Planting park sprinkling irrigation management method and system based on intelligent Internet of Things

Abstract

The invention is suitable for the technical field of agricultural intelligent irrigation control and environmental perception data processing, and provides a planting park sprinkling irrigation management method and system based on the intelligent Internet of Things, and the method comprises the steps: obtaining a plurality of reference data samples consistent with the sprinkling irrigation background information in a target planting area, the reference data sample comprises original particle composition data in air before spray irrigation and a corresponding unit water volume humidity increasing rate value after spray irrigation. The invention provides a quantifiable input intensity factor generation mechanism by constructing a time evolution trend mapping relation between a non-moisture source particle component proportion and a unit water volume humidity increase rate. Compared with a processing mode in the prior art that potential influences may be missed by directly removing the particle components, the method has the advantages that the retention ratio is calculated by using the slope deviation value, and dynamic weakening processing of the non-moisture source particle components in the original data is realized.

Description

Technical Field

[0001] This invention belongs to the field of agricultural intelligent irrigation control and environmental sensing data processing technology, and particularly relates to a method and system for sprinkler irrigation management in planting areas based on the Internet of Things. Background Technology

[0002] In existing agricultural irrigation management systems, the identification and control of sprinkler irrigation demand typically relies on various monitoring parameters such as ambient temperature and humidity, soil moisture content, and meteorological data. Some more advanced demand analysis models also incorporate air particle composition as a reference variable, arguing that changes in the concentration of specific particles can, to some extent, reflect indirect trends in evapotranspiration intensity, plant physiological activity, or water status. Therefore, in smart IoT-enabled planting parks with environmental monitoring capabilities, air particle composition data is increasingly being incorporated into the input parameter system for sprinkler irrigation regulation, helping to determine whether there is an actual demand for sprinkler irrigation.

[0003] However, in practical applications, some systems directly preprocess the raw particle composition data, identifying and removing particles not directly related to moisture changes (such as soil loosening, disturbance from manual inspections, or dust from planting area boundaries), retaining only a subset deemed moisture-related for input into the analysis model. While this approach simplifies the data structure and improves model computational efficiency, it relies too heavily on rule-based classification, neglecting the potential indirect influence of certain "non-moisture-source particles" on humidity changes at specific stages or in specific crop environments. For example, these particles may affect evaporation rates due to physical shielding, reflection, or carrying biological particles, but these potential effects are often overlooked by existing rules, leading to significant biases in the analysis model's judgment of actual humidity responses. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for sprinkler irrigation management in plantations based on the Internet of Things, in order to solve the problems mentioned in the background art.

[0005] This invention is implemented as follows: a method for sprinkler irrigation management in a planting area based on the Internet of Things, the method comprising: Acquire several reference data samples with consistent background information of sprinkler irrigation in the target planting area. The reference data samples include the original particle composition data of the air before sprinkler irrigation and the corresponding humidity increase rate value per unit water volume after sprinkler irrigation. Based on the preset identification mechanism, the proportion of non-moisture source particles in the original particle composition data of each reference data sample is determined, and the first trend of the proportion and the second trend of the humidity increase rate per unit water volume are constructed in chronological order. Linear fitting is performed on the first trend and the second trend to obtain the corresponding first trend slope and second trend slope. If the first trend is linearly increasing and the second trend is linearly decreasing, and the absolute value of the second trend slope is less than the absolute value of the first trend slope, then the delivery retention ratio is generated based on the difference between the two. In subsequent sprinkler irrigation management, the delivery retention ratio is applied to the non-water source particle components in the future original particle composition data that will be delivered to the sprinkler irrigation demand analysis model, and the corrected particle composition data is input into the model to obtain the corrected demand intensity value for subsequent sprinkler irrigation regulation.

[0006] As a further limitation of the technical solution of the embodiment of the present invention, the consistency of the sprinkler irrigation background information means that the crop type corresponding to the reference data sample is consistent, the growth stage is consistent, the collection time is within the same natural cycle, and the variation range of sprinkler irrigation water volume, ambient temperature and ambient humidity is within the set allowable range.

[0007] As a further limitation of the technical solution of this invention embodiment, based on a preset identification mechanism, the steps of determining the proportion of non-moisture source particles in the original particle composition data of each reference data sample, and constructing a first trend of the proportion and a second trend of the rate of increase in humidity per unit volume of water according to time sequence, specifically include: For each reference data sample, the original particle composition data of the air in the target planting area before sprinkler irrigation is obtained, and the particle components in the unit volume are classified and identified based on particle size structure characteristics, component identification parameters or preset analysis devices. The part of the particle components that are not from water sources is determined, and its proportion in the overall particle composition data is calculated and recorded as the proportion of non-water source particle components. The proportions of non-moisture-sourced particles in all reference data samples are arranged in chronological order to form the first trend. At the same time, the rate of increase in air humidity per unit amount of water in each reference data sample is arranged in the same chronological order to form the second trend.

