Intelligent fertilization system driven by analysis of vegetable nutrient requirements

Abstract

The application provides an intelligent fertilization system driven by vegetable nutrient requirement analysis, relates to the technical field of data processing, and acquires the soil area of the target vegetable to be planted through a historical planting cycle determination module to determine the historical planting cycle; a historical record acquisition module acquires corresponding fertilization record information and soil record information under each planting cycle; a prediction model training module trains a model according to the record information to generate a planting cycle-soil fertility change prediction model; a soil fertility matching module acquires nutrient requirement data to perform soil fertility matching and output a preset soil fertility threshold; and a fertilization guidance module drives the prediction model to output a predicted planting cycle less than the preset soil fertility threshold to perform soil fertility reminding. The application solves the technical problem that the existing fertilization process fails to deeply mine and utilize historical planting data, resulting in low fertilization efficiency and insufficient accuracy, improves the scientificity and accuracy of the fertilization process, and improves the fertilization efficiency.

Description

Technical Field

[0001] This application relates to the field of data processing technology, specifically to an intelligent fertilization system driven by vegetable nutrient requirement analysis. Background Technology

[0002] In vegetable cultivation, soil fertility directly affects nutrient supply, and the scientific and precise application of fertilizers determines crop growth quality and yield. Current fertilization processes typically require soil sampling and fertility testing before each planting to determine the appropriate fertilizer application rate. Frequent soil testing consumes significant time and manpower, increasing production costs. Secondly, soil fertility and properties change significantly after multiple cultivations. This change is influenced not only by the type of crop previously planted but also by the type and amount of fertilizer applied in the past. Current fertilization processes rely on growers' experience or the results of a single soil test, neglecting the long-term impact of historical fertilization records on soil fertility. This can easily lead to inaccurate fertilizer application, resulting in over-fertilization or nutrient deficiency. Furthermore, current methods lack the ability to predict future changes in soil fertility, forcing growers to continuously adjust fertilization plans during crop growth, leading to delayed fertilization decisions and impacting healthy crop growth. Summary of the Invention

[0003] This application provides an intelligent fertilization system driven by vegetable nutrient requirement analysis, which solves the technical problem that the existing fertilization process relies on grower experience or soil test results and fails to deeply explore and utilize historical planting data, resulting in low fertilization efficiency and insufficient fertilization accuracy. It achieves the technical effect of improving the scientificity and accuracy of the fertilization process, while improving fertilization efficiency.

[0004] In view of the above problems, this application provides an intelligent fertilization system driven by vegetable nutrient requirement analysis. The system includes: a historical planting cycle determination module, which is used to acquire the soil area where the target vegetable is planted and determine the historical planting cycle of the soil area; a historical record acquisition module, which is used to collect fertilization record information and soil record information corresponding to each planting cycle; a prediction model training module, which is used to train a model based on the fertilization record information and the soil record information to generate a planting cycle-soil fertility change prediction model; a soil fertility matching module, which is used to acquire the nutrient requirement data of the target vegetable, perform soil fertility matching based on the nutrient requirement data, and output a preset soil fertility threshold; and a fertilization guidance module, which is used to drive the planting cycle-soil fertility change prediction model, output predicted planting cycles that are less than the preset soil fertility threshold, and provide soil fertility reminders based on the predicted planting cycles.

[0005] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0006] The historical planting cycle determination module acquires the soil area where the target vegetable is planted and determines the historical planting cycle of the soil area, providing a data foundation for subsequent fertilization decisions. The historical record collection module collects fertilization records and soil records corresponding to each planting cycle, providing comprehensive data support for model training. The prediction model training module trains the model based on the fertilization and soil records, generating an accurate planting cycle-soil fertility change prediction model, avoiding frequent soil sampling before planting and reducing operational costs. The soil fertility matching module acquires the nutrient requirement data of the target vegetable, performs soil fertility matching based on the nutrient requirement data, outputs a preset soil fertility threshold, and thus accurately controls the amount of fertilizer used, avoiding over- or under-fertilization. The fertilization guidance module drives the planting cycle-soil fertility change prediction model, outputs predicted planting cycles lower than the preset soil fertility threshold, and provides soil fertility reminders based on the predicted planting cycles, guiding growers' fertilization operations and ensuring that the soil fertility level is always within the optimal range for target crop growth.

