An analysis and decision-making method for crop growth monitoring data

Abstract

The present invention relates to the technical field of crop growth prediction, and in particular to an analysis and decision-making method for crop growth monitoring data. The method comprises the following steps: acquiring crop growth monitoring data and natural light data; performing crop growth phototropism intensity analysis on the crop growth monitoring data to generate crop phototropism intensity data; comparing the crop phototropism intensity data with a preset phototropism intensity threshold, and when the crop phototropism intensity data is less than the preset phototropism intensity threshold, performing artificial light source trend correction based on the crop growth monitoring data, thereby generating crop growth light source adjustment data; dividing the crop growth monitoring data into crop life cycles according to the crop growth light source adjustment data, and generating crop growth stage data. The present invention significantly improves the accuracy and real-time performance of the analysis and decision-making of crop growth monitoring data by integrating light data, refining the crop life cycle division, and realizing abnormal monitoring and decision-making feedback mechanisms.

Description

Technical Field

[0001] The present invention relates to the technical field of crop growth prediction, and in particular to an analysis and decision-making method for crop growth monitoring data. Background Art

[0002] In the early days, farmers relied on experience and visual observation of crop growth, and mainly made decisions based on intuitive climate and soil conditions. Although this method is simple, it is inefficient and susceptible to subjective factors. With the development of science and technology, especially the introduction of remote sensing technology, crop monitoring began to rely on ground observations by equipment such as satellites and drones. In the 21st century, the rapid development of information technology has promoted the innovation of data collection and processing methods. The application of big data technology, the Internet of Things (IoT) and artificial intelligence (AI) has greatly improved the real-time and accuracy of crop growth monitoring. Through data mining and machine learning algorithms, researchers can extract more valuable information and make more scientific decisions. In addition, with the rise of precision agriculture, analysis and decision-making methods based on geographic information systems (GIS) and decision support systems (DSS) have also become popular. However, existing technologies often ignore the impact of natural light on crop growth, and the division of crop growth stages is not clear enough, making it difficult to formulate corresponding management strategies for different stages, resulting in low accuracy and comprehensiveness of crop growth monitoring and analysis decisions. Summary of the invention

[0003] Based on this, it is necessary to provide an analysis and decision-making method for crop growth monitoring data to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for analyzing and making decisions on crop growth monitoring data is provided, the method comprising the following steps:

[0005] Step S1: Acquire crop growth monitoring data and natural light data; perform crop growth phototropism intensity analysis on the crop growth monitoring data to generate crop phototropism intensity data; compare the crop phototropism intensity data with a preset phototropism intensity threshold, and when the crop phototropism intensity data is less than the preset phototropism intensity threshold, perform artificial light source trend correction based on the crop growth monitoring data, thereby generating crop growth light source adjustment data;

[0006] Step S2: dividing the crop growth monitoring data into crop life cycles according to the crop growth light source adjustment data to generate crop growth stage data, wherein the crop growth stage data includes the crop seedling stage, the crop rapid growth stage, the crop reproductive growth stage and the crop maturity stage; performing multi-dimensional crop index analysis on the crop growth monitoring data according to the seedling stage, the crop rapid growth stage, the crop reproductive growth stage and the crop maturity stage to generate crop lushness data in the bud stage, crop growth status data in the rapid growth stage, crop flowering status data in the reproductive growth stage and crop fruit maturity data in the maturity stage;

[0007] Step S3: monitoring the crop growth abnormality of the crop growth monitoring data based on the crop lushness data at the budding stage, the crop growth status data at the rapid growth stage, the crop flowering status data at the reproductive growth stage, and the crop fruit maturity data at the mature stage, thereby generating crop growth monitoring and early warning data;

[0008] Step S4: Utilize the crop growth monitoring and early warning data to simulate crop growth decision on the crop growth stage data, and generate crop growth decision simulation data; perform closed-loop feedback on the crop growth decision simulation data, and generate a crop growth decision adjustment mechanism; perform decision visualization on the crop growth monitoring and early warning data according to the crop growth decision adjustment mechanism, and thus generate crop growth monitoring decision visualization data.

[0009] The present invention provides a reliable data basis for subsequent analysis by acquiring crop growth monitoring data and natural light data. This stage ensures the comprehensiveness of the data and contributes to the accuracy of subsequent decision-making. By analyzing the phototropism intensity of crops, crop phototropism intensity data is generated, which helps to understand the response of crops to light. Artificial light source trend correction according to the lack of light can effectively improve the photosynthesis efficiency of crops and promote healthy growth. By setting the phototropism intensity threshold, the phototropism intensity of crops is monitored and adjusted in real time, which can ensure that crops obtain the best light conditions at different growth stages, thereby optimizing the crop growth environment. The crop life cycle is divided according to the crop growth light source adjustment data, so that the data at different growth stages are clearer and more orderly. This systematic division lays the foundation for subsequent indicator analysis and management decisions. Multidimensional crop indicator analysis is performed on each growth stage, and the generated lushness data of the bud stage, growth status data of the rapid growth period, flowering status data of the reproductive growth period and fruit maturity data of the mature stage make the crop growth status more comprehensive and three-dimensional, which is conducive to refined management. The crop growth abnormality monitoring of each growth stage data, the crop growth monitoring early warning data is generated, and potential problems can be identified in time to prevent the negative impact of pests and diseases, malnutrition and other situations on crop growth. Through the early warning data, agricultural managers can quickly take corresponding measures to reduce risks and ensure the stability and high yield of crop growth. The crop growth decision simulation data is used for decision simulation, and the generated crop growth decision simulation data can evaluate the effects of different management strategies before actual operation, so as to select the best solution for implementation. By closed-loop feedback of the decision simulation data, the crop growth decision adjustment mechanism generated ensures that the management measures can be continuously optimized and adjusted according to the actual situation, and improves the flexibility and effectiveness of the decision. The crop growth monitoring decision is visualized so that the complex data is displayed in an intuitive form, which helps managers and stakeholders at all levels to quickly understand the situation and promote collaboration and communication. Therefore, the present invention significantly improves the analysis and decision accuracy and real-time performance of crop growth monitoring data by integrating light data, refining the crop life cycle division, and realizing abnormal monitoring and decision feedback mechanism.

[0010] Preferably, step S1 comprises the following steps:

[0011] Step S11: using sensors to obtain crop growth monitoring data and natural light data;

[0012] Step S12: performing data preprocessing on the crop growth monitoring data to generate standard crop growth monitoring data, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization;

[0013] Step S13: extracting the crop growth direction from the standard crop growth monitoring data to obtain crop growth direction data; analyzing the phototropism intensity of the natural light data using the crop growth direction data to generate crop phototropism intensity data;

[0014] Step S14: Compare the crop phototropism intensity data with a preset phototropism intensity threshold. When the crop phototropism intensity data is less than the preset phototropism intensity threshold, perform artificial light source trend correction based on the crop growth monitoring data to generate crop growth light source adjustment data.

[0015] The present invention obtains crop growth monitoring data and natural light data by using sensors. By real-time monitoring of crop growth conditions and light conditions, growth problems and environmental changes can be discovered in time, providing basic data for subsequent data analysis. Data preprocessing is performed on crop growth monitoring data to generate standard crop growth monitoring data. Preprocessing includes data cleaning, denoising, missing value filling and data standardization. By improving data quality and reducing the influence of noise and outliers, the accuracy and reliability of data analysis can be enhanced, laying a good foundation for subsequent analysis. Crop growth orientation extraction is performed on standard crop growth monitoring data to obtain crop growth orientation data. Crop phototropism intensity analysis is performed on natural light data according to crop growth orientation data to generate crop phototropism intensity data. By extracting crop growth direction information, the response of crops to light can be analyzed, and crop growth in which areas is restricted can be identified, thereby providing data support for crop spatial distribution optimization. The crop phototropism intensity data is compared with a preset phototropism intensity threshold. When the crop phototropism intensity data is less than the preset threshold, artificial light source trend correction is performed based on the crop growth monitoring data to generate crop growth light source adjustment data. Through intelligent light source adjustment, it can ensure that crops get enough light during the growth process, thus promoting their healthy growth. This process can not only increase crop yields, but also reduce energy consumption and improve resource utilization efficiency. Through data-driven decision-making, it helps farmers or agricultural managers develop more reasonable agricultural management strategies.

[0016] Preferably, performing crop phototropism intensity analysis on natural light data using crop growth direction data includes:

[0017] The crop top spatial azimuth angle data are extracted from the standard crop growth monitoring data through the crop growth azimuth data to obtain the crop top spatial azimuth angle data; the natural light incident angle data are extracted from the natural light data to obtain the natural light incident angle data;

[0018] The angle difference between the spatial orientation angle data of the crop top and the natural light incident angle data is calculated to generate the crop light angle difference; the crop light area is analyzed on the standard crop growth monitoring data through the crop light angle difference to generate the crop light receiving area; the crop light intensity calculation formula is used to calculate the crop light angle difference and the crop light receiving area to obtain the crop light intensity data;

[0019] The formula for calculating the phototropism intensity of crops is as follows:

[0020]

[0021] In the formula, is the crop phototropism intensity data, is the phototropism coefficient of the crop species, is the light receiving area of ​​the crop, is the angular difference between the crop azimuth and the illumination angle.

[0022] The present invention extracts the spatial azimuth angle of the crop top from the standard crop growth monitoring data through the crop growth azimuth data to obtain the spatial azimuth angle data of the crop top. The orientation and growth direction of the crop top are understood to provide necessary spatial data for subsequent light analysis, and help identify potential problems in crop growth, such as uneven light distribution. The natural light incident angle is extracted from the natural light data to obtain the natural light incident angle data. By accurately measuring the incident angle of light, its impact on crop growth, especially the changes in light intensity and direction, can be analyzed to provide a basis for light source adjustment. The angle difference is calculated for the spatial azimuth angle data of the crop top and the natural light incident angle data to generate the crop light angle difference. Calculating the angle difference can help evaluate the matching degree between the light conditions and the crop growth direction, thereby optimizing the light utilization efficiency. The crop light area analysis is performed on the standard crop growth monitoring data through the crop light angle difference to generate the crop light receiving area. The light area that the crop can effectively receive is evaluated to help identify areas with insufficient or excessive light, and provide a basis for precise management. The crop phototropism intensity calculation formula is used to calculate the crop phototropism intensity based on the crop light angle difference and the crop light receiving area to obtain the crop phototropism intensity data. Through the phototropism intensity calculation, the crop response to light can be quantified, which helps predict the growth potential of crops, optimize lighting strategies, and improve crop yield and quality. Through quantitative analysis of light, it helps farmers or agricultural managers make more scientific decisions on light source adjustment. Through precise light analysis, resource utilization can be maximized, crop growth efficiency can be improved, and light source energy waste can be reduced. Ensure that crops receive uniform and sufficient light, improve growth conditions, and thus improve crop resistance and yield.

