statistical analysis of simulated environmental experiments. If the current value 980 is less than 1200, the system performs an intensity difference calculation, i.e., 1200 minus 980, resulting in 220. The system generates supplementary planting measures based on the unit intensity value of each plant. For example, prioritizing high-intensity marigolds, 220 divided by 65 needs to be added, resulting in 3.38, rounded to 4 plants. The system records the type, quantity, and planting location of the supplementary plants and writes them into the deployment adjustment instruction list.

[0045] The fifth step is to generate a complete configuration plan. The system integrates the plant species, spatial layout map, and replenishment density adjustment data of all vulnerable areas to generate a "Biological Repellency Configuration Master Table." Each row of data includes the area number, main plant species, auxiliary plant species, total number of plants deployed, current intensity value, target intensity value, replenishment quantity, and the time window for implementing the measures. The sixth step is periodic trend monitoring. The system sets the monitoring period to 7 days. Through the insect monitoring module, it counts the average insect density in each area over 7 days. If the increase in the current period exceeds 30% compared to the previous period, the system judges it as an out-of-limit trend and re-executes the entire process of plant matching, deployment optimization, and intensity adjustment to ensure the long-term effectiveness and timely response of the repellency barrier.

[0046] The compatibility analysis module obtains the plant growth cycle and repellency decay patterns in the biological repellency protection configuration. Based on the differences in pest sensitivity to different repellency factors, it determines the compatibility between natural enemies and repellent plants. This includes: obtaining the repellency decay patterns of each plant from a pre-established plant database based on the plant growth cycle data in the biological protection configuration; generating a comparison list of the intensity of plant-pest interactions based on pest sensitivity differences to obtain preliminary details of the protection decay distribution; and using data comparison tools to analyze the differences in pest sensitivity to repellency factors, combined with the predatory characteristics of natural enemy insects, from... The system filters suitable natural enemy species from a pre-established database to determine a list of target natural enemy species. If there is a time conflict between the natural enemy insects in the target natural enemy species list and the plant growth cycle, an optimized plan for the release time nodes is generated using a time node adjustment tool. For the release quantity, a density distribution calculation tool is used to generate an allocation plan to obtain the final natural enemy release arrangement. Based on the final natural enemy release arrangement, a compatibility assessment tool is used to determine the adaptability of the natural enemy insects and repellent plants in spatial distribution. If the environmental adaptability of a certain area is lower than a preset threshold, an adjusted distribution plan is generated to determine the final protection configuration combination.

[0047] The compatibility analysis module acquires the temporal variation characteristics of plant repulsion and, combined with the sensitivity response characteristics of target pests to different repulsion factors, scientifically screens and optimizes the release scheme of natural enemy insects. This ensures that the biological repulsion layer and the natural enemy control layer are highly coordinated in both time and space, forming a stable and efficient composite biological protection strategy. The first step in the module's operation is to acquire the growth cycle of repellent plants and the decay pattern of their repulsion effect. The system reads the species, planting time, and current status information of each plant deployed in the biological repulsion configuration module, and extracts its life cycle stage division and the repulsion efficacy of each stage from the plant information database. The plant life cycle includes the budding stage, growth stage, flowering stage, and decline stage, each stage corresponding to a certain number of days and a repulsion index. Taking marigolds as an example, their total life cycle is 60 days. The germination period is from day 1 to day 10, with an avoidance index of 30; the growth period is from day 11 to day 25, with the index rising to 45; the peak flowering period is from day 26 to day 40, with the index reaching its highest point of 65; and the decline period is from day 41 to day 60, with the index rapidly dropping below 30. The system constructs a "plant-time avoidance curve" with time as the horizontal axis and avoidance index as the vertical axis, and aligns the plant deployment time in each region to form a "regional avoidance intensity distribution map".

[0048] The second step is pest sensitivity analysis. The system accesses a pest behavior database to extract the response levels of the tomato leafminer to different repellent factors. Each factor, such as terpenes, coumarins, and linalool, corresponds to a sensitivity index, representing the intensity of the pest's repellent response to that substance under standard experimental conditions. The tomato leafminer's sensitivity index to terpenes in marigolds is 80, to coumarins secreted by vetiver is 55, and to menthol is 65. The system matches the main volatile components of each plant with the pest sensitivity index, calculating the plant-insect "effect strength value" by multiplying the plant repellency index by the insect sensitivity index and then dividing by 100. For example, on day 30, the marigold repellency index is 65, the terpene sensitivity index is 80, and the effect strength value is 65 multiplied by 80 divided by 100, resulting in 52. The system writes these calculation results into an "effect strength comparison list" and updates it daily, constructing a "plant protection effect change map of pests."

[0049] The third step is the screening of target natural enemy insects. Based on the aforementioned protection map, the system identifies time periods where the plant's avoidance ability significantly declines, defining them as "avoidance gaps." Taking marigolds as an example, their avoidance index rapidly drops below 30 after day 40. This index is set as the minimum effective threshold, based on the minimum effective value under a 50% insect avoidance probability experiment. Therefore, the period from day 41 onwards is determined to be the avoidance protection decline interval. The system marks the overlap between the insect's high activity period and the plant's avoidance decline period as a "high-risk period." The system then calls upon the natural enemy insect database to match natural enemy insects that are active during the high-risk period and have a significant control effect on the tomato leafminer. The Trichogramma wasp has a predation cycle of 18 days, an optimal temperature of 22-30 degrees Celsius, and parasitizes moth eggs with a parasitism success rate of 80%. If the high-risk period is from day 41 to day 55, and the temperature is around 26 degrees Celsius, the system lists the Trichogramma wasp as a target natural enemy.

[0050] The fourth step is to optimize the release plan. If the Trichogramma wasps are released on day 30, while their peak parasitism period is from day 4 to day 14 after release (days 34 to 44), the plant avoidance index is still at a medium-high level, indicating functional overlap. The system determines this as a release time conflict. Using the time node adjustment tool, the system postpones the release time to day 38, so the peak parasitism period falls between days 42 and 52, completely covering the avoidance window. The system then calculates the release density. The basic release rate is 2000 Trichogramma wasps per 100 square meters. If the insect density exceeds 20 wasps per square meter, the release rate is doubled. If the insect density in the area is 30 wasps per square meter, the release rate is 2000 multiplied by 30 and divided by 20, resulting in 3000 wasps per 100 square meters. The system integrates the release time, release quantity, and release area coordinates into a "natural enemy release schedule".

[0051] The fifth step is spatial compatibility assessment. The system simulates the activity radius and environmental adaptability of natural enemy insects in the target area and analyzes their compatibility with plant density, height, and shading. If a certain area has a plant density as high as 12 plants per square meter, a height of 0.6 meters, and a shading rate exceeding 65%, while the optimal light conditions for Trichogramma wasps are no less than 4500 lux, the system determines that the compatibility of this area is low. The system issues deployment adjustment measures, such as reducing the planting density to 8 plants per square meter or maintaining a row spacing of no less than 0.6 meters. All adjustments are written into the "Optimized Combination of Protective Configuration," which clearly specifies the plant species, deployment parameters, natural enemy release time, release quantity, release location, and spatial coordination measures, ultimately forming the most compatible biological protection combination scheme to achieve synergistic rather than conflicting protective effects.

[0052] The timing-based activation control module, based on compatibility analysis results, adjusts the activation sequence of three protective elements—electrically controlled isolation netting, repellent plants, and predatory insects—over time. If the effectiveness of a previous protective element decreases to a critical value, the next protective element is activated. This process includes: retrieving initial activation sequence data for the electrically controlled isolation netting, repellent plants, and predatory insects over time from a pre-established database of protective elements; continuously tracking the current effectiveness of the electrically controlled isolation netting using real-time monitoring tools; comparing the specific decrease in effectiveness with a preset critical value to determine if the trigger condition has been met; and if the specific decrease in effectiveness reaches the preset critical value, then the sequence is adjusted accordingly. The tool dynamically updates the activation sequence, optimizes and adjusts the configuration parameters of repellent plants, obtains the adjusted time dimension data, and determines whether it meets the preset collaborative optimization criteria. Based on the adjusted time dimension data, the collaborative optimization tool matches and calculates the mode parameters of repellent plants with the activation parameters of natural enemy insects to obtain the collaborative activation sequence of the two in the time dimension, and determines the specific start time of the mode. The sequence execution tool loads the collaborative activation sequence data into the protection element control module, preloads the mode of natural enemy insects, obtains the final protection element activation scheme, and determines whether its execution order in the time dimension meets the optimization target.

