A composite intelligent agricultural management system based on multi-source parameter control

Abstract

The application provides a kind of compound wisdom agricultural management system based on multi-source parameter control, it is related to agricultural planting management technical field;The application extracts the core development needs of each regional crop accurately through big data analysis of multi-source historical data, avoids the deviation of experience threshold setting;With the help of spatial correlation analysis, the same level and secondary adjacent areas are divided, breaking the limitations of isolated control of each area, and providing topological basis for cross-regional collaboration;By classifying the equipment operating parameters into core parameters and secondary parameters and establishing a multi-level collaborative control mechanism, the priority of the control action is realized, and the core development needs of the high-priority area are ensured to be prioritized;By combining the dynamic evaluation needs priority of crop growth cycle, the initial threshold of equipment parameters can be self-adapted to tighten or relax with the crop development process, and finally a management scheme containing specific execution value and timing is generated.

Description

Technical Field

[0001] This invention relates to the field of agricultural planting management technology, and in particular to a composite intelligent agricultural management system based on multi-source parameter control. Background Technology

[0002] With the deep penetration of the Internet of Things and big data into the agricultural sector, smart agriculture has moved from concept to reality. However, existing smart agricultural management technologies still face some challenges in practical applications. Current technologies largely rely on human experience or fixed rules to set threshold ranges for equipment parameters such as irrigation, fertilization, and temperature control. This fails to fully leverage the core developmental needs of crops embedded in historical multi-source data (environmental parameters, equipment status, and crop parameters) from various areas of the plantation. This results in a systematic discrepancy between threshold settings and actual crop needs, leading to resource waste and potentially impacting yields due to insufficient regulation.

[0003] Traditional smart agriculture systems typically manage individual planting areas as independent units, neglecting the strong spatial correlations between adjacent areas in terms of environmental parameter transmission and equipment linkage response. As revealed by spatial autocorrelation analysis theory, regional economic and agricultural activities generally exhibit spatial clustering and diffusion effects; environmental changes in adjacent areas can have cross-regional impacts through soil moisture migration and microclimate conduction. Current technologies have failed to quantify the strength of these spatial correlations, let alone establish a hierarchical collaborative control mechanism, leading to both local over-regulation and global resource misallocation.

[0004] The lack of prioritization in equipment operating parameters means that existing systems apply equal weight to all parameters, failing to differentiate between parameters that have a direct causal impact on core crop developmental needs and those that are merely secondary parameters with non-persistent effects. This approach, when resources are limited or multiple regions face simultaneous stress, is highly susceptible to missing critical control windows due to unclear prioritization, especially during demand-sensitive stages such as flowering and fruit enlargement, where control efficiency drops significantly.

[0005] Therefore, it is necessary to provide a composite intelligent agricultural management system based on multi-source parameter control to solve the above-mentioned technical problems. Summary of the Invention

[0006] To address the aforementioned technical problems, this invention provides a composite intelligent agricultural management system based on multi-source parameter control to solve the problems in existing agricultural management, such as the lack of data-driven threshold settings for equipment parameters, the isolation of management in different regions and the lack of coordination mechanisms, and the lack of priority classification for equipment operating parameters.

[0007] This invention provides a composite intelligent agricultural management system based on multi-source parameter control, comprising: The data processing module is used to collect historical multi-source data from various areas within the plantation, including environmental parameters, equipment status, and crop parameters. Based on the historical multi-source data, the module uses statistical analysis methods to obtain the core developmental needs of crops in each area and sets the initial threshold range for equipment parameters in each area. The correlation analysis module is used to obtain the crop types, equipment distribution and environmental correlation of each area in the current plantation, and to divide the spatial correlation between each area through correlation analysis methods, and to identify the same-level adjacent areas and secondary adjacent areas of each area. The hierarchical construction module is used to classify the operating parameters of equipment in each region based on the division of the region into same-level adjacent regions and secondary adjacent regions, so as to establish a multi-level collaborative control mechanism with different priorities. The operating parameter classification includes classification into core parameters and secondary parameters. The priority assessment module is used to obtain the growth cycle of crops in each area of ​​the current plantation and, based on historical multi-source data, assess the demand priority of different crop areas at the current growth stage. The adjustment management module is used to dynamically adjust the initial threshold range of equipment parameters in each region by combining the determined demand priorities with the established multi-level collaborative control mechanism, and finally generate the adjustment management plan for each region.

