Tobacco leaf growth management method, device and equipment and storage medium

Abstract

The embodiment of the invention discloses a tobacco leaf growth management method and device, equipment and a storage medium, and the method comprises the steps: obtaining growth attribute data corresponding to target tobacco leaves at preset intervals; wherein the growth attribute data comprises at least one growth index parameter of the current soil water content, the current illumination intensity, the current leaf area index and the current pest and disease damage probability; determining a growth index weight corresponding to the growth index parameter based on the growth attribute data, and determining a growth rate prediction value based on the growth index weight and the growth attribute data; and determining a target tobacco leaf management parameter based on the growth rate prediction value, and sending a target growth management instruction to a target management and control device based on the target tobacco leaf management parameter. According to the method, a dynamic weight distribution system can be constructed, the influence weights of a plurality of key factors in different growth stages of the tobacco leaves are quantified, the comprehensive influence of each factor on the growth rate of the tobacco leaves is comprehensively considered, and high-precision prediction of key growth nodes and growth states of the tobacco leaves is realized.

Description

Technical Field

[0001] This invention relates to the field of agricultural intelligent control technology, and in particular to a method, apparatus, equipment and storage medium for tobacco leaf growth management. Background Technology

[0002] This solution relates to the field of agricultural intelligent monitoring technology. With the transformation of modern agriculture towards digitalization and intelligence, Internet of Things sensor technology has been widely used in the real-time monitoring of indicators such as soil environment, crop physiology and pests and diseases, providing multi-source data support for crop growth modeling. At the same time, the development of deep learning algorithms and multi-objective optimization theory has promoted the transformation of agricultural management from "experience-driven" to "data-driven".

[0003] Existing growth prediction technologies rely on a combination of decision tree models, support vector machines, and random forest models. While this enables the application of multiple models, the modeling logic has significant limitations. On the one hand, when selecting key environmental parameters through decision trees, the different priorities of environmental factors at different growth stages are not considered, and there is a lack of dynamic weight allocation mechanism, resulting in insufficient adaptability of the model to key growth nodes (such as the topping period of tobacco leaves and the full blooming period of daylilies). Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, and storage medium for tobacco leaf growth management, which can achieve high-precision prediction of key growth nodes and growth status of tobacco leaves, providing a reliable basis for the dynamic optimization of subsequent field management strategies, and ultimately improving the level of refined management of tobacco planting and ensuring tobacco yield and quality.

[0005] In a first aspect, embodiments of the present invention provide a method for tobacco leaf growth management, the method comprising:

[0006] At preset intervals, the growth attribute data corresponding to the target tobacco leaves is acquired; wherein, the growth attribute data includes at least one growth index parameter among: current soil moisture content, current light intensity, current leaf area index, and current probability of pests and diseases; based on the growth attribute data, the growth index weights corresponding to the growth index parameters are determined, and the growth rate prediction value is determined based on the growth index weights and the growth attribute data; based on the growth rate prediction value, the target tobacco leaf management parameters are determined, and the target growth management command is sent to the target control device based on the target tobacco leaf management parameters.

[0007] In a second aspect, embodiments of the present invention provide a tobacco leaf growth management device, the device comprising:

[0008] The data acquisition module is used to acquire the corresponding growth attribute data of the target tobacco leaves at preset intervals; wherein, the growth attribute data includes at least one growth index parameter selected from: current soil moisture content, current light intensity, current leaf area index, and current pest and disease probability; the growth rate prediction module is used to determine the growth index weight corresponding to the growth index parameter based on the growth attribute data, and determine the predicted growth rate value based on the growth index weight and the growth attribute data; the growth management module is used to determine the target tobacco leaf management parameters based on the predicted growth rate value, and send the target growth management instruction to the target control device based on the target tobacco leaf management parameters.

[0009] Thirdly, embodiments of the present invention provide a computer device, the computer device comprising:

[0010] One or more processors;

[0011] Memory, used to store one or more programs;

[0012] When the one or more programs are executed by the one or more processors, the one or more processors implement the tobacco leaf growth management method described in any embodiment.

[0013] Fourthly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the tobacco leaf growth management method described in any embodiment.

[0014] The technical solution provided by this invention acquires the corresponding growth attribute data of the target tobacco leaf at preset intervals. The growth attribute data includes at least one growth indicator parameter selected from current soil moisture content, current light intensity, current leaf area index, and current pest and disease probability. Based on the growth attribute data, the weights of the corresponding growth indicator parameters are determined; based on the growth indicator weights and the growth attribute data, a predicted growth rate is determined; based on the predicted growth rate, target tobacco leaf management parameters are determined; and based on the target tobacco leaf management parameters, a target growth management instruction is sent to the target control device. This invention solves the problem that existing technologies for tobacco leaf growth prediction do not consider the differences in the influence of environmental factors at different growth stages. It can construct a dynamic weight allocation system to accurately quantify the influence weights of key factors such as soil moisture, light intensity, and pests and diseases at different growth stages of tobacco leaves. It comprehensively considers the combined impact of each factor on the tobacco leaf growth rate, achieving high-precision prediction of key growth nodes and growth states of tobacco leaves. This provides a reliable basis for the dynamic optimization of subsequent field management strategies, ultimately improving the level of refined management in tobacco planting and ensuring tobacco yield and quality. Attached Figure Description

[0015] Figure 1This is a flowchart of a tobacco leaf growth management method provided in an embodiment of the present invention;

[0016] Figure 2 This is a flowchart of another tobacco leaf growth management method provided in an embodiment of the present invention;

[0017] Figure 3 This is a flowchart of a preprocessing method for initial growth data provided in an embodiment of the present invention;

[0018] Figure 4 This is a flowchart of a method for determining a weight matrix provided in an embodiment of this method;

[0019] Figure 5 This is a schematic diagram of the structure of a tobacco leaf growth management device provided in an embodiment of the present invention;

[0020] Figure 6 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. The acquisition, storage, use, and processing of data in the technical solutions of the embodiments of the present invention all comply with the relevant provisions of national laws and regulations.

[0022] Figure 1 This is a flowchart of a tobacco leaf growth management method provided by an embodiment of the present invention. The embodiment of the present invention can be applied to scenarios where dynamic management is carried out during the growth process of tobacco leaves. The method can be executed by a tobacco leaf growth management device, which can be implemented by software and / or hardware.