[0053] First, initial activation sequence data of three protective elements—electrically controlled isolation netting, repellent plants, and predatory insects—are extracted from a pre-established protective element database, along with their time-series activation. This data includes the activation start time, duration of action, and corresponding period of high effectiveness for each element. For example, the electrically controlled isolation netting is routinely activated from day 1, the highly effective repellency period for repellent plants is from day 15 to day 35 after planting, and the highly effective parasitism period for predatory insects is from day 5 to day 20 after release. This data is loaded into the system control module to construct a time-axis activation graph, which serves as a reference for subsequent dynamic adjustments. Subsequently, the system continuously tracks the current effectiveness of the electrically controlled isolation netting through real-time monitoring tools. The monitoring parameters include insect crossing frequency, the voltage value of the electrically controlled netting, and the structural shielding integrity. The system operates on a 30-minute monitoring cycle. An image recognition camera captures images in front of the netting, and image analysis methods are used to identify the number of insects crossing the grid area, yielding the insect crossing frequency F, measured in "times / 30 minutes." The system presets an insect frequency risk threshold of Fmax, set at 30 times. Crossing frequency score is calculated proportionally using the formula 1 minus F divided by Fmax. If F is 15 times, the crossing frequency score is 1 minus 15 divided by 30, resulting in 0.5. Voltage value V is read in real-time by the monitoring module. The rated voltage V0 is set to 24 volts, and the voltage score is V divided by V0. For example, if V is 21 volts, the voltage score is 21 divided by 24, resulting in 0.875. Structural shielding integrity C is obtained by identifying the shielding rate of the electrical control network mesh, with a value range of 0 to 1. For example, a shielding integrity score of 0.9 results in a score of 0.9. The system assigns weights to the three indicators: crossing frequency score with a weight of 0.4, voltage score with a weight of 0.3, and structural shielding integrity score with a weight of 0.3. After weighted calculation, the protection effectiveness index E for the current period is obtained, calculated as follows: crossing frequency score multiplied by 0.4, plus voltage score multiplied by 0.3, plus structural shielding integrity score multiplied by 0.3. For example, in the above example, E is calculated as 0.5 multiplied by 0.4, plus 0.875 multiplied by 0.3, plus 0.9 multiplied by 0.3, resulting in 0.2 plus 0.2625 plus 0.27, and E finally equals 0.7325, which is 73.25 points on a percentage scale. The system sets the critical value for protection effectiveness to 85 points. When the E value is below 85 points for two consecutive monitoring cycles, or below 80 points for any single cycle, the system determines that the protection effectiveness of the electrical control isolation net has decreased, thus meeting the trigger condition.

[0054] When the system determines that the specific value of the decline in the protective effect of the electrically controlled isolation net reaches a preset critical value, that is, the protective effect index is below 85 points for two consecutive monitoring cycles, or below 80 points for any cycle, the system immediately calls the sequence adjustment tool to dynamically update the current protective activation sequence. During the update process, it first determines whether there is a possibility of early enhancement configuration based on the repellent plant species, growth start date, and current growth days recorded in the protective element database. For example, for already planted plants, the database marks the highly effective repellency period as 15 to 35 days after planting, and the current system records 13 days of planting, indicating that they have not yet entered the highly effective period. At this time, the system uses the plant growth condition analysis tool to determine whether the current environment is conducive to the early improvement of the repellency index. If the current area has no less than 6 hours of sunshine, soil moisture between 60% and 80%, and temperature between 20 and 30 degrees Celsius, the system determines that the plants can enter the effective period earlier through optimization measures. According to experimental data, under the above conditions, the repellency index of marigolds can reach above 60 points on the 14th day. The system advances the originally planned effective start date from day 15 to day 14 and updates it to the new effective time point. Next, the system determines whether this adjustment meets the synergistic optimization criteria. Specifically, it extracts the release date and parasitic high-efficiency interval from the natural enemy insect release plan. For example, assuming the original release date for *Trichogramma* was day 20, and its high-efficiency period is from day 25 to day 40, the overlap between the high-efficiency period of the repelling plant and the natural enemy's high-efficiency period is from day 25 to day 35, a total of 11 days. The system calculates the synergistic overlap rate, which is equal to the number of overlapping days divided by the total length of the repelling plant's high-efficiency period. For instance, if the plant's high-efficiency period is adjusted to day 14 to day 35, a total of 22 days, the synergistic overlap rate is 11 divided by 22, resulting in 0.5, or 50%. If the system's synergistic optimization criterion is a synergistic overlap rate of no less than 40%, then the adjustment is considered to meet the synergistic requirements. Finally, the system records the updated start time of the repellent plant action, the release date of the natural enemy insects, and the synergistic overlap rate into the time dimension adjustment log, and uses this as a basis to generate the next synergistic activation sequence, ensuring that all protective elements achieve efficient connection and joint protection in time.

[0055] After the system adjusts the time-dimensional parameters of the repellent plants, it matches and calculates the adjusted repellent plant model parameters with the activation parameters of the natural enemy insects to generate a co-activation sequence in the time dimension and determine the optimal activation time. First, the system extracts the start and end times of the latest highly effective repellency period for the repellent plants. For example, after adjustment, the highly effective period for the repellent plants is from day 14 to day 35, a total of 22 days. Next, it extracts the release plans and action parameters of the natural enemy insects from the protection element database. For example, if the planned release date is day 20, the parasitic highly effective period is from day 5 to day 20 after release, i.e., day 25 to day 40 is the highly effective predation window. The system performs a time-axis overlap analysis on the highly effective periods of the two types of elements, finding that the time overlap interval is from day 25 to day 35, a total of 11 days. The system uses a co-matching algorithm to calculate the overlap rate, which is the number of overlapping days divided by the number of days of the highly effective period of the repellent plants. The result is 11 divided by 22, which is 0.5, or 50%. The system then compares the overlap rate with the minimum coordination threshold set by the system, which is 0.4, or 40%. Since the current overlap rate is 50%, higher than the set value, the system determines that the current configuration meets the time coordination conditions. To further optimize the coordination effect, the system attempts to fine-tune the release date of the natural enemy insects. Without changing the release preparation process, the release date is moved forward by one day to day 19. This adjusts the high-efficiency period of the natural enemy insects to day 24 to day 39, overlapping with the high-efficiency period of marigolds by day 24 to day 35, a total of 12 days. The system recalculates the overlap rate as 12 divided by 22, resulting in approximately 0.545, or 54.5%, thus improving the coordination effect. The system records this adjustment as a candidate optimal solution. Afterwards, the system performs a release date offset impact check to ensure that the adjustment will not cause subsequent timing conflicts and confirms that the release resources and environmental conditions support this early release arrangement. Ultimately, the system determines day 19 as the optimal activation point for predatory insects, forming a synergistic activation sequence: repellent plants begin to function on day 14, predatory insects are released on day 19, and the two form a highly efficient coordinated protective zone from day 24 to day 35. This activation sequence will be written into the system scheduling table and used as the execution benchmark for the time control module, driving various subsequent protective elements to be deployed and operated synergistically at the optimal time.