[0008] Preferably, the step of collecting historical multi-source data from various areas within the plantation, including environmental parameters, equipment status, and crop parameters; and based on this historical multi-source data, using statistical analysis methods to obtain the core developmental needs of crops in each area, and setting initial threshold ranges for equipment parameters in each area, includes the following steps: Historical multi-source data of various areas within the plantation are collected at fixed intervals, and the collected historical multi-source data is cleaned and normalized according to the regional dimension. The historical multi-source data includes environmental parameters, equipment status and crop parameters. Based on the processed historical multi-source data, the core developmental requirements of crops in each region were extracted through data statistical analysis methods. These core developmental requirements include critical water threshold, nutrient sensitive range, and temperature suitability zone indicators. Based on the core development needs of each region and combined with equipment capability constraints, the initial threshold range of equipment parameters for each region is set.

[0009] Preferably, the steps of obtaining crop types, equipment distribution, and environmental relevance in each area of ​​the current plantation, and using correlation analysis to divide the spatial relationships between areas and identify the same-level and secondary adjacent areas of each area, include: Acquire data on crop types, equipment distribution, and environmental relevance in each area of ​​the current plantation, and establish a current status mapping table; Each region with a pre-defined initial threshold range for device parameters is used as an analysis unit. Based on the current state mapping table, the correlation strength between regions in terms of environmental parameter transmission and device linkage response is quantified through correlation analysis. Based on the strength of the association, the spatial relationships between the regions are divided, and the same-level adjacent regions and secondary adjacent regions of each region are identified.

[0010] Preferably, the step of classifying the operating parameters of equipment in each region based on the division of adjacent regions at the same level and secondary adjacent regions to establish a multi-level collaborative control mechanism with different priorities includes: Based on the division of adjacent areas at the same level and secondary adjacent areas, analyze the scope and degree of influence of the operating parameters of equipment in each area on the local area and adjacent areas; The operating parameters of equipment in each region are classified into categories, including: Parameters whose adjustment actions, within one control cycle after execution, can cause at least one core developmental requirement indicator in the region to deviate beyond the preset tolerance range, and whose deviation has a direct causal relationship with the developmental progress of the crop at the current growth stage, are defined as core parameters; Parameters that only affect the core developmental requirements of the region when the environmental parameters or crop parameters in the region reach the preset trigger threshold, and are not continuously effective, are secondary parameters. Based on the hierarchical results of core parameters and secondary parameters, a multi-level collaborative control mechanism with different priorities is established. The multi-level collaborative control mechanism includes the execution of core parameters before secondary parameters and the linkage of adjacent regions at the same level before adjacent regions at the secondary level.

[0011] Preferably, the steps of obtaining the growth cycle of crops in each area of ​​the current plantation and assessing the demand priority of different crop areas at the current growth stage based on historical multi-source data include: Obtain the growth cycle information of crops in each area of ​​the current plantation, and identify the current growth stage of crops in each area. The growth stages include seedling stage, vegetative growth stage, flowering stage, and fruit enlargement stage. Based on the acquired historical multi-source data, a crop demand-stage mapping relationship is established according to the growth stage dimension; Based on the crop demand-stage mapping relationship, the demand priority of different crop regions at the current growth cycle stage is assessed to obtain the demand priority of each region.

[0012] Preferably, the steps of dynamically adjusting the initial threshold range of equipment parameters in each region by combining the determined demand priority with the established multi-level collaborative control mechanism, and finally generating a control management plan for each region, include: The priority of demand in each region obtained from the assessment is used as input and matched with the multi-level coordinated regulation mechanism to determine the adjustment direction and adjustment magnitude weight of the core parameters and secondary parameters in each region. Based on the initial threshold range of equipment parameters in each region, and combined with the adjustment direction and adjustment magnitude weight of the core parameters and secondary parameters in each region, the initial threshold range of equipment parameters is dynamically adjusted, including: tightening or relaxing the threshold of core parameters in high-demand priority regions, and adjusting the threshold of secondary parameters in low-demand priority regions according to the linkage rules of the multi-level collaborative control mechanism. The dynamically adjusted equipment parameter thresholds for each region are summarized to generate a regulation and management plan for each region. The regulation and management plan includes the specific execution values ​​and execution sequence of the core and secondary parameters for each region under the current growth cycle.