[0007] In summary, this application, through the collection and analysis of historical planting and fertilization data, utilizes predictive models to anticipate changes in soil fertility in advance, and combines this with the nutrient requirements of vegetables to provide intelligent fertilization matching and guidance, ensuring that crops receive adequate nutrients. At the same time, it avoids the complex operation of frequently collecting soil fertility data in the traditional fertilization process, significantly improving the accuracy and efficiency of fertilization, and greatly enhancing the efficiency and scientific nature of agricultural production.

[0008] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0009] Figure 1 A schematic diagram of the structure of an intelligent fertilization system driven by vegetable nutrient requirement analysis provided in an embodiment of this application;

[0010] Figure 2 A flowchart illustrating the process of dividing soil regions into multiple soil sub-regions according to the type of vegetables planted in the intelligent fertilization system driven by vegetable nutrient demand analysis provided in this application embodiment;

[0011] Figure 3This is a schematic diagram illustrating the process of model training based on fertilization record information and soil record information in an intelligent fertilization system driven by vegetable nutrient requirement analysis, as provided in an embodiment of this application.

[0012] Attached diagram labels: Historical planting cycle determination module 10, historical record collection module 20, prediction model training module 30, soil fertility matching module 40, fertilization guidance module 50. Detailed Implementation

[0013] This application provides an intelligent fertilization system driven by vegetable nutrient requirement analysis, which solves the technical problem that the existing fertilization process relies on grower experience or soil test results and fails to deeply explore and utilize historical planting data, resulting in low fertilization efficiency and insufficient fertilization accuracy. It achieves the technical effect of improving the scientificity and accuracy of the fertilization process, while also improving fertilization efficiency.

[0014] like Figure 1 As shown in the embodiment of this application, an intelligent fertilization system driven by vegetable nutrient requirement analysis is provided. The system includes:

[0015] The historical planting cycle determination module 10 is used to obtain the soil area where the target vegetable is planted and determine the historical planting cycle of the soil area.

[0016] Specifically, historical planting cycles refer to the number and cycles in which different crops have been planted in a specific soil area in the past. Different planting cycles have a cumulative impact on soil fertility, so understanding historical planting cycles helps to better grasp the dynamic changes in soil fertility.

[0017] The historical planting cycle determination module 10 acquires relevant information about the planting area of ​​the planned target vegetables, especially records of past planting activities on that land. For example, if potatoes, tomatoes, and carrots have been planted in rotation on a plot, the time, crop type, and duration of each planting cycle need to be recorded. Agricultural management databases, GPS positioning technology, and agricultural IoT devices can be used to accurately track and record the planting history of different plots. By acquiring this information, a clear understanding of the historical planting situation in the soil area can be obtained, providing a necessary data foundation for subsequent analysis of soil fertility changes and prediction of future fertilization needs.

[0018] The historical record acquisition module 20 is used to collect fertilization record information and soil record information corresponding to each planting cycle.

[0019] Specifically, the historical data collection module 20 collects fertilization and soil-related data from different planting cycles. This includes records of fertilizer type, application amount, and application time for each planting cycle (fertilization record information); and soil physicochemical property data, such as soil pH, organic matter content, and nitrogen, phosphorus, and potassium content (soil record information). For example, in the first potato planting cycle, the amount of nitrogen fertilizer used and the soil organic matter content during the planting process are recorded. Similarly, in the second tomato planting cycle, changes in fertilization and soil conditions are recorded. This information can be collected and managed using sensors, agricultural management systems, and databases. These records provide crucial historical data for the predictive model training module 30, reflecting the long-term impact of different fertilization strategies on soil fertility, thus providing accurate references for predictive model training.