[0008] As a further limitation of the technical solution of this embodiment of the invention, linear fitting is performed on the first trend and the second trend to obtain the corresponding first trend slope and second trend slope. If the first trend is linearly increasing and the second trend is linearly decreasing, and the absolute value of the second trend slope is less than the absolute value of the first trend slope, then the step of generating the delivery retention ratio based on the difference between the two specifically includes: Linear fitting is performed on the first trend and the second trend based on the least squares fitting technique, and the slopes of the first trend and the second trend are calculated. If the slope of the first trend is positive and the slope of the second trend is negative, and the absolute value of the slope of the second trend is less than the absolute value of the slope of the first trend, then calculate the ratio of the relative deviations between the absolute values ​​of the two slopes. Based on the relative deviation ratio and combined with a preset adjustment amplitude factor, a delivery retention ratio is generated to adjust the input intensity of non-moisture source particle components in the sprinkler irrigation demand analysis model.

[0009] As a further limitation of the technical solution of this invention, in subsequent sprinkler irrigation management, after obtaining the original particle composition data for calculating the demand intensity value, a subset of non-water source particle components is identified, and the intensity of the non-water source particle component subset is adjusted by using the delivery retention ratio, rather than being directly removed; the adjusted non-water source particle component data and the remaining particle data are input into the sprinkler irrigation demand analysis model to generate a corrected demand intensity value for subsequent sprinkler irrigation regulation.

[0010] A smart Internet of Things (IoT) based sprinkler irrigation management system for plantations, the system comprising: The sample acquisition module is used to acquire several reference data samples with consistent background information of sprinkler irrigation in the target planting area. The reference data samples include the original particle composition data of the air before sprinkler irrigation and the corresponding humidity increase rate value per unit water volume after sprinkler irrigation. The correlation identification module is used to determine the proportion of non-moisture source particles in the original particle composition data of each reference data sample based on a preset identification mechanism, and to construct the first trend of the proportion and the second trend of the humidity increase rate per unit water volume in chronological order. The delivery retention ratio generation module is used to perform linear fitting on the first trend and the second trend respectively to obtain the corresponding first trend slope and second trend slope. If the first trend is linearly increasing and the second trend is linearly decreasing, and the absolute value of the second trend slope is less than the absolute value of the first trend slope, then the delivery retention ratio is generated based on the difference between the two. The model input adjustment module is used to apply the delivery retention ratio to the non-water source particle components in the future original particle composition data that will be delivered to the sprinkler irrigation demand analysis model in subsequent sprinkler irrigation management, and input the corrected particle composition data into the model to obtain the corrected demand intensity value for subsequent sprinkler irrigation regulation.

[0011] As a further limitation of the technical solution of the embodiment of the present invention, the consistency of the sprinkler irrigation background information means that the crop type corresponding to the reference data sample is consistent, the growth stage is consistent, the collection time is within the same natural cycle, and the variation range of sprinkler irrigation water volume, ambient temperature and ambient humidity is within the set allowable range.

[0012] As a further limitation of the technical solution of this embodiment of the invention, the correlation identification module specifically includes: The component identification unit is used to acquire the original particle composition data of the air in the target planting area before irrigation for each reference data sample, and classify and identify the particle components in a unit volume based on particle size structure characteristics, component identification parameters or preset analysis devices, determine the part of the non-moisture source particle components, and calculate its proportion in the overall particle composition data, which is recorded as the proportion of non-moisture source particle components. The trend building unit is used to arrange the proportion of non-moisture source particle components in all reference data samples in chronological order to form the first trend, and at the same time, arrange the air humidity increase rate caused by a unit amount of water in each reference data sample in the same chronological order to form the second trend.

[0013] As a further limitation of the technical solution of this embodiment of the invention, the delivery retention ratio generation module specifically includes: The trend fitting unit is used to perform linear fitting on the first trend and the second trend based on the least squares fitting technique, and calculate the corresponding slopes of the first trend and the second trend. The condition judgment unit is used to calculate the relative deviation ratio between the absolute values ​​of the slopes of the two trends if the slope of the first trend is positive, the slope of the second trend is negative, and the absolute value of the slope of the second trend is less than the absolute value of the slope of the first trend. The factor generation unit is used to generate, based on the relative deviation ratio and in combination with a preset adjustment amplitude factor, the delivery retention ratio for adjusting the input intensity of non-moisture source particle components in the sprinkler irrigation demand analysis model.

[0014] As a further limitation of the technical solution of this invention, in subsequent sprinkler irrigation management, after obtaining the original particle composition data for calculating the demand intensity value, a subset of non-water source particle components is identified, and the intensity of the non-water source particle component subset is adjusted by using the delivery retention ratio, rather than being directly removed; the adjusted non-water source particle component data and the remaining particle data are input into the sprinkler irrigation demand analysis model to generate a corrected demand intensity value for subsequent sprinkler irrigation regulation.

[0015] Compared with the prior art, the present invention has the following beneficial effects: This invention proposes a quantifiable input intensity factor generation mechanism by constructing a temporal evolution trend mapping relationship between the proportion of non-moisture-source particles and the rate of humidity increase per unit volume of water. Compared to existing technologies that directly remove such particles, potentially missing their impact, this invention uses slope deviation to calculate the retention ratio, achieving dynamic attenuation of non-moisture-source particles in the original data. This method not only avoids the erroneous removal of useful information but also significantly improves the fit of the sprinkler irrigation demand analysis model to the actual humidity response. In an already deployed IoT environment, this solution can be directly implemented by combining sampling sensors and data analysis modules, applicable to various crops and different sprinkler irrigation cycles, demonstrating good application feasibility and engineering value. Attached Figure Description

[0016] Figure 1 A flowchart of the method provided in the embodiments of the present invention; Figure 2 This is a flowchart illustrating the identification and trend construction of non-moisture source particle components in the method provided in this embodiment of the invention; Figure 3 This is a flowchart illustrating the generation of trend fitting and delivery retention ratio in the method provided in this embodiment of the invention; Figure 4 Application architecture diagram of the system provided in the embodiments of the present invention; Figure 5 This is a structural block diagram of the correlation identification module in the system provided in the embodiments of the present invention; Figure 6 This is a structural block diagram of the retention ratio generation module in the system provided in the embodiment of the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0018] Figure 1 A flowchart of the method provided by an embodiment of the present invention is shown.