[0013] Compared with related technologies, the composite intelligent agricultural management system based on multi-source parameter control provided by this invention has the following beneficial effects: This invention utilizes big data analysis of multi-source historical data to accurately extract the core developmental needs of crops in various regions, avoiding the biases inherent in empirically-based threshold settings. By employing spatial correlation analysis to divide adjacent regions into equal and secondary levels, it breaks the limitations of isolated regional regulation, providing a topological basis for cross-regional collaboration. Furthermore, by classifying equipment operating parameters into core and secondary parameters and establishing a multi-level collaborative regulation mechanism, it achieves priority ranking of regulatory actions, ensuring that the core developmental needs of high-priority regions are prioritized. Combined with dynamic assessment of demand priorities based on the crop growth cycle, the initial thresholds of equipment parameters can adaptively tighten or loosen as the crop develops, ultimately generating a management plan containing specific execution values ​​and time sequences. This accurately meets the needs of crops at key stages while optimizing the allocation efficiency of resources such as water and fertilizer, effectively avoiding over-regulation or under-regulation, and significantly improving the accuracy and synergy of smart agriculture management. Attached Figure Description

[0014] Figure 1 This is a system block diagram of a composite intelligent agricultural management system based on multi-source parameter control according to the present invention. Detailed Implementation

[0015] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0016] Example

[0017] In the specific implementation process, such as Figure 1 As shown, a composite smart agricultural management system based on multi-source parameter control includes: The data processing module is used to collect historical multi-source data from various areas within the plantation, including environmental parameters, equipment status, and crop parameters. Based on the historical multi-source data, the module uses statistical analysis methods to obtain the core developmental needs of crops in each area and sets the initial threshold range for equipment parameters in each area. The correlation analysis module is used to obtain the crop types, equipment distribution and environmental correlation of each area in the current plantation, and to divide the spatial correlation between each area through correlation analysis methods, and to identify the same-level adjacent areas and secondary adjacent areas of each area. The hierarchical construction module is used to classify the operating parameters of equipment in each region based on the division of the region into same-level adjacent regions and secondary adjacent regions, so as to establish a multi-level collaborative control mechanism with different priorities. The operating parameter classification includes classification into core parameters and secondary parameters. The priority assessment module is used to obtain the growth cycle of crops in each area of ​​the current plantation and, based on historical multi-source data, assess the demand priority of different crop areas at the current growth stage. The adjustment management module is used to dynamically adjust the initial threshold range of equipment parameters in each region by combining the determined demand priorities with the established multi-level collaborative control mechanism, and finally generate the adjustment management plan for each region.

[0018] In a specific implementation, the data processing module includes the following steps: Historical multi-source data is collected from various areas within the plantation at fixed intervals. The collected historical multi-source data is then cleaned and normalized according to the regional dimension. The historical multi-source data includes environmental parameters, equipment status, and crop parameters.

[0019] Based on processed historical multi-source data, the core developmental requirements of crops in each region are extracted through data statistical analysis methods. These core developmental requirements include critical water threshold, nutrient sensitive range, and temperature suitability zone indicators.

[0020] Specifically, for the critical water threshold, piecewise regression analysis is used: soil moisture content is used as the independent variable, and key crop growth indicators (such as fruit weight and leaf area) are used as the dependent variable. A relationship curve is plotted to find two key inflection points, including a lower critical point: when the moisture content is below this value, the growth indicators show a significant decline (e.g., a decline exceeding 15%), which is the critical threshold for insufficient water; and an upper critical point: when the moisture content is above this value, there is a risk of waterlogging or disease, which is the critical threshold for excessive water. The interval between the two inflection points is set as the critical water threshold range. For the nutrient sensitive interval, fertilizer application rate (N / P / K) is used as the independent variable, and crop growth rate or quality indicators are used as the dependent variable. The nonlinear relationship between fertilizer application rate and effect is analyzed to find the interval with the greatest marginal benefit—that is, within this interval, for every unit increase in fertilizer application rate, the crop response is the strongest; below this interval, the effect is weak, and above this interval, leaf burn or excessive absorption occurs. This interval is the nutrient sensitive interval. For the temperature suitability zone index, Gaussian fitting or polynomial fitting is used: with temperature as the independent variable and crop daily growth rate as the dependent variable, an inverted U-shaped curve is fitted, where the temperature range corresponding to the peak of the curve (the range on both sides of the peak where the growth rate is not less than 90% of the maximum value) is the temperature suitability zone.

