Agricultural product digital management big data analysis service system

Abstract

The invention relates to the technical field of intelligent agriculture and agricultural big data analysis, in particular to an agricultural product digital management big data analysis service system, which comprises a data acquisition module used for acquiring crop growth environment parameters and real-time physiological characterization parameters; the net assimilation rate calculation module is used for calculating a net assimilation rate; the physiological damage analysis module is used for converting the crop growth environment parameters into instantaneous micro-stress intensity and generating an accumulated physiological damage index based on the instantaneous micro-stress intensity; the quality conversion prediction module is used for calculating a predicted quality cumulant based on the net assimilation rate and the cumulative physiological injury index; the closed-loop feedback control module is used for calculating a difference value between a preset quality target value and the predicted quality cumulant, and generating an environment control correction based on the difference value; the crop health status misjudgment caused by neglect of recessive physiological stress is avoided, and full-link digital management from environment monitoring to accurate regulation and control starting from the end is realized.

Description

Technical Field

[0001] This invention relates to the field of smart agriculture and agricultural big data analysis technology, specifically to a big data analysis service system for digital management of agricultural products. Background Technology

[0002] The big data analysis service system for digital management of agricultural products is a technology that uses sensor networks to acquire crop growth environment parameters and real-time physiological characterization parameters, and uses data analysis to guide agricultural production. Existing agricultural management technologies mainly acquire environmental data such as light intensity, ambient temperature and carbon dioxide concentration through distributed sensor networks, aiming to ensure the suitability of the crop growth environment by monitoring environmental parameters. However, in practical applications, relying solely on environmental monitoring data cannot accurately reflect the true physiological state of crops, resulting in a technical problem of data disconnect from actual physiological conditions. While a single environmental parameter may be within acceptable limits, the actual net assimilation rate of crops under the combined effects of multiple factors may be low, leading to blind spots in production efficiency assessments. Even when environmental data appears smooth and compliant, the crop may already be nearing the critical point of functional collapse due to accumulated physiological stress, exhibiting subtle lag effects and nonlinear cumulative damage. Directly managing crops based on such environmental data can easily lead to misjudgments of crop health, resulting in flawed management decisions and a decline in agricultural product quality. Summary of the Invention

[0003] To address the aforementioned technical problems, this invention provides a big data analysis service system for digital management of agricultural products. Specifically, the technical solution of this invention includes: The data acquisition module is used to acquire crop growth environment parameters and real-time physiological characterization parameters; The net assimilation rate calculation module is used to calculate the net assimilation rate based on crop growth environment parameters and real-time physiological characterization parameters. The physiological damage analysis module is used to convert crop growth environment parameters into instantaneous micro-stress intensity and generate a cumulative physiological damage index based on the instantaneous micro-stress intensity. The quality conversion prediction module is used to calculate the predicted cumulative quality based on the net assimilation rate and the cumulative physiological damage index. The closed-loop feedback control module is used to calculate the difference between the preset quality target value and the predicted cumulative quality, and to generate an environmental control correction amount based on the difference.

[0004] Preferably, the data acquisition module includes: The environmental data acquisition unit is used to acquire crop growth environment parameters, including light intensity, ambient temperature, and carbon dioxide concentration, through a distributed sensor network. The physiological data acquisition unit is used to acquire real-time physiological characterization parameters, including chlorophyll fluorescence kinetic parameters and stomatal conductance, through non-contact biochemical sensors. The data alignment unit is used to align crop growth environment parameters with real-time physiological characterization parameters on the time axis and construct a normalized input vector.

[0005] Preferably, the net assimilation rate calculation module performs the following processing: The light intensity is called and the light reaction rate is calculated based on the initial light energy utilization rate. The carbon dioxide concentration is used to calculate the dark reaction rate based on the carboxylation conductance coefficient; The harmonic average of the light reaction rate and the dark reaction rate is calculated to obtain the fundamental rate; Call the ambient temperature and calculate the temperature correction term based on the temperature tolerance variance; Call upon chlorophyll fluorescence kinetic parameters and calculate physiological correction terms based on maximum fluorescence values; Multiply the baseline rate, temperature correction term, and physiological correction term together, and subtract the maintenance respiratory rate to obtain the net assimilation rate.