[0019] Specifically, a method for managing sprinkler irrigation in a planting area based on the Internet of Things (IoT) includes the following steps: Step S100: Obtain several reference data samples with consistent background information of sprinkler irrigation in the target planting area. The reference data samples include the original particle composition data of the air before sprinkler irrigation and the corresponding humidity increase rate value per unit water volume after sprinkler irrigation.

[0020] The consistency of the sprinkler irrigation background information means that the crop types corresponding to the reference data samples are consistent, the growth stages are consistent, the collection time is within the same natural cycle, and the variation range of sprinkler irrigation water volume, ambient temperature and ambient humidity are all within the set allowable range.

[0021] In this embodiment of the invention, the target planting area can be an orchard, vegetable greenhouse, tea garden, nursery, or other cultivated land with conditions suitable for sprinkler irrigation operations, equipped with air monitoring devices and sprinkler irrigation control devices. It is also equipped with a smart IoT system to acquire data in real time, including air environment parameters, sprinkler irrigation behavior parameters, and crop attribute information. The smart IoT system may include an air particle collector, temperature and humidity sensors, water metering devices, and a networked control terminal, possessing remote data transmission and analysis capabilities, and supporting the linked analysis of sprinkler irrigation behavior data and environmental changes.

[0022] The research foundation of the method established in this invention stems from the widely used sprinkler irrigation demand analysis models in existing technologies. The goal of these models is to estimate the current water demand intensity of crops after acquiring real-time environmental data of the target area, thus assisting in intelligent sprinkler irrigation decision-making. Common model forms include regression analysis based on environmental parameters, water evapotranspiration simulation, or multi-factor weighting, ultimately outputting a corresponding sprinkler irrigation intensity value. However, in existing modeling practices, although airborne particle composition data is considered as one of the influencing factors, components "not directly related to water evaporation or condensation" are usually directly removed during data preprocessing. These components are treated as interference and filtered out, retaining only those highly correlated with water behavior for modeling. These removed particle components typically include some anthropogenic particles (such as dust generated by agricultural machinery operation), residual organic pollutant particles, and soil dust particles.

[0023] However, this simple elimination method has significant shortcomings. First, in planting scenarios where equipment has been running for a long time, sprinkler irrigation is frequent, or crop varieties are densely packed, the proportion of these "non-water-source particle components" in the actual data gradually increases. Complete elimination would weaken the model's ability to perceive overall particle behavior during long-term evolution. Second, some non-water-source particle components themselves have certain hygroscopic, light-blocking, or heat-transfer effects. For example, highly hygroscopic organic fine particles may indirectly change the rate of air humidity regulation or affect the degree of stomatal opening on plant leaves, thus producing a weak but cumulative interference on the rate of humidity change. Third, under certain extreme weather or abnormal environmental conditions, these components may become sensitive indicators of humidity changes. Therefore, the "elimination processing" used in existing technologies may mask the potential validity of this part of the data.

[0024] On the other hand, existing methods lack a direct, effective, and clearly structured approach to determine the impact of non-moisture source particles on sprinkler irrigation demand analysis. Existing solutions may employ complex modeling techniques such as multidimensional feature modeling, principal component analysis, or nonlinear perturbation analysis, but these methods not only rely on high fitting accuracy but also have high requirements for sample size, model robustness, and computational cost, making them difficult to apply stably in production practice.

[0025] In this embodiment of the invention, to more scientifically and systematically identify the actual impact of these components, a "humidity increase rate per unit volume of water" is introduced as a responsive parameter reflecting the sprinkler irrigation effect, and is combined with "particle composition data" for linked modeling and analysis. The aforementioned particle composition data can be obtained through a particle analysis component deployed in an air monitoring terminal in the planting area. This particle analysis component may include an optical particle counter or laser particle scanner with particle size recognition capabilities, coupled with a built-in particle composition analysis module for classification and identification. The humidity increase rate per unit volume of water is obtained by continuously measuring air humidity values ​​before and after sprinkler irrigation operations, and calculating the rate of change based on the actual sprayed water volume. The required hardware, such as temperature and humidity sensors and sprinkler irrigation meters, are all conventional and mature equipment.

[0026] In selecting reference data samples, this invention specifically stipulates that the background information of sprinkler irrigation must be consistent. The purpose is to eliminate the dominant interference of dominant factors such as crop type, growth stage or climate cycle on changes in air humidity by controlling variables, and then identify the marginal impact of particle composition on the basis of ensuring environmental consistency. The basis for setting the allowable range is derived from the conventional water volume and temperature and humidity ranges statistically analyzed in agricultural meteorological monitoring or regional planting specifications, to ensure that the differences between data samples are within an acceptable range.