[0021] In this embodiment, a smart agriculture plantation has tomatoes planted in area A (fruit enlargement stage) and lettuce planted in area B (vegetative growth stage). Historical data from area A (tomatoes during fruit enlargement stage) were statistically analyzed. For the extraction of critical water thresholds, the relationship between soil moisture content and single tomato weight in area A over the past 6 months was analyzed: when the moisture content was below 55%, the average fruit weight decreased by 18%, so the lower critical point was 55%; when the moisture content was above 78%, the incidence of root diseases jumped from 5% to 35%, so the upper critical point was 78%. Therefore, the critical water threshold for area A was 55%~78%. Nutrient sensitivity range extraction: Analysis of the relationship between historical fertilization amounts and fruit enlargement rates in area A revealed that within the nitrogen fertilizer range of 150~210 mg / kg, the slope of the enlargement rate's response to fertilization amount was the largest (for every 10 mg / kg increase, the daily enlargement amount increased by 0.8 g); below 150 mg / kg, the curve was flat; above 210 mg / kg, tip burn occurred. Therefore, the nutrient sensitivity range is 150~210 mg / kg. Temperature suitability zone extraction: The temperature-daily growth rate curve for region A was fitted, with the peak occurring at 26.5℃. The range above 90% of the peak value was defined as 24.5~28.5℃. Therefore, the suitable temperature zone is 24.5~28.5℃.

[0022] Based on the core development needs of each region and combined with equipment capability constraints, the initial threshold range of equipment parameters for each region is set.

[0023] Specifically, a mapping table is established based on the correspondence between equipment parameters and environmental effects in historical data. For example, based on the obtained critical moisture threshold of 55% to 78%, the mapping table is consulted, and the final initial threshold range needs to be intersected with the effective range of the equipment to set the initial threshold range of equipment parameters for each region.

[0024] In the specific implementation process, the steps of the correlation analysis module include: Obtain data on crop types, equipment distribution, and environmental relevance in each area of ​​the current plantation, and establish a current status mapping table.

[0025] Specifically, each region is treated as a row, and the three types of information are treated as columns, forming a two-dimensional mapping table. A weight coefficient is also assigned to each type of information, because not all information contributes equally to the correlation analysis. The weight of device distribution is usually higher than that of simple geographical distance, since even if two regions are adjacent, environmental transmission is weak if there is a barrier between them.

[0026] Each region with a pre-defined initial threshold range for device parameters is used as an analysis unit. Based on the current state mapping table, the correlation strength between regions in terms of environmental parameter transmission and device linkage response is quantified through correlation analysis.

[0027] Specifically, the correlation strength is quantified through two calculation dimensions and a weighted summation method. This includes calculating the environmental parameter transmission strength: taking environmental parameter sequences (e.g., temperature sequences) from two regions within the same time period, calculating the transmission entropy. For example, if a temperature change in region A significantly predicts subsequent temperature changes in region B, environmental transmission exists, and the transmission strength equals the prediction contribution (a value between 0 and 1), while also incorporating geographical factor corrections (e.g., strength decreases by 5% for every 1 meter increase in distance). The second calculation is the equipment linkage response strength. Historical data is collected to determine the timeframe within which a device in region B responds after a device in region A performs an action. For instance, if an irrigation valve in region A opens, and the irrigation valve in region B automatically opens within 15 minutes (because irrigation in region A causes an increase in soil moisture in region B), this is recorded as a linkage event. The calculation formula is: Linkage Strength = Number of Linkage Events / Total Number of Device Actions in Region A. Finally, the correlation strength is calculated as: α × Environmental Transmission Strength + β × Equipment Linkage Strength, where α = 0.6 and β = 0.4.