[0056] After the co-activation sequence is generated, the system loads the time-series data into the protection element control module via a sequence execution tool, driving various protection elements to operate in the planned sequence. The sequence execution tool is a control execution unit in this invention used to load the time parameters and protection element operation instructions from the co-activation sequence into the protection element control module, driving various protection elements to operate in a predetermined time sequence. The core function of this tool is to convert the activation time, duration, action sequence, and execution parameters recorded in the protection plan into specific operation instructions recognizable by the equipment control module, ensuring precise time-series alignment of the adjustment of the electrically controlled isolation net, the environmental management of repellent plants, and the release of natural enemy insects. The sequence execution tool includes functional modules such as scheduling parsing, parameter conversion, pre-loading scheduling, and execution monitoring. First, it parses the time information in the co-activation sequence to form a task queue. Second, it converts the activation date, operation type, and execution parameters (such as release quantity) into a standard control command format. Then, it performs relevant equipment status checks and command pre-loading one day before startup to ensure the system is ready for execution. Finally, it issues execution commands at the set time points and monitors whether each task is completed on time. If a delay or failure occurs, it outputs an abnormal status and invokes a remedial mechanism. First, the system reads key time nodes in the co-activation sequence, including the start date, day 14, end date, and day 35 of the high-efficiency period for repellent plants, and the optimal release date for natural enemy insects, day 19, and establishes a precise time schedule based on this. The protection element control module allocates tasks according to this schedule, prioritizing the pre-loading of the release pattern for natural enemy insects. The pre-loading process consists of two stages: The first stage verifies the preparation conditions. The system reads the insect release parameters from the protection element database, confirming that the minimum release unit is 2000 insects per 100 square meters, and assesses whether incremental release is needed based on the insect density in the monitored area. If the current insect density is 30 insects per square meter, and the system's set baseline density is 20 insects, then the release increment ratio is 30 divided by 20, resulting in 1.5. Therefore, the release should be 1.5 times the baseline quantity, i.e., 3000 insects per 100 square meters. On the 18th day, the system completes the conversion of the release quantity and confirms the material preparation. Simultaneously, it checks whether the temperature and humidity environment during the release window meets the insect's adaptation conditions, such as a temperature between 22 and 30 degrees Celsius and humidity between 60% and 80%. If these conditions are met, it is marked as "release conditions met." The second stage involves locking the execution parameters, which involves inputting the release date, the 19th day, the release quantity (3000 insects), and the coordinates of the release area into the built-in time control table. The system puts the release device into standby mode on the night of the 18th day and presets the start command to be executed at 8:00 AM on the 19th day.

[0057] Subsequently, the system performs a compliance check on the execution order of the complete activation scheme. The judgment logic is as follows: First, it checks whether the high-efficiency period of repellent plants, from day 14 to day 35, completely covers the early part of the high-efficiency predation period of natural enemy insects, i.e., day 24 to day 39. The intersection of the two time periods is calculated: day 24 to day 35, a total of 12 days, accounts for 16 days of the 16-day high-efficiency period of natural enemy insects. The result is 0.75, and the synergistic coverage rate is 75%. Second, it checks whether the release time is within the high-efficiency period of repellent plants. The current release date is day 19, which falls between day 14 and day 35, satisfying the synergistic activation logic. Finally, the system compares the synergistic coverage rate with the set optimization target. The system sets a minimum target of a synergistic coverage rate of no less than 60%, and the current rate is 75%, meeting the optimization requirements. Based on this, the system confirms that the execution order of the current activation sequence is conflict-free and complete in the time dimension, with a high synergistic ratio, and meets the optimization target. Ultimately, the activation scheme for the protective elements was solidified into a formal scheduling instruction and entered a state of pending execution. The control module would then automatically execute the instruction at the corresponding time point according to the plan, achieving precise linkage and continuous coverage of different protective measures over time.

[0058] The time-series activation control module aims to establish a dynamic, interconnected control mechanism across time for three types of protective elements: electrically controlled isolation netting, repellent plants, and predatory insects. The first step involves the system retrieving the initial activation data and duration of action for each of the three elements from the protective element database. Electrically controlled isolation netting protection, by default, continues from deployment on day 1 until system termination, providing full-cycle, permanent protection. The effective repellency period for repellent plants is determined based on the plant species and growth cycle; for example, marigolds have an effective repellency period from day 20 to day 40 after planting. For Trichogramma wasps, as predatory insects, their effective predation period is from day 4 to day 18 after release. The system constructs a three-segment basic timeline based on the duration of action of each element and establishes an initial activation sequence table, including the activation start date, the number of days of effective protection, and the estimated protection intensity.

[0059] The second step involves the system initiating a real-time monitoring mechanism for the protective effect of the electrically controlled isolation net. The system retrieves data from boundary sensors, grid cameras, and the electrically controlled isolation net status recognition module to calculate the effective coverage area of ​​the net. The calculation method is to divide the effective grid area within each region by the total area of ​​the region and multiply by 100. Assuming the total area of ​​the target region is 100 square meters, and the current effective grid area, confirmed by image recognition and sensors, is 88 square meters, then the protection integrity rate is 88%. The system sets a critical value of 90% for the protective effect of the electrically controlled isolation net. This value is obtained by fitting a curve of insect penetration probability under conditions of gradually increasing grid damage rate, demonstrating that 90% is the turning point where the penetration rate rapidly increases. When the real-time calculated value falls below 90%, it is considered that the protective effect has significantly decreased, triggering a second protective layer—a mechanism to repel plants.

[0060] The third step involves the system dynamically adjusting the activation sequence. First, it checks the status of the currently planted repellent plants to determine if they meet the conditions for early or delayed activation. Taking the marigolds as an example, they have been planted for 18 days, with the normal high-efficiency period originally set for days 20 to 40. The system currently reads environmental parameters showing a light intensity of 6 hours per day, humidity of 70%, and soil pH of 6.2, all meeting the conditions for early activation of the marigolds. The system predicts that supplemental lighting and fertilization can raise the repellency intensity to over 60 points by day 19, exceeding the system's set repellency activation threshold of 50 points. This value is determined by the minimum intensity required for a 50% repellency rate in the tomato leafminer repellency experiment. Based on this, the system advances the marigold activation period to days 19 to 35.

[0061] The fourth step involves the system matching the activation window of the natural enemy insects. Originally, the release date of the Trichogramma wasp was set for day 40, with the peak predation period from day 44 to day 58. However, by this time, the plant's repellency effect had diminished to less than 30 minutes, placing it in a protective vacuum. The system moved the Trichogramma wasp release date forward to day 31, making its peak period from day 35 to day 49, seamlessly coinciding with day 35, the final day of the marigold enhancement phase. The system calculated the synergistic overlap to be 15 days, accounting for 88.2% of the total 17-day plant enhancement cycle, exceeding the system's set synergy threshold of 25%. This threshold is derived from the minimum time window required to ensure continuous effectiveness after the overall repellency and predation intensities are combined in the simulated protection linkage experiment; therefore, the current timing is deemed to meet the requirements.

[0062] Fifth, the system uses a collaborative optimization tool to generate a new "time-coordinated activation sequence." Specifically, the duration of the electrically controlled isolation net protection is from day 1 to day 60; the period for strengthening repellent plants is from day 19 to day 35; the release time of the Trichogramma wasps is day 31; and the high-efficiency period is from day 35 to day 49. The system then calls the sequence execution tool to write this time sequence into the main control module, setting the corresponding time points to activate the lighting system, automatic fertilization equipment, and Trichogramma wasp release system, and writing all parameters into the operation instruction file. The instructions include: increasing light intensity starting on day 18 and maintaining it for 6 hours; controlling the water and fertilizer application cycle to once every 3 days from day 19 to day 35; and activating the Trichogramma wasp release device on day 31, releasing 3000 wasps per 100 square meters. The release is based on the current insect density of 30 wasps per square meter, the system's base release rate of 2000 wasps per 100 square meters, and the density multiplier is 30 divided by 20, resulting in a 1.5-fold increase.

[0063] Finally, the system performs a completeness check on the entire protection element activation process, verifying whether there are any gaps or overlaps in the protection elements within any time period. The system confirms that the electrically controlled isolation netting protection is permanently and uninterrupted, and that the reinforcement period of repellent plants and the predation period of natural enemies form continuous coverage, meeting the protection time integrity index. If everything is confirmed to be correct, the system outputs a "Multi-Element Protection Activation Plan Master Table," which includes each type of protection method, activation date, reinforcement parameters, time overlap percentage, and predicted protection intensity value, and sends it to the control terminal for execution, thus constructing a highly time-coordinated intelligent pest protection system for the entire facility agriculture environment.

[0064] The spatial collaborative monitoring module monitors the interaction intensity of different protective elements within the same area, obtaining the synergy effect coefficient of different protective elements. If the synergy effect coefficient is lower than a preset standard, the spatial distribution density of protective elements is redistributed. This includes: obtaining specific spatial distribution parameters from pre-established regional division data; tracking the location information of different protective elements within the same area in real time; continuously recording the interaction intensity between elements using data acquisition tools to obtain corresponding raw data records; standardizing the raw data records using data processing tools to calculate the synergy effect coefficient between protective elements; if the synergy effect coefficient is lower than a preset threshold, generating distribution optimization instructions through parameter update tools to determine the area to be adjusted; dynamically adjusting the spatial distribution parameters within the area to be adjusted using distribution optimization tools to obtain the adjusted density distribution information and determine whether it meets the preset standard comparison requirements; and continuously tracking the adjusted interaction intensity using regional monitoring tools based on the adjusted density distribution information to obtain new synergy effect data and determine whether the preset target value has been achieved.