[0023] like Figure 1 As shown, the tobacco leaf growth management method includes the following steps:

[0024] S110. Acquire the corresponding growth attribute data of the target tobacco leaf at preset intervals.

[0025] The target tobacco leaf can be any tobacco leaf requiring growth management. The core objective of this invention is to address the shortcomings of existing field management optimization schemes in crop growth modeling, namely insufficient specificity and a lack of systematic approach, thereby achieving accurate prediction of tobacco leaf growth status and scientific adaptation of management strategies. Specifically, addressing the shortcoming of traditional modeling methods that do not consider the different priorities of environmental factors at different growth stages, this invention constructs a dynamic weight allocation system to accurately quantify the influence weights of key factors such as soil moisture, light intensity, and pests and diseases at different tobacco leaf growth stages, particularly focusing on the dominant factors in core stages such as topping, thus enhancing the model's ability to specifically capture growth dynamics.

[0026] Furthermore, growth attribute data can be data related to the growth of the target tobacco leaves. Specifically, growth attribute data includes at least one growth indicator parameter selected from: current soil moisture content, current light intensity, current leaf area index, and current probability of pests and diseases. Specifically, growth attribute data of the target tobacco leaves can be acquired at preset intervals using preset devices. Subsequent analysis of this data can determine the dynamic growth status of the target tobacco leaves, dynamically adjust the management plan accordingly, and achieve accurate prediction of the target tobacco leaf growth status and scientific adaptation of management strategies.

[0027] S120. Determine the growth index weights corresponding to the growth index parameters based on the growth attribute data, and determine the predicted growth rate value based on the growth index weights and the growth attribute data.

[0028] The growth index weights can be the weights of the influence of growth index parameters on the growth rate of tobacco leaves. Specifically, the weights of growth indicators for the current period can be determined based on the growth attribute data of the target tobacco leaves. For example, the weights of growth indicators corresponding to the current soil moisture content, current light intensity, and current leaf area index can be determined. The predicted growth rate value can be the predicted value of the growth rate of the target tobacco leaves for the current period. Specifically, all growth index parameters and their corresponding weights can be substituted into the formula for calculating the growth rate to determine the predicted growth rate value.

[0029] S130. Determine the target tobacco leaf management parameters based on the predicted growth rate, and send the target growth management instruction to the target control device based on the target tobacco leaf management parameters.

[0030] Target tobacco leaf management parameters can be parameters for managing target tobacco leaves. These parameters include target irrigation amount, target fertilizer amount, and target pest and disease control dosage; that is, the optimal parameter values ​​can be determined from these three aspects. Specifically, management parameters that match the predicted growth rate can be determined based on a preset management parameter calculation formula. Furthermore, the target control device can be a device used to perform growth control operations on the target tobacco leaves. Specifically, the target control device can include: an intelligent irrigation system, a drone fertilization device, or a biological control release device. Target growth management instructions can be instructions that control the target control device to perform control operations. After determining the target tobacco leaf management parameters, target growth management instructions can be generated based on these parameters and sent to the target control device to dynamically adjust the irrigation amount, fertilizer amount, and pest and disease control dosage of the target tobacco leaves.

[0031] The technical solution provided by this invention acquires the corresponding growth attribute data of the target tobacco leaf at preset intervals. The growth attribute data includes at least one growth indicator parameter selected from current soil moisture content, current light intensity, current leaf area index, and current pest and disease probability. Based on the growth attribute data, the weights of the corresponding growth indicator parameters are determined; based on the growth indicator weights and the growth attribute data, a predicted growth rate is determined; based on the predicted growth rate, target tobacco leaf management parameters are determined; and based on the target tobacco leaf management parameters, a target growth management instruction is sent to the target control device. This invention solves the problem that existing technologies for tobacco leaf growth prediction do not consider the differences in the influence of environmental factors at different growth stages. It can construct a dynamic weight allocation system to accurately quantify the influence weights of key factors such as soil moisture, light intensity, and pests and diseases at different growth stages of tobacco leaves. It comprehensively considers the combined impact of each factor on the tobacco leaf growth rate, achieving high-precision prediction of key growth nodes and growth states of tobacco leaves. This provides a reliable basis for the dynamic optimization of subsequent field management strategies, ultimately improving the level of refined management in tobacco planting and ensuring tobacco yield and quality.

[0032] Figure 2This is a flowchart of another tobacco leaf growth management method provided by an embodiment of the present invention. This embodiment of the present invention can be applied to scenarios where dynamic management is carried out during the growth of tobacco leaves. Based on the above embodiments, this embodiment further explains how the growth index weights include: soil moisture weight, light intensity weight, and pest and disease weight; how to determine the growth index weights corresponding to the growth index parameters based on the growth attribute data; how to determine the predicted growth rate value based on the growth index weights and the growth attribute data; and how to determine the target tobacco leaf management parameters based on the predicted growth rate value. This device can be implemented by software and / or hardware and integrated into a computer device with application development capabilities.

[0033] like Figure 2 As shown, the tobacco leaf growth management method includes the following steps:

[0034] S210. Acquire the corresponding growth attribute data of the target tobacco leaf at preset intervals.

[0035] Optionally, obtain the corresponding growth attribute data of the target tobacco leaves, including:

[0036] The initial growth data of the target tobacco leaves is obtained; the initial growth data is corrected based on the spatiotemporal consistency calibration formula, and then the corrected initial growth data is denoised based on the Kalman filter algorithm to obtain growth attribute data.

[0037] The initial growth data can be based on raw growth data acquired by the data collection equipment. For example, initial growth data (soil moisture content S0, light intensity L0, leaf area index LAI0, and pest probability P0) can be collected by deploying soil moisture sensors, light intensity sensors, tobacco biomass monitoring equipment, and pest and disease identification cameras. Furthermore, the initial growth data can be corrected based on a spatiotemporal consistency calibration formula to eliminate sensor drift errors and generate calibration data. Specifically, the spatiotemporal consistency calibration formula is:

[0038] ;

[0039] ;

[0040] in, This represents the current soil moisture content. The initial soil moisture content is given by α, which is the moisture compensation coefficient ranging from 0.95 to 0.99. β is the temperature correction factor, with a value range of 0.04-0.06℃, and T is the ambient temperature of the target tobacco leaf. Given the current light intensity, The initial light intensity, This is the illumination attenuation compensation coefficient, with a value ranging from 1.00 to 1.04. This is the time drift factor, ranging from 0.08 to 0.12. .