[0023] Preferably, step S14 includes the following steps:

[0024] Step S141: comparing the crop phototropism intensity data with a preset phototropism intensity threshold, and when the crop phototropism intensity data is less than the preset phototropism intensity threshold, locating the weak phototropism area of ​​the crop based on the crop growth monitoring data to obtain the weak phototropism area data of the crop;

[0025] Step S142: performing artificial light source setting on the crop weak phototropism area data to obtain artificial light source setting data, wherein the artificial light source setting includes artificial light source incident angle setting, artificial light source brightness setting and artificial light source color setting;

[0026] Step S143: calculating the illumination trend intensity of the artificial light source for the artificial light source setting data and the crop weak phototropism area data to obtain the phototropism intensity data of the crop weak phototropism area; dynamically adjusting the phototropism intensity data of the crop weak phototropism area according to the crop phototropism intensity data, so that the phototropism intensity data of the crop weak phototropism area is always greater than or equal to the crop phototropism intensity data, thereby generating the phototropism intensity adjustment data of the weak phototropism area;

[0027] Step S144: using the weak phototropism area phototropism intensity adjustment data to perform artificial light source trend correction on the artificial light source setting data, thereby generating crop growth light source adjustment data.

[0028] The present invention compares the crop phototropism intensity data with a preset phototropism intensity threshold. When the crop phototropism intensity data is less than the preset phototropism intensity threshold, the weak phototropism area of ​​the crop is located to obtain the weak phototropism area data of the crop. The area with insufficient light can be identified in time, helping farmers or agricultural managers to concentrate on making targeted light source adjustments and improve the utilization efficiency of light. Artificial light source settings are performed on the crop weak phototropism area data to obtain artificial light source setting data. The artificial light source settings include artificial light source incident angle, artificial light source brightness and artificial light source color settings. By reasonably setting the artificial light source, the lighting conditions of the crop in the weak light area can be improved to ensure that it obtains the required light energy, thereby promoting its growth. The artificial light source setting data and the crop weak phototropism area data are calculated for the artificial light source illumination trend intensity to obtain the crop weak phototropism area phototropism intensity data. The crop weak phototropism area phototropism intensity data is dynamically adjusted according to the crop phototropism intensity data to ensure that the crop weak phototropism area phototropism intensity data is greater than or equal to the crop phototropism intensity data, thereby generating weak phototropism area phototropism intensity adjustment data. By dynamically adjusting the light intensity, it is possible to ensure that crops receive sufficient light in weak phototropism areas, promote uniform growth, reduce growth differences, and increase overall crop yields. The artificial light source setting data is corrected for artificial light source trends using the phototropism intensity adjustment data in weak phototropism areas, thereby generating crop growth light source adjustment data. Through continuous light source adjustment, it is possible to ensure that crops receive optimal light at different growth stages and environmental conditions, optimize crop photosynthesis, and improve crop growth efficiency and quality. Timely adjustment of light source settings allows crops to maintain healthy growth under weak light conditions and improves crop stress resistance.

[0029] Preferably, step S2 comprises the following steps:

[0030] Step S21: dividing the crop growth monitoring data into crop life cycles according to the crop growth light source adjustment data to generate crop growth stage data, wherein the crop growth stage data includes the crop seedling stage, the crop rapid growth stage, the crop reproductive growth stage and the crop maturity stage;

[0031] Step S22: performing root resistance imaging on the crop growth monitoring data at the seedling stage to generate a three-dimensional root image at the budding stage; extracting main root depth information of the crop from the three-dimensional root image at the budding stage to obtain main root depth information data of the crop; extracting branch root bifurcation information from the three-dimensional root image at the budding stage to obtain branch root bifurcation information data of the crop; performing root luxuriance analysis on the crop at the budding stage based on the main root depth information data and the branch root bifurcation information data of the crop to generate luxuriance data of the crop at the budding stage;

[0032] Step S23: performing leaf spectral scanning on the crop growth monitoring data based on the crop rapid growth period to obtain leaf spectral data of the rapid growth stage; performing leaf physiological state analysis on the leaf spectral data of the rapid growth stage to generate crop growth state data of the rapid growth stage;

[0033] Step S24: performing a time series remote sensing scan of crop flower buds based on the crop growth monitoring data during the crop reproductive growth period to obtain time series remote sensing data of flower buds during the reproductive growth period; performing a flower bud vegetation index calculation on the time series remote sensing data of flower buds during the reproductive growth period to generate flowering state data of crops during the reproductive growth period;

[0034] Step S25: Perform a crop fruit hardness test on the crop growth monitoring data based on the crop maturity period to obtain fruit hardness data at the maturity stage; perform a fruit maturity degree analysis on the fruit hardness data at the maturity stage to generate crop fruit maturity degree data at the maturity stage.

[0035] The present invention uses high-precision sensors to monitor crop growth and natural light data in real time. Real-time data acquisition improves the understanding of crop growth status and allows rapid response to changes. It enhances the scientific nature of crop management, enables accurate fertilization and irrigation based on data, and optimizes resource use. Data preprocessing improves data quality, reduces errors and deviations, and ensures the accuracy of subsequent analysis. By standardizing data, the comparability between different data sets is enhanced, providing a basis for multi-source data fusion. Through the analysis of orientation, the lighting conditions can be optimized, the growth of crops towards light can be promoted, and the photosynthetic efficiency can be improved. It provides a basis for precise lighting management and enhances the growth momentum of crops. The lighting conditions are analyzed using the crop phototropism intensity calculation formula. The understanding of crop lighting requirements is improved, and targeted lighting adjustments can be made according to crop types. It helps to reduce the impact of insufficient light on crop growth and ensure the healthy growth of crops. Artificial light sources are set for weak phototropism areas, including angle, brightness and color adjustment. The light source can be flexibly adjusted according to the specific needs of the crop, which improves the utilization efficiency of light. Through the intervention of artificial light sources, the stagnation of crop growth caused by insufficient natural light is reduced, and the overall growth rate of crops is improved. Crop life cycle division based on light source adjustment data. Crop growth stages are clarified to provide a basis for developing precise management strategies at different stages. Helps implement intervention measures at key growth stages to maximize yield and quality. Use electrical resistance imaging technology to obtain three-dimensional images of the root system. Intuitively display the root structure to facilitate analysis of root health and guide root management. Enhanced visualization of root growth helps farmers identify potential problems and take timely measures. Spectral scanning of leaves to assess physiological status. By analyzing spectral data, nutrient deficiencies or pests and diseases can be quickly identified to optimize disease prevention and control. Helps to achieve crop health management and improve overall production efficiency. Use remote sensing technology to monitor the dynamics of flower bud development. Predict flowering time, optimize pollination conditions, and increase crop yields. Provide data support for agricultural production plans to ensure field management at the best time. Assess fruit maturity through hardness testing. Provide scientific basis for fruit maturity to ensure harvesting in optimal conditions.

[0036] Preferably, step S23 includes the following steps:

[0037] Step S231: performing leaf spectral scanning on crop growth monitoring data based on the crop rapid growth period to obtain leaf spectral data in the rapid growth stage;

[0038] Step S232: converting the leaf spectrum data in the rapid growth stage into a full spectrum reflectance curve to generate a leaf full spectrum reflectance curve; performing fluctuation curve segmentation on the leaf full spectrum reflectance curve to generate a leaf full spectrum fluctuation curve; performing band analysis on the leaf full spectrum fluctuation curve to generate leaf full spectrum fluctuation curve band data;

[0039] Step S233: comparing the blade full spectrum fluctuation curve band data with the preset red light band threshold, when the blade full spectrum fluctuation curve band data is greater than or equal to the preset red light band threshold, the corresponding blade full spectrum fluctuation curve band data is marked as the red light band; when the blade full spectrum fluctuation curve band data is less than the preset red light band threshold, the corresponding blade full spectrum fluctuation curve band data is marked as the near red light band;

[0040] Step S234: performing chlorophyll absorption peak characteristic analysis on the full spectrum fluctuation curve of the leaves through the red light band to generate chlorophyll absorption peak characteristic data; performing moisture characteristic analysis on the full spectrum fluctuation curve of the leaves through the near-red light band to generate moisture characteristic data;

[0041] Step S235: Analyze the leaf physiological status of the leaf spectrum data in the rapid growth stage using the chlorophyll absorption peak characteristic data and the water characteristic data, thereby generating the crop growth status data in the rapid growth stage.

[0042] The present invention can quickly obtain the growth status data of crops during the growth period through leaf spectral scanning, provide real-time feedback, and help farmers understand the growth of crops in a timely manner. Compared with traditional visual inspection, spectral scanning can provide more accurate and objective data, reduce human errors, and the generated leaf full spectrum reflectance curve provides a comprehensive data basis for subsequent analysis, so that the information of different bands can be fully utilized. Fluctuation curve segmentation and band analysis can reveal subtle changes in leaf reflection characteristics and help analyze the health level of plants under different growth conditions. The leaf full spectrum fluctuation curve band data is compared with the preset red light band threshold to achieve accurate marking of the red light band and the near red light band, thereby improving the accuracy of data analysis. By distinguishing the red light and near red light bands, clear data stratification can be provided for subsequent chlorophyll and water feature analysis, thereby improving the effectiveness of subsequent analysis. By performing chlorophyll absorption peak feature analysis in the red light band, the photosynthetic capacity of crops can be better understood, providing a direct basis for judging the health status of crops. The water feature analysis of the near red light band helps to assess the water status of crops, thereby guiding irrigation and water management and reducing water resource waste. By combining the chlorophyll absorption peak characteristic data and the moisture characteristic data for analysis, a comprehensive physiological status assessment of crops in the rapid growth stage can be provided. The generated crop growth status data in the rapid growth stage provides a scientific basis for farmers and agricultural managers, helping them make data-driven decisions, optimize management measures, and improve crop yields and quality.

[0043] Preferably, step S24 includes the following steps:

[0044] Step S241: performing a time series remote sensing scan of crop flower buds based on crop growth monitoring data during the crop reproductive growth period to obtain time series remote sensing data of flower buds during the reproductive growth period;

[0045] Step S242: geometrically correcting the flower bud time series remote sensing data of the reproductive growth stage to generate corrected remote sensing data of the flower buds of the reproductive growth stage; classifying the flower bud states of the corrected remote sensing data of the flower buds of the reproductive growth stage to generate classified data of the flower bud states, wherein the classified data of the flower bud states include a non-flowering state, a flowering state, and a post-flowering state;

[0046] Step S243: Calculating vegetation indexes for the flower bud corrected remote sensing data in the reproductive growth stage according to the non-flowering state, the flowering state, and the post-flowering state, respectively, to obtain a first state vegetation index, a second state vegetation index, and a third state vegetation index; calculating the mean of the first state vegetation index, the second state vegetation index, and the third state vegetation index, to obtain a mean vegetation index for the flower bud period;

[0047] Step S244: Analyze the flowering status of the flower bud time series remote sensing data in the reproductive growth stage using the mean index of the flower bud period vegetation, thereby generating flowering status data of crops in the reproductive growth stage.