[0006] Preferably, the physiological damage analysis module determines the instantaneous micro-stress intensity based on crop growth environment parameters, including: Calculate the absolute value of the difference between the ambient temperature and the optimal growth temperature; Determine whether the absolute value of the difference is greater than the temperature tolerance threshold width; If the absolute value of the difference is greater than the temperature tolerance threshold width, calculate the absolute value of the difference minus the temperature tolerance threshold width, and divide the result by the temperature normalization factor to obtain the temperature stress component. If the absolute value of the difference is less than or equal to the temperature tolerance threshold width, set the temperature stress component to zero; Determine whether the light intensity is less than the light saturation point; If the light intensity is less than the light saturation point, calculate the light saturation point minus the light intensity, and divide the result by the light saturation point to obtain the light energy deficit component. If the light intensity is greater than or equal to the light saturation point, set the light energy deficit component to zero; The instantaneous micro-stress intensity is generated by adding the temperature stress component and the light energy deficit component.

[0007] Preferably, the physiological damage analysis module generates a cumulative physiological damage index based on the instantaneous micro-stress intensity, including: Recall the cumulative physiological damage index from the previous moment; Based on the biological recovery rate constant, the exponential decay value of the cumulative physiological damage index at the previous moment is calculated. The nonlinear increment of instantaneous micro-stress intensity is calculated based on the fatigue nonlinear factor and the cumulative physiological damage index of the previous moment. The cumulative physiological damage index at the current moment is generated by adding the exponential decay value to the nonlinear increment.

[0008] Preferably, the quality conversion prediction module performs the following processing: The assimilation coefficient is determined based on the growth day; The product of the assimilation product distribution coefficient and the net assimilation rate is calculated to obtain the quality output rate. Based on the damage reduction coefficient, calculate the quality loss rate corresponding to the cumulative physiological damage index; Calculate the difference between the quality output rate and the quality loss rate; Integrate the difference over a preset time period to generate a cumulative predicted quality value.

[0009] Preferably, it also includes a shelf-life assessment module for: Call the cumulative physiological damage index and integrate it over time to obtain the damage integral value; Calculate the ratio of the damage score to the preset physiological tolerance limit score; Calculate the difference between 1 and the ratio; The attenuation factor is obtained by exponentially calculating the difference based on the attenuation curvature coefficient. Multiply the theoretical maximum shelf life by the decay factor to generate the effective shelf life in days.

[0010] Preferably, the closed-loop feedback control module performs the following processing: A neural network model trained using historical data, with input being a sequence of environmental parameters and output being a quality index, is used to calculate the sensitivity gradient of quality to environmental parameters. Calculate the quality gap by subtracting the predicted cumulative quality from the preset quality target value; The adjustment step size is obtained by calculating the product of the quality gap and the feedback control gain. The environmental control correction is generated by multiplying the adjustment step size by the sensitivity gradient.

[0011] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention constructs a net assimilation rate calculation model by integrating crop growth environment parameters and real-time physiological characterization parameters; using the harmonic mean of light-dark response rates and temperature and physiological correction terms, it accurately quantifies the actual production efficiency of crops under the coupling effect of multiple factors; this effectively solves the blind spot problem in the prior art where a single environmental parameter is qualified, but the lack of physiological data support makes it impossible to assess the low efficiency of crop combination, and realizes accurate perception of the true growth status of crops; 2. This invention proposes a physiological damage analysis method that transforms environmental parameters into instantaneous micro-stress intensity and generates a cumulative physiological damage index. By introducing biological recovery rate and fatigue nonlinearity factor, the system can simulate the hysteresis effect and nonlinear cumulative characteristics of organisms, accurately identify the breakpoint where environmental data appears smooth and compliant but the internal functions of crops are close to collapse, thereby avoiding misjudgment of crop health status due to neglecting latent physiological stress. 3. This invention constructs a quality conversion prediction model, determines the assimilation product allocation coefficient based on growth days, and calculates the difference between the net assimilation rate and the quality loss caused by cumulative damage. This method realizes the quantitative mapping from physiological indicators to economic value, reflecting the biological principle that high-quality agricultural products can only be formed when the accumulation of net assimilation output exceeds the metabolic consumption caused by damage repair, effectively improving the scientificity and accuracy of agricultural product quality prediction. 4. This invention establishes a closed-loop feedback control mechanism, which uses a neural network model to calculate the sensitivity gradient of quality to environmental parameters, and generates environmental control correction quantities based on the gap between the preset quality target and the predicted cumulative amount. This value-oriented reverse regulation strategy can dynamically adjust the environmental set point according to the final quality requirements, correct the future assimilation rate and damage trajectory, thereby realizing full-link digital management from environmental monitoring to precise regulation from the end in mind. Attached Figure Description