[0041] Furthermore, the Kalman filter algorithm can be used to denoise the sensor data, and its state update formula is as follows:

[0042]

[0043] in For the first The calibrated data at the time, For the first Predicted data for each moment, For Kalman gain, The data consists of the original sensor data, and H represents the observation matrix. Simultaneously, to address the issue of sensor accuracy degradation, a self-calibration mechanism based on electrode passivation is introduced. This mechanism involves periodically emitting a reference signal and comparing the sensor response value with the standard value. Calculate the drift coefficient of the sensor. The data acquisition results are dynamically corrected based on the drift coefficient to ensure the reliability of long-term monitoring.

[0044] In the formula for the sensor's drift coefficient: The interval between two self-calibration cycles (unit: h); This refers to the change in the target parameter monitored during the interval period, such as the change in soil moisture content. ;

[0045] Data correction: Substitute the drift coefficient into the original data acquisition formula to dynamically correct the monitoring results and ensure the accuracy and stability of long-term monitoring.

[0046] After denoising the corrected initial growth data using the Kalman filter algorithm, growth attribute data (including soil moisture content) are obtained. Light intensity Leaf area index and probability of pests and diseases For example, Figure 3 This is a flowchart of a preprocessing method for initial growth data provided in an embodiment of the present invention.

[0047] S220. Determine the first influencing parameter of the current soil moisture content relative to the tobacco growth rate, and determine the soil moisture weight corresponding to the current soil moisture content based on the first influencing parameter and the moisture baseline weight.

[0048] The first influencing parameter can represent the gradient of the influence of current soil moisture content on the tobacco leaf growth rate. Here, the first influencing parameter quantifies the relationship between soil moisture and growth rate, and is used to dynamically adjust the weights before calculating the growth rate through a multi-factor coupling model. Specifically, the ratio of the partial derivative of the preset growth rate index to the partial derivative of the current soil moisture content can be used as the first influencing parameter. Furthermore, the soil moisture weight can be the weight of the influence of soil moisture on the growth rate of the target tobacco leaf at the current time. Specifically, the first influencing parameter can be substituted into the preset formula for calculating the weight coefficients (described below) to obtain the soil moisture weight corresponding to the current moment.

[0049] S230. Determine the second influencing parameter of the current light intensity relative to the tobacco leaf growth rate. Based on the second influencing parameter and the light baseline weight, determine the light intensity weight corresponding to the current soil moisture content.

[0050] The second influencing parameter can represent the gradient of the influence of the current light intensity on the tobacco leaf growth rate. Here, the second influencing parameter quantifies the relationship between light intensity and growth rate, and is used to dynamically adjust the weights before calculating the growth rate through a multi-factor coupling model. Specifically, the ratio of the partial derivative of the preset growth rate index to the partial derivative of the current light intensity can be used as the second influencing parameter. Furthermore, the light intensity weight can be the influence weight of the light intensity on the growth rate of the target tobacco leaf at the current time. Specifically, the second influencing parameter can be substituted into the preset formula for calculating the weight coefficients to obtain the light intensity weight corresponding to the current moment.

[0051] S240. Determine the third influencing parameter of the current probability of pests and diseases relative to the tobacco growth rate. Based on the third influencing parameter and the benchmark weight of pests and diseases, determine the pest and disease weight corresponding to the current probability of pests and diseases.

[0052] The third influencing parameter can represent the gradient of the impact of the current pest and disease probability on the tobacco leaf growth rate. Here, the third influencing parameter quantifies the relationship between pest and disease probability and growth rate, and is used to dynamically adjust the weights before calculating the growth rate through a multi-factor coupling model. Specifically, the ratio of the partial derivative of the preset growth rate index to the partial derivative of the current pest and disease probability can be used as the third influencing parameter. Furthermore, the pest and disease probability weight can be the weight of the impact of the current pest and disease probability on the growth rate of the target tobacco leaf. Specifically, the third influencing parameter can be substituted into the preset weight coefficient formula to obtain the pest and disease weight corresponding to the current moment.

[0053] For example, Figure 4 This is a flowchart illustrating how to determine a weight matrix, as provided in an embodiment of this method. Figure 4As shown, weight assignments can be calculated via an attention mechanism by inputting calibration data (i.e., current growth attribute data) into an improved LSTM network.

[0054]

[0055] in, The weights need to be redefined each time. By focusing on key growth stages, a dynamic weight matrix is ​​generated to assist in subsequent multi-factor coupling modeling. The current growth stage query vector is a vector corresponding to the current growth stage of the tobacco leaf generated after inputting calibration data. It is used to calculate the attention weight with the historical environmental parameter key matrix. The historical environmental parameter key matrix is ​​constructed based on historical environmental monitoring data collected by multi-source sensors; =64 is used as a scaling factor to calculate attention weights and output lighting weights.

[0056] The improved LSTM network introduces a pre-defined formula for calculating the weight coefficients:

[0057]

[0058] in, For the first Real-time weights of environmental factors The parameter represents the effect of this factor on the growth rate of tobacco leaves.

[0059]

[0060] λ is the weight adjustment coefficient; The preset growth rate index; For the first Calibrated parameters for each environmental factor; As factors The baseline weights are determined through offline training; this step further incorporates an attention mechanism, calculating the attention weights at each time step. By dynamically focusing on key growth stages, the model can improve its prediction accuracy for the coupling effects of complex environments.

[0061] Based on the above calculations, the weighting of various environmental factors on tobacco leaf growth (especially focusing on key stages such as topping) exhibits clear hierarchical differences, specifically described as follows:

[0062] Soil moisture weight It is at the highest level of influence, with its weight range stable in the core dominant range. It is the most critical factor affecting the absorption of nutrients and the expansion and weight gain of tobacco leaves during the topping period. Its weight fluctuation range is the smallest, and its regulatory effect on growth dynamics is the most significant.