[0048] The present invention can efficiently collect time series data of the reproductive growth stage by remote sensing scanning of crop flower buds, providing a sufficient data basis for subsequent analysis. This step can realize dynamic monitoring of the flower bud development process, help to timely discover growth abnormalities, and support precise management and decision-making. By geometrically correcting the remote sensing data, image distortion can be eliminated to ensure the spatial accuracy of the data, thereby providing reliable basic data for subsequent analysis. Flower bud state classification can effectively distinguish different growth stages, generate classification data of non-flowering, flowering and post-flowering states, and provide a clear structure for dynamic analysis of plant growth. Using different flower bud states to calculate the vegetation index of remote sensing data, the growth status of plants at different growth stages can be quantified, providing an intuitive reflection of the physiological state. By calculating the mean vegetation index of the flower bud state, a comprehensive index can be obtained, which represents the overall growth health status of the crop in the flower bud stage, which helps to compare changes at different time points. Flowering status analysis based on the mean index of vegetation in the flower bud cycle can comprehensively evaluate the growth status of crops and help farmers determine whether the crops are in the best flowering period. The generated flowering status data of crops in the reproductive growth stage provides a scientific basis for crop management. Farmers can adjust management measures such as fertilization and irrigation according to the analysis results to improve crop yield and quality.

[0049] Preferably, step S25 comprises the following steps:

[0050] Step S251: extracting crop fruit morphology data from crop growth monitoring data based on crop maturity period to obtain crop fruit morphology data;

[0051] Step S252: Perform a crop fruit hardness test based on the crop fruit morphology data to obtain fruit hardness data at the mature stage; perform a periodic smooth hardness extraction on the fruit hardness data at the mature stage to generate fruit periodic smooth trend hardness data;

[0052] Step S253: Perform fruit fullness analysis on the fruit cycle flat trend hardness data through the crop fruit morphology data to generate fruit fullness data; use the fruit fullness data to perform fruit maturity analysis on the mature stage fruit hardness data to generate mature stage crop fruit maturity data.

[0053] The present invention can fully understand the size, shape and other physical characteristics of the fruit by extracting the morphological data of the crop fruit, and provide basic data for subsequent analysis. The crop fruit morphological data can be used to evaluate the appearance quality of the fruit, thereby helping farmers to find abnormal fruits in time and promote quality control. The test of the fruit hardness data at the mature stage can effectively reflect the maturity of the fruit, and the hardness is usually closely related to the edibility, taste and storage characteristics of the fruit. By extracting the periodic gentle hardness of the fruit hardness data at the mature stage, the generated fruit periodic gentle trend hardness data helps to analyze the trend of hardness changing over time, and provides a more accurate basis for the prediction of the ripening time. The fullness analysis of the fruit periodic gentle trend hardness data using the fruit morphological data can quantify the fullness of the fruit, thereby more accurately evaluating the nutritional value and market value of the fruit. The fruit hardness data at the mature stage is analyzed by the fruit fullness data, and the generated crop fruit maturity data at the mature stage provides a comprehensive basis for evaluating the final maturity state of the fruit, helping farmers to harvest at the best time and improve yield and quality.

[0054] Preferably, step S3 comprises the following steps:

[0055] Step S31: integrating the crop lushness data at the budding stage, the crop growth status data at the rapid growth stage, the crop flowering status data at the reproductive growth stage, and the crop fruit maturity data at the mature stage into growth monitoring indicators to generate crop growth monitoring indicator data;

[0056] Step S32: dividing the data set based on the crop growth monitoring indicator data to generate a model training set and a model test set; using a decision tree algorithm to perform model training on the model training set to generate a crop growth monitoring and early warning pre-model; performing model optimization iteration on the crop growth monitoring and early warning pre-model through the model test set, thereby generating a crop growth monitoring and early warning model;

[0057] Step S33: Importing the crop growth monitoring data into the crop growth monitoring and early warning model to perform abnormal crop growth monitoring, thereby generating crop growth monitoring and early warning data.

[0058] The present invention integrates crop data at different growth stages to generate crop growth monitoring index data, so that agricultural managers can fully understand the growth status of crops. This integration provides a more comprehensive perspective and helps decision makers better identify growth trends and potential problems. The integrated monitoring index data improves the comparability between various growth stages, so that the crop growth conditions at different time points can be directly compared, which helps to timely discover growth anomalies and take measures. By dividing the crop growth monitoring index data into a model training set and a test set, the overfitting problem can be effectively avoided, thereby enhancing the generalization ability and reliability of the model, so that it can perform well in practical applications. Using a decision tree algorithm for model training can generate a crop growth monitoring and early warning model with good interpretability. The decision tree can automatically select the most important features, reduce human intervention, and improve the accuracy of prediction. By optimizing and iterating the early warning model through the model test set, the model parameters can be continuously adjusted to adapt it to the actual situation, thereby improving the prediction accuracy of crop growth monitoring and reducing the false alarm rate. Importing crop growth monitoring data into the early warning model for real-time monitoring can quickly identify abnormal conditions in crop growth. This rapid response capability helps farmers take timely measures to reduce potential losses. The generated crop growth monitoring and early warning data provides data-based decision support for agricultural management, helps optimize resource allocation and formulate more scientific management strategies.

[0059] Preferably, step S4 comprises the following steps:

[0060] Step S41: using the crop growth monitoring and early warning data to make crop growth decisions on the crop growth stage data to generate crop growth decision data; performing strategy simulation on the crop growth decision data to generate crop growth decision simulation data;

[0061] Step S42: performing decision feedback on the crop growth decision simulation data to generate crop growth decision feedback data; constructing a closed-loop feedback mechanism for the crop growth monitoring and early warning data based on the crop growth decision feedback data to generate a crop growth decision adjustment mechanism;

[0062] Step S43: Decision visualization is performed on the crop growth monitoring and early warning data according to the crop growth decision adjustment mechanism, thereby generating crop growth monitoring decision visualization data.

[0063] The present invention generates crop growth decision data by making decisions using crop growth monitoring and early warning data, thereby ensuring that agricultural managers make scientific growth strategies based on real-time data. This data-based decision helps reduce uncertainty and improve the effectiveness of decision-making. By performing strategy simulation on crop growth decision data and generating crop growth decision simulation data, the potential effects of different management measures can be evaluated before actual implementation. The simulation results can help decision makers identify the best strategy and optimize resource allocation. Decision feedback is performed on crop growth decision simulation data to generate crop growth decision feedback data, which can achieve dynamic monitoring and evaluation of decision effects. This feedback mechanism helps to identify problems and deficiencies in the implementation process, so as to make timely adjustments. A closed-loop feedback mechanism is constructed based on crop growth decision feedback data to generate a crop growth decision adjustment mechanism, making agricultural management more flexible. Farmers can continuously adjust management strategies based on feedback results to ensure healthy growth of crops. Decision visualization is performed on monitoring and early warning data according to the crop growth decision adjustment mechanism to generate crop growth monitoring decision visualization data, so that complex data is presented in an intuitive form, which is convenient for managers to quickly understand and analyze. Visualized data not only improves the decision-making efficiency of agricultural managers, but also provides a common perspective for collaboration between different departments (such as agriculture, environment, market, etc.), and promotes information sharing and communication.

[0064] The beneficial effect of the present invention is that by acquiring crop growth monitoring data and natural light data and performing phototropism intensity analysis, the light demand of crops can be evaluated in time, providing data basis for subsequent light source adjustment. When the crop phototropism intensity data is lower than the preset threshold, artificial light source trend correction is performed to effectively supplement the insufficient natural light, optimize the crop growth environment, and improve the crop growth efficiency. By clarifying the life cycle stage of the crop (such as seedling stage, rapid growth stage, etc.), specific management and fertilization strategies can be formulated for different growth stages to optimize resource use. Analyzing the indicator data of each growth stage (such as lushness, growth status, etc.) provides farmers with more detailed growth status feedback and helps to adjust management measures in time. Monitoring the growth abnormality of the data at each growth stage can detect potential growth problems (such as pests and diseases, malnutrition, etc.) early, and take measures to reduce losses in time. The generated crop growth monitoring and early warning data provides a basis for subsequent decision-making and improves the predictability and effectiveness of crop management. Using monitoring and early warning data for growth decision simulation can simulate the effects of different management plans, help farmers choose the best plan, and reduce the risks brought by blind decision-making. By generating a decision adjustment mechanism through closed-loop feedback, management strategies can be continuously optimized based on real-time data, ensuring dynamic adjustment of crop growth and improving management efficiency. Decision visualization enables farmers to intuitively understand monitoring results and decision-making processes, thereby enhancing the scientific nature and operability of decision-making and improving management levels. Therefore, the present invention significantly improves the accuracy and real-time nature of analysis and decision-making of crop growth monitoring data by integrating illumination data, refining crop life cycle divisions, and implementing abnormal monitoring and decision feedback mechanisms. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 A schematic diagram of the steps of a method for analyzing and making decisions on crop growth monitoring data;

[0066] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0067] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0068] Figure 4 for Figure 1 Detailed implementation steps of step S4 in FIG.

[0069] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0070] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0071] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0072] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0073] To achieve this, please refer to Figures 1 to 4 , a method for analyzing and making decisions on crop growth monitoring data, the method comprising the following steps:

[0074] Step S1: Acquire crop growth monitoring data and natural light data; perform crop growth phototropism intensity analysis on the crop growth monitoring data to generate crop phototropism intensity data; compare the crop phototropism intensity data with a preset phototropism intensity threshold, and when the crop phototropism intensity data is less than the preset phototropism intensity threshold, perform artificial light source trend correction based on the crop growth monitoring data, thereby generating crop growth light source adjustment data;

[0075] Step S2: dividing the crop growth monitoring data into crop life cycles according to the crop growth light source adjustment data to generate crop growth stage data, wherein the crop growth stage data includes the crop seedling stage, the crop rapid growth stage, the crop reproductive growth stage and the crop maturity stage; performing multi-dimensional crop index analysis on the crop growth monitoring data according to the seedling stage, the crop rapid growth stage, the crop reproductive growth stage and the crop maturity stage to generate crop lushness data in the bud stage, crop growth status data in the rapid growth stage, crop flowering status data in the reproductive growth stage and crop fruit maturity data in the maturity stage;

[0076] Step S3: monitoring the crop growth abnormality of the crop growth monitoring data based on the crop lushness data at the budding stage, the crop growth status data at the rapid growth stage, the crop flowering status data at the reproductive growth stage, and the crop fruit maturity data at the mature stage, thereby generating crop growth monitoring and early warning data;

[0077] Step S4: Utilize the crop growth monitoring and early warning data to simulate crop growth decision on the crop growth stage data, and generate crop growth decision simulation data; perform closed-loop feedback on the crop growth decision simulation data, and generate a crop growth decision adjustment mechanism; perform decision visualization on the crop growth monitoring and early warning data according to the crop growth decision adjustment mechanism, and thus generate crop growth monitoring decision visualization data.