[0012] The present invention will be further explained below with reference to the accompanying drawings and embodiments: Figure 1 This is a system block diagram of the present invention. Detailed Implementation

[0013] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.

[0014] Example 1: Please see Figure 1 A big data analysis service system for digital management of agricultural products, comprising: The data acquisition module is used to acquire crop growth environment parameters and real-time physiological characterization parameters; The net assimilation rate calculation module is used to calculate the net assimilation rate based on crop growth environment parameters and real-time physiological characterization parameters. The physiological damage analysis module is used to convert crop growth environment parameters into instantaneous micro-stress intensity and generate a cumulative physiological damage index based on the instantaneous micro-stress intensity. The quality conversion prediction module is used to calculate the predicted cumulative quality based on the net assimilation rate and the cumulative physiological damage index. The closed-loop feedback control module is used to calculate the difference between the preset quality target value and the predicted cumulative quality, and to generate an environmental control correction amount based on the difference. The data acquisition module includes: The environmental data acquisition unit is used to acquire crop growth environment parameters, including light intensity, ambient temperature, and carbon dioxide concentration, through a distributed sensor network. The physiological data acquisition unit is used to acquire real-time physiological characterization parameters, including chlorophyll fluorescence kinetic parameters and stomatal conductance, through non-contact biochemical sensors. The data alignment unit is used to align crop growth environment parameters with real-time physiological characterization parameters on the time axis and construct a normalized input vector.

[0015] This embodiment proposes a big data analysis service system for digital management of agricultural products. The system aims to solve the technical problem of the disconnect between environmental monitoring data and the actual physiological state of crops in existing agricultural management technologies. By constructing a digital twin model of crop physiology, it realizes full-link digital management from environmental perception to quality prediction and then to closed-loop regulation. The system mainly includes a data acquisition module, a net assimilation rate calculation module, a physiological damage analysis module, a quality conversion prediction module, and a closed-loop feedback control module. The data acquisition module, as the system's sensing front end, is specifically configured to perform the following operations: The environmental data acquisition unit utilizes a distributed sensor network deployed in the crop canopy and root zone to collect crop growth environment parameters in real time; these parameters include light intensity. Ambient temperature and carbon dioxide concentration ;in, Indicates the current sampling time; The physiological data acquisition unit utilizes non-contact biochemical sensors, such as chlorophyll fluorescence imagers and stomatalometers, to acquire real-time physiological characterization parameters of crops; these parameters include chlorophyll fluorescence kinetic parameters reflecting light energy conversion efficiency. And porosity, which reflects gas exchange capacity. ; The data alignment unit performs spatiotemporal alignment processing. Given the potential inconsistency in sampling frequencies between environmental and physiological data, the data alignment unit uses interpolation algorithms or sliding window averaging to align crop growth environmental parameters with real-time physiological characterization parameters along the time axis. Strict alignment is performed on the upper part; the system combines the aligned environmental parameters with physiological parameters to construct a normalized input vector. The construction process employs a max-min normalization method: for any physical quantity Its normalized value ,in and These are the maximum and minimum values ​​of the parameter in the historical dataset, respectively, thus mapping input data of different dimensions to the [0,1] interval and eliminating differences in physical units; thereby eliminating the influence of different physical dimensions on subsequent calculations.

[0016] Example 2: The net assimilation rate calculation module performs the following processing: The light intensity is called and the light reaction rate is calculated based on the initial light energy utilization rate. The carbon dioxide concentration is used to calculate the dark reaction rate based on the carboxylation conductance coefficient; The harmonic average of the light reaction rate and the dark reaction rate is calculated to obtain the fundamental rate; Call the ambient temperature and calculate the temperature correction term based on the temperature tolerance variance; Call upon chlorophyll fluorescence kinetic parameters and calculate physiological correction terms based on maximum fluorescence values; Multiply the baseline rate, temperature correction term, and physiological correction term together, and subtract the maintenance respiratory rate to obtain the net assimilation rate.