[0065] First, based on pre-established regional division data, the facility agriculture environment is divided into several independent and numbered spatial units, each with an area of ​​25 square meters. The numbering method adopts the format of "region number plus serial number", such as A01, A02, etc. The system extracts parameters such as the spatial boundary coordinates, area, and relationship between adjacent units for each unit from the regional division data, and establishes a spatial distribution data table as the basis. Subsequently, the system reads the deployment information of three types of protective elements, namely, electrically controlled isolation nets, repellent plants, and natural enemy insects, in each spatial unit, including the net coverage rate of the electrically controlled nets, the planting density and location coordinates of the repellent plants, and the release time and location of the natural enemy insects. To achieve dynamic tracking of the synergistic relationship of these elements within the same area, the system continuously acquires the spatial distribution status and interaction of each element through data acquisition tools. The distribution parameters of the electrically controlled isolation net are determined by the fixed coordinates recorded during net installation and the opening and closing status monitored in real time. The location of the repellent plants is determined by the plant planting log and geocoding, and the density is expressed as the number of plants per square meter. The activity of natural enemy insects is determined by the release plan and behavior recognition results. The system identifies the appearance area and dwell time of the insects through insect body marking data. The system records the spatial superposition relationship of the above three types of elements within the same spatial unit every 30 minutes as a sampling cycle, and writes it into the original data record table with "protection element combination number + timestamp" as the index. The interaction intensity is recorded by a combination of event counting and position overlap calculation. For example, if the cumulative duration of position overlap between natural enemy insects and repellent plants in the same area reaches 20 minutes within a certain time period, and the total sampling time is 30 minutes, then the overlap rate between repellent plants and natural enemy insects is 20 divided by 30, which is 0.666. Similarly, if the overlap area between the area covered by the electrically controlled isolation net and the actual location of the avoidance plants is 20 square meters, and the total area is 25 square meters, then the overlap rate is 20 divided by 25, resulting in 0.8. The system records the overlap rate and activity overlap time between various element pairs in a standardized manner as raw intensity values ​​between 0 and 1, which serve as the input basis for subsequent synergistic effect analysis, forming a raw data record set of interactions, supporting the accurate analysis and control of the dynamic synergistic level of multiple protective elements in the same space.

[0066] After acquiring the raw interaction data records, the system immediately calls data processing tools to standardize the collected data in order to calculate the synergistic effect coefficients between protective elements. First, the system extracts the pairwise interaction strength values ​​between the three types of elements in each spatial unit from the raw data records: the coverage overlap rate between the electrically controlled isolation net and the repellent plants, the proportion of overlapping activity times between the repellent plants and their natural enemies, and the proportion of spatial intersection frequency between the electrically controlled isolation net and their natural enemies. The value range of each data point is uniformly normalized to decimals between 0 and 1 to ensure comparability across different dimensions. For example, in a certain area, the overlap rate between the electrically controlled isolation net and the repellent plants is 0.75, the proportion of overlapping activity times between the repellent plants and their natural enemies is 0.60, and the negative score of the electrically controlled isolation net's interference value with the natural enemies' activity is 0.55. The system uses these three data points as input parameters and calculates the synergy coefficient for the region using an arithmetic mean method. The formula is the sum of the three indicators divided by 3, i.e., (0.75 + 0.60 + 0.55) divided by 3, resulting in a synergy coefficient of 0.633. The system sets a minimum standard threshold of synergy at 0.70. This threshold is determined based on a historical protection effectiveness regression model, reflecting insufficient synergy and a significantly increased probability of pest penetration when the value is below this threshold. When the calculated result is below this threshold, the system automatically identifies the spatial unit as a low-synergy region, recording its number and the specific values ​​of each indicator. Subsequently, the system calls a parameter update tool to analyze which pair of protection elements in the region has the lowest synergy, using this as the optimization target. Assuming that the synergy value between repellent plants and natural enemy insects in this region is the lowest, at only 0.40, far lower than the other two, the system generates optimization instructions aimed at improving this synergy. Optimization strategies include increasing the density of repellent plants and adjusting the timing or location of natural enemy release. The system encapsulates the optimization target, protection element category, adjustment parameters, and spatial unit number into distributed optimization instructions, writes them into the instruction list, and distributes them for execution in the next scheduling cycle.

[0067] The data processing tool is a key analytical component used to standardize, extract indicators, and calculate synergy coefficients from the raw interactive data collected by the spatial collaborative monitoring module. Its main function is to unify the processing of interactive information from multiple protective elements of different dimensions and sources, outputting comparable and decision-making-significant synergy evaluation indicators. The tool first normalizes the raw data, converting parameters such as the overlap rate of the electric isolation net and the avoidant plants, the proportion of overlapping activity times between avoidant plants and natural enemy insects, and the spatial interference intensity between the electric isolation net and natural enemy insects into standard values ​​between 0 and 1 to eliminate interference from unit differences. Subsequently, the tool calculates the standardized synergy strength scores between each pair of the three elements, using spatial units as the unit, and synthesizes the synergy coefficient for the region based on weighted average or arithmetic average methods to measure the overall level of multi-element collaborative work within the current region. When the synergy coefficient of a certain region is lower than a set threshold, such as below 0.70, the data processing tool also has a diagnostic function, identifying the main element pairs causing the low synergy, generating a parameter structure analysis table, and providing basic data support for subsequent distribution optimization. Through centralized management and dynamic calculation, the data processing tool plays a bridging role between monitoring data and control decisions in this invention, and is one of the core technical units for realizing intelligent collaborative assessment and regulation of multi-element pest protection systems.

[0068] When the system identifies a region where the synergy coefficient is below the set threshold of 0.70, it immediately invokes the distribution optimization tool to dynamically adjust the spatial distribution parameters within that region. First, the system reads the basic configuration data of the low-synergy region, including the coverage of the electrically controlled isolation net, the planting density and location coordinates of repellent plants, and the release frequency and activity records of predatory insects. Assuming the current planting density of repellent plants in this region is 8 plants per square meter, the release frequency of predatory insects is once every 5 days, and the element pair with the lowest synergy is repellent plants and predatory insects, with an initial synergy value of 0.40. Based on the preset optimization logic, the system determines that the main reason affecting the synergy is the insufficient density of repellent plants, which has an insignificant effect on inducing the spatial behavior of predators. Therefore, the primary adjustment target is to increase the density of repellent plants. According to the response model established in the experimental database, the system knows that when the density of repellent plants is increased to 12 plants per square meter, the corresponding synergy strength can be increased to above 0.60. Therefore, the system sets the adjustment target to increase the density from 8 plants to 12 plants, an increase of 4 plants per square meter. Subsequently, the system recalculated the total number of plants in the adjusted area and generated a new spatial layout map, ensuring that the plant spacing was greater than 30 cm to avoid overlapping shading. The system simultaneously verified whether the coverage of the electrically controlled isolation net was obstructed by the increased plant density. If the grid coverage rate remained above 90%, it was determined that the adjustment would not negatively impact other protective elements. Next, the system predicted a synergistic effect increase of 0.40 plus 0.20 based on the new density configuration, resulting in 0.60. If combined with a fine-tuning of the release time, such as advancing the release time of natural enemies by one day to overlap their peak activity with the new plant deployment period, the synergistic effect would further increase by 0.05, ultimately reaching 0.65. Although it did not reach the target of 0.70, the system allowed a tolerance range of less than 5%, therefore, it was determined that this adjustment met the standard comparison requirements. The adjustment results will be written into the protection configuration table as updated density distribution information and used for monitoring, comparison, and verification in the next cycle.

[0069] The distribution optimization tool is a key execution module used to analyze, adjust, and optimize the spatial parameters of protective elements in areas with insufficient synergy. Its core function is to dynamically modify the deployment and density distribution of three types of protective elements—electrically controlled isolation nets, repellent plants, and predatory insects—within a spatial range, based on the adjustment targets generated by the system, when the synergy coefficient is below a preset threshold. The tool first reads the area number to be optimized and its current spatial deployment data, including the coverage area of ​​the electrically controlled net, the planting density and coordinates of repellent plants, and the release location and frequency of predatory insects. Then, based on the system's built-in response relationship model and historical experimental data, it analyzes the sensitivity of each element parameter to improving the synergy effect, prioritizing the adjustment of the elements with the greatest potential for improvement. For example, if the synergy score between repellent plants and predators is low and the plant density is significantly insufficient in a certain area, the tool will automatically set a new target density and recalculate the required number of plants, planting locations, and spacing to ensure that the plant distribution meets the synergy coverage requirements without interfering with the effectiveness of the electrically controlled net. During the adjustment process, the distribution optimization tool also performs boundary constraint checks, such as ensuring that the space occupied does not exceed the area, the electronic control coverage rate is not less than 90%, and the release paths do not overlap, to ensure the physical feasibility and system compatibility of the adjustment results. Finally, the tool writes the optimized density distribution data and deployment instructions into the update list for the control module to implement according to the scheduling cycle.