[0020] The prediction model training module 30 is used to train the model based on the fertilization record information and the soil record information to generate a planting cycle-soil fertility change prediction model.

[0021] Specifically, the prediction model training module 30 uses historical data collected by the historical data acquisition module 20 to train a prediction model to predict future changes in soil fertility. For example, if a large amount of phosphate fertilizer was applied when tomatoes were grown in a certain area in the past, the model will learn the impact of this fertilization behavior on soil phosphorus content and predict how the phosphorus content in the soil will change after the next planting. By training on a large amount of historical data, the model is automatically adjusted and optimized to predict the soil fertility level after a certain crop is planted in the future.

[0022] By training the model, we can predict the trend of soil fertility changes in future planting cycles based on existing data. This allows for predictive adjustments to the fertilization process based on historical data, eliminating the need for frequent soil sampling. This reduces operational costs while improving the accuracy and scientific nature of fertilization.

[0023] The soil fertility matching module 40 is used to acquire the nutrient requirement data of the target vegetable, perform soil fertility matching based on the nutrient requirement data, and output a preset soil fertility threshold.

[0024] Specifically, nutrient requirement data refers to the nutrient components and their quantitative data required by vegetables during their growth, such as the content of elements like nitrogen, phosphorus, and potassium. The preset soil fertility threshold is the ideal soil fertility standard set based on the nutrient requirement data of the target vegetables; a value below this threshold indicates that fertilization is necessary.

[0025] The soil fertility matching module 40 first retrieves the essential nutrient types and recommended intake levels for the target vegetable from an agricultural database. For example, tomatoes require high levels of potassium and phosphorus, but have relatively low nitrogen requirements. Based on the nutrient requirements of the target vegetable, it matches the soil fertility standards needed for the vegetable's cultivation process and outputs preset soil fertility thresholds based on these standards. For example, it sets the nitrogen, phosphorus, and potassium content in the soil.

[0026] By setting reasonable soil fertility thresholds based on the nutrient requirements of vegetables, the amount of fertilizer used can be precisely controlled according to the current soil fertility, ensuring that vegetables receive sufficient nutrient support during their growth and avoiding over- or under-fertilization.

[0027] The fertilization guidance module 50 is used to drive the planting cycle-soil fertility change prediction model, output the predicted planting cycle that is less than the preset soil fertility threshold, and provide soil fertility reminders based on the predicted planting cycle.

[0028] Specifically, the fertilization guidance module 50, by driving a previously trained planting cycle-soil fertility change prediction model, predicts future soil fertility changes at the end of each planting cycle. If the prediction results show that the soil fertility in a certain cycle is lower than a preset soil fertility threshold, such as excessively low nitrogen content, it generates corresponding fertilization suggestions to remind growers to supplement nitrogen fertilizer in a timely manner, ensuring that the soil fertility level remains within the optimal range for the target crop's growth. This predictive reminder mechanism avoids the lag and blindness in fertilization decisions, improving the efficiency and accuracy of fertilization.

[0029] Furthermore, the system described in this application embodiment is also used to perform the following steps:

[0030] Access the digital soil management system to obtain the location of the soil area; based on the location of the soil area, determine whether the target vegetable has been continuously planted in the historical planting cycles of the soil area; if the target vegetable has been continuously planted in the soil area, obtain a global training instruction; based on the global training instruction, perform global model training on the fertilization record information and the soil record information to generate a planting cycle-soil fertility change prediction model.

[0031] Specifically, a digital soil management system is a system that uses digital technology to monitor and manage soil information, typically including data on the physical, chemical, and biological properties of the soil, as well as planting history, fertilizer use, etc. The system uses tools such as sensors, GPS positioning, and data analysis to achieve real-time monitoring and historical analysis of soil conditions.