[0017] The net assimilation rate calculation module is based on the non-rectangular hyperbolic model of photosynthesis and enzyme kinetics principles in plant physiology, and is used to calculate the net assimilation rate of crops. Net assimilation rate at time This module can quantify the actual crop production efficiency under the coupled effects of environmental factors, and specifically performs the following calculation steps: Calculate the light reaction rate and the dark reaction rate; the module calls the light intensity. And based on the pre-calibrated initial light energy utilization rate Calculate the photoreaction rate At the same time, the carbon dioxide concentration was adjusted. And based on the pre-calibrated carboxylation conductivity coefficient Calculate the dark reaction rate ; Here, parameters and The calibration method is as follows: the three-dimensional surface data of light-carbon dioxide-photosynthetic rate of a specific variety are measured in a controlled experimental environment, and the initial value is obtained by fitting using the nonlinear least squares method; The fundamental rate is calculated; to simulate a smooth transition between light and carbon confinement, the module uses a harmonic averaging method to calculate the coupling value of the photoreaction rate and the dark reaction rate, thus obtaining the fundamental rate. ; ; Calculate correction items; module calls ambient temperature. The temperature correction term is calculated using the Gaussian function form. This correction term reflects the relationship between enzyme activity and temperature, and the calculation formula is as follows: ,in For the optimal growth temperature, This represents the standard deviation of temperature tolerance. At the same time, the module calls chlorophyll fluorescence kinetic parameters. Calculate the physiological correction term This correction term reflects the actual health of Optical System II, and is calculated using the following formula: ,in This represents the maximum fluorescence value of the crop under ideal health conditions; The module calculates the net assimilation rate; it multiplies the baseline rate, temperature correction term, and physiological correction term to obtain the total assimilation rate, and then subtracts the baseline maintenance respiratory rate from it. Finally, the net assimilation rate is obtained. ; ; in, The baseline respiratory rate at 25 degrees Celsius. The breathing temperature coefficient is typically set to 2.0. Through the above calculations, this system addresses the blind spot in evaluation where a single environmental parameter is qualified but the combined efficiency is low.

[0018] Example 3: The physiological damage analysis module determines the intensity of instantaneous micro-stress based on crop growth environment parameters, including: Calculate the absolute value of the difference between the ambient temperature and the optimal growth temperature; Determine whether the absolute value of the difference is greater than the temperature tolerance threshold width; If the absolute value of the difference is greater than the temperature tolerance threshold width, calculate the absolute value of the difference minus the temperature tolerance threshold width, and divide the result by the temperature normalization factor to obtain the temperature stress component. If the absolute value of the difference is less than or equal to the temperature tolerance threshold width, set the temperature stress component to zero; Determine whether the light intensity is less than the light saturation point; If the light intensity is less than the light saturation point, calculate the light saturation point minus the light intensity, and divide the result by the light saturation point to obtain the light energy deficit component. If the light intensity is greater than or equal to the light saturation point, set the light energy deficit component to zero; The instantaneous micro-stress intensity is generated by adding the temperature stress component and the light energy deficit component.

[0019] The physiological damage analysis module is responsible for converting physical environmental parameters into a dimensionless physiological stress index, i.e., instantaneous micro-stress intensity. The process specifically includes: Module calculates ambient temperature with optimal growth temperature The absolute value of the difference between them; determine whether the absolute value of the difference is greater than the preset temperature tolerance threshold width. The threshold Set the temperature fluctuation range that will not cause physiological stress to crops; If the absolute value of the difference is greater than Then calculate the absolute value of the difference minus The result was then divided by the temperature normalization factor. Thus, the temperature stress component is obtained; where Take the difference between the crop's lethal temperature and its optimum temperature; if the absolute value of the difference is less than or equal to... Then the temperature stress component is set to zero; At the same time, the module determines the light intensity. Is it less than the light saturation point? If the light intensity is less than the light saturation point, the result of subtracting the light intensity from the light saturation point is calculated, and this result is divided by the light saturation point to obtain the light energy deficit component. If the light intensity is greater than or equal to the light saturation point, the light energy deficit component is set to zero, and the module adds the temperature stress component to the light energy deficit component to generate the instantaneous micro-stress intensity. ; ; This step transforms discrete environmental variables into scalars that are detrimental to the plant, which then serve as input for subsequent cumulative calculations.