[0027] It should be noted that the method of this invention is based on the full collection and analysis of a large number of historical sprinkler irrigation data samples, ensuring that the first trend (change in particle composition ratio) and the second trend (change in the rate of increase in humidity per unit water volume) in subsequent studies have good support in terms of data volume, so that the calculation of linear fitting slope and the generation of delivery retention ratio have sufficient stability and practical significance.

[0028] Furthermore, the plantation sprinkler irrigation management method based on smart IoT also includes the following steps: Step S200: Based on a preset identification mechanism, determine the proportion of non-moisture source particles in the original particle composition data of each reference data sample, and construct a first trend of the proportion and a second trend of the rate of increase in humidity per unit amount of water in chronological order.

[0029] Specifically, Figure 2 A flowchart illustrating the identification and trend construction of non-moisture source particle components is shown.

[0030] The process, based on a pre-defined identification mechanism, involves determining the proportion of non-moisture-source particles in the original particle composition data of each reference data sample, and constructing a first trend of change in this proportion and a second trend of change in the rate of increase in humidity per unit volume of water, specifically including the following steps: Step S201: For each reference data sample, obtain the original particle composition data of the air in the target planting area before sprinkler irrigation, and classify and identify the particle components in the unit volume based on particle size structure characteristics, component identification parameters or preset analysis device, determine the part of the non-moisture source particle components, and calculate its proportion in the overall particle composition data, which is recorded as the proportion of non-moisture source particle components. Step S202: Arrange the proportions of non-moisture source particle components in all reference data samples in chronological order to form the first trend. At the same time, arrange the air humidity increase rate caused by unit water volume in each reference data sample in the same chronological order to form the second trend.

[0031] Furthermore, the plantation sprinkler irrigation management method based on smart IoT also includes the following steps: Step S300: Perform linear fitting on the first trend and the second trend respectively to obtain the corresponding first trend slope and second trend slope. If the first trend is linearly increasing and the second trend is linearly decreasing, and the absolute value of the second trend slope is less than the absolute value of the first trend slope, then generate the delivery retention ratio based on the difference between the two.

[0032] Specifically, Figure 3 The flowchart for generating trend fitting and delivery retention ratio is shown.

[0033] The process involves linearly fitting the first and second trends to obtain their respective slopes. If the first trend shows a linear increase and the second trend shows a linear decrease, and the absolute value of the second trend slope is less than the absolute value of the first trend slope, then the delivery retention ratio is generated based on the difference between the two. This process includes the following steps: Step S301: Based on the least squares fitting technique, linear fitting is performed on the first trend and the second trend respectively, and the corresponding first trend slope and second trend slope are calculated. Step S302: If the slope of the first trend is positive and the slope of the second trend is negative, and the absolute value of the slope of the second trend is less than the absolute value of the slope of the first trend, then calculate the relative deviation ratio between the absolute values ​​of the two slopes. Step S303: Based on the relative deviation ratio and combined with a preset adjustment amplitude factor, generate the delivery retention ratio for adjusting the input intensity of non-moisture source particle components in the sprinkler irrigation demand analysis model.

[0034] In this embodiment of the invention, the specific implementation process of step S201 is as follows: First, air particle collection equipment deployed in the target planting area collects raw particle composition data before sprinkler irrigation. The collection equipment is preferably an environmental monitoring terminal integrating particle size identification and composition analysis capabilities, specifically including a laser particle counter, a time-of-flight mass spectrometer, or a portable aerosol analysis device with multi-segment spectral analysis capabilities. These devices, based on mature technologies in the existing environmental monitoring field such as light scattering, mass spectrometry, and charge mobility, can perform real-time quantitative and classification analysis of suspended particles in the air within a unit volume range. They are commercially viable devices that can be directly applied in existing technologies and are feasible for implementation.

[0035] After acquiring the raw particle composition data, the system calls upon matching particle size structure feature judgment rules and component identification parameter sets for classification. For example, particle size structure features can be grouped according to set intervals (such as PM0.3-0.5, PM0.5-1.0, PM1.0-2.5, etc.); component identification parameters combine particle density, mass spectrometry fragment peak values, hygroscopicity evaluation values, etc., and identify particle components not directly related to water vapor through rule matching or simple feature vector classification methods (such as KNN classifiers, threshold partitioning algorithms), such as dust impurities, fertilizer spray residues, and particles settled in agricultural machinery exhaust, and regard them as "non-moisture source particle components". The proportion of such components in the total number of particles is calculated, which is the proportion of non-moisture source particle components and serves as one of the feature values ​​of the current reference data sample.

[0036] After proceeding to step S202, the proportions of non-moisture-source particles identified in all reference samples are arranged chronologically to form the first trend. Since the collection period covers a relatively long timeframe, the first trend accurately reflects whether the proportion of non-moisture-source particles in the air shows a systematic increase as the intensity of operations in the planting area changes or pollution sources accumulate. For example, if the proportion of non-moisture-source particles in the air gradually increases from 15% to 19% due to increased equipment operating time, higher cultivation frequency, or shorter spraying cycles, then the slope of the first trend is positive, showing a linear increase.

[0037] Meanwhile, the "humidity increase rate per unit volume of water" values ​​after irrigation in each reference sample were arranged in chronological order to construct a second trend. This reflects whether the ability of ambient air to increase humidity is decreasing under the condition of a constant unit volume of irrigation water. For example, if the average humidity increase per liter of water decreases from 10% initially to 7%, the corresponding trend slope is negative, showing a linear decrease.