[0032] First, the system connects to a digital soil management system to obtain the location information of the soil area where the target vegetable is grown, including geographic coordinates or spatial area boundaries. This allows for access to historical planting information and soil data for that plot. Based on the historical planting records of this soil area, it is determined whether the target vegetable variety has been continuously grown in that area over multiple planting cycles. Continuous planting may have a cumulative effect on soil fertility and nutrient balance. For example, if a plot of land has been planted with tomatoes for three consecutive years, this is marked as continuous planting, as continuous tomato planting may lead to the depletion of nitrogen and potassium in the soil.

[0033] If a target vegetable is detected to be continuously planted in a certain soil area, a global training command is issued to trigger extensive model training on historical fertilization and soil data for the entire soil area, generating a more comprehensive predictive model. Through this global training command, the model training process utilizes not only data from the current planting cycle but also historical data from the entire soil area, especially fertilization records and long-term trends in soil changes, to perform comprehensive global model training. This ultimately generates a planting cycle-soil fertility change predictive model covering a wider time span and spatial range. For example, fertilization, crop growth, and soil fertility change data for this soil area over the past ten years can be used to predict fertility change trends for the next few years.

[0034] For example, a plot of land may have been continuously planted with the same vegetable (such as tomatoes) for the past five years. A digital soil management system can be used to obtain the plot's geographical location and determine the continuity of planting. Subsequently, global training is triggered, using all fertilization data and soil fertility data (such as nitrogen, phosphorus, and potassium content) to train a model that predicts potential future changes in soil fertility. This predictive model will help growers develop more precise fertilization plans for the next round of tomato planting, thereby avoiding nutrient imbalances caused by long-term cultivation of the same crop.

[0035] Global training can integrate more data dimensions, including not only fertilization records for a single round, but also long-term changes in soil fertility and the cumulative impact of planting behavior on the soil. The trained predictive model can provide more comprehensive and accurate guidance for future fertilization decisions.

[0036] Furthermore, the system described in this application embodiment is also used to perform the following steps:

[0037] If the target vegetable is not continuously planted in the soil area, the soil area is divided according to the type of vegetable planted to obtain multiple soil sub-regions, wherein each soil sub-region corresponds to the same type of vegetable planted; based on the multiple soil sub-regions, multiple fertilization records and multiple soil records are obtained; based on the multiple fertilization records and multiple soil records, multiple planting cycle-soil fertility change prediction models are generated and output; based on the multiple planting cycle-soil fertility change prediction models, regional fertilization is performed on the multiple soil sub-regions.

[0038] Specifically, if the soil area where the target vegetable was grown was found to have been planted with different types of vegetables in past planting cycles, rather than the same type of vegetable continuously, then the soil area is divided into multiple sub-regions based on the types of vegetables previously grown. For example, if a plot of land was planted with tomatoes, potatoes, and carrots in its historical planting cycles, then the soil area will be divided into three sub-regions, each corresponding to a specific type of vegetable.

[0039] Multiple fertilization records and multiple soil records were acquired from these sub-regions. Each soil sub-region had its own independent fertilization records and soil fertility change data. For example, the sub-region where tomatoes were grown might have used more nitrogen fertilizer, while the sub-region where carrots were grown might have used more potassium fertilizer. This data was used for subsequent model training.

[0040] Because each sub-region has its own unique fertilization patterns and soil changes, independently trained models are needed to reflect these differences. Based on the fertilization and soil data for each sub-region, multiple planting cycle-soil fertility change prediction models are generated. These models can be used to predict future soil fertility changes in different sub-regions. For each different soil sub-region, based on its respective planting cycle-soil fertility change prediction model, the future soil fertility conditions of each sub-region are predicted, enabling precise regional fertilizer application. Appropriate amounts of nitrogen fertilizer are applied to the tomato region, phosphorus fertilizer is supplemented to the potato region, and potassium fertilizer is increased to the carrot region. This differentiated fertilization ensures that crops in each region receive the most suitable nutrients, improves the accuracy of the fertilization process, and optimizes soil nutrient distribution.