[0020] Example 4: The physiological damage analysis module generates a cumulative physiological damage index based on the instantaneous micro-stress intensity, including: Recall the cumulative physiological damage index from the previous moment; Based on the biological recovery rate constant, the exponential decay value of the cumulative physiological damage index at the previous moment is calculated. The nonlinear increment of instantaneous micro-stress intensity is calculated based on the fatigue nonlinear factor and the cumulative physiological damage index of the previous moment. The cumulative physiological damage index at the current moment is generated by adding the exponential decay value to the nonlinear increment.

[0021] The physiological damage analysis module further generates a cumulative physiological damage index based on the instantaneous micro-stress intensity. To simulate the hysteresis effect and nonlinear cumulative characteristics of organisms; This process employs an iterative calculation method; the module calls the cumulative physiological damage index from the previous moment. ; Based on biological recovery rate constant Calculate the exponential decay value of the cumulative physiological damage index at the previous moment, i.e. This term characterizes the process by which crops repair damage through metabolic compensation after stress is relieved, i.e., the Masking effect. Meanwhile, based on fatigue nonlinear factors The instantaneous micro-stress intensity was calculated using the cumulative physiological damage index from the previous moment. The nonlinear increment, i.e. ;in This is the damage accumulation rate coefficient, in units of , To calculate the step size; when At that time, this item indicates that as damage accumulates, the crop's resistance to new stresses decreases exponentially; The module adds the exponentially decaying value to the nonlinear increment to generate the cumulative physiological damage index at the current moment. ; ; The above parameters , and The calibration method is as follows: In a controlled artificial climate chamber, the target crop is subjected to step-type high temperature and strong light stress of different intensities, and crop physiological data during the stress period and recovery period are continuously recorded; a time series dataset is constructed using the measured data, and the Levenberg-Marquardt optimization algorithm is used to perform nonlinear regression fitting on the above difference equation, so as to solve for a set of coefficient values ​​that minimizes the mean square error. The model can accurately identify the breaking point where environmental data appears smooth and compliant, but the internal physiological functions of crops are close to collapse.

[0022] Example 5: The quality conversion prediction module performs the following processing: The assimilation coefficient is determined based on the growth day; The product of the assimilation product distribution coefficient and the net assimilation rate is calculated to obtain the quality output rate. Based on the damage reduction coefficient, calculate the quality loss rate corresponding to the cumulative physiological damage index; Calculate the difference between the quality output rate and the quality loss rate; Integrate the difference over a preset time period to generate a cumulative predicted quality value.

[0023] The quality conversion prediction module is used to map physiological indicators to economic value; this module performs the following processing: Determine the assimilation coefficient based on the crop's current growth days (GDD). Specifically, the calculation is performed using a Logistic S-type growth function: ; in, The maximum allocation ratio during the fruit ripening period is preset to 0.85; The allocation rate coefficient characterizes the rate at which vegetative growth transforms into reproductive growth; The accumulated temperature threshold at which the distribution coefficient reaches half its value; this coefficient characterizes the proportion of photosynthetic products transported to the fruit and changes dynamically with the growth stage. Calculate the partition coefficient of assimilation products With net assimilation rate The product of these factors yields the quality output rate, which represents the positive accumulation of crops. Based on damage reduction coefficient Calculate the cumulative physiological damage index The corresponding quality loss rate, i.e. This item represents the additional metabolic cost incurred in repairing damage; among which, the damage reduction coefficient... With net assimilation rate Same physical dimensions, for example Its physical meaning is the equivalent photosynthetic product consumption rate required per unit dimensionless damage index during the repair process, ensuring the consistency of physical units in subsequent difference calculations; The module calculates the difference between the quality output rate and the quality loss rate, and applies this difference over a preset time period. Integrate within the range to generate the predicted quality cumulative quantity. ; ; This formula embodies the biological principle of increasing revenue and reducing expenditure. High-quality agricultural products can only be formed when the accumulation of net assimilation output exceeds the additional metabolic consumption caused by cumulative damage.