[0028] In this embodiment, the environmental transfer intensity: historical data shows that after the heating fan in area A is turned on, the temperature in area B rises by an average of 1.2 °C within 20 minutes, the p-value of the Granger causality test < 0.01, and the transfer intensity = 0.82; the equipment linkage intensity: in the past 30 days, after the irrigation valve in area A is turned on, the irrigation valve in area B has responded 18 times within 15 minutes, and area A has been turned on 40 times in total, and the linkage intensity = 18 / 40 = 0.45; the comprehensive correlation intensity = 0.6×0.82 + 0.4×0.45 = 0.492 + 0.18 = 0.672 (about 0.78, considering the correction of equipment capacity differences). According to the level of the correlation intensity, divide the spatial correlation relationships between regions, and clarify the same-level adjacent regions and secondary adjacent regions of each region.

[0029] Specifically, set two correlation thresholds T1 and T2. For each region, traverse its correlation intensity with all other regions, including: if the correlation intensity ≥ T1, it is marked as a same-level adjacent region; if T2 ≤ correlation intensity < T1, it is marked as a secondary adjacent region; if the correlation intensity < T2, there is no adjacent relationship and it is not included in the scope of collaborative regulation. Finally, with each region as the center, list its list of same-level adjacent regions and list of secondary adjacent regions.

[0030] In the specific implementation process, the specific steps of the hierarchical construction module include: According to the divided same-level adjacent regions and secondary adjacent regions, analyze the influence range and influence degree of the operating parameters of the equipment in each region on this region and adjacent regions.

[0031] Specifically, taking each region as a unit, list all adjustable operating parameters of all equipment in this region. For each parameter, evaluate its influence on the core development demand index of this region within one control cycle (such as 2 hours) after adjustment: the influence degree is measured by the offset: after adjusting this parameter, among the three indicators of the moisture critical threshold, nutrient sensitive interval, and temperature suitable zone, at least one has a large offset; the offset needs to be compared with the preset tolerance range: for example, the temperature tolerance is set to ±1 °C. If the adjustment of the heating fan power causes the temperature to offset by 2 °C, it exceeds the tolerance, indicating a large influence degree. Then, retrieve the change records of the environmental parameters in the adjacent regions after the parameter adjustment in the historical data, and count the amplitude and delay time of the influence.

[0032] Classify the operating parameters of the equipment in each region, including: if the adjustment action of the operating parameter can cause at least one core development demand index of this region to have an offset exceeding the preset tolerance range within one control cycle after execution, and this offset has a direct causal relationship with the development process of the current growth cycle stage of the crop, then the operating parameter is defined as a core parameter; if the operating parameter only affects the core development demand of this region when the environmental parameters or crop parameters in this region reach the preset trigger threshold and is not continuously effective, it is a secondary parameter.

[0033] Based on the hierarchical results of core parameters and secondary parameters, a multi-level collaborative control mechanism with different priorities is established. The multi-level collaborative control mechanism includes the execution of core parameters before secondary parameters and the linkage of adjacent regions at the same level before adjacent regions at the secondary level.

[0034] In the specific implementation process, the steps for prioritizing the evaluation module include: Obtain the growth cycle information of crops in each area of ​​the current plantation, and identify the current growth stage of crops in each area. The growth stages include seedling stage, vegetative growth stage, flowering stage, and fruit enlargement stage.

[0035] Specifically, obtain planting information for each region, including: sowing date, crop variety, and standard growth cycle table. For example, the standard growth cycle of the tomato variety "Jinpeng No. 1" is: seedling stage 0-25 days, vegetative growth stage 26-55 days, flowering stage 56-70 days, and fruit enlargement stage 71-120 days. If tomatoes in area A have been planted for 85 days, the main timeline is determined to be the fruit enlargement stage.

[0036] Based on the acquired historical multi-source data, a crop demand-stage mapping relationship is established according to the growth stage dimension.

[0037] Specifically, all collected historical multi-source data is grouped according to four defined growth stages. For example, all historical data for "tomato - fruit enlargement stage" is grouped into one group, all historical data for "tomato - flowering stage" into another group, and so on, covering each region, each crop, and each stage. Next, for each stage, the sensitivity to three core developmental needs is calculated. Specifically, for water sensitivity, the decrease in key crop indicators (fruit weight / leaf area / number of flowers) when soil moisture content deviates from the optimal value during that stage is calculated; for nutrient sensitivity, the slope of crop growth rate change when fertilizer application deviates from the optimal value during that stage is calculated; and for temperature sensitivity, the decrease in daily crop growth rate when temperature deviates from the suitable zone during that stage is calculated. It should be noted that the priority order of needs varies completely for different crops and different stages. For example, water is the most sensitive factor during the tomato fruit enlargement stage, while temperature is the most sensitive factor during the strawberry flowering stage.