[0038] After proceeding to step S302, if the slope of the first trend is positive and the slope of the second trend is negative, and the absolute value of the second slope is less than the absolute value of the first slope, it indicates that although the proportion of non-moisture source particles in the air is continuously increasing, the humidity increase per unit volume of irrigation water has not decreased proportionally. In other words, these particles classified as "non-moisture source" may still participate in humidity diffusion or retention to some extent. At this point, the ratio of the relative deviation between the absolute values ​​of the two slopes is defined as the core parameter for evaluating the correction space, which helps to quantify the degree of this "partial effectiveness" and thus set the delivery retention ratio.

[0039] The preset adjustment amplitude factor is usually set based on the sensitivity analysis results of the fitting effect of non-moisture source particle components on the humidity response curve in historical samples, combined with expert experience or field survey results, in order to achieve a balance between ensuring the effective preservation of information and reducing interference components.

[0040] In addition to the relative deviation ratio, other methods such as the slope difference ratio (i.e., the ratio of the slope of the first trend to the slope difference between the two), the mean ratio of the fitting residuals (such as the ratio of the mean of the fitting residuals of the humidity trend to the mean of the fitting residuals of the particle trend), or the inverse normalized value of the trend correlation coefficient can be used to characterize the degree of deviation between the two types of trends, thereby constructing a more adaptive retention ratio generation mechanism.

[0041] For example, if the slope of the first trend is +0.012 and the slope of the second trend is -0.006, then the difference in the absolute values ​​of the two slopes is 0.006, and the relative deviation ratio is: 0.006 / 0.012 = 0.5.

[0042] If the system's preset adjustment amplitude factor is 0.6 (that is, when it is confirmed that there is a certain "partial validity", it is allowed to retain no more than 60% of the input intensity), then the calculated delivery retention ratio is: delivery retention ratio = 0.5 × 0.6 = 0.3.

[0043] Therefore, for the currently identified non-moisture source particle components, their input intensity in the sprinkler irrigation demand analysis model will be adjusted to 30% of the original value. That is, only 30% will participate in the model analysis, while the remaining 70% will be weakened as inefficient or invalid information, thus achieving an input intensity control strategy that better reflects the actual effect. This mechanism effectively avoids the risk of excessively removing potentially useful information or blindly amplifying interfering components.

[0044] The delivery retention ratio generation mechanism, built upon the second trend mapping relationship, is fundamentally based on a reverse assessment of the actual influence of non-moisture-source particle components from the perspective of humidity response effects. Compared to the crude approach of simply classifying and eliminating components based on their source in existing technologies, this invention introduces the objective indicator of humidity increase rate per unit volume of water, which is highly correlated with sprinkler irrigation effects. By combining time series analysis and linear fitting, it can more intuitively reveal whether those particle components classified as "non-moisture-source" still play a role in the actual environmental response, thus providing a more scientific data attenuation strategy.

[0045] The significance of this mechanism lies in the fact that, when faced with the gradual increase in the proportion of non-moisture-source components in the particle composition during long-term use, the system can dynamically judge the trend of its effectiveness change and make input corrections through quantification, thereby improving the model's ability to perceive actual humidity changes and enhancing the response accuracy and adaptability of sprinkler irrigation control strategies.

[0046] This mechanism has promising application prospects, especially suitable for smart IoT platforms deployed in smart planting parks. It can seamlessly connect with existing sensing and data acquisition systems, significantly improving the ability of sprinkler irrigation decision-making systems to identify and adapt to complex environmental interference factors, and providing a solid data support foundation and implementation path for precision agriculture, water resource conservation management, and smart irrigation strategy optimization.

[0047] Furthermore, the plantation sprinkler irrigation management method based on smart IoT also includes the following steps: In step S400, during subsequent sprinkler irrigation management, the delivery retention ratio is applied to the non-water source particle components in the future original particle composition data that will be delivered to the sprinkler irrigation demand analysis model, and the corrected particle composition data is input into the model to obtain the corrected demand intensity value for subsequent sprinkler irrigation regulation.

[0048] In subsequent sprinkler irrigation management, after obtaining the original particle composition data for calculating the demand intensity value, the non-water source particle component subset is identified. The intensity of the non-water source particle component subset is adjusted by the delivery retention ratio, rather than being directly removed. The adjusted non-water source particle component data and the remaining particle data are input into the sprinkler irrigation demand analysis model to generate the corrected demand intensity value for subsequent sprinkler irrigation regulation.

[0049] In this embodiment of the invention, the processing flow executed in step S400 not only inherits the generation mechanism of the previous delivery retention ratio, but also embeds this delivery retention ratio into the parameter correction chain of the original data structure in the execution link of actual sprinkler irrigation demand analysis, forming a fully closed-loop control process of "identification-judgment-adjustment-modeling-output", thereby significantly enhancing the cognitive adaptability of sprinkler irrigation demand decision-making to humidity response capability under complex air particle composition background.

[0050] In practical implementation, the system first acquires raw particle composition data of the current air within the target planting area. This data can be collected in real time by a high-sensitivity air particle acquisition device deployed in the sprinkler irrigation area. This device typically uses an optical particle counter combined with a micro-component analysis module (such as a PM component analysis device based on beta-ray absorption or a laser particle size distribution detector) to acquire the particle size distribution and component proportion in a unit volume of air at a sampling cycle of minutes. After acquisition, the data enters the particle recognition module. In this module, a built-in particle size threshold model and characteristic absorption spectrum template are used to identify a subset of particle components belonging to "non-moisture sources," such as calcium carbonate dust from construction dust, titanium-iron dust from road pollution, and non-volatile impurity particles released during biological decomposition.