[0063] Light intensity weight It is at the medium level of influence, and its weight range falls within the important influence range. It is an important supporting factor for the photosynthesis and organic matter accumulation of tobacco leaves during the topping period. Its weight fluctuation range is slightly larger than that of soil moisture, and it needs to be dynamically adapted in combination with weather changes.

[0064] The impact weight of pests and diseases It is at the basic level of influence, and its weight range is in the auxiliary control range. Because the tobacco leaves at the topping stage have strong resistance and the foundation of prevention and control has been established in the early stage, its direct impact on growth dynamics is relatively weak, and its weight fluctuation range is the smallest. Its control priority should only be increased when the risk of pests and diseases increases significantly.

[0065] This hierarchical representation clearly demonstrates the dominant differences of different factors at key growth stages, while also providing logical connection with subsequent growth dynamic modeling and field management optimization—that is, soil moisture should be the primary control target, light intensity should be the secondary adaptation target, and the impact of pests and diseases should be the dynamic supplementary control target.

[0066] S250. The first sub-rate is obtained by weighting all growth index weights with the corresponding growth index parameters. The second sub-rate is obtained by multiplying the preset period and temperature sensitivity factor. The first sub-rate is multiplied by the model convergence coefficient and then summed with the second sub-rate to determine the predicted growth rate.

[0067] The growth index weights can be the weights of the influence of growth index parameters on the tobacco leaf growth rate. These weights include the aforementioned soil moisture weight, light intensity weight, and pest and disease weight. The first sub-rate can be the growth rate determined based on the current environmental parameters of the target tobacco leaf. Specifically, the soil moisture weight can be multiplied by the current soil moisture content, the light intensity weight by the current light intensity, and the pest and disease weight by the current pest and disease probability. The sum of these three products yields the first sub-rate. Optionally, to ensure that the final predicted growth rate is within a reasonable agronomic range, the sum of the three products can be multiplied by the model convergence coefficient to obtain the first sub-rate.

[0068] Furthermore, a temperature sensitivity factor is used to quantify the additional impact of environmental temperature changes on tobacco growth rate. A second sub-rate represents the rate at which environmental changes affect tobacco growth. The model convergence coefficient can be a constraint on the growth rate, ensuring that the final output growth rate prediction is within a reasonable agronomical range. The predicted growth rate can be a prediction of the growth rate of the target tobacco leaf at the current moment. Specifically, the calculated first sub-rate can be multiplied by the model convergence coefficient and then summed with the second sub-rate to determine the predicted growth rate.

[0069] For example, the formula for determining the predicted growth rate is:

[0070]

[0071] in, The predicted growth rate of tobacco leaves is the core output of the model, used to quantify the growth activity of tobacco leaves at specific growth stages (such as the crowning stage, topping stage, and maturity stage).

[0072] The model convergence coefficient is used to adjust the overall amplitude of the multi-factor coupled calculation results, ensuring that the final output growth rate prediction value is within a reasonable agronomic range, and avoiding deviation of the prediction results from the actual growth law due to parameter superposition.

[0073] For the first The dynamic weights of environmental factors are the result of dynamic allocation of attention weights, used to quantify the degree of influence of different environmental factors on the growth rate of tobacco leaves. The weights are dynamically adjusted according to the growth stage of tobacco leaves.

[0074] For the first The calibrated parameters of each environmental factor are the output results of multi-source data acquisition and preprocessing, including key environmental indicators such as calibrated soil moisture content, light intensity, and probability of pests and diseases. Errors have been eliminated through mechanisms such as spatiotemporal consistency calibration, Kalman filtering noise reduction, and sensor self-calibration to ensure data accuracy.

[0075] It is a temperature-sensitive factor used to quantify the additional impact of changes in ambient temperature on the growth rate of tobacco leaves.

[0076] The time gradient refers to the time interval between two data collections or model calculations. It is used to reflect the cumulative effect of environmental factors on growth rate over time, ensuring that the model can reflect the dynamic temporal changes in tobacco growth.

[0077] Since tobacco growth is influenced by multiple factors such as soil moisture, light, and pests and diseases, the above calculations use a cumulative logic of "weight × parameter" to integrate scattered environmental indicators into a unified growth rate prediction value, avoiding the one-sidedness of predictions based on a single factor. This is achieved through a convergence coefficient. Temperature-sensitive factors Coordinated regulation.

[0078] Since the topping period is a critical turning point for nutrient accumulation and leaf development in tobacco leaves, and the maturity period is directly related to the quality of tobacco harvest, narrowing the prediction time range of these two nodes through the model can make the calculation of irrigation amount, fertilizer amount, and pest and disease control dosage more in line with the actual growth needs of tobacco leaves. For example, it can avoid nutrient waste caused by premature fertilization due to the prediction deviation of the topping period, or affect the leaf swelling and weight gain by fertilization too late. At the same time, it can reduce the problems of premature or late harvesting caused by the prediction deviation of the maturity period.

[0079] The accuracy of the above model in predicting key growth nodes needs to be further confirmed through subsequent verification: select different tobacco regions (such as the southern red soil tobacco region and the northern brown soil tobacco region) and different tobacco varieties, collect measured data for multiple growth cycles, compare and analyze the data with the model prediction results, and gradually optimize the model parameters (such as the range of values ​​for η and ε) to finally achieve accurate matching between the prediction results and the actual growth nodes, providing reliable support for field management optimization.

[0080] The predicted growth rate is output here. The time series is constructed in the form of key-value pairs of time nodes and predicted values, and its core features are as follows:

[0081] (1) Strictly consistent with the acquisition cycle of sensor data to ensure that the time dimension of the predicted value is synchronized with the monitoring dimension of the environmental data, and to avoid subsequent optimization errors caused by time misalignment;

[0082] (2) The numerical value changes dynamically with the growth stage of tobacco leaves. From the clump stage to the pre-topping stage, the predicted value shows a gradual upward trend; it reaches its peak around the topping stage; and it gradually decreases after entering the maturity stage.

[0083] (3) The predicted value at each time node is calculated by the multi-factor coupling formula in step 3. Its specific value is determined by the calibrated environmental parameters, dynamic weights and model parameters (η, ε, ΔT) corresponding to that node, and is updated in real time with the actual changes in the field environment.