[0038] Based on the crop demand-stage mapping relationship, the demand priority of different crop regions at the current growth cycle stage is assessed to obtain the demand priority of each region.

[0039] Specifically, by taking the current stage and the demand-stage mapping relationship, each region is assigned a priority score to determine which region most needs to be prioritized for adjustment at this moment. The higher the sensitivity coefficient, the more "vulnerable" the region is to environmental deviations, and the higher its priority.

[0040] In the specific implementation process, the steps for adjusting the management module include: The priority of demand in each region obtained from the assessment is used as input and matched with the multi-level coordinated regulation mechanism to determine the adjustment direction and adjustment magnitude weight of the core parameters and secondary parameters in each region.

[0041] Specifically, a correspondence is established between demand priority levels and multi-level collaborative control mechanisms, including: For priority level 1 (highest), the core parameter processing method is direct execution according to the adjustment direction, with adjustment amplitude = deviation × 1.0; the secondary parameter processing method is temporary non-execution; the linkage rule is synchronous linkage between adjacent areas at the same level, and delayed linkage between adjacent areas at the secondary level; for priority level 2, the core parameter processing method is execution according to the adjustment direction, with adjustment amplitude = deviation × 0.7; the secondary parameter processing method is passive adaptation according to the linkage rule; the linkage rule is linkage between adjacent areas at the same level, and no linkage between adjacent areas at the secondary level; for priority level 3, the core parameter processing method is no adjustment, the secondary parameter processing method is no execution, and the linkage rule is completely passive, waiting for the upper-level area linkage to trigger.

[0042] Based on the initial threshold range of equipment parameters in each region, and combined with the adjustment direction and adjustment magnitude weight of the core and secondary parameters in each region, the initial threshold range of equipment parameters is dynamically adjusted, including: tightening or relaxing the threshold of core parameters in high-demand priority regions, and adjusting the threshold of secondary parameters in low-demand priority regions according to the linkage rules of the multi-level collaborative control mechanism.

[0043] Specifically, using the initial threshold as the anchor point, the final threshold is calculated according to the adjustment direction and amplitude weights. The formula for its dynamic adjustment is: Adjusted threshold = Initial threshold + Adjustment direction × Deviation × Amplitude weight.

[0044] The dynamically adjusted equipment parameter thresholds for each region are summarized to generate a regulation and management plan for each region. The regulation and management plan includes the specific execution values ​​and execution sequence of the core and secondary parameters for each region under the current growth cycle.

[0045] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1A device that provides the functions specified in one or more boxes.

[0046] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-Erasable Programmable Read-Only Memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0047] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

Claims

1. A multi-source parameter control-based composite intelligent agricultural management system, characterized in that, The management system includes: The data processing module is used to collect historical multi-source data from various areas within the plantation, including environmental parameters, equipment status, and crop parameters. Based on the historical multi-source data, the module uses statistical analysis methods to obtain the core developmental needs of crops in each area and sets the initial threshold range for equipment parameters in each area. The correlation analysis module is used to obtain the crop types, equipment distribution and environmental correlation of each area in the current plantation, and to divide the spatial correlation between each area through correlation analysis methods, and to identify the same-level adjacent areas and secondary adjacent areas of each area. The hierarchical construction module is used to classify the operating parameters of equipment in each region based on the division of the region into same-level adjacent regions and secondary adjacent regions, so as to establish a multi-level collaborative control mechanism with different priorities. The operating parameter classification includes classification into core parameters and secondary parameters. The priority assessment module is used to obtain the growth cycle of crops in each area of ​​the current plantation and, based on historical multi-source data, assess the demand priority of different crop areas at the current growth stage. The adjustment management module is used to dynamically adjust the initial threshold range of equipment parameters in each region by combining the determined demand priorities with the established multi-level collaborative control mechanism, and finally generate the adjustment management plan for each region.