[0078] The present invention provides a reliable data basis for subsequent analysis by acquiring crop growth monitoring data and natural light data. This stage ensures the comprehensiveness of the data and contributes to the accuracy of subsequent decision-making. By analyzing the phototropism intensity of crops, crop phototropism intensity data is generated, which helps to understand the response of crops to light. Artificial light source trend correction according to the lack of light can effectively improve the photosynthesis efficiency of crops and promote healthy growth. By setting the phototropism intensity threshold, the phototropism intensity of crops is monitored and adjusted in real time, which can ensure that crops obtain the best light conditions at different growth stages, thereby optimizing the crop growth environment. The crop life cycle is divided according to the crop growth light source adjustment data, so that the data at different growth stages are clearer and more orderly. This systematic division lays the foundation for subsequent indicator analysis and management decisions. Multidimensional crop indicator analysis is performed on each growth stage, and the generated lushness data of the bud stage, growth status data of the rapid growth period, flowering status data of the reproductive growth period and fruit maturity data of the mature stage make the crop growth status more comprehensive and three-dimensional, which is conducive to refined management. The crop growth abnormality monitoring of each growth stage data, the crop growth monitoring early warning data is generated, and potential problems can be identified in time to prevent the negative impact of pests and diseases, malnutrition and other situations on crop growth. Through the early warning data, agricultural managers can quickly take corresponding measures to reduce risks and ensure the stability and high yield of crop growth. The crop growth decision simulation data is used for decision simulation, and the generated crop growth decision simulation data can evaluate the effects of different management strategies before actual operation, so as to select the best solution for implementation. By closed-loop feedback of the decision simulation data, the crop growth decision adjustment mechanism generated ensures that the management measures can be continuously optimized and adjusted according to the actual situation, and improves the flexibility and effectiveness of the decision. The crop growth monitoring decision is visualized so that the complex data is displayed in an intuitive form, which helps managers and stakeholders at all levels to quickly understand the situation and promote collaboration and communication. Therefore, the present invention significantly improves the analysis and decision accuracy and real-time performance of crop growth monitoring data by integrating light data, refining the crop life cycle division, and realizing abnormal monitoring and decision feedback mechanism.

[0079] In the embodiment of the present invention, reference Figure 1 The above is a schematic diagram of the steps of a method for analyzing and making decisions on crop growth monitoring data of the present invention. In this example, the method for analyzing and making decisions on crop growth monitoring data includes the following steps:

[0080] Step S1: Acquire crop growth monitoring data and natural light data; perform crop growth phototropism intensity analysis on the crop growth monitoring data to generate crop phototropism intensity data; compare the crop phototropism intensity data with a preset phototropism intensity threshold, and when the crop phototropism intensity data is less than the preset phototropism intensity threshold, perform artificial light source trend correction based on the crop growth monitoring data, thereby generating crop growth light source adjustment data;

[0081] In an embodiment of the present invention, the growth status data of crops are obtained by using technologies such as sensors, remote sensing equipment or drones. These data should include key indicators such as crop height, leaf area, and chlorophyll content. A light sensor is used to record natural light intensity data within a specific time period, including sunshine duration and light intensity changes, for subsequent analysis. The acquired crop growth monitoring data is analyzed to calculate the phototropism intensity of the crop. This can be achieved by calculating the relationship between the crop growth direction and the light direction and the effect of light intensity on crop growth. According to the analysis results, a crop phototropism intensity data is generated, which records the phototropism intensity values ​​of crops at different growth stages. According to the crop type and growth stage, one or more phototropism intensity thresholds are preset for subsequent comparative analysis. The generated crop phototropism intensity data is compared and analyzed with the preset phototropism intensity threshold. When the crop phototropism intensity data is less than the preset threshold, it means that the crop cannot obtain sufficient light under natural light conditions, affecting its normal growth. When it is found that the crop phototropism intensity is insufficient, the crop growth monitoring data is used to analyze the crop's demand for light, and the appropriate artificial light source type (such as LED growth lamp) and its placement are evaluated and selected. Adjust the brightness and spectrum of artificial light sources according to the lighting requirements and growth stages of different crops to optimize lighting conditions. Record the adjustment plan of artificial light sources as crop growth light source adjustment data, which includes information such as light source type, brightness, lighting time and adjustment recommendations.

[0082] Step S2: dividing the crop growth monitoring data into crop life cycles according to the crop growth light source adjustment data to generate crop growth stage data, wherein the crop growth stage data includes the crop seedling stage, the crop rapid growth stage, the crop reproductive growth stage and the crop maturity stage; performing multi-dimensional crop index analysis on the crop growth monitoring data according to the seedling stage, the crop rapid growth stage, the crop reproductive growth stage and the crop maturity stage to generate crop lushness data in the bud stage, crop growth status data in the rapid growth stage, crop flowering status data in the reproductive growth stage and crop fruit maturity data in the maturity stage;

[0083] In the embodiment of the present invention, by using the crop growth light source adjustment data generated in step S1, suitable lighting conditions are provided for crops at different growth stages, thereby ensuring that the crops can obtain the best growth environment at each stage of their life cycle. According to the adjusted lighting conditions and the growth characteristics of the crops, the life cycle of the crops is divided into the following four main stages: Seedling stage: from seed germination to seedling growth. Rapid growth period: after the seedling stage, crop growth accelerates and biomass increases rapidly. Reproductive growth period: the stage when crops begin to bloom and bear fruit. Maturity period: the fruit of the crop begins to mature and is ready to be harvested. According to the life cycle division results, crop growth stage data is generated, and the start and end time of each stage and the relevant environmental conditions are recorded. According to the growth monitoring data of the seedling stage, the root growth, the number of leaves, the leaf area and other indicators are calculated and analyzed, and the lushness data of the crops in the budding stage is generated, which reflects the health status and growth potential of the seedlings. The growth monitoring data of the rapid growth period is analyzed to evaluate the photosynthesis efficiency, nutrient absorption, etc., and the growth status data of the crops in the rapid growth stage is generated to provide a basis for subsequent management. Based on the monitoring data of the reproductive growth period, the flower bud formation and flowering time are evaluated, and the flowering status data of crops in the reproductive growth stage are generated to understand the pollination and fruiting of crops. Using the growth monitoring data of the maturity period, the shape, hardness, color, etc. of the fruit are analyzed to generate the maturity degree data of the fruit of the mature stage crops to guide the harvest time.

[0084] Step S3: monitoring the crop growth abnormality of the crop growth monitoring data based on the crop lushness data at the budding stage, the crop growth status data at the rapid growth stage, the crop flowering status data at the reproductive growth stage, and the crop fruit maturity data at the mature stage, thereby generating crop growth monitoring and early warning data;

[0085] In the embodiment of the present invention, the following data are summarized for comprehensive analysis: Data on crop luxuriance in the budding stage: reflecting the growth status and health level of seedlings. Data on crop growth status in the rapid growth stage: showing the growth performance of crops in the rapid growth period. Data on crop flowering status in the reproductive growth stage: indicating the flowering status and the development status of flower buds. Data on fruit maturity of crops in the mature stage: describing the maturity progress and quality of fruits. Determine the normal index range for each growth stage, and establish a statistical method (such as Z-score, standard deviation, etc.) to identify abnormal values. For example: budding stage: luxuriance is lower than the preset threshold. Rapid growth stage: the growth status is significantly lower than the historical average level. Reproductive growth stage: the flowering rate is lower than the normal range. Mature stage: the fruit maturity is insufficient or the fruit hardness is abnormal. A model is constructed based on machine learning or data mining technology (such as decision trees, random forests, support vector machines, etc.), and potential growth abnormalities are identified by analyzing the above data. The integrated data of each stage is input into the abnormal monitoring model for real-time analysis. Monitor the crop growth data in real time to detect whether any data point exceeds the preset normal range. When the model detects an abnormality, it automatically generates crop growth monitoring and early warning data, including: slow growth, delayed flowering, and unfull fruit. Abnormal conditions are graded, such as mild, moderate, and severe. Relevant monitoring data and analysis results are attached for decision-making reference. Relevant monitoring data and analysis results are attached for decision-making reference. In addition to early warning information, corresponding management suggestions can also be made based on abnormal conditions, such as adjusting water and fertilizer management, increasing light, etc., to promote the restoration of normal growth of crops.

[0086] Step S4: Utilize the crop growth monitoring and early warning data to simulate crop growth decision on the crop growth stage data, and generate crop growth decision simulation data; perform closed-loop feedback on the crop growth decision simulation data, and generate a crop growth decision adjustment mechanism; perform decision visualization on the crop growth monitoring and early warning data according to the crop growth decision adjustment mechanism, and thus generate crop growth monitoring decision visualization data.

[0087] In an embodiment of the present invention, by relying on previously generated crop growth monitoring and early warning data, relevant data of the crop growth stage are prepared to ensure sufficient basis for decision-making. Decision simulation is performed using existing crop growth models (such as dynamic system models, climate adaptation models, etc.). Model inputs include: crop growth monitoring and early warning data, environmental factors (such as climate, soil type, fertilization conditions, etc.). Key decision variables are determined, such as water management, fertilization strategies, and pest and disease control measures. The simulation model is run to simulate the changes in crop growth under different management strategies, and crop growth decision simulation data is generated, including: impact assessment of various management measures, expected crop growth status and yield prediction. The differences between the simulation results and the actual growth conditions are collected to form feedback data, including: deviations between simulation predictions and actual observations. Error analysis data is generated to identify potential deficiencies in the model. Based on the feedback data, a crop growth decision adjustment mechanism is generated. The specific steps include: adjusting the management strategy to respond to the deviation between the simulation and actual data. Optimizing model parameters to ensure that future simulations are more accurate. Intuitive charts and interfaces are designed using data visualization software (such as Tableau, Power BI, etc.) or a custom-developed visualization platform. The visualization content includes: the trend chart of simulation results, the comparison chart of actual data and simulation data, and the dynamic display of feedback data. According to the crop growth decision adjustment mechanism, the crop growth monitoring decision visualization data is dynamically generated to provide managers with a clear decision basis.

[0088] Preferably, step S1 comprises the following steps:

[0089] Step S11: using sensors to obtain crop growth monitoring data and natural light data;

[0090] Step S12: performing data preprocessing on the crop growth monitoring data to generate standard crop growth monitoring data, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization;

[0091] Step S13: extracting the crop growth direction from the standard crop growth monitoring data to obtain crop growth direction data; analyzing the phototropism intensity of the natural light data using the crop growth direction data to generate crop phototropism intensity data;

[0092] Step S14: Compare the crop phototropism intensity data with a preset phototropism intensity threshold. When the crop phototropism intensity data is less than the preset phototropism intensity threshold, perform artificial light source trend correction based on the crop growth monitoring data to generate crop growth light source adjustment data.