[0024] Example 6: This system also includes a shelf-life assessment module, used for: Call the cumulative physiological damage index and integrate it over time to obtain the damage integral value; Calculate the ratio of the damage score to the preset physiological tolerance limit score; Based on attenuation curvature coefficient The damage effect term is obtained by performing an exponential operation on this ratio. Calculate the difference between 1 and the damage effect term, and use it as the attenuation factor; Multiply the theoretical maximum shelf life by the decay factor to generate the effective shelf life in days.

[0025] The system also includes a shelf life assessment module to quantify the impact of pre-harvest stress on post-harvest life; Module call cumulative physiological damage index The damage integral value is obtained by integrating it over the entire growth cycle. Calculate the damage score and divide it by the preset physiological tolerance limit score. The ratio; Represents the upper limit of cumulative damage that causes irreversible changes in crop cell structure; Calculate the difference between 1 and this ratio, and base it on the attenuation curvature coefficient. The difference is then subjected to an exponential operation to obtain the attenuation factor; The module determines the theoretical maximum shelf life of this product under ideal conditions. Multiply by the decay factor to generate the effective shelf life in days. ; ; Normally set This indicates that shelf life decreases sharply under high damage conditions; this scheme can guide subsequent sales radius decisions.

[0026] Example 7: The closed-loop feedback control module performs the following processing: A neural network model trained using historical data, with input being a sequence of environmental parameters and output being a quality index, is used to calculate the sensitivity gradient of quality to environmental parameters. Calculate the quality gap by subtracting the predicted cumulative quality from the preset quality target value; The adjustment step size is obtained by calculating the product of the quality gap and the feedback control gain. The environmental control correction is generated by multiplying the adjustment step size by the sensitivity gradient.

[0027] The closed-loop feedback control module executes a value-oriented reverse regulation strategy; The module utilizes a neural network model trained on historical data to calculate the sensitivity gradient of quality to environmental parameters online; for example, it calculates the partial derivative of quality with respect to temperature. This characterizes the direction and magnitude of the effect of current temperature changes on the final quality. Calculate the preset quality target value Subtract the predicted cumulative quality The quality gap; Calculate the quality gap and feedback control gain The product of these factors yields the adjustment step size; where the feedback control gain is... The matrix is ​​set as a diagonal matrix, with the elements on its main diagonal containing a dimension conversion factor to convert mass units to environmental parameter units. Different weight values ​​are preset according to the response characteristics of each environmental parameter actuator. The adjustment step size is multiplied by the sensitivity gradient to generate the environmental control correction. ; ; To prevent system oscillations caused by excessively large gradient values, the module adjusts the environmental control parameters. Perform saturation limiting: if the calculated If the maximum allowable rate of change threshold of the device is exceeded, the output value will be clamped at the threshold. The system uses this correction to adjust the setpoint of the environmental control device, thereby correcting the future assimilation rate and damage trajectory, and realizing closed-loop control with the end in mind.

[0028] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A big data analysis service system for digital management of agricultural products, characterized in that, include: The data acquisition module is used to acquire crop growth environment parameters and real-time physiological characterization parameters; The net assimilation rate calculation module is used to calculate the net assimilation rate based on crop growth environment parameters and real-time physiological characterization parameters. The physiological damage analysis module is used to convert crop growth environment parameters into instantaneous micro-stress intensity and generate a cumulative physiological damage index based on the instantaneous micro-stress intensity. The quality conversion prediction module is used to calculate the predicted cumulative quality based on the net assimilation rate and the cumulative physiological damage index. The closed-loop feedback control module is used to calculate the difference between the preset quality target value and the predicted cumulative quality, and to generate an environmental control correction amount based on the difference.

2. The big data analysis service system for digital management of agricultural products according to claim 1, characterized in that, The data acquisition module includes: The environmental data acquisition unit is used to acquire crop growth environment parameters, including light intensity, ambient temperature, and carbon dioxide concentration, through a distributed sensor network. The physiological data acquisition unit is used to acquire real-time physiological characterization parameters, including chlorophyll fluorescence kinetic parameters and stomatal conductance, through non-contact biochemical sensors. The data alignment unit is used to align crop growth environment parameters with real-time physiological characterization parameters on the time axis and construct a normalized input vector.