[0084] S260. Determine the target tobacco leaf management parameters based on the predicted growth rate, and send the target growth management instruction to the target control device based on the target tobacco leaf management parameters.

[0085] For example, a reference soil moisture can be determined based on the predicted growth rate; the current moisture difference can be determined based on the reference soil moisture and the current soil moisture; and the target irrigation amount can be determined based on the current moisture difference and the irrigation baseline amount. A reference leaf area index can be determined based on the predicted growth rate; the current leaf area index difference can be determined based on the reference leaf area index and the current leaf area index; and the target fertilizer amount can be determined based on the current leaf area index difference and the fertilizer baseline amount. The maximum light intensity can be determined based on the predicted growth rate; the light disturbance amount can be determined based on the maximum light intensity and the current light intensity; and the target pest and disease control dosage can be determined based on the pest and disease impact threshold, the current pest and disease probability, the environmental disturbance coefficient, and the light disturbance amount.

[0086] The reference soil moisture can be the soil moisture suitable for the growth of the target tobacco leaves. The reference leaf area index can be the leaf area index suitable for the growth of the target tobacco leaves. The maximum light intensity is the light intensity corresponding to the light saturation point of the target tobacco leaves. The reference soil moisture, reference leaf area index, and maximum light intensity are positively correlated with the growth rate of tobacco leaves. Therefore, the reference soil moisture, reference leaf area index, and maximum light intensity corresponding to the predicted growth rate can be determined based on the positive correlation.

[0087] Furthermore, the current soil moisture can be subtracted from the reference soil moisture to obtain the current moisture difference value. This current moisture difference value, along with the irrigation baseline amount, can then be substituted into the formula for determining the irrigation amount to obtain the target irrigation amount. Similarly, the current leaf area index (LAI) can be subtracted from the reference LAI to obtain the current LAI difference value. This current LAI difference value, along with the fertilizer baseline amount, can then be substituted into the formula for determining the fertilizer amount to obtain the target fertilizer amount. Finally, the ratio of the current light intensity to the maximum light intensity can be multiplied by the light interference coefficient to obtain the light interference amount. Substituting the pest and disease impact threshold, the current pest and disease probability, the environmental interference coefficient, and the light interference amount into the formula for determining the control dosage yields the target pest and disease control dosage.

[0088] For example, target irrigation amount Target fertilizer application rate and the dosage for controlling target pests and diseases The formula for determining it is:

[0089]

[0090]

[0091]

[0092] in, As the baseline irrigation amount, The baseline fertilizer application rate, For reference soil moisture, For reference leaf area index, Threshold for the impact of pests and diseases. The environmental interference coefficient is... For light interference, This represents the maximum light intensity.

[0093] Furthermore, the current humidity difference The calculation formula is:

[0094]

[0095] For the calibrated soil moisture content, and growth rate The impact has been weighted through the above steps. Quantification. If... In a rapid growth phase, it will correspond to It needs to be maintained at Upper limit, at this time Smaller than average Closer to the benchmark irrigation amount Ensure that water supply matches growth needs; if decline, Lower, Increase Reduce accordingly to avoid excessive moisture affecting quality;

[0096] Current leaf area index difference The calculation formula is:

[0097]

[0098] This is the calibrated leaf area index, which is directly positively correlated with growth rate. The higher the altitude, the faster the leaves develop, and the more nutrients are consumed. At its peak, Need to approach quickly ,at this time Smaller than average Approximately the benchmark fertilization rate Ensure that nutrient supply can support a high growth rate; if decline, Growth slowdown Increase Reduce and avoid nutrient residues that cause tobacco leaves to remain green and mature late.

[0099] Light interference The calculation formula is:

[0100]

[0101] For the calibrated probability of pests and diseases, its effect on The influence is through weights Quantification. If... When the value is in the high range, the tobacco leaf tissue is tender and has weak resistance. At this time, if near It needs to be increased Strengthen prevention and control to avoid diseases and pests causing A sudden drop; simultaneously, light interference items It will correct the prevention and control effect—if the light intensity Approaching the light saturation point The risk of disease and pest transmission may increase. Increase Adjustments should be made accordingly to ensure that prevention and control measures are adapted to the environment.

[0102] Furthermore, it can be based on the target irrigation volume. Target fertilizer application rate and the dosage for controlling target pests and diseases Generate target growth management instructions. The following example uses the target irrigation amount. For example, the formula for determining the corresponding irrigation control command is:

[0103] In the formula:

[0104] For irrigation system control signals (determined according to the type of actuator, such as electric valve drive voltage);

[0105] This is a proportionality coefficient used to quickly respond to current irrigation deviations and reduce instantaneous errors;

[0106] These are integral coefficients used to eliminate long-term accumulated deviations and avoid steady-state errors.

[0107] This represents the optimal irrigation amount output in the preceding steps.

[0108] The actual irrigation volume, which is fed back in real time by the irrigation system, is collected by a flow sensor.

[0109] This is the time integral term of the irrigation deviation, reflecting the cumulative effect of the deviation.

[0110] This PI control algorithm, through the synergistic effect of rapid proportional term adjustment and steady-state integral term correction, can stabilize the irrigation volume control accuracy within ±5%, meeting the precise soil moisture requirements for tobacco growth, while avoiding equipment vibration caused by frequent adjustments.

[0111] Optionally, after sending the target growth management instruction to the target control device based on the target tobacco leaf management parameters, the actual growth rate of the target tobacco leaf can also be obtained, and the prediction deviation value can be determined based on the actual growth rate and the predicted growth rate value; the model parameters in the predicted growth rate formula model can be updated based on the prediction deviation value; wherein, the model parameters include at least one of the following: temperature sensitivity factor, model convergence coefficient, soil moisture weight, light intensity weight, and pest and disease weight.

[0112] The formula for calculating the prediction deviation is as follows:

[0113]

[0114] in, This indicates the deviation from the growth rate prediction; a positive value indicates that the measured growth rate is higher than the predicted value, and a negative value indicates that the measured value is lower than the predicted value. This represents the actual growth rate measured using biomass monitoring equipment. This is the predicted growth rate output by the growth dynamics model.