2. The multi-source parameter control-based compound intelligent agricultural management system according to claim 1, characterized in that, The process involves collecting historical multi-source data from various areas within the plantation, including environmental parameters, equipment status, and crop parameters. Based on this historical multi-source data, statistical analysis methods are used to obtain the core developmental needs of crops in each area, and initial threshold ranges for equipment parameters in each area are set. The steps include: Historical multi-source data of various areas within the plantation are collected at fixed intervals, and the collected historical multi-source data is cleaned and normalized according to the regional dimension. The historical multi-source data includes environmental parameters, equipment status and crop parameters. Based on the processed historical multi-source data, the core developmental requirements of crops in each region were extracted through data statistical analysis methods. These core developmental requirements include critical water threshold, nutrient sensitive range, and temperature suitability zone indicators. Based on the core development needs of each region and combined with equipment capability constraints, the initial threshold range of equipment parameters for each region is set.

3. The multi-source parameter control based compound intelligent agricultural management system according to claim 1, characterized in that, The steps of obtaining crop types, equipment distribution, and environmental relevance in each area of ​​the current plantation, and using correlation analysis to divide the spatial relationships between areas and identify the same-level and secondary adjacent areas of each area, include: Acquire data on crop types, equipment distribution, and environmental relevance in each area of ​​the current plantation, and establish a current status mapping table; Each region with a pre-defined initial threshold range for device parameters is used as an analysis unit. Based on the current state mapping table, the correlation strength between regions in terms of environmental parameter transmission and device linkage response is quantified through correlation analysis. Based on the strength of the association, the spatial relationships between the regions are divided, and the same-level adjacent regions and secondary adjacent regions of each region are identified.

4. The composite intelligent agricultural management system based on multi-source parameter control according to claim 1, characterized in that, The method involves classifying the operating parameters of equipment in each region based on their corresponding and secondary adjacent regions, thereby establishing a multi-level collaborative control mechanism with different priorities. The steps include: Based on the division of adjacent areas at the same level and secondary adjacent areas, analyze the scope and degree of influence of the operating parameters of equipment in each area on the local area and adjacent areas; The operating parameters of equipment in each region are classified into categories, including: Parameters whose adjustment actions, within one control cycle after execution, can cause at least one core developmental requirement indicator in the region to deviate beyond the preset tolerance range, and whose deviation has a direct causal relationship with the developmental progress of the crop at the current growth stage, are defined as core parameters; Parameters that only affect the core developmental requirements of the region when the environmental parameters or crop parameters in the region reach the preset trigger threshold, and are not continuously effective, are secondary parameters. Based on the hierarchical results of core parameters and secondary parameters, a multi-level collaborative control mechanism with different priorities is established. The multi-level collaborative control mechanism includes the execution of core parameters before secondary parameters and the linkage of adjacent regions at the same level before adjacent regions at the secondary level.

5. A composite intelligent agricultural management system based on multi-source parameter control according to claim 1, characterized in that, The steps of obtaining the growth cycle of crops in each area of ​​the current plantation and assessing the demand priority of different crop areas at the current growth stage based on historical multi-source data include: Obtain the growth cycle information of crops in each area of ​​the current plantation, and identify the current growth stage of crops in each area. The growth stages include seedling stage, vegetative growth stage, flowering stage, and fruit enlargement stage. Based on the acquired historical multi-source data, a crop demand-stage mapping relationship is established according to the growth stage dimension; Based on the crop demand-stage mapping relationship, the demand priority of different crop regions at the current growth cycle stage is assessed to obtain the demand priority of each region.

6. The composite intelligent agricultural management system based on multi-source parameter control according to claim 1, characterized in that, The process involves combining the determined demand priorities with the established multi-level collaborative control mechanism to dynamically adjust the initial threshold ranges of equipment parameters in each region, ultimately generating a control and management plan for each region. The steps include: The priority of demand in each region obtained from the assessment is used as input and matched with the multi-level coordinated regulation mechanism to determine the adjustment direction and adjustment magnitude weight of the core parameters and secondary parameters in each region. Based on the initial threshold range of equipment parameters in each region, and combined with the adjustment direction and adjustment magnitude weight of the core parameters and secondary parameters in each region, the initial threshold range of equipment parameters is dynamically adjusted, including: tightening or relaxing the threshold of core parameters in high-demand priority regions, and adjusting the threshold of secondary parameters in low-demand priority regions according to the linkage rules of the multi-level collaborative control mechanism. The dynamically adjusted equipment parameter thresholds for each region are summarized to generate a regulation and management plan for each region. The regulation and management plan includes the specific execution values ​​and execution sequence of the core and secondary parameters for each region under the current growth cycle.

Images