3. The big data analysis service system for digital management of agricultural products according to claim 1, characterized in that, The net assimilation rate calculation module performs the following processing: The light intensity is called and the light reaction rate is calculated based on the initial light energy utilization rate. The carbon dioxide concentration is used to calculate the dark reaction rate based on the carboxylation conductance coefficient; The harmonic average of the light reaction rate and the dark reaction rate is calculated to obtain the fundamental rate; Call the ambient temperature and calculate the temperature correction term based on the temperature tolerance variance; Call upon chlorophyll fluorescence kinetic parameters and calculate physiological correction terms based on maximum fluorescence values; Multiply the baseline rate, temperature correction term, and physiological correction term together, and subtract the maintenance respiratory rate to obtain the net assimilation rate.

4. The big data analysis service system for digital management of agricultural products according to claim 1, characterized in that, The physiological damage analysis module determines the instantaneous micro-stress intensity based on crop growth environment parameters, including: Calculate the absolute value of the difference between the ambient temperature and the optimal growth temperature; Determine whether the absolute value of the difference is greater than the temperature tolerance threshold width; If the absolute value of the difference is greater than the temperature tolerance threshold width, calculate the absolute value of the difference minus the temperature tolerance threshold width, and divide the result by the temperature normalization factor to obtain the temperature stress component. If the absolute value of the difference is less than or equal to the temperature tolerance threshold width, set the temperature stress component to zero; Determine whether the light intensity is less than the light saturation point; If the light intensity is less than the light saturation point, calculate the light saturation point minus the light intensity, and divide the result by the light saturation point to obtain the light energy deficit component. If the light intensity is greater than or equal to the light saturation point, set the light energy deficit component to zero; The instantaneous micro-stress intensity is generated by adding the temperature stress component and the light energy deficit component.

5. The big data analysis service system for digital management of agricultural products according to claim 1, characterized in that, The physiological damage analysis module generates a cumulative physiological damage index based on the instantaneous micro-stress intensity, including: Recall the cumulative physiological damage index from the previous moment; Based on the biological recovery rate constant, the exponential decay value of the cumulative physiological damage index at the previous moment is calculated. The nonlinear increment of instantaneous micro-stress intensity is calculated based on the fatigue nonlinear factor and the cumulative physiological damage index of the previous moment. The cumulative physiological damage index at the current moment is generated by adding the exponential decay value to the nonlinear increment.

6. The big data analysis service system for digital management of agricultural products according to claim 1, characterized in that, The quality conversion prediction module performs the following processing: The assimilation coefficient is determined based on the growth day; The product of the assimilation product distribution coefficient and the net assimilation rate is calculated to obtain the quality output rate. Based on the damage reduction coefficient, calculate the quality loss rate corresponding to the cumulative physiological damage index; Calculate the difference between the quality output rate and the quality loss rate; Integrate the difference over a preset time period to generate a cumulative predicted quality value.

7. The big data analysis service system for digital management of agricultural products according to claim 1, characterized in that, It also includes a shelf-life assessment module for: Call the cumulative physiological damage index and integrate it over time to obtain the damage integral value; Calculate the ratio of the damage score to the preset physiological tolerance limit score; The damage effect term is obtained by performing an exponential calculation based on the comparison value of the attenuation curvature coefficient. Calculate the difference between 1 and the damage effect term to obtain the attenuation factor; Multiply the theoretical maximum shelf life by the decay factor to generate the effective shelf life in days.

8. The big data analysis service system for digital management of agricultural products according to claim 1, characterized in that, The closed-loop feedback control module performs the following processing: A neural network model trained using historical data, with input being a sequence of environmental parameters and output being a quality index, is used to calculate the sensitivity gradient of quality to environmental parameters. Calculate the quality gap by subtracting the predicted cumulative quality from the preset quality target value; The adjustment step size is obtained by calculating the product of the quality gap and the feedback control gain. The environmental control correction is generated by multiplying the adjustment step size by the sensitivity gradient.

Images