[0070] Once the system uses the distribution optimization tool to adjust the spatial parameters of protective elements within a specific area and generates new density distribution information, it immediately activates the regional monitoring tool to continuously track the interaction intensity of protective elements in the adjusted area to evaluate the optimization effect. The regional monitoring tool uses the adjusted area's number as an index to reload the updated spatial configuration data, including the coverage area of ​​the electrically controlled isolation net, the planting density and spatial coordinates of repellent plants, and the latest release time and location of natural enemy insects. The system collects and records the real-time relationships between the three types of protective elements in each area using a 30-minute monitoring cycle. First, it monitors the coverage relationship between the electrically controlled isolation net and the repellent plants, calculating the effective coverage ratio of the net above the repellent plant area using the shading overlap rate. The calculation method is the ratio of the net's coverage area to the overlapping area of ​​the repellent plant distribution area. For example, if the overlapping area is 20 square meters and the plant distribution area is 25 square meters, the score is 20 divided by 25, resulting in 0.8. Secondly, the spatial behavioral overlap between avoidant plants and predatory insects is monitored. Image recognition is used to record the dwell time of predators near avoidant plants. Assuming a total monitoring period of 30 minutes, if *Trichogramma rubrum* spends a cumulative 18 minutes in the avoidant plant area, the overlap time ratio is 18 divided by 30, resulting in 0.6. Thirdly, the system monitors the interference coefficient between the electrically controlled isolation net and predators, recording the integrity of the predator's flight path within the electrically controlled area. If the path integrity is 0.75, the three indicators are 0.8, 0.6, and 0.75, respectively. The regional monitoring tool transmits these three standardized indicators to the data processing tool, which recalculates the synergistic effect coefficient for the current period using a weighted average method with weights of 0.4, 0.3, and 0.3. The calculation process is 0.8 multiplied by 0.4, plus 0.6 multiplied by 0.3, plus 0.75 multiplied by 0.3, resulting in 0.32 plus 0.18 plus 0.225, with a final synergistic effect coefficient of 0.725. The system compares this value with a preset target value, with a target threshold set at 0.70. If the current value is equal to or higher than this value, the adjustment is considered to have achieved the expected effect. If the synergy effect coefficient is higher than the target value for two consecutive periods, the system marks the area as "synergy achieved" and writes the final adjustment plan and effect data into the optimization result log for model updates and strategy optimization reference in the next period. Through this continuous tracking and closed-loop verification mechanism, it is ensured that each distribution adjustment has a quantifiable synergy effect improvement and meets the overall performance requirements for stable system operation and pest control.

[0071] The "Time-Sequence Activation Control Module" and the "Spatial Collaborative Monitoring Module" together constitute the core of regulation for the growth cycle and repellency factor release behavior of repellent plants. To address the controllability of the growth cycle of repellent plants, this system introduces a planting time planning submodule and a crop-pest collaborative historical model. Utilizing planting start parameters (e.g., tomato transplanting date T0) and regional bioclimatic data, combined with modeling results of the leafminer life cycle from a historical pest database (e.g., larval hatching date T0+25 days), the system automatically calculates the optimal sowing window for repellent plants. For example, if the peak odor release period of vetiver is 35 days after sowing, the system automatically plans the sowing time to be completed 5 days before T0. This sowing plan is output to the planting unit through the main control system, which can be executed by an automated sowing robot or prompt the manual operation system, thereby achieving "pre-deployment" of the biological barrier and ensuring effective interference before the pest-sensitive period.

[0072] To address the timing control of repulsive factors—primarily volatile organic compounds (VOCs) released by repellent plants (such as limonene, linalool, geraniol, and sesquiterpenes)—a multi-level "factor enhancement and induced release" mechanism was designed. On one hand, while the release of odors from natural plants exhibits a degree of spontaneity and periodicity, making "instantaneous start-stop control" difficult, it can be indirectly regulated by adjusting environmental variables (such as temperature, humidity, and light). For example, before the pest infestation warning is triggered, the system can increase greenhouse temperature or implement short-term intense light to promote the upregulation of plant secondary metabolism and accelerate the synthesis rate of volatile substances. On the other hand, the system allows for artificial induction of repellent plants, such as mechanical pruning, artificial damage, or topping 3-5 days before a pest warning, rapidly increasing the intensity of odor factor release through the wound release mechanism, creating a "pre-emptive odor peak."

[0073] Furthermore, to address the issues of continuity and stability in the release of repellent factors, this system incorporates an "odor slow-release module," which is an artificial carrier-type repellent factor release device. This module contains plant extracts such as citronellal, geraniol, and eucalyptus oil, which are homologous to or similar to natural repellent factors. It compensates for and controls areas where natural release is insufficient through microporous membrane-controlled release, heated diffusion, or pneumatic diffusion. This module can be controlled by a time-series activation control module, setting release on / off and intermittent spraying modes at different time periods based on insect infestation monitoring signals, further achieving "semi-active release regulation" of the repellent factors. Under this architecture, the system can flexibly combine "biological-artificial" repellent factors to construct a stable, controllable, and rapidly responsive odor barrier.

[0074] Regarding how to achieve spatial collaborative control, this system uses a "spatial collaborative monitoring module" to dynamically monitor pest infestations and coordinate biological control resources across the control areas (outer periphery, buffer zone, and central zone). This module, based on multi-point deployed insect-attracting devices, visual recognition nodes, and environmental sensors, acquires information on insect density, plant status, and the environment in each area, and generates a real-time pest distribution map through heat map modeling. When the system determines that the pest infestation index in the outer periphery is rising or that the central area is about to enter a high-incidence period, it will automatically activate the corresponding area's repellent plants to release induction commands, slow-release devices to activate commands, and other auxiliary measures (such as energizing the electrically controlled isolation net and delaying the release of natural enemies), thus forming a layered control rhythm of "from the outside in, surrounding from the periphery to intercepting the inner zone."

[0075] In summary, this invention achieves effective control and coordinated response of repellent plants and their factors in time and space by (1) establishing a periodic matching model and automatic sowing control mechanism for repellent plants, (2) constructing a multi-mode repellent factor release enhancement mechanism, including environmental induction, mechanical induction and odor slow-release compensation device, and (3) constructing a real-time pest monitoring network covering the periphery-buffer-center area and scheduling the release strategy according to the spatiotemporal distribution. This ensures that control measures respond in advance and are executed in conjunction at key nodes in the pest development cycle, thereby achieving the temporal interference and regional repellency targets of pests such as leaf miners, and improving the intelligence, stability and effectiveness of the integrated pest management system.

[0076] The main function of the spatial collaborative monitoring module is to monitor in real time the synergistic effects of three different types of protective elements—electrically controlled isolation netting, repellent plants, and predatory insects—within the same agricultural area. This module uses a regional grid as the basic unit, with each grid covering 25 square meters. The system divides the entire facility agriculture environment into several non-overlapping grids and assigns a unique number to each grid. During the deployment phase, the system records the distribution of the three types of protective elements within each grid through GPS positioning, blueprint modeling, and database pre-setting. This includes the coverage grid coordinates of the electrically controlled isolation netting, the planting points and number of repellent plants, and the release area and frequency of predatory insects.

[0077] During the operational phase, the system initiates data acquisition tasks in 30-minute intervals. The data acquisition tool consists of temperature and humidity sensors, an image recognition unit, and a pest capture feedback system. It is used to collect the interaction intensity between three types of elements within each grid cell. The interaction intensity is recorded as follows: the intensity between the electrically controlled isolation net and repellent plants is calculated based on the shading ratio and airflow distribution value; the interaction intensity between repellent plants and natural enemy insects is calculated based on the change in volatile organic compound concentration in the natural enemy activity area per unit time; the interaction intensity between the electrically controlled isolation net and natural enemies is calculated based on the overlap between the average residence time of the natural enemy and the protection shading radius. Each type of interaction intensity is standardized to a score from 0 to 100. The system records these scores as raw data in the "Regional Element Interaction Raw Data Table".