[0115] Based on the probability distribution of prediction bias, a Bayesian update algorithm is used to correct the model parameters. The updated formula is as follows:

[0116]

[0117] in, For the updated model parameter set, The model parameter set before the update is defined as follows: ;

[0118] For parameter correction, its dimension is the same as... Consistent, the value is determined by both the magnitude of the deviation and the parameter sensitivity; In the current parameter set Below, prediction bias The likelihood probability of occurrence; For prediction bias The prior probability of occurrence is determined based on the statistical distribution of historical bias data;

[0119] Through this Bayesian update mechanism, the model parameters are dynamically adjusted based on measured data, so that the predicted growth values ​​gradually approach the actual growth state. For example, when... Furthermore, when the result is significant, it can be achieved by increasing η or adjusting the weights. Improve the model's prediction values, thereby optimizing the generation accuracy of subsequent field management parameters.

[0120] The technical effects of the embodiments of the present invention are as follows:

[0121] 1. This scheme achieves high-precision prediction of tobacco leaf growth status. In step 1, a spatiotemporal consistency calibration algorithm (including parameters such as humidity compensation coefficient α=0.95-0.99 and light attenuation compensation coefficient γ=1.00-1.04) and Kalman filtering are used for noise reduction. By dynamically correcting sensor drift error and filtering out environmental interference noise, the correlation coefficient between basic data such as soil moisture content and light intensity and the accurate manual measurement values ​​is maintained at a high level, providing high-quality data support for subsequent modeling. By improving the LSTM network and attention mechanism, a dynamic weight matrix is ​​generated in combination with the agronomic characteristics of tobacco leaf growth (such as soil moisture weight being in the core dominant region), which accurately quantifies the priority of the influence of different environmental factors on the growth rate. Based on the multi-factor coupling model GR, the system integrates the synergistic effect of environmental parameters, weight allocation and time effect. In summary, this prediction system can effectively capture the dynamic patterns of tobacco leaf growth, making the judgment of key growth nodes such as topping and maturity more consistent with the actual growth process. It solves the problem of ambiguous growth node prediction caused by insufficient data quality and one-sided consideration of influencing factors in traditional methods, and provides a solid time-series basis for the accurate formulation of subsequent field management strategies.

[0122] 2. Based on accurate growth prediction results, step 4 generates a customized management parameter set through a multi-objective optimization algorithm, which, combined with the PI control algorithm in step 5, achieves precise equipment control. Irrigation volume control accuracy is stabilized within ±5%, and the optimal irrigation volume Qopt can be dynamically adjusted based on the soil moisture content deviation ΔS=S1−Sopt to avoid water waste. Fertilizer application is calculated based on the leaf area index deviation ΔLAI=LAI1−LAIopt, ensuring precise matching of nutrient supply and growth rate. Simultaneously, the Bayesian update algorithm in step 6 continuously optimizes model parameters, further improving the adaptability of management strategies. Ultimately, this achieves efficient utilization of irrigation and fertilization resources, reduces ineffective inputs, ensures effective pest and disease control, and helps improve tobacco yield and quality.

[0123] The technical solution provided in this invention involves acquiring the corresponding growth attribute data of the target tobacco leaves at preset intervals; determining a first influencing parameter of the current soil moisture content relative to the tobacco leaf growth rate, and determining the soil moisture weight corresponding to the current soil moisture content based on the first influencing parameter and the humidity benchmark weight; determining a second influencing parameter of the current light intensity relative to the tobacco leaf growth rate, and determining the light intensity weight corresponding to the current soil moisture content based on the second influencing parameter and the light benchmark weight; determining a third influencing parameter of the current pest and disease probability relative to the tobacco leaf growth rate, and determining the pest and disease weight corresponding to the current pest and disease probability based on the third influencing parameter and the pest and disease benchmark weight; obtaining a first sub-rate by weighting all growth index weights with the corresponding growth index parameters, obtaining a second sub-rate by multiplying the preset period and the temperature sensitivity factor, multiplying the first sub-rate by the model convergence coefficient and then summing it with the second sub-rate to determine the predicted growth rate value; determining the target tobacco leaf management parameters based on the predicted growth rate value, and sending a target growth management instruction to the target control device based on the target tobacco leaf management parameters.

[0124] This invention addresses the problem that existing tobacco growth prediction technologies fail to consider the differences in environmental factors at different growth stages. It can construct a dynamic weight allocation system to accurately quantify the influence weights of key factors such as soil moisture, light intensity, and pests and diseases at different tobacco growth stages. It comprehensively considers the combined impact of each factor on the tobacco growth rate, achieving high-precision prediction of key growth nodes and growth status of tobacco leaves. This provides a reliable basis for the dynamic optimization of subsequent field management strategies, ultimately improving the level of refined management in tobacco planting and ensuring tobacco yield and quality.

[0125] Figure 5 This is a schematic diagram of a tobacco leaf growth management device provided in an embodiment of the present invention. The embodiment of the present invention can be applied to scenarios where dynamic management is carried out during the growth process of tobacco leaves. The device can be implemented by software and / or hardware and integrated into a computer device with application development capabilities.

[0126] like Figure 5 As shown, the tobacco growth management device includes: a data acquisition module 310, a growth rate prediction module 320, and a growth management module 330.

[0127] The data acquisition module 310 is used to acquire the corresponding growth attribute data of the target tobacco leaf at preset intervals; wherein the growth attribute data includes at least one growth index parameter among: current soil moisture content, current light intensity, current leaf area index, and current pest and disease probability; the growth rate prediction module 320 is used to determine the growth index weight corresponding to the growth index parameter based on the growth attribute data, and determine the predicted growth rate value based on the growth index weight and the growth attribute data; the growth management module 330 is used to determine the target tobacco leaf management parameters based on the predicted growth rate value, and send the target growth management instruction to the target control device based on the target tobacco leaf management parameters.