[0093] In an embodiment of the present invention, a growth monitoring sensor and a light sensor are installed in the crop planting area to obtain crop growth data and environmental light data in real time. The growth monitoring sensor is used to obtain the growth monitoring data of the crop during the growth process, including the growth height, leaf area, chlorophyll content, etc. of the crop. At the same time, the light sensor is used to obtain natural light data, including light intensity, light duration, spectral distribution, etc. The acquired crop growth monitoring data is cleaned to remove data points or abnormal data that are incorrectly recorded by the sensor. The noise in the data is eliminated by filtering or other denoising algorithms, so that the data is smoother and truly reflects the growth of the crop. The missing monitoring data is filled, and commonly used methods include mean filling, interpolation, or prediction filling based on time series. The processed crop growth monitoring data is standardized to ensure the consistency of the data and adapt it to subsequent analysis and calculation. The pre-processed data forms standardized crop growth monitoring data as the basis for further analysis. Through image processing or sensor data analysis, the growth direction data of the crop under different lighting conditions is extracted, mainly focusing on the angle and direction of the crop toward the light source. According to the characteristics of the growth direction, the crop growth direction data is generated to reflect the crop's response direction to the light source. The crop growth direction data is used to analyze the natural light data to determine the phototropism intensity of the crop under the existing light conditions. Based on the analysis results, the crop phototropism intensity data is generated to reflect the photosynthesis efficiency and light source responsiveness of the crop under the current light conditions. The crop phototropism intensity data is compared with the preset phototropism intensity threshold to determine whether the crop is under ideal light conditions. When the phototropism intensity data is lower than the threshold, it indicates that the natural light is insufficient and the trend correction of the artificial light source is required. According to the crop growth monitoring data, the direction and intensity of the artificial light source are adjusted to ensure that the crop can obtain suitable light conditions. Through light source adjustment, crop growth light source adjustment data is generated to record the changes in the light source and the response of the crop to optimize light source management.

[0094] Preferably, performing crop phototropism intensity analysis on natural light data using crop growth direction data includes:

[0095] The crop top spatial azimuth angle data are extracted from the standard crop growth monitoring data through the crop growth azimuth data to obtain the crop top spatial azimuth angle data; the natural light incident angle data are extracted from the natural light data to obtain the natural light incident angle data;

[0096] The angle difference between the spatial orientation angle data of the crop top and the natural light incident angle data is calculated to generate the crop light angle difference; the crop light area is analyzed on the standard crop growth monitoring data through the crop light angle difference to generate the crop light receiving area; the crop light intensity calculation formula is used to calculate the crop light angle difference and the crop light receiving area to obtain the crop light intensity data;

[0097] The formula for calculating the phototropism intensity of crops is as follows:

[0098]

[0099] In the formula, is the crop phototropism intensity data, is the phototropism coefficient of the crop species, is the light receiving area of ​​the crop, is the angular difference between the crop azimuth and the illumination angle.

[0100] In an embodiment of the present invention, crop growth azimuth data and standard crop growth monitoring data are obtained. These data generally include the growth direction and spatial position of the crop top. Using the crop growth azimuth data, the position of the crop top (i.e., the highest point of the crop) is first located. This can be achieved by obtaining the coordinates of the crop top through image processing technology or sensor data. The spatial orientation of the crop top is calculated in three dimensions, and the spatial orientation angle of the crop top relative to the ground is extracted, including azimuth and elevation, to generate crop top spatial orientation angle data, which represents the spatial angle of the crop top relative to the horizontal plane (unit: degree). This angle is used for the relationship between crops and light in subsequent analysis. Natural light data is input, and the data source may include light sensors, meteorological data or other measuring equipment, usually including the azimuth and altitude of the sun at different times of the day. The natural light data is analyzed, and the sun's light incidence angle (sun altitude angle and sun azimuth angle) is calculated according to the time and geographical location. These data can be obtained through astronomical calculation formulas, usually using a solar position model (such as the NOAA solar position calculation model). By calculating the incident angle of the sun and combining it with the relative position of the ground, the incident angle of natural light is extracted to generate the natural light incident angle data, including the azimuth and incident angle of light (unit: degree), which is used for the subsequent angle difference calculation. Crop top spatial azimuth angle data and natural light incident angle data. Compare the crop top spatial azimuth angle data (crop azimuth and pitch angle) with the natural light incident angle data (sun azimuth and altitude angle) to calculate the angle difference between the two. The angle represents the relative angle between the crop top and the light. Use the cosine formula to calculate the spatial angle between the crop and the light source to generate the crop lighting angle difference, which is used to describe the angle between the spatial azimuth angle of the crop top and the light incident angle (unit: degree). According to the crop lighting angle difference, determine the illuminated area received by the crop. The smaller the angle, the larger the illuminated area; the larger the angle, the smaller the illuminated area. Through geometric analysis, calculate the actual illuminated area received by the crop top at a specific angle, assuming that the crop surface is an irregular plane or arc surface. Calculate using the illumination area formula: actual illumination area = maximum illumination area of ​​the crop under vertical illumination × cosine value of the illumination angle difference of the crop, generate crop illumination area data (unit: square meter), indicating the effective illumination area of ​​the crop under current illumination conditions. Use the crop phototropism intensity calculation formula to calculate the crop phototropism intensity, combine the illumination angle difference and the illumination receiving area to obtain the crop phototropism intensity, generate crop phototropism intensity data (unit: dimensionless), indicating the current attraction or induction intensity of the crop to light. The greater the phototropism intensity, the stronger the crop's response to the light source. Finally, combine the crop phototropism intensity data with other agricultural parameters (such as moisture, soil, and climate conditions) to conduct a comprehensive analysis of crop growth and light utilization.This can help optimize crop planting plans and adjust parameters such as lighting and planting density to improve crop growth efficiency.

[0101] Preferably, step S14 includes the following steps:

[0102] Step S141: comparing the crop phototropism intensity data with a preset phototropism intensity threshold, and when the crop phototropism intensity data is less than the preset phototropism intensity threshold, locating the weak phototropism area of ​​the crop based on the crop growth monitoring data to obtain the weak phototropism area data of the crop;

[0103] Step S142: performing artificial light source setting on the crop weak phototropism area data to obtain artificial light source setting data, wherein the artificial light source setting includes artificial light source incident angle setting, artificial light source brightness setting and artificial light source color setting;

[0104] Step S143: calculating the illumination trend intensity of the artificial light source for the artificial light source setting data and the crop weak phototropism area data to obtain the phototropism intensity data of the crop weak phototropism area; dynamically adjusting the phototropism intensity data of the crop weak phototropism area according to the crop phototropism intensity data, so that the phototropism intensity data of the crop weak phototropism area is always greater than or equal to the crop phototropism intensity data, thereby generating the phototropism intensity adjustment data of the weak phototropism area;

[0105] Step S144: using the weak phototropism area phototropism intensity adjustment data to perform artificial light source trend correction on the artificial light source setting data, thereby generating crop growth light source adjustment data.

[0106] In an embodiment of the present invention, by obtaining crop phototropism intensity data and a preset phototropism intensity threshold. Compare the crop phototropism intensity data with the preset phototropism intensity threshold. When the crop phototropism intensity data is less than the preset threshold, it is considered that the crop has a weak phototropism area. Positioning analysis is performed on the weak phototropism area, and combined with the crop growth monitoring data, the area where the crop is in a low phototropism intensity is identified. Through a positioning system or image processing technology, the specific range of the weak phototropism area is determined, and the crop weak phototropism area data is generated. The data indicates that the crop is in an area with low phototropism intensity, including a specific location and a regional range. Design a suitable artificial light source system for the weak phototropism area of ​​the crop. Set the parameters of the artificial light source according to the distribution of the weak phototropism area and the specific needs of the crop. Set the incident angle of the artificial light source to ensure that the light can cover the weak phototropism area to the maximum extent. The setting of the incident angle can be calculated by geometric analysis to ensure that the light source and the top position of the crop form an optimal irradiation angle. Set the brightness of the artificial light source, and the brightness needs to be reasonably set according to the photosynthesis requirements of the crop to ensure that the crop can obtain sufficient light intensity. Set the color of the artificial light source. Light sources of different colors will affect the growth of crops. For example, blue light and red light are usually used to promote plant growth and photosynthesis. Generate artificial light source setting data, including the incident angle, brightness and color parameters of the artificial light source. These data will be used to adjust the lighting conditions of the weak phototropism area of ​​the crop. According to the setting data of the artificial light source, calculate the light intensity of the artificial light source on the weak phototropism area of ​​the crop. The calculation formula can consider the impact of the incident angle, brightness and color of the artificial light source on the growth of the crop, and generate the phototropism intensity data of the weak phototropism area of ​​the crop, that is, the phototropism intensity of the weak phototropism area of ​​the crop under the action of the artificial light source. The data is dynamically adjusted with the original crop phototropism intensity data to keep the phototropism intensity of the weak phototropism area within a reasonable range, ensuring that the light intensity of the weak phototropism area is greater than or equal to the average phototropism intensity of the crop to achieve light balance, and generate the phototropism intensity adjustment data of the weak phototropism area to ensure that the adjusted artificial light source setting can make up for the insufficient light in the weak phototropism area and optimize the growth environment of the crop. According to the phototropism intensity adjustment data of the weak phototropism area, the original artificial light source setting data is corrected. The correction includes the adjustment of the incident angle, brightness and color of the artificial light source. The goal of the correction is to enable the artificial light source to continuously provide stable lighting, ensure that the weak phototropism area of ​​the crop can obtain sufficient light, and maintain the uniform growth of the crop. According to the corrected light source data, the output of the light source is adjusted in real time, instructions for controlling the light source equipment are generated, and crop growth light source adjustment data is generated, which is used to adjust the configuration of the artificial light source in real time, optimize the crop growth environment, ensure uniform light distribution, and improve the overall photosynthetic efficiency of the crop.

[0107] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0108] Step S21: dividing the crop growth monitoring data into crop life cycles according to the crop growth light source adjustment data to generate crop growth stage data, wherein the crop growth stage data includes the crop seedling stage, the crop rapid growth stage, the crop reproductive growth stage and the crop maturity stage;

[0109] Step S22: performing root resistance imaging on the crop growth monitoring data at the seedling stage to generate a three-dimensional root image at the budding stage; extracting main root depth information of the crop from the three-dimensional root image at the budding stage to obtain main root depth information data of the crop; extracting branch root bifurcation information from the three-dimensional root image at the budding stage to obtain branch root bifurcation information data of the crop; performing root luxuriance analysis on the crop at the budding stage based on the main root depth information data and the branch root bifurcation information data of the crop to generate luxuriance data of the crop at the budding stage;

[0110] Step S23: performing leaf spectral scanning on the crop growth monitoring data based on the crop rapid growth period to obtain leaf spectral data of the rapid growth stage; performing leaf physiological state analysis on the leaf spectral data of the rapid growth stage to generate crop growth state data of the rapid growth stage;

[0111] Step S24: performing a time series remote sensing scan of crop flower buds based on the crop growth monitoring data during the crop reproductive growth period to obtain time series remote sensing data of flower buds during the reproductive growth period; performing a flower bud vegetation index calculation on the time series remote sensing data of flower buds during the reproductive growth period to generate flowering state data of crops during the reproductive growth period;

[0112] Step S25: Perform a crop fruit hardness test on the crop growth monitoring data based on the crop maturity period to obtain fruit hardness data at the maturity stage; perform a fruit maturity degree analysis on the fruit hardness data at the maturity stage to generate crop fruit maturity degree data at the maturity stage.