[0078] Next, the system enters the stage of calculating the synergy effect coefficient. The synergy effect coefficient of each area grid consists of the interaction strength values ​​between the three types of elements. The calculation method is to add the interaction strength values ​​of each pairwise combination of the three groups, take the average, and then divide by the theoretical maximum value of 100, resulting in a decimal between 0 and 1. For example, if the three interaction strength values ​​in a certain area grid are 65, 70, and 55, the average of the three is 63.3, and the synergy effect coefficient is 0.633. The system sets the critical threshold for synergy effect to 0.75. This threshold is calculated repeatedly through a regression model based on 90 consecutive days of pest penetration rate and protection stability monitoring data. It indicates that areas below this value have had a pest invasion probability of more than 20% in past observations, and is therefore set as the minimum required value for synergy effect.

[0079] The interaction strength value between electrically controlled isolation nets and repellent plants is a parameter that measures the influence of electrically controlled isolation net structures, such as insect-proof nets, on key factors (such as light and airflow) in the growth environment of repellent plants. The system collects light intensity and airflow data at plant locations under conditions of both presence and absence of insect-proof netting by deploying light and wind speed sensors within each protected area. The light shading rate is calculated by dividing the difference in light intensity between the shaded and unshaded areas in the same grid at the same time by the light intensity of the unshaded area, yielding a percentage. The degree of airflow interference is calculated using the wind speed change ratio. The system weights the light shading ratio and the airflow interference ratio at a ratio of 7:3, then multiplies the result by 100 to obtain an interaction strength score ranging from 0 to 100. A higher score indicates a more significant positive synergy between the electrically controlled isolation net structure and the repellent plants; conversely, a lower score indicates severe shading interference and a weakened synergistic relationship. The interaction strength value between repellent plants and their natural enemy insects reflects the degree to which the volatile components released by the plants and their spatial distribution characteristics guide or interfere with the behavior of natural enemy insects. The system monitors the concentration level of volatiles from repellent plants in each grid cell in real time using gas sensors, in parts per million (ppm). It also analyzes the behavioral trajectories of natural enemy insects under different concentration gradients using an image recognition system, including path deviation angle, dwell time, and avoidance frequency. When natural enemy insects exhibit obvious avoidance or concentration behavior, the system records the frequency and spatial correlation of their behavior, maps changes in volatile concentration to behavioral response intensity, and models the interaction strength value between repellent plants and their natural enemies using behavioral deviation ratios and concentration fluctuation ratios. Higher values ​​indicate a more pronounced attraction or avoidance effect of the plants on the natural enemy, and a stronger interaction relationship. The interaction strength value between electrically controlled isolation netting and natural enemy insects measures the impact of the protective facilities on the spatial freedom and behavioral integrity of the natural enemy insects. The system deploys an infrared trajectory tracking system and high-definition cameras in the predator release area to acquire real-time data on the insects' flight paths, speeds, number of turns, and the distribution of areas where they remain after release. By comparing this data with the natural behavioral trajectories of predator insects recorded in the area without protective measures, the system calculates the flight path compression rate, the reduction in activity time, and the number of repeated stay areas after the grid structure is implemented. A high path compression rate and a significant reduction in activity time indicate substantial interference from the protective measures, resulting in a lower interaction strength value. Conversely, smaller differences indicate no significant negative interaction between the electrically controlled isolation net and the predators, leading to a higher interaction strength value. Finally, the system converts these behavioral compression indicators into standardized scores, mapped to strength values ​​from 0 to 100, for use in subsequent calculations of the synergistic effect coefficient.

[0080] If the synergy coefficient of a certain area grid is lower than 0.75, the system will determine that the protection configuration in that area is unreasonable and initiate a distribution optimization process. The system first analyzes the main factors affecting the synergy coefficient, determining that it is due to insufficient coverage of the electrically controlled isolation net, insufficient density of repellent plants, or low frequency of natural enemy release. Taking the low frequency of natural enemy release as an example, the current release frequency is once every 2 days, with 2000 birds released each time, and the release area is one point in the center of the grid. The system uses a model to calculate that increasing the release frequency to once a day and the release density to 3000 birds each time, and setting 2 release points within the grid, is expected to increase the natural enemy-related interaction strength value from the original 55 to 75, an increase of 36%. The system writes all optimization measures into the "Protection Distribution Adjustment Instruction List".

[0081] Next, the distribution optimization tool executes all adjustment instructions, updates the grid for each specified area, and generates an "Adjusted Protection Density Configuration Table," which details the adjusted plant density, protective netting location, and natural enemy release parameters. After the update, the system initiates a 24-hour re-monitoring process, re-collecting various interaction intensity values ​​and recalculating the synergy coefficient. If the new synergy coefficient is equal to or higher than 0.75, the adjustment is considered effective; if it remains below 0.75, the system will conduct a second round of analysis, simultaneously optimizing two or more protection elements if necessary, and continuously iterating automatically until the target synergy standard is reached or exceeded. The entire process constructs a self-optimizing, adaptive intelligent collaborative protection control mechanism, ensuring that multiple protection elements form the optimal spatial combination, thereby improving the integrated control effect against pests such as tomato leafminer.

[0082] The effectiveness evaluation and feedback module, based on the spatial distribution density adjustment results, continuously monitors pest population changes and protection effect feedback to obtain a multi-level pest protection system. This system includes: classifying and storing spatial distribution and density adjustment data through a pre-established dynamic configuration database to obtain the distribution status of protection elements in different regions and determine initial configuration information; continuously collecting pest population fluctuation data using monitoring tools based on the initial configuration information, and combining this with protection feedback information to obtain real-time performance data of protection elements in each region; and analyzing the correlation between pest population fluctuations and protection feedback using logical judgment tools based on the real-time performance data. If the fluctuation exceeds a preset threshold, parameter adjustment instructions are generated to determine the need for optimization. The system calculates and adjusts protection parameters. Based on parameter adjustment instructions, an adaptive adjustment algorithm is used to dynamically update the protection parameters, obtain the adjusted multi-level system configuration information, and determine whether it meets the requirements for stable configuration. Using the adjusted multi-level system configuration information, a secondary calibration is performed on the spatial distribution of protection elements to obtain updated density distribution data and determine the protection coverage of each area. Based on the updated density distribution data, the matching degree between protection feedback and pest population fluctuations is continuously tracked to obtain new monitoring data and determine whether the multi-level system has reached a stable configuration state. Using the new monitoring data, a data storage tool is used to update the adjusted spatial distribution and density adjustment information to the dynamic configuration database, obtaining a complete record of protection element configuration.

[0083] In this implementation, the effect evaluation and feedback module first extracts the initial protection element configuration information for each area in the current facility agriculture environment through a pre-established dynamic configuration database. This configuration information includes the aperture size of the insect-proof mesh, the planting density and types of repellent plants, and the release frequency and quantity of natural enemy insects. Each parameter has been determined through preliminary baseline surveys and expert modeling. The database is indexed by region number, timestamp, and parameter type for easy retrieval. The system relies on high-definition image acquisition equipment, infrared sensor traps, and population monitoring sensors to collect pest activity data every hour, including the number of pests in the traps per unit area, the types and quantities of pests identified in the images, etc. The collected data is normalized and noise-reduced by the processing module, and a moving average is calculated using a 24-hour rolling window to avoid occasional data anomalies interfering with the overall trend judgment. Next, the system correlates the monitored pest population trends with the records of protective parameter changes within the corresponding time periods. A logical judgment tool then performs trend difference analysis. When the pest density increase in a monitoring unit exceeds 20% within 72 consecutive hours, or when a single monitoring value is more than twice the average value of the area over the past 7 days, the system determines that the protective effect in that area has declined to a critical state, triggering a parameter optimization mechanism. This threshold is set based on historical control experiment data, with a 20% continuous increase and a 2x abnormal peak value serving as the critical threshold for economic loss within the facility, corresponding to a vegetable leaf damage rate exceeding 15%. After the trigger mechanism is activated, the system generates parameter adjustment instructions based on the protection intensity allocation principle. For example, if the current insect-proof netting aperture is 1 mm and the coverage rate is 85%, but the pest population continues to grow, the system will reduce the mesh aperture to 0.8 mm and increase the coverage rate to 95%. If the density of repellent plants is 12 plants per square meter and the relevant population has low sensitivity, the density will be increased to 18 plants per square meter, and the plants will be replaced with species with higher volatility. If the release interval of natural enemy insects is once every 7 days and the control response is delayed, the interval will be adjusted to once every 5 days and the total release amount will be increased by 20%. All adjustment instructions are input into the adaptive adjustment algorithm. The algorithm automatically selects the adjustment range and implementation order by comparing the difference between the current parameter status and the target value, and verifies the system resources and deployment capabilities. After the adjustment is completed, the system remodels the distribution density of the adjusted multi-layer protection elements in three-dimensional space, calculates the protection overlap of each area and the probability of blind spots, and ensures that the protection coverage of each grid unit is not less than 90%. Simultaneously, the system enters a secondary monitoring phase. This phase involves curve fitting between the pest population trend and the protection parameter change trend within the 72 hours following the adjustment, and calculating the Pearson correlation coefficient between the two sets of data. If this value is higher than 0.85 and the pest density remains decreasing or stable, the system is deemed to have reached the protection stability threshold. Finally, all new configuration parameters, execution time, feedback effects, and stability judgment results are uploaded to the dynamic configuration database by the data writing module, serving as the basis for the next round of adjustments.This assessment and feedback process forms a closed-loop control flow consisting of six stages: initial configuration extraction, population change analysis, dynamic parameter adjustment, multi-layer coverage calibration, stability determination, and database recording. This ensures that the protection system can perform multi-level dynamic optimization efficiently and accurately under various pest invasion scenarios.