[0128] The technical solution provided by this invention acquires the corresponding growth attribute data of the target tobacco leaf at preset intervals. The growth attribute data includes at least one growth indicator parameter selected from current soil moisture content, current light intensity, current leaf area index, and current pest and disease probability. Based on the growth attribute data, the weights of the corresponding growth indicator parameters are determined; based on the growth indicator weights and the growth attribute data, a predicted growth rate is determined; based on the predicted growth rate, target tobacco leaf management parameters are determined; and based on the target tobacco leaf management parameters, a target growth management instruction is sent to the target control device. This invention solves the problem that existing technologies for tobacco leaf growth prediction do not consider the differences in the influence of environmental factors at different growth stages. It can construct a dynamic weight allocation system to accurately quantify the influence weights of key factors such as soil moisture, light intensity, and pests and diseases at different growth stages of tobacco leaves. It comprehensively considers the combined impact of each factor on the tobacco leaf growth rate, achieving high-precision prediction of key growth nodes and growth states of tobacco leaves. This provides a reliable basis for the dynamic optimization of subsequent field management strategies, ultimately improving the level of refined management in tobacco planting and ensuring tobacco yield and quality.

[0129] In one optional implementation, the growth index weights include: soil moisture weight, light intensity weight, and pest and disease weight. The growth rate prediction module 320 includes: a growth index weight determination unit, configured to: determine a first influence parameter of the current soil moisture content relative to the tobacco leaf growth rate; determine a soil moisture weight corresponding to the current soil moisture content based on the first influence parameter and the moisture baseline weight; determine a second influence parameter of the current light intensity relative to the tobacco leaf growth rate; determine a light intensity weight corresponding to the current soil moisture content based on the second influence parameter and the light baseline weight; and determine a third influence parameter of the current pest and disease probability relative to the tobacco leaf growth rate; determine a pest and disease weight corresponding to the current pest and disease probability based on the third influence parameter and the pest and disease baseline weight.

[0130] In one optional implementation, the growth rate prediction module 320 includes a growth rate prediction value determination unit, configured to: sum all growth index weights with corresponding growth index parameters to obtain a first sub-rate; multiply the preset period and a temperature sensitivity factor to obtain a second sub-rate; wherein the temperature sensitivity factor is used to quantify the additional impact of environmental temperature changes on tobacco leaf growth rate; multiply the first sub-rate with the model convergence coefficient and then sum it with the second sub-rate to determine the growth rate prediction value.

[0131] In one optional implementation, the target tobacco management parameters include: target irrigation amount, target fertilizer amount, and target pest and disease control dosage. The growth management module 330 includes: a tobacco management parameter determination unit, used for: determining reference soil moisture based on the predicted growth rate value; determining the current moisture difference based on the reference soil moisture and the current soil moisture; determining the target irrigation amount based on the current moisture difference and the irrigation baseline amount; determining a reference leaf area index based on the predicted growth rate value; determining the current leaf area index difference based on the reference leaf area index and the current leaf area index; determining the target fertilizer amount based on the current leaf area index difference and the fertilizer baseline amount; determining the maximum light intensity based on the predicted growth rate value; determining the light interference amount based on the maximum light intensity and the current light intensity; and determining the target pest and disease control dosage based on the pest and disease impact threshold, the current pest and disease probability, the environmental interference coefficient, and the light interference amount; wherein, the maximum light intensity is the light intensity corresponding to the light saturation point of the target tobacco leaf.

[0132] In one optional implementation, the data acquisition module 310 is specifically used to: acquire the corresponding initial growth data of the target tobacco leaf; correct the initial growth data based on the spatiotemporal consistency calibration formula; and then perform noise reduction processing on the corrected initial growth data based on the Kalman filter algorithm to obtain the growth attribute data.

[0133] In one optional implementation, the spatiotemporal consistency calibration formula is:

[0134] ;

[0135] ;

[0136] in, This represents the current soil moisture content. The initial soil moisture content is given by α, which is the moisture compensation coefficient ranging from 0.95 to 0.99. β is the temperature correction factor, with a value range of 0.04-0.06℃, and T is the ambient temperature of the target tobacco leaf. Given the current light intensity, The initial light intensity, This is the illumination attenuation compensation coefficient, with a value ranging from 1.00 to 1.04. This is the time drift factor, ranging from 0.08 to 0.12. .

[0137] In an optional embodiment, the tobacco leaf growth management device further includes a reference adjustment module, configured to: after sending a target growth management instruction to a target control device based on the target tobacco leaf management parameters, obtain the actual growth rate of the target tobacco leaf, determine a prediction deviation value based on the actual growth rate and the predicted growth rate value; and update the model parameters in the predicted growth rate formula model based on the prediction deviation value; wherein the model parameters include at least one of: temperature sensitivity factor, model convergence coefficient, soil moisture weight, light intensity weight, and pest and disease weight.

[0138] The tobacco leaf growth management device provided in the embodiments of the present invention can execute the tobacco leaf growth management method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0139] Figure 6 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Figure 6 A block diagram of an exemplary computer device 12 suitable for implementing embodiments of the present invention is shown. Figure 6 The computer device 12 shown is merely an example and should not be construed as limiting the functionality or scope of the embodiments of the present invention. The computer device 12 can be any terminal device with computing capabilities and can be configured in tobacco leaf growth management equipment.

[0140] like Figure 6 As shown, the computer device 12 is represented in the form of a general-purpose computing device. The components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and bus 18 connecting different system components (including system memory 28 and processing unit 16).

[0141] Bus 18 can be one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0142] Computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0143] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache 32. Computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (… Figure 6 Not shown; usually referred to as a "hard drive"). Although Figure 6 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. System memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0144] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of the present invention.

[0145] Computer device 12 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), and with one or more devices that enable a user to interact with the computer device 12, and / or with any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed through input / output (I / O) interface 22. Furthermore, computer device 12 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 20. Figure 6 As shown, network adapter 20 communicates with other modules of computer device 12 via bus 18. It should be understood that, although... Figure 6As not shown, it can be used in conjunction with computer device 12 with other hardware and / or software modules, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0146] Processing unit 16 executes various functional applications and data processing by running programs stored in system memory 28, such as implementing the tobacco leaf growth management method provided in this embodiment of the invention, which includes:

[0147] At preset intervals, the growth attribute data corresponding to the target tobacco leaves is acquired; wherein, the growth attribute data includes at least one growth index parameter among: current soil moisture content, current light intensity, current leaf area index, and current probability of pests and diseases; based on the growth attribute data, the growth index weights corresponding to the growth index parameters are determined, and the growth rate prediction value is determined based on the growth index weights and the growth attribute data; based on the growth rate prediction value, the target tobacco leaf management parameters are determined, and the target growth management command is sent to the target control device based on the target tobacco leaf management parameters.