[0113] In the embodiment of the present invention, different stages of crop growth are identified according to the light adjustment data of the crop and the growth characteristics of the crop, including the seedling stage, the rapid growth stage, the reproductive growth stage and the mature stage. The crop life cycle is divided using the time series information, growth change and environmental data of the crop growth. Combined with the standard growth model and real-time monitoring data, the current growth stage of the crop is accurately located, the crop growth stage data is generated, and the time range and characteristics of the seedling stage, the rapid growth stage, the reproductive growth stage and the mature stage of the crop are clearly divided. Based on the monitoring data of the seedling stage of the crop, the root system resistance imaging technology is used to obtain the three-dimensional image data of the root system and generate the three-dimensional image of the root system in the germination stage. This image shows the distribution and growth status of the root system by analyzing the resistance change of the root system. The three-dimensional root system image is processed to extract the main root system depth information data of the crop, and the depth of the root system into the soil is determined by analyzing the main trunk part of the root system. The three-dimensional root system image is extracted from the branch root bifurcation information data, and the bifurcation point, branch number and distribution of the root system are analyzed to reflect the complexity and luxuriance of the root system. According to the main root depth and branch root bifurcation information, the root luxuriance analysis is carried out in the budding stage, and the crop luxuriance data in the budding stage is generated to evaluate the health and growth potential of the root system. The root luxuriance data of the crop is generated to help analyze the development of the root system and the stability of crop growth. In the rapid growth period of the crop, the leaf spectrum scanning technology is used to collect high-precision spectral data of the crop leaves to generate leaf spectrum data in the rapid growth stage. Spectral data can reflect the pigment content, health status and photosynthesis efficiency of the leaves. The spectral data is analyzed for the physiological status of the leaves, focusing on the nitrogen content, chlorophyll concentration and water status of the leaves, to evaluate the health status and growth rate of the crops in the rapid growth period, and to generate crop growth status data in the rapid growth stage, which is used to evaluate the physiological activity and growth rate of the crops and determine whether the environment or fertilization plan needs to be adjusted. In the reproductive growth period of the crop, remote sensing technology is used to scan the flower buds in time series to obtain the flower bud time series remote sensing data in the reproductive growth stage. This data records the growth and changes of the flower buds. Based on remote sensing data, the flower bud vegetation index is calculated. This index can reflect the flowering status and health of crops by analyzing the reflectivity of flower buds and the spectral characteristics of vegetation, and generate flowering status data of crops in the reproductive growth stage, which is used to determine the timing, quantity and quality of crop flowering and help adjust agricultural management plans. During the crop maturity period, fruit hardness tests are conducted to obtain fruit hardness data in the mature stage. By analyzing the changes in fruit hardness, the degree of maturity is determined. Further maturity analysis is performed on the hardness data, including peel hardness, internal fiber structure of the fruit, etc., to generate fruit maturity data. By comparing the changes in hardness in different time periods during the maturity period, the optimal harvest time is predicted, and the maturity data of crops in the mature stage is generated, providing a scientific basis for fruit picking and ensuring that crops are harvested at the best time.

[0114] Preferably, step S23 includes the following steps:

[0115] Step S231: performing leaf spectral scanning on crop growth monitoring data based on the crop rapid growth period to obtain leaf spectral data in the rapid growth stage;

[0116] Step S232: converting the leaf spectrum data in the rapid growth stage into a full spectrum reflectance curve to generate a leaf full spectrum reflectance curve; performing fluctuation curve segmentation on the leaf full spectrum reflectance curve to generate a leaf full spectrum fluctuation curve; performing band analysis on the leaf full spectrum fluctuation curve to generate leaf full spectrum fluctuation curve band data;

[0117] Step S233: comparing the blade full spectrum fluctuation curve band data with the preset red light band threshold, when the blade full spectrum fluctuation curve band data is greater than or equal to the preset red light band threshold, the corresponding blade full spectrum fluctuation curve band data is marked as the red light band; when the blade full spectrum fluctuation curve band data is less than the preset red light band threshold, the corresponding blade full spectrum fluctuation curve band data is marked as the near red light band;

[0118] Step S234: performing chlorophyll absorption peak characteristic analysis on the full spectrum fluctuation curve of the leaves through the red light band to generate chlorophyll absorption peak characteristic data; performing moisture characteristic analysis on the full spectrum fluctuation curve of the leaves through the near-red light band to generate moisture characteristic data;

[0119] Step S235: Analyze the leaf physiological status of the leaf spectrum data in the rapid growth stage using the chlorophyll absorption peak characteristic data and the water characteristic data, thereby generating the crop growth status data in the rapid growth stage.

[0120] In an embodiment of the present invention, a high-resolution spectrometer is used to perform leaf spectral scanning on crops in a rapid growth period to obtain reflectance data of crop leaves at different wavelengths. The spectral data obtained by scanning is sorted and preliminarily analyzed to generate leaf spectral data in the rapid growth stage. This data reflects the absorption and reflection of light in different bands by the leaves, which can help analyze the health status and photosynthesis efficiency of the crops, generate spectral data of crop leaves in the rapid growth period, and provide a basis for subsequent spectral analysis. The leaf spectral data is converted into a full-spectrum reflectance curve, and the spectral data is converted into a continuous reflectance curve to generate a full-spectrum reflectance curve for the leaves, reflecting the spectral characteristics of the leaves from ultraviolet to infrared bands. By analyzing the fluctuation characteristics of the reflectance curve, the curve is segmented into a fluctuation curve using an automated algorithm to generate a full-spectrum fluctuation curve for the leaves, showing the changing trend of reflectance in different bands. Further band analysis is performed on the fluctuation curve to extract information from specific bands and generate band data of the full spectrum fluctuation curve of leaves, including information of key bands such as red light and near infrared. These bands are closely related to the health status, photosynthesis and water status of leaves. The full spectrum reflectance curve and fluctuation curve data of leaves are obtained to provide data support for subsequent band feature analysis. The band data of the full spectrum fluctuation curve of leaves are compared and analyzed with the preset red light band threshold: when the band data is greater than or equal to the red light band threshold, the part is marked as the red light band. The absorption of the red light band is related to the chlorophyll content and is an important indicator for evaluating photosynthesis. When the band data is less than the red light band threshold, the part is marked as the near infrared band. The near infrared band is mainly used to analyze the water status of leaves and has characteristics related to plant health. Full spectrum band data with red light band and near infrared band labels are generated to provide a data basis for further feature analysis. Based on the red light band data, chlorophyll absorption peak characteristic analysis is performed, focusing on the absorption characteristics of leaves in the red light band, and generating chlorophyll absorption peak characteristic data. This analysis reflects the chlorophyll content and photosynthesis capacity of the leaves. Based on the near-infrared band data, water characteristic analysis is performed, the water characteristics of the leaves are extracted, and water characteristic data is generated. The near-infrared band is closely related to the water content of the plant. The water content of the leaves can be detected by the change in reflectivity, and chlorophyll absorption peak characteristic data and water characteristic data can be generated. These data can provide key information on the health of the leaves. Using the acquired chlorophyll absorption peak characteristic data and water characteristic data, a comprehensive analysis of the leaf spectral data during the rapid growth period is performed. By analyzing the chlorophyll absorption peak data, the photosynthesis efficiency and growth momentum of the leaves can be evaluated; through the water characteristic data, the water status of the crops and the potential risk of drought or over-humidity can be analyzed.Finally, the crop growth status data in the rapid growth stage is generated. This data comprehensively reflects the health status, photosynthesis efficiency and water balance of the crops in the rapid growth period. The generated crop growth status data can provide a scientific basis for crop management decisions, such as whether it is necessary to adjust the irrigation amount or adjust the light conditions.

[0121] Preferably, step S24 includes the following steps:

[0122] Step S241: performing a time series remote sensing scan of crop flower buds based on crop growth monitoring data during the crop reproductive growth period to obtain time series remote sensing data of flower buds during the reproductive growth period;

[0123] Step S242: geometrically correcting the flower bud time series remote sensing data of the reproductive growth stage to generate corrected remote sensing data of the flower buds of the reproductive growth stage; classifying the flower bud states of the corrected remote sensing data of the flower buds of the reproductive growth stage to generate classified data of the flower bud states, wherein the classified data of the flower bud states include a non-flowering state, a flowering state, and a post-flowering state;

[0124] Step S243: Calculating vegetation indexes for the flower bud corrected remote sensing data in the reproductive growth stage according to the non-flowering state, the flowering state, and the post-flowering state, respectively, to obtain a first state vegetation index, a second state vegetation index, and a third state vegetation index; calculating the mean of the first state vegetation index, the second state vegetation index, and the third state vegetation index, to obtain a mean vegetation index for the flower bud period;

[0125] Step S244: Analyze the flowering status of the flower bud time series remote sensing data in the reproductive growth stage using the mean index of the flower bud period vegetation, thereby generating flowering status data of crops in the reproductive growth stage.

[0126] In the embodiment of the present invention, by using high-resolution remote sensing technology to perform time-series remote sensing scanning of flower buds of crops in the reproductive growth stage, the time-series change information of the flower buds of the crops is obtained, and the time-series remote sensing data of the flower buds in the reproductive growth stage is generated. The remote sensing data can track the changes of flower buds from non-flowering, flowering to post-flowering in real time, record the spectrum and image characteristics under different growth states, obtain the time-series remote sensing data of flower buds in the reproductive growth stage, and provide a basis for subsequent analysis. The obtained flower bud time-series remote sensing data is geometrically corrected to correct the spatial distortion and geometric deviation of the remote sensing image, generate flower bud correction remote sensing data, and ensure the accuracy of subsequent analysis. The data after geometric correction is classified into flower bud states, and according to the characteristics of the flower buds in the remote sensing image (such as spectral reflectance, structural morphology, etc.), the flower buds are divided into three states: non-flowering state, flowering state and post-flowering state, and the flower bud state classification data is generated, which is used to identify the flower bud conditions in different growth stages, and the classification data based on the flower bud state is generated, which provides a basis for the subsequent vegetation index calculation. Vegetation indexes are calculated for different states of flower buds: First state vegetation index: For flower buds in the non-flowering state, vegetation index is calculated using remote sensing data to analyze plant vitality when the flower buds are not blooming. Second state vegetation index: For flower buds in the flowering state, vegetation index is calculated, mainly to analyze plant health and flowering abundance during flowering. Third state vegetation index: For flower buds in the post-flowering state, vegetation index is calculated to evaluate plant state and health after flowering. The vegetation indexes of these three states are averaged to generate the mean vegetation index of the flower bud cycle, which reflects the plant health and flowering of the entire flower bud growth cycle, and the mean vegetation index of the flower bud cycle is obtained, which is a measure of the comprehensive performance of the flower bud state in the reproductive growth period. Based on the mean vegetation index of the flower bud cycle, the flowering state of the flower bud time series remote sensing data in the reproductive growth period is analyzed. By analyzing the changes in vegetation index in different time periods, the health state of the flowering stage and the abundance and breadth of flowering are evaluated. Combined with the vegetation mean index, the flowering status data of crops in the reproductive growth stage are generated, including information such as flowering time, flowering amount and flowering quality of crops. Finally, the flowering status data of crops are generated, which can accurately determine the timing, scale and quality of crop flowering, and provide key data of flowering period for agricultural management.