[0084] In this system, the specific calculation process after all adjustment commands are input into the adaptive adjustment algorithm includes the following five steps: First, the system extracts the current parameter status values. For example, the current area has an insect-proof grid aperture of 1 mm, a repellent plant planting density of 12 plants per square meter, and a natural enemy insect release frequency of once every 7 days. Simultaneously, it extracts optimization target values, such as a grid aperture target of 0.8 mm, a plant density target of 18 plants per square meter, and a release frequency target of once every 5 days. The difference between each parameter is calculated through direct numerical difference, i.e., the current value minus the target value, to obtain the adjustment range. The initial adjustment ranges obtained at this point are: a reduction of 0.2 mm in grid aperture, an increase of 6 plants per square meter in plant density, and a reduction of 2 days in release frequency. Second, the system ranks the parameters according to their sensitivity to pest control effects. The sensitivity level is obtained through a response model built from historical monitoring data, prioritizing the adjustment of parameters with higher sensitivity. If adjusting the grid aperture affects the pest density reduction rate by 10% for every 0.1 mm reduction, 2% for every 1 increase in repellent plant density, and 3% for every 1 day decrease in natural enemy release frequency, then the grid aperture has the highest priority. In the third step, the system introduces resource constraints and deployment capabilities, calling upon the remaining material inventory and manual operation capabilities recorded in the database. For example, if the remaining grid material is only sufficient to cover 80% of the current area, and manual allocation takes more than 24 hours, the system determines that the current resources are insufficient to achieve full coverage with the minimum aperture, and sets the adjustment range to a maximum reduction of 0.1 mm. Another example is when the repellent plant seed inventory is sufficient and deployment time is only 2 hours; the system prioritizes adjusting the plant density to 18 plants per square meter. For natural enemy insects, if the remaining release quantity only supports 2 releases, the release frequency is adjusted to once every 6 days. Fourth, the system generates an adjustment sequence based on the aforementioned adjustment magnitude and priority, in the following order: First, increase the density of repellent plants to 18 plants per square meter; second, adjust the mesh size of the insect-proof net from 1 mm to 0.9 mm; third, adjust the release frequency of natural enemy insects from 7 days to 6 days. Each step is accompanied by a timestamp, implementation sequence number, and estimated completion time. Fifth, the system loads the pre-defined execution instructions into the task management module and establishes a data feedback path with the protection effect evaluation module to ensure immediate feedback on the execution effect after each step. If a measure fails to achieve the expected effect, the algorithm process is re-executed for the next round of optimization, forming a complete closed loop.

[0085] The Pearson correlation coefficient is used in this system to assess the strength of the relationship between pest population change trends and adjustments to protective parameters. The specific calculation process is as follows: First, the system extracts two sets of time-series data. The first set is pest population change data, represented by monitoring values ​​at consecutive time points. For example, the average pest density from day 1 to day 7 is 35, 30, 28, 25, 22, 20, and 19 individuals per square meter, respectively. The second set is the changes in protective parameters within the corresponding time period, using the adjustment range of a key parameter as a representative value. For example, the grid aperture for the corresponding 7 days is 1.0, 0.95, 0.9, 0.9, 0.85, 0.85, and 0.8 mm, respectively. The system standardizes both sets of data by subtracting their mean and dividing by their standard deviation, resulting in two standardized series that are comparable. Next, the system multiplies the two standardized values ​​one-to-one according to the number of days. For example, if the pest change value on the first day is 0.95 and the protection parameter change value is -0.85, the product is -0.8075; this process is repeated for 7 days to calculate the product sequence. The system then sums these 7 product values ​​to obtain a total sum. This total sum is then divided by the number of observation days, 7, to obtain the standardized value of the covariance between the two variables, which is the final result of the Pearson correlation coefficient. For example, if the total sum is -5.95, the correlation coefficient is -0.85. This coefficient is a value between -1 and 1. When the coefficient is close to 1, it indicates a positive correlation between the two sets of data, with consistent trends; close to -1, it indicates a negative correlation, i.e., one increases and the other decreases; close to 0, it indicates no significant linear relationship. In this system, if the absolute value of the Pearson correlation coefficient is greater than or equal to 0.85 and is negative, it indicates that the adjustment of the protection parameter has a significant inhibitory effect on pest density, meeting the protection optimization goal; if it is less than this value, the system re-executes the adjustment mechanism.