[0051] Subsequently, the system calls the delivery retention ratio calculated in the previous steps and applies this factor to the identified subset of non-moisture-sourced particles. For example, if the concentration of the non-moisture-sourced particle component subset in the current original particle composition data is 80 μg / m³, and the delivery retention ratio is 0.45, then the system adjusts the input intensity of this subset to: 80 × 0.45 = 36 μg / m³.

[0052] The adjusted data, along with the remaining uncorrected particle composition data, is fed into the sprinkler irrigation demand analysis model. This model is typically a multivariate regression model or a neural network model built based on the crop water demand response curve. Input dimensions include multiple indicators such as air temperature and humidity, wind speed, particle composition, and water temperature. The output variable is the sprinkler irrigation water demand per unit area for the current time period. The adjusted particle input retains some potentially useful information without manually removing data, while reducing its potential misleading effect on demand calculations. This results in a more scientifically corrected sprinkler irrigation demand intensity value, providing decision support for subsequent implementation.

[0053] The following is a specific example to illustrate the specific technical solution of the present invention: Suppose that a certain planting area has set up sampling records every year during the jointing stage of sorghum for 5 consecutive years, and selected 2 sets of data samples with consistent sprinkler irrigation background information each year, for a total of 10 sets of historical samples. The sampling time for each set of samples is 10:00-10:30 am during the jointing stage of that year, and the ambient temperature and humidity on the sampling day are within the set allowable range to ensure the consistency of physiological state and environmental conditions.

[0054] Each set of reference data samples includes the following: Percentage of non-moisture source particles before sprinkler irrigation (unit: %): 28%, 28.5%, 29%, 29.5%, 30%, 30.5%, 31%, 31.5%, 32%, 32.5%.

[0055] The rate of increase in humidity per unit volume of water after sprinkler irrigation (unit: % / L): 1.12, 1.11, 1.10, 1.09, 1.08, 1.07, 1.06, 1.05, 1.04, 1.03.

[0056] Based on the least squares linear fitting: the slope of the first trend (the proportion of non-moisture source particles) is approximately +0.28; the slope of the second trend (the rate of increase in humidity per unit water volume) is approximately -0.09.

[0057] The relative deviation ratio is calculated as 0.09 ÷ 0.28 ≈ 0.3214. Combined with the preset adjustment amplitude factor N = 0.6, the final delivery retention ratio is 0.3214 × 0.6 ≈ 0.19284. That is, under the current conditions, only 19.284% of the identified non-moisture source particles will be retained and delivered to the sprinkler irrigation demand analysis model for calculation, while the rest will not participate in the model calculation.

[0058] Assuming the current concentration of non-moisture source particles is 100 μg / m³, the actual data used for model calculation is: 100 × 0.19284 = 19.284 μg / m³.

[0059] In other words, this invention no longer directly excludes the component, but instead "reduces its weight" so that its input strength in the model is weakened but its potential contribution is still retained.

[0060] In summary: The correction mechanism proposed in this invention does not rely on highly complex qualitative reasoning of components, nor does it require manual labeling of causal mappings between a large number of interference items and target items. Instead, it reflects the degree of "relative ineffectiveness" of non-water-source particle components in the system at the statistical level through the difference relationship of trend mapping. This mechanism can flexibly adapt to the differences in particle backgrounds of different crops and regions, and has good applicability for promotion.

[0061] Its core significance lies in introducing environmental information that is often overlooked or simply excluded into the scientific evaluation logic, so that the sprinkler irrigation control model can more realistically reflect the humidity response mechanism in the actual planting environment, thereby improving control efficiency, reducing energy waste, and enhancing the robustness and adaptability of the model in long-term operation.

[0062] In the future, this mechanism can be combined with multi-dimensional remote sensing data and aerosol dynamic monitoring data to expand into smart agriculture application scenarios such as unmanned farms and fully automated sprinkler irrigation systems, and has broad industrialization prospects.

[0063] Furthermore, Figure 4 An application architecture diagram of the system provided in an embodiment of the present invention is shown.

[0064] In another preferred embodiment of the present invention, a sprinkler irrigation management system for a planting area based on the Internet of Things includes: The sample acquisition module 100 is used to acquire several reference data samples with consistent background information of sprinkler irrigation in the target planting area. The reference data samples include the original particle composition data of the air before sprinkler irrigation and the corresponding humidity increase rate value per unit water volume after sprinkler irrigation.

[0065] The consistency of the sprinkler irrigation background information means that the crop types corresponding to the reference data samples are consistent, the growth stages are consistent, the collection time is within the same natural cycle, and the variation range of sprinkler irrigation water volume, ambient temperature and ambient humidity are all within the set allowable range.

[0066] Furthermore, the smart IoT-based sprinkler irrigation management system for plantations also includes: The correlation identification module 200 is used to determine the proportion of non-moisture source particles in the original particle composition data of each reference data sample based on a preset identification mechanism, and to construct a first trend of the proportion and a second trend of the rate of increase in humidity per unit water volume in chronological order.