[0127] Preferably, step S25 comprises the following steps:

[0128] Step S251: extracting crop fruit morphology data from crop growth monitoring data based on crop maturity period to obtain crop fruit morphology data;

[0129] Step S252: Perform a crop fruit hardness test based on the crop fruit morphology data to obtain fruit hardness data at the mature stage; perform a periodic smooth hardness extraction on the fruit hardness data at the mature stage to generate fruit periodic smooth trend hardness data;

[0130] Step S253: Perform fruit fullness analysis on the fruit cycle flat trend hardness data through the crop fruit morphology data to generate fruit fullness data; use the fruit fullness data to perform fruit maturity analysis on the mature stage fruit hardness data to generate mature stage crop fruit maturity data.

[0131] In the embodiment of the present invention, the fruit of the crop maturity period is monitored in real time by using three-dimensional imaging technology, remote sensing monitoring and other means, and the morphological information such as the size, shape, and surface features of the fruit are extracted to generate crop fruit morphological data. The morphological data includes the diameter, volume, skin smoothness, morphological integrity, etc. of the fruit. The data provide a basis for further analysis of the hardness and maturity of the fruit, and the crop fruit morphological data is obtained, which provides input for fruit hardness testing and maturity analysis. Based on the fruit morphological data, the fruit is tested for hardness using non-destructive hardness testing technology to obtain the fruit hardness data in the mature stage. The hardness test can evaluate the firmness of the fruit and the degree of hardening during the ripening process. The obtained hardness data is subjected to periodic gentle hardness extraction, that is, by analyzing the change trend of the hardness data in different time periods, the stable section of the hardness change of the fruit in the ripening cycle is extracted, and the fruit periodic gentle trend hardness data is generated, and the fruit periodic gentle trend hardness data reflecting the hardness change trend of the fruit in the ripening cycle is generated, which is used to further analyze the fullness and maturity of the fruit. Through the morphological data and hardness trend data of the fruit, the fullness of the fruit is analyzed, the internal fullness and the appearance fullness of the fruit are evaluated, and the fruit fullness data is generated. This data reflects whether the fruit has reached the optimal development stage and determines whether there are holes or unfull fruit inside. The fruit fullness data is combined with the hardness data to analyze the maturity of the fruit in the mature stage, assess whether the fruit has reached the optimal picking time or is overripe, and generate the maturity data of the crop fruit in the mature stage. Finally, the crop fruit maturity data is generated to accurately judge the maturity of the fruit, providing a basis for fruit picking and subsequent processing.

[0132] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0133] Step S31: integrating the crop lushness data at the budding stage, the crop growth status data at the rapid growth stage, the crop flowering status data at the reproductive growth stage, and the crop fruit maturity data at the mature stage into growth monitoring indicators to generate crop growth monitoring indicator data;

[0134] Step S32: dividing the data set based on the crop growth monitoring indicator data to generate a model training set and a model test set; using a decision tree algorithm to perform model training on the model training set to generate a crop growth monitoring and early warning pre-model; performing model optimization iteration on the crop growth monitoring and early warning pre-model through the model test set, thereby generating a crop growth monitoring and early warning model;

[0135] Step S33: Importing the crop growth monitoring data into the crop growth monitoring and early warning model to perform abnormal crop growth monitoring, thereby generating crop growth monitoring and early warning data.

[0136] In the embodiment of the present invention, by collecting and collating the monitoring data from each growth stage of the crop, the data include the lushness data of the budding stage, the growth state data of the rapid growth stage, the flowering state data of the reproductive growth stage, and the fruit maturity data of the mature stage. The data of these different stages are normalized to ensure the dimensional consistency between different indicators. The monitoring data of each stage are feature extracted and integrated to form comprehensive crop growth monitoring index data, which is used to comprehensively reflect the growth state of the crop throughout the growth cycle, and generate crop growth monitoring index data. The data includes the key indicators of crop growth from budding to maturity, and provide input for subsequent model training. According to the crop growth monitoring index data, the data is divided into a model training set and a model test set. The training set is used for the preliminary training of the model, and the test set is used for the performance evaluation and optimization of the model. The model training set is trained using a decision tree algorithm to generate a crop growth monitoring and early warning pre-model. The decision tree algorithm can generate a tree structure according to different crop growth stage indicators, thereby helping to identify potential problems or abnormalities in crop growth. The preliminarily generated early warning model is tested by the test set to evaluate the accuracy, sensitivity and specificity of the model. Based on the test results, the model is iteratively optimized, and the model parameters are continuously adjusted to finally generate a crop growth monitoring and early warning model, which can predict potential anomalies in crop growth and generate an optimized crop growth monitoring and early warning model, which can effectively detect and predict abnormalities in crop growth. The crop growth monitoring data acquired in real time is imported into the trained crop growth monitoring and early warning model. The early warning model is used to automatically monitor the growth of crops and identify abnormalities, such as abnormal growth rate, delayed flowering, or insufficient fruit maturity. When the model detects an abnormality, it generates crop growth monitoring and early warning data, which contains detailed information about the abnormality, such as the abnormal stage, the cause of the abnormality, and treatment suggestions. The crop growth monitoring and early warning data is generated to provide decision support for the precise management of crops, and can be used to take measures in advance to avoid yield losses caused by abnormal crop growth.

[0137] As an example of the present invention, refer to Figure 4 As shown, in this example, step S4 includes:

[0138] Step S41: using the crop growth monitoring and early warning data to make crop growth decisions on the crop growth stage data to generate crop growth decision data; performing strategy simulation on the crop growth decision data to generate crop growth decision simulation data;

[0139] Step S42: performing decision feedback on the crop growth decision simulation data to generate crop growth decision feedback data; constructing a closed-loop feedback mechanism for the crop growth monitoring and early warning data based on the crop growth decision feedback data to generate a crop growth decision adjustment mechanism;

[0140] Step S43: Decision visualization is performed on the crop growth monitoring and early warning data according to the crop growth decision adjustment mechanism, thereby generating crop growth monitoring decision visualization data.

[0141] In the embodiment of the present invention, by using crop growth monitoring and early warning data, the data of each growth stage is analyzed to formulate a decision strategy for crop growth. This includes management measures and intervention strategies required for different stages (such as germination, rapid growth, reproductive growth and maturity). The decision results are summarized as crop growth decision data, which reflects the recommended crop management measures at different growth stages. Based on the crop growth decision data, a simulation tool is used to evaluate the strategy effect, simulate the impact of different management measures on crop growth, and generate crop growth decision simulation data. The data shows the predicted results of crop growth under different strategies, helping decision makers to evaluate which strategies can achieve the best growth effect. The generated crop growth decision data and crop growth decision simulation data will provide a basis for subsequent decision feedback. The generated crop growth decision simulation data is analyzed and evaluated to verify the actual effect after the implementation of the strategy. Feedback information on crop growth is collected to generate crop growth decision feedback data, which includes growth indicators and monitoring results after implementation, reflecting the effectiveness of the decision. Based on the crop growth decision feedback data, a closed-loop feedback mechanism is established to combine the feedback results with the initial monitoring data to form the basis for decision adjustment and generate a crop growth decision adjustment mechanism. This mechanism ensures that the crop growth management strategy is dynamically adjusted based on monitoring and feedback to cope with changes and abnormal situations. A complete crop growth decision feedback data and crop growth decision adjustment mechanism are formed to ensure the timeliness and effectiveness of decision making. According to the crop growth decision adjustment mechanism, the crop growth monitoring and early warning data are visualized, and graphical tools are used to convert the data into easy-to-understand charts, curves or heat maps. The visualization results should clearly display the monitoring data, decision results and adjustment strategies of each growth stage, so that users can quickly identify the state of crop growth and the effects of management measures. The final crop growth monitoring decision visualization data includes various visualization charts to help decision makers fully understand the dynamic changes in crop growth and the required management adjustments. The generated crop growth monitoring decision visualization data will provide decision makers with clear and intuitive information support, so that timely measures can be taken to optimize crop management.

[0142] The beneficial effect of the present invention is that by acquiring crop growth monitoring data and natural light data and performing phototropism intensity analysis, the light demand of crops can be evaluated in time, providing data basis for subsequent light source adjustment. When the crop phototropism intensity data is lower than the preset threshold, artificial light source trend correction is performed to effectively supplement the insufficient natural light, optimize the crop growth environment, and improve the crop growth efficiency. By clarifying the life cycle stage of the crop (such as seedling stage, rapid growth stage, etc.), specific management and fertilization strategies can be formulated for different growth stages to optimize resource use. Analyzing the indicator data of each growth stage (such as lushness, growth status, etc.) provides farmers with more detailed growth status feedback and helps to adjust management measures in time. Monitoring the growth abnormality of the data at each growth stage can detect potential growth problems (such as pests and diseases, malnutrition, etc.) early, and take measures to reduce losses in time. The generated crop growth monitoring and early warning data provides a basis for subsequent decision-making and improves the predictability and effectiveness of crop management. Using monitoring and early warning data for growth decision simulation can simulate the effects of different management plans, help farmers choose the best plan, and reduce the risks brought by blind decision-making. By generating a decision adjustment mechanism through closed-loop feedback, management strategies can be continuously optimized based on real-time data, ensuring dynamic adjustment of crop growth and improving management efficiency. Decision visualization enables farmers to intuitively understand monitoring results and decision-making processes, thereby enhancing the scientific nature and operability of decision-making and improving management levels. Therefore, the present invention significantly improves the accuracy and real-time nature of analysis and decision-making of crop growth monitoring data by integrating illumination data, refining crop life cycle divisions, and implementing abnormal monitoring and decision feedback mechanisms.