[0086] 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. An integrated pest management system for tomato leafminer pests in greenhouse vegetables, characterized in that, include: The spatial distribution acquisition module acquires spatial distribution data of pest invasion paths in facility agriculture environments to determine the intensity of protection level requirements for different areas. The protection parameter calculation module calculates the specifications and installation density of the insect-proof mesh in each area based on the required intensity of the protection level. If the pest density in the outer area exceeds a preset threshold, the mesh aperture is adjusted to the minimum specification to obtain the configuration scheme for the first layer of electrically controlled isolation netting protection barrier, specifically: Based on the protection level and demand intensity data, a spatial stratification algorithm is used to initially divide the insect control grid distribution in each region. The pest density information in the outer region is compared. If the pest density exceeds the preset threshold, an initial adjustment plan for the insect control grid is generated, and the basic data of the grid distribution in each region is obtained. Based on the basic data of grid distribution, the specification parameters of the insect-proof grid are analyzed. Data processing tools are used to match and calculate the grid aperture and minimum specification to obtain the specification configuration scheme of the insect-proof grid in each area. By combining the specification configuration scheme with the installation density and pest density data of the surrounding area, if the installation density is lower than the preset threshold corresponding to the pest density, the distribution density of the pest-proof grid is dynamically adjusted to determine the grid density optimization result for each area. Based on the grid density optimization result, and considering the construction requirements of the electrically controlled isolation barrier, an information integration tool is used to merge the specification parameters and installation density data to obtain a complete configuration scheme for the first layer of the electrically controlled isolation barrier. Using this complete configuration scheme, and considering the protection level requirements of the surrounding area, a data verification tool is used to detect the coverage of the pest-proof grid. If the coverage does not reach the preset threshold, an adjustment instruction for supplementary grid distribution is generated to determine the final deployment data of the electrically controlled isolation barrier. Based on the final deployment data of the electrically controlled isolation barrier, and combining the pest density and preset threshold information, a protection intensity distribution map for each area is generated using a data mapping tool, providing a basis for dynamic adjustment of the protection level. Using the protection intensity distribution map, and considering the long-term adaptability of the pest-proof grid and the electrically controlled isolation barrier, a logical comparison tool is used to periodically analyze the pest density change trend. If the change trend exceeds the preset threshold, an update scheme for the grid specifications and density is generated to determine the continuous optimization data for the protection level. The biological avoidance configuration module analyzes the coverage of the electrically controlled isolation net protective barrier and increases the density of avoidant plants in areas where the electrically controlled isolation net protection has defects, thus obtaining a second layer of biological avoidance protection configuration, specifically: Based on the coverage data of the electrically controlled isolation net barrier, a data comparison tool is used to detect the protection strength of each area. If any area is found to have a protection strength lower than a preset threshold, an adjustment requirement list for that area is generated, resulting in detailed distribution information for that area. Using this distribution information, a pre-established plant database is used to select plant species that are suitable for the area's environment, thus establishing a preliminary plant species list. Based on this preliminary list and spatial layout requirements, geographic information systems (GIS) tools are used to divide the area into geographically defined regions, generating a plant planting distribution map and obtaining an optimized spatial layout plan. Finally, based on this optimized plan, if the protection strength of a certain area is lower than a preset threshold, a specific instruction to increase the density is generated, determining the final protection configuration data. The compatibility analysis module obtains the plant growth cycle and the decay pattern of the repulsion effect in the biological repulsion protection configuration, and judges the compatibility between natural enemies and repulsive plants based on the differences in the sensitivity of pests to different repulsion factors. The timing activation control module, based on compatibility analysis results, adjusts the activation sequence of three protective elements—electrically controlled isolation netting, plant repellency, and predatory insects—over time. If the effectiveness of a previous protective element drops to a critical value, the next protective element's mode is activated. Specifically: Based on a pre-established database of protective elements, the initial activation sequence data of electric control isolation net protection, repellent plants, and natural enemy insects in the time dimension are obtained. The current effect of electric control isolation net protection is continuously tracked through real-time monitoring tools. The specific value of the effect decline is obtained and compared with the preset threshold value to determine whether the triggering condition has been met. If the specific value of the effect decrease reaches the preset threshold, the activation sequence is dynamically updated using a sequence adjustment tool. The configuration parameters of the avoidant plants are optimized and adjusted, and the adjusted time dimension data is obtained to determine whether it meets the preset collaborative optimization standard. Based on the adjusted time dimension data, the collaborative optimization tool matches and calculates the mode parameters of the avoidant plants with the activation parameters of the natural enemy insects to obtain the collaborative activation sequence of the two in the time dimension, and determines the specific start time of the mode. The sequence execution tool loads the collaborative activation sequence data into the protection element control module, performs preloading processing on the mode of the natural enemy insects, obtains the final protection element activation scheme, and determines whether its execution order in the time dimension meets the optimization target. The spatial collaborative monitoring module monitors the interaction intensity of different protective elements in the same area and obtains the synergistic effect coefficient of different protective elements. If the synergistic effect coefficient is lower than the preset standard, the spatial distribution density of protective elements is redistributed. The effect evaluation and feedback module adjusts the results based on spatial distribution density, and obtains a multi-level pest protection system by continuously monitoring changes in pest populations and feedback on protection effectiveness.

2. The integrated pest management system for tomato leafminer pests in greenhouse vegetables according to claim 1, characterized in that: The spatial distribution acquisition module acquires spatial distribution data of pest invasion paths in the facility agriculture environment, and determines the intensity of protection level requirements for different areas, including: By deploying multi-point monitoring devices in the outer, intermediate buffer, and internal core areas of facility agriculture through sensor networks, frequency data and type information of pest activities are collected at regular intervals. Pest activity record tables are generated for the monitoring points to obtain the preliminary distribution of pest activities in each area. Based on the pest activity record table, the pest species in different areas are classified and organized using data classification tools. Combined with the pre-established pest behavior characteristic database, the activity patterns of pests in each area are determined. If the frequency of pests in the outer area is higher than the preset threshold, they are marked as high-risk species, and a classified pest risk list is obtained. By using the pest risk list, the spatial distribution of high-risk species along the invasion path is tracked, and geographic information tools are used to draw the movement path map of pests from the outer area to the inner core area, and the key nodes of pest invasion in each area are identified. Based on the key nodes and the pest risk list, and combined with the protection level classification standards, the demand intensity value of the region is calculated using a data comparison tool. If the demand intensity value exceeds the preset threshold, a protection plan is generated, and the basis for adjusting the protection level of different regions is obtained.

3. The integrated pest management system for tomato leafminer pests in greenhouse vegetables according to claim 1, characterized in that: The compatibility analysis module obtains the plant growth cycle and the decay pattern of the repellency effect in the biological repellency protection configuration. Based on the differences in the sensitivity of pests to different repellency factors, it determines the compatibility between natural enemies and repellent plants, including: Based on the plant growth cycle data in the biological protection configuration, the decay pattern of the repulsion effect of each plant is obtained from the pre-established plant information database. Considering the differences in pest sensitivity, a comparison list of the intensity of the interaction between plants and pests is generated to obtain preliminary details of the distribution of protection decay. Based on the preliminary details of the protective attenuation distribution, data comparison tools were used to analyze the differences in the sensitivity of pests to avoidance factors. Combined with the predatory characteristics of natural enemy insects, suitable natural enemy species were screened from a pre-established database to determine the list of target natural enemy species. If there is a time conflict between the natural enemy insects in the target natural enemy species list and the plant growth cycle, an optimized plan for the release time node is generated by using the time node adjustment tool. For the release quantity, a density distribution calculation tool is used to generate an allocation plan to obtain the final natural enemy release arrangement. Based on the final release schedule of natural enemies, a compatibility assessment tool is used to determine the adaptability of natural enemy insects and repellent plants in spatial distribution. If the environmental adaptability of a certain area is lower than a preset threshold, an adjusted distribution scheme is generated to determine the final combination of protective configurations.

4. The integrated pest management system for tomato leafminer pests in greenhouse vegetables according to claim 1, characterized in that: The spatial collaborative monitoring module monitors the interaction intensity of different protective elements within the same area, obtains the synergistic effect coefficient of different protective elements, and if the synergistic effect coefficient is lower than a preset standard, redistributes the spatial distribution density of protective elements, including: Based on the pre-established regional division data, specific parameters of spatial distribution are obtained from it. The location information of different protection elements in the same area is tracked in real time. The interaction intensity between elements is continuously recorded through data acquisition tools to obtain the corresponding raw data records. The raw data records are standardized using data processing tools to calculate the synergy coefficient between protection elements. If the synergy coefficient is lower than the preset threshold, a distribution optimization instruction is generated using a parameter update tool to determine the area that needs to be adjusted. The spatial distribution parameters within the area to be adjusted are dynamically adjusted using the distribution optimization tool, and the adjusted density distribution information is obtained to determine whether it meets the preset standard comparison requirements. Based on the adjusted density distribution information, the intensity of the adjusted interaction is continuously tracked through regional monitoring tools to obtain new synergistic effect data and determine whether the preset target value has been achieved.

5. The integrated pest management system for tomato leafminer pests in greenhouse vegetables according to claim 1, characterized in that: The effect evaluation and feedback module, based on the spatial distribution density adjustment results, continuously monitors pest population changes and protection effect feedback to obtain a multi-level pest protection system including: By using a pre-established dynamic configuration database, data on spatial distribution and density adjustment are classified and stored to obtain the distribution status of protective elements in different areas and determine the initial configuration information. Based on the initial configuration information, monitoring tools are used to continuously collect data on the fluctuation of pest populations. Combined with protection feedback information, real-time performance data of protection elements in each area are obtained. By using real-time performance data, logical judgment tools are used to analyze the correlation between pest population fluctuations and protection feedback. If the fluctuation exceeds a preset threshold, parameter adjustment instructions are generated to determine the protection parameters that need to be optimized.

6. The integrated pest management system for tomato leafminer pests in greenhouse vegetables according to claim 5, characterized in that: The effect evaluation and feedback module, based on the spatial distribution density adjustment results, continuously monitors pest population changes and protection effect feedback to obtain a multi-level pest protection system, which also includes: Based on the parameter adjustment instructions, the protection parameters are dynamically updated using an adaptive adjustment algorithm to obtain the adjusted multi-level system configuration information and determine whether it meets the requirements for stable configuration. By using the adjusted multi-level system configuration information, a secondary calibration is performed on the spatial distribution of protective elements to obtain updated density distribution data and determine the protective coverage of each area. Based on the updated density distribution data, we continuously track the matching degree between protection feedback and pest population fluctuations, obtain new monitoring data, and determine whether the multi-level system has reached a stable configuration state. Using the new monitoring data, data storage tools are used to update the adjusted spatial distribution and density information to the dynamic configuration database, resulting in a complete record of protection element configurations.

Images