[0148] This embodiment provides a computer-readable storage medium storing a computer program thereon. When executed by a processor, the program implements the tobacco leaf growth management method as provided in any embodiment of the present invention, including:

[0149] At preset intervals, the growth attribute data corresponding to the target tobacco leaves is acquired; wherein, the growth attribute data includes at least one growth index parameter among: current soil moisture content, current light intensity, current leaf area index, and current probability of pests and diseases; based on the growth attribute data, the growth index weights corresponding to the growth index parameters are determined, and the growth rate prediction value is determined based on the growth index weights and the growth attribute data; based on the growth rate prediction value, the target tobacco leaf management parameters are determined, and the target growth management command is sent to the target control device based on the target tobacco leaf management parameters.

[0150] The computer storage medium of this invention can be any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0151] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0152] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0153] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as C, Java, Smalltalk, C++, C#, and Python, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0154] Those skilled in the art will understand that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby allowing them to be stored in a storage device for execution by a computing device, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0155] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A method for tobacco leaf growth management, characterized by, The method comprises: acquiring corresponding growth attribute data of the target tobacco leaf every preset period; wherein the growth attribute data comprises at least one growth index parameter of current soil moisture content, current light intensity, current leaf area index, and current disease and pest probability; determining a growth index weight corresponding to the growth index parameter based on the growth attribute data, and determining a growth rate prediction value based on the growth index weight and the growth attribute data; determining a target tobacco leaf management parameter based on the growth rate prediction value, and sending a target growth management instruction to a target management device based on the target tobacco leaf management parameter.

2. The method of claim 1, wherein, The growth index weight comprises a soil moisture weight, a light intensity weight, and a disease and pest weight, and determining the growth index weight corresponding to the growth index parameter based on the growth attribute data comprises: determining a first influence parameter of the current soil moisture content relative to the tobacco leaf growth rate, determining a soil moisture weight corresponding to the current soil moisture content based on the first influence parameter and a moisture reference weight; determining a second influence parameter of the current light intensity relative to the tobacco leaf growth rate, determining a light intensity weight corresponding to the current soil moisture content based on the second influence parameter and a light reference weight; determining a third influence parameter of the current disease and pest probability relative to the tobacco leaf growth rate, and determining a disease and pest weight corresponding to the current disease and pest probability based on the third influence parameter and a disease and pest reference weight.

3. The method of claim 2, wherein, The method comprises: summing all growth index weights and corresponding growth index parameters to obtain a first sub-rate; multiplying the preset period and a temperature sensitive factor to obtain a second sub-rate; wherein the temperature sensitive factor is used to quantify the additional influence of environmental temperature change on the tobacco leaf growth rate; multiplying the first sub-rate and a model convergence coefficient, and then adding the second sub-rate to determine the growth rate prediction value.

4. The method of claim 1, wherein, The target tobacco leaf management parameter comprises a target irrigation amount, a target fertilization amount, and a target disease and pest control dose, and determining the target tobacco leaf management parameter based on the growth rate prediction value comprises: determining a reference soil moisture based on the growth rate prediction value, determining a current moisture difference value based on the reference soil moisture and the current soil moisture, and determining the target irrigation amount based on the current moisture difference value and an irrigation reference amount; determining a reference leaf area index based on the growth rate prediction value, determining a current leaf area index difference value based on the reference leaf area index and the current leaf area index, and determining the target fertilization amount based on the current leaf area index difference value and a fertilization reference amount; determining a maximum light intensity based on the growth rate prediction value, determining a light interference amount based on the maximum light intensity and the current light intensity, and determining the target disease and pest control dose based on a disease and pest influence threshold value, the current disease and pest probability, an environmental interference coefficient, and the light interference amount; wherein the maximum light intensity is a light intensity corresponding to a light saturation point of the target tobacco leaf.

5. The method of claim 1, wherein, The method comprises: obtaining corresponding initial growth data of the target tobacco leaf; correcting the initial growth data based on a space-time consistency calibration formula, and performing denoising processing on the corrected initial growth data based on a Kalman filtering algorithm to obtain the growth attribute data.

6. The method of claim 5, wherein, The space-time consistency calibration formula is: ； ； Wherein, is the current soil moisture content, is the initial soil moisture content, and a is a humidity compensation coefficient, with a value range of 0.95-0.99 , β is a temperature correction factor, with a value range of 0.04-0.06℃, and T is the ambient temperature of the target tobacco leaf; is the current light intensity, is the initial light intensity, is a light attenuation compensation coefficient, with a value range of 1.00-1.04, is a time drift coefficient, with a range of 0.08-0.12 .

7. The method of claim 3, wherein, After sending the target growth management instruction to the target management and control device based on the target tobacco leaf management parameter, the method further includes: obtaining an actual growth rate of the target tobacco leaf, and determining a prediction deviation value based on the actual growth rate and the growth rate prediction value; updating a model parameter in a predicted growth rate formula model based on the prediction deviation value; wherein the model parameter includes at least one of a temperature sensitive factor, a model convergence coefficient, a soil moisture weight, a light intensity weight, and a disease and pest weight.

8. A tobacco plant growth management apparatus, characterized by, The device includes: a data acquisition module configured to obtain corresponding growth attribute data of the target tobacco leaf every interval preset period; wherein the growth attribute data includes at least one growth index parameter of current soil water content, current light intensity, current leaf area index, and current disease and pest probability; a growth rate prediction module configured to determine a growth index weight corresponding to the growth index parameter based on the growth attribute data, and determine a growth rate prediction value based on the growth index weight and the growth attribute data; a growth management module configured to determine a target tobacco leaf management parameter based on the growth rate prediction value, and send a target growth management instruction to a target management and control device based on the target tobacco leaf management parameter.

9. A computer device, comprising: The computer device includes: one or more processors; a memory configured to store one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the tobacco leaf growth management method as claimed in any one of claims 1-7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the tobacco leaf growth management method as claimed in any one of claims 1-7.

Images