[0067] Specifically, Figure 5 A structural block diagram of the correlation identification module 200 in the system provided in an embodiment of the present invention is shown.

[0068] In a preferred embodiment of the present invention, the correlation identification module 200 specifically includes: The component identification unit 201 is used to acquire the original particle composition data of the air in the target planting area before irrigation for each reference data sample, and classify and identify the particle components in a unit volume based on particle size structure characteristics, component identification parameters or preset analysis devices, determine the part of the non-moisture source particle components, and calculate its proportion in the overall particle composition data, which is recorded as the proportion of non-moisture source particle components. The trend building unit 202 is used to arrange the proportion of non-moisture source particle components in all reference data samples in chronological order to form the first trend, and at the same time arrange the air humidity increase rate caused by unit water volume in each reference data sample in the same chronological order to form the second trend.

[0069] Furthermore, the smart IoT-based sprinkler irrigation management system for plantations also includes: The delivery retention ratio generation module 300 is used to perform linear fitting on the first trend and the second trend respectively to obtain the corresponding first trend slope and second trend slope. If the first trend is linearly increasing and the second trend is linearly decreasing, and the absolute value of the second trend slope is less than the absolute value of the first trend slope, then the delivery retention ratio is generated based on the difference between the two.

[0070] Specifically, Figure 6 The diagram shows a structural block diagram of the retention ratio generation module 300 in the system provided by an embodiment of the present invention.

[0071] In a preferred embodiment of the present invention, the delivery retention ratio generation module 300 specifically includes: The trend fitting unit 301 is used to perform linear fitting on the first trend and the second trend based on the least squares fitting technique, and calculate the corresponding first trend slope and second trend slope. The condition judgment unit 302 is used to calculate the relative deviation ratio between the absolute values ​​of the slopes of the two trends if the slope of the first trend is positive, the slope of the second trend is negative, and the absolute value of the slope of the second trend is less than the absolute value of the slope of the first trend. The factor generation unit 303 is used to generate, based on the relative deviation ratio and in combination with a preset adjustment amplitude factor, the delivery retention ratio for adjusting the input intensity of non-moisture source particle components in the sprinkler irrigation demand analysis model.

[0072] Furthermore, the smart IoT-based sprinkler irrigation management system for plantations also includes: The model input adjustment module 400 is used to apply the delivery retention ratio to the non-water source particle components in the future original particle composition data that will be delivered to the sprinkler irrigation demand analysis model in subsequent sprinkler irrigation management, and input the corrected particle composition data into the model to obtain the corrected demand intensity value for subsequent sprinkler irrigation regulation.

[0073] In subsequent sprinkler irrigation management, after obtaining the original particle composition data for calculating the demand intensity value, the non-water source particle component subset is identified. The intensity of the non-water source particle component subset is adjusted by the delivery retention ratio, rather than being directly removed. The adjusted non-water source particle component data and the remaining particle data are input into the sprinkler irrigation demand analysis model to generate the corrected demand intensity value for subsequent sprinkler irrigation regulation.

[0074] It should be understood that although the steps in the flowcharts of the various embodiments of the present invention are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the various embodiments may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0075] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0076] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0077] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

[0078] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for sprinkler irrigation management in a planting area based on smart Internet of Things, characterized in that, The method includes: Acquire several reference data samples with consistent background information of sprinkler irrigation in the target planting area. The reference data samples include the original particle composition data of the air before sprinkler irrigation and the corresponding humidity increase rate value per unit water volume after sprinkler irrigation. Based on the preset identification mechanism, the proportion of non-moisture source particles in the original particle composition data of each reference data sample is determined, and the first trend of the proportion and the second trend of the humidity increase rate per unit water volume are constructed in chronological order. Linear fitting is performed on the first trend and the second trend to obtain the corresponding first trend slope and second trend slope. If the first trend is linearly increasing and the second trend is linearly decreasing, and the absolute value of the second trend slope is less than the absolute value of the first trend slope, then the delivery retention ratio is generated based on the difference between the two. In subsequent sprinkler irrigation management, the delivery retention ratio is applied to the non-water source particle components in the future original particle composition data that will be delivered to the sprinkler irrigation demand analysis model, and the corrected particle composition data is input into the model to obtain the corrected demand intensity value for subsequent sprinkler irrigation regulation.

2. The method for sprinkler irrigation management of planting areas based on smart Internet of Things according to claim 1, characterized in that, The consistency of the sprinkler irrigation background information means that the crop types corresponding to the reference data samples are consistent, the growth stages are consistent, the collection time is within the same natural cycle, and the variation range of sprinkler irrigation water volume, ambient temperature and ambient humidity are all within the set allowable range.

3. The method for sprinkler irrigation management of planting areas based on smart Internet of Things according to claim 1, characterized in that, Based on a pre-defined identification mechanism, the steps of determining the proportion of non-moisture-source particles in the original particle composition data of each reference data sample, and constructing a first trend of change of this proportion in chronological order, and a second trend of change of the rate of increase in humidity per unit volume of water, specifically include: For each reference data sample, the original particle composition data of the air in the target planting area before sprinkler irrigation is obtained, and the particle components in the unit volume are classified and identified based on particle size structure characteristics, component identification parameters or preset analysis devices. The part of the particle components that are not from water sources is determined, and its proportion in the overall particle composition data is calculated and recorded as the proportion of non-water source particle components. The proportions of non-moisture-sourced particles in all reference data samples are arranged in chronological order to form the first trend. At the same time, the rate of increase in air humidity per unit amount of water in each reference data sample is arranged in the same chronological order to form the second trend.