[0143] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0144] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for analyzing and making decisions on crop growth monitoring data, characterized in that: The following steps are involved: Step S1: Acquire crop growth monitoring data and natural light data; The crop growth monitoring data is subjected to a crop growth phototropism intensity analysis to generate crop phototropism intensity data; the crop phototropism intensity data is compared with a preset phototropism intensity threshold, and when the crop phototropism intensity data is less than the preset phototropism intensity threshold, an artificial light source trend correction is performed based on the crop growth monitoring data to generate crop growth light source adjustment data; step S1 comprises the following steps: Step S11: using sensors to obtain crop growth monitoring data and natural light data; Step S12: performing data preprocessing on the crop growth monitoring data to generate standard crop growth monitoring data, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization; Step S13: extracting the crop growth direction of the standard crop growth monitoring data to obtain crop growth direction data; performing crop phototropism intensity analysis on the natural light data using the crop growth direction data to generate crop phototropism intensity data; performing crop phototropism intensity analysis on the natural light data using the crop growth direction data includes: The crop top spatial azimuth angle data are extracted from the standard crop growth monitoring data through the crop growth azimuth data to obtain the crop top spatial azimuth angle data; the natural light incident angle data are extracted from the natural light data to obtain the natural light incident angle data; The angle difference between the spatial orientation angle data of the crop top and the natural light incident angle data is calculated to generate the crop light angle difference; the crop light area is analyzed on the standard crop growth monitoring data through the crop light angle difference to generate the crop light receiving area; the crop light intensity calculation formula is used to calculate the crop light angle difference and the crop light receiving area to obtain the crop light intensity data; The formula for calculating the phototropism intensity of crops is as follows: In the formula, is the crop phototropism intensity data, is the phototropism coefficient of the crop species, is the light receiving area of ​​the crop, is the angle difference between the crop azimuth and the illumination angle; Step S14: comparing the crop phototropism intensity data with a preset phototropism intensity threshold, and when the crop phototropism intensity data is less than the preset phototropism intensity threshold, performing artificial light source trend correction based on the crop growth monitoring data, thereby generating crop growth light source adjustment data; Step S2: dividing the crop growth monitoring data into crop life cycles according to the crop growth light source adjustment data to generate crop growth stage data, wherein the crop growth stage data includes the crop seedling stage, the crop rapid growth stage, the crop reproductive growth stage and the crop maturity stage; performing multi-dimensional crop index analysis on the crop growth monitoring data according to the crop seedling stage, the crop rapid growth stage, the crop reproductive growth stage and the crop maturity stage to generate crop lushness data in the bud stage, crop growth status data in the rapid growth stage, crop flowering status data in the reproductive growth stage and crop fruit maturity data in the maturity stage; Step S3: monitoring the crop growth abnormality of the crop growth monitoring data based on the crop lushness data at the budding stage, the crop growth status data at the rapid growth stage, the crop flowering status data at the reproductive growth stage, and the crop fruit maturity data at the mature stage, thereby generating crop growth monitoring and early warning data; Step S4: Utilize the crop growth monitoring and early warning data to simulate crop growth decision on the crop growth stage data, and generate crop growth decision simulation data; perform closed-loop feedback on the crop growth decision simulation data, and generate a crop growth decision adjustment mechanism; perform decision visualization on the crop growth monitoring and early warning data according to the crop growth decision adjustment mechanism, and thus generate crop growth monitoring decision visualization data.

2. The method for analyzing and making decisions on crop growth monitoring data according to claim 1, characterized in that: Step S14 includes the following steps: Step S141: comparing the crop phototropism intensity data with a preset phototropism intensity threshold, and when the crop phototropism intensity data is less than the preset phototropism intensity threshold, locating the weak phototropism area of ​​the crop based on the crop growth monitoring data to obtain the weak phototropism area data of the crop; Step S142: performing artificial light source setting on the crop weak phototropism area data to obtain artificial light source setting data, wherein the artificial light source setting includes artificial light source incident angle setting, artificial light source brightness setting and artificial light source color setting; Step S143: calculating the illumination trend intensity of the artificial light source for the artificial light source setting data and the crop weak phototropism area data to obtain the phototropism intensity data of the crop weak phototropism area; dynamically adjusting the phototropism intensity data of the crop weak phototropism area according to the crop phototropism intensity data, so that the phototropism intensity data of the crop weak phototropism area is always greater than or equal to the crop phototropism intensity data, thereby generating the phototropism intensity adjustment data of the weak phototropism area; Step S144: using the weak phototropism area phototropism intensity adjustment data to perform artificial light source trend correction on the artificial light source setting data, thereby generating crop growth light source adjustment data.

3. The analysis and decision-making method for crop growth monitoring data according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: dividing the crop growth monitoring data into crop life cycles according to the crop growth light source adjustment data to generate crop growth stage data, wherein the crop growth stage data includes the crop seedling stage, the crop rapid growth stage, the crop reproductive growth stage and the crop maturity stage; Step S22: performing root resistance imaging on the crop growth monitoring data at the seedling stage to generate a three-dimensional root image at the budding stage; extracting main root depth information of the crop from the three-dimensional root image at the budding stage to obtain main root depth information data of the crop; extracting branch root bifurcation information from the three-dimensional root image at the budding stage to obtain branch root bifurcation information data of the crop; performing root luxuriance analysis on the crop at the budding stage based on the main root depth information data and the branch root bifurcation information data of the crop to generate luxuriance data of the crop at the budding stage; Step S23: performing leaf spectral scanning on the crop growth monitoring data based on the crop rapid growth period to obtain leaf spectral data of the rapid growth stage; performing leaf physiological state analysis on the leaf spectral data of the rapid growth stage to generate crop growth state data of the rapid growth stage; Step S24: performing a time series remote sensing scan of crop flower buds based on the crop growth monitoring data during the crop reproductive growth period to obtain time series remote sensing data of flower buds during the reproductive growth period; performing a flower bud vegetation index calculation on the time series remote sensing data of flower buds during the reproductive growth period to generate flowering state data of crops during the reproductive growth period; Step S25: Perform a crop fruit hardness test on the crop growth monitoring data based on the crop maturity period to obtain fruit hardness data at the maturity stage; perform a fruit maturity degree analysis on the fruit hardness data at the maturity stage to generate crop fruit maturity degree data at the maturity stage.

4. The method for analyzing and making decisions on crop growth monitoring data according to claim 3, characterized in that: Step S23 includes the following steps: Step S231: performing leaf spectral scanning on crop growth monitoring data based on the crop rapid growth period to obtain leaf spectral data in the rapid growth stage; Step S232: converting the leaf spectrum data in the rapid growth stage into a full spectrum reflectance curve to generate a leaf full spectrum reflectance curve; performing fluctuation curve segmentation on the leaf full spectrum reflectance curve to generate a leaf full spectrum fluctuation curve; performing band analysis on the leaf full spectrum fluctuation curve to generate leaf full spectrum fluctuation curve band data; Step S233: comparing the blade full spectrum fluctuation curve band data with the preset red light band threshold, when the blade full spectrum fluctuation curve band data is greater than or equal to the preset red light band threshold, the corresponding blade full spectrum fluctuation curve band data is marked as the red light band; when the blade full spectrum fluctuation curve band data is less than the preset red light band threshold, the corresponding blade full spectrum fluctuation curve band data is marked as the near red light band; Step S234: performing chlorophyll absorption peak characteristic analysis on the full spectrum fluctuation curve of the leaves through the red light band to generate chlorophyll absorption peak characteristic data; performing moisture characteristic analysis on the full spectrum fluctuation curve of the leaves through the near-red light band to generate moisture characteristic data; Step S235: Utilizing the chlorophyll absorption peak characteristic data and the water characteristic data, the leaf spectral data in the rapid growth stage are analyzed for leaf physiological status, thereby generating crop growth status data in the rapid growth stage.

5. The method for analyzing and making decisions on crop growth monitoring data according to claim 3, characterized in that: Step S24 includes the following steps: Step S241: performing a time series remote sensing scan of crop flower buds based on crop growth monitoring data during the crop reproductive growth period to obtain time series remote sensing data of flower buds during the reproductive growth period; Step S242: geometrically correcting the flower bud time series remote sensing data of the reproductive growth stage to generate corrected remote sensing data of the flower buds of the reproductive growth stage; classifying the flower bud states of the corrected remote sensing data of the flower buds of the reproductive growth stage to generate classified data of the flower bud states, wherein the classified data of the flower bud states include a non-flowering state, a flowering state, and a post-flowering state; Step S243: Calculating vegetation indexes for the flower bud corrected remote sensing data in the reproductive growth stage according to the non-flowering state, the flowering state, and the post-flowering state, respectively, to obtain a first state vegetation index, a second state vegetation index, and a third state vegetation index; calculating the mean of the first state vegetation index, the second state vegetation index, and the third state vegetation index, to obtain a mean vegetation index for the flower bud period; Step S244: Analyze the flowering status of the flower bud time series remote sensing data in the reproductive growth stage using the mean index of the flower bud period vegetation, thereby generating flowering status data of crops in the reproductive growth stage.

6. The method for analyzing and making decisions on crop growth monitoring data according to claim 3, characterized in that: Step S25 includes the following steps: Step S251: extracting crop fruit morphology data from crop growth monitoring data based on crop maturity period to obtain crop fruit morphology data; Step S252: Perform a crop fruit hardness test based on the crop fruit morphology data to obtain fruit hardness data at the mature stage; perform a periodic smooth hardness extraction on the fruit hardness data at the mature stage to generate fruit periodic smooth trend hardness data; Step S253: Perform fruit fullness analysis on the fruit cycle flat trend hardness data through the crop fruit morphology data to generate fruit fullness data; use the fruit fullness data to perform fruit maturity analysis on the mature stage fruit hardness data to generate mature stage crop fruit maturity data.

7. The method for analyzing and making decisions on crop growth monitoring data according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: integrating the crop lushness data at the budding stage, the crop growth status data at the rapid growth stage, the crop flowering status data at the reproductive growth stage, and the crop fruit maturity data at the mature stage into growth monitoring indicators to generate crop growth monitoring indicator data; Step S32: dividing the data set based on the crop growth monitoring indicator data to generate a model training set and a model test set; using a decision tree algorithm to perform model training on the model training set to generate a crop growth monitoring and early warning pre-model; performing model optimization iteration on the crop growth monitoring and early warning pre-model through the model test set, thereby generating a crop growth monitoring and early warning model; Step S33: Importing the crop growth monitoring data into the crop growth monitoring and early warning model to perform abnormal crop growth monitoring, thereby generating crop growth monitoring and early warning data.

8. The method for analyzing and making decisions on crop growth monitoring data according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: using the crop growth monitoring and early warning data to make crop growth decisions on the crop growth stage data to generate crop growth decision data; performing strategy simulation on the crop growth decision data to generate crop growth decision simulation data; Step S42: performing decision feedback on the crop growth decision simulation data to generate crop growth decision feedback data; constructing a closed-loop feedback mechanism for the crop growth monitoring and early warning data based on the crop growth decision feedback data to generate a crop growth decision adjustment mechanism; Step S43: Decision visualization is performed on the crop growth monitoring and early warning data according to the crop growth decision adjustment mechanism, thereby generating crop growth monitoring decision visualization data.

Images