4. The method for sprinkler irrigation management of planting areas based on smart Internet of Things according to claim 3, characterized in that, Linear fitting is performed on the first and second trends respectively to obtain the corresponding slopes of the first and second trends. If the first trend shows a linear increase and the second trend shows a linear decrease, and the absolute value of the slope of the second trend is less than the absolute value of the slope of the first trend, then the step of generating the delivery retention ratio based on the difference between the two specifically includes: Linear fitting is performed on the first trend and the second trend based on the least squares fitting technique, and the slopes of the first trend and the second trend are calculated. If the slope of the first trend is positive and the slope of the second trend is negative, and the absolute value of the slope of the second trend is less than the absolute value of the slope of the first trend, then calculate the ratio of the relative deviations between the absolute values ​​of the two slopes. Based on the relative deviation ratio and combined with a preset adjustment amplitude factor, a delivery retention ratio is generated to adjust the input intensity of non-moisture source particle components in the sprinkler irrigation demand analysis model.

5. The method for sprinkler irrigation management of planting areas based on smart Internet of Things according to claim 4, characterized in that, In subsequent sprinkler irrigation management, after obtaining the original particle composition data for calculating the demand intensity value, the non-water source particle component subset is identified. The intensity of the non-water source particle component subset is adjusted by the delivery retention ratio, rather than being directly removed. The adjusted non-water source particle component data and the remaining particle data are input into the sprinkler irrigation demand analysis model to generate the corrected demand intensity value for subsequent sprinkler irrigation regulation.

6. A sprinkler irrigation management system for planting areas based on the Internet of Things, characterized in that, The system includes: The sample acquisition module is used to acquire several reference data samples with consistent background information of sprinkler irrigation in the target planting area. The reference data samples include the original particle composition data of the air before sprinkler irrigation and the corresponding humidity increase rate value per unit water volume after sprinkler irrigation. The correlation identification module is used to determine the proportion of non-moisture source particles in the original particle composition data of each reference data sample based on a preset identification mechanism, and to construct the first trend of the proportion and the second trend of the humidity increase rate per unit water volume in chronological order. The delivery retention ratio generation module is used to perform linear fitting on the first trend and the second trend respectively to obtain the corresponding first trend slope and second trend slope. If the first trend is linearly increasing and the second trend is linearly decreasing, and the absolute value of the second trend slope is less than the absolute value of the first trend slope, then the delivery retention ratio is generated based on the difference between the two. The model input adjustment module is used to apply the delivery retention ratio to the non-water source particle components in the future original particle composition data that will be delivered to the sprinkler irrigation demand analysis model in subsequent sprinkler irrigation management, and input the corrected particle composition data into the model to obtain the corrected demand intensity value for subsequent sprinkler irrigation regulation.

7. The smart IoT-based sprinkler irrigation management system for plantations according to claim 6, characterized in that, The consistency of the sprinkler irrigation background information means that the crop types corresponding to the reference data samples are consistent, the growth stages are consistent, the collection time is within the same natural cycle, and the variation range of sprinkler irrigation water volume, ambient temperature and ambient humidity are all within the set allowable range.

8. The smart IoT-based sprinkler irrigation management system for plantations according to claim 7, characterized in that, The correlation identification module specifically includes: The component identification unit is used to acquire the original particle composition data of the air in the target planting area before irrigation for each reference data sample, and classify and identify the particle components in a unit volume based on particle size structure characteristics, component identification parameters or preset analysis devices, determine the part of the non-moisture source particle components, and calculate its proportion in the overall particle composition data, which is recorded as the proportion of non-moisture source particle components. The trend building unit is used to arrange the proportion of non-moisture source particle components in all reference data samples in chronological order to form the first trend, and at the same time, arrange the air humidity increase rate caused by a unit amount of water in each reference data sample in the same chronological order to form the second trend.

9. The smart IoT-based sprinkler irrigation management system for plantations according to claim 8, characterized in that, The delivery retention ratio generation module specifically includes: The trend fitting unit is used to perform linear fitting on the first trend and the second trend based on the least squares fitting technique, and calculate the corresponding slopes of the first trend and the second trend. The condition judgment unit is used to calculate the relative deviation ratio between the absolute values ​​of the slopes of the two trends if the slope of the first trend is positive, the slope of the second trend is negative, and the absolute value of the slope of the second trend is less than the absolute value of the slope of the first trend. The factor generation unit is used to generate, based on the relative deviation ratio and in combination with a preset adjustment amplitude factor, the delivery retention ratio for adjusting the input intensity of non-moisture source particle components in the sprinkler irrigation demand analysis model.

10. The smart IoT-based sprinkler irrigation management system for plantations according to claim 9, characterized in that, In subsequent sprinkler irrigation management, after obtaining the original particle composition data for calculating the demand intensity value, the non-water source particle component subset is identified. The intensity of the non-water source particle component subset is adjusted by the delivery retention ratio, rather than being directly removed. The adjusted non-water source particle component data and the remaining particle data are input into the sprinkler irrigation demand analysis model to generate the corrected demand intensity value for subsequent sprinkler irrigation regulation.

Images