[0041] Furthermore, such as Figure 2 As shown in the embodiments of this application, the system is also used to perform the following steps:

[0042] Obtain the total planting area of ​​the soil region; obtain the planting area of ​​multiple regions corresponding to the multiple soil sub-regions; calculate the ratio coefficient of the planting area of ​​the multiple regions to the total planting area, retain N soil sub-regions that are greater than or equal to the preset ratio coefficient, and output N planting cycle-soil fertility change prediction models, where N is a positive integer greater than 1.

[0043] Specifically, the total planting area of ​​the soil region is obtained, which is the total area of ​​the entire plot that can be used for planting. Then, the planting area of ​​each soil sub-region is obtained separately. For example, a farmland has a total area of ​​5 hectares. Soil sub-region 1 (tomatoes) occupies 2 hectares, sub-region 2 (potatoes) occupies 1 hectare, and sub-region 3 (carrots) occupies 2 hectares.

[0044] Next, the proportion of the planted area in each region to the total area is calculated, that is, the proportion of the area of ​​each soil sub-region to the total planted area. For example, if the tomato region has an area of ​​2 hectares and the total area is 5 hectares, then the proportion is 2 / 5, or 40%. A preset proportion is set to retain larger soil sub-regions. The proportion of each region is compared with the preset proportion, and N soil sub-regions with a proportion greater than or equal to the preset proportion are retained, where N is a positive integer greater than 1. Models are trained on these N soil sub-regions to generate N planting cycle-soil fertility change prediction models for each soil sub-region. For example, the preset proportion is 20%. The proportion of the tomato region is 40%, the proportion of the potato region is 20%, and the proportion of the carrot region is 40%, all of which have an area proportion greater than or equal to the preset 20%, so all three sub-regions will be retained.

[0045] By screening sub-region areas, resources and efforts can be concentrated on soil sub-regions that have a greater impact on overall yield, thereby more effectively optimizing fertilization strategies and improving crop yield and quality.

[0046] Furthermore, such as Figure 3 As shown in the embodiment of this application, the prediction model training module 30 is further configured to perform the following steps:

[0047] A Markov chain distribution is established between each historical planting cycle, the fertilization record information, and the soil record information, wherein the fertilization record information is the incentive variable and the soil record information is the transition variable; the nutrient requirement data of the target vegetable is input, and the soil record information is initialized and matched for evaluation to obtain soil fertility labels; state transition training is performed based on the Markov chain distribution and the soil fertility labels to generate a planting cycle-soil fertility change prediction model.

[0048] Specifically, a Markov chain distribution is used to establish the relationship between historical planting cycles and fertilization and soil record information. Each planting cycle can be viewed as a "state" in the Markov chain, while each fertilization is the incentive variable affecting the state change, and the soil record information is the transfer variable, describing the change in soil state after each fertilization action. The Markov chain assumes that the current state depends only on the previous state and is not affected by it, thus describing the changes in soil fertility under different planting cycles and fertilization strategies. For example, in the first planting cycle, fertilization behavior (the type and amount of fertilizer applied) affects the soil nutrient status, which in turn affects the soil fertility status in the next cycle.

[0049] Input the nutrient requirements of the target vegetable, such as the nitrogen, phosphorus, and potassium content required for tomatoes. Based on this data, an initial matching assessment is performed on soil records from various historical planting cycles. By comparing the current soil fertility with the requirements of the target vegetable, a preliminary fertility status is determined, and a soil fertility label is generated, such as "high fertility" or "low fertility." This soil fertility label indicates whether the current soil is suitable for planting the target crop.

[0050] State transition training is performed using the generated Markov chain distribution and soil fertility labels. The specific training process includes defining various possible soil states based on the soil fertility labels, such as high fertility, medium fertility, and low fertility. These states are associated with the actual soil fertility level, nutrient content (such as nitrogen, phosphorus, and potassium), and other soil chemical properties. The fertility state transition probabilities are continuously adjusted using the Markov chain distribution between historical planting cycles, fertilization records, and soil records until convergence. The transition probability reflects the likelihood of soil fertility changes under the current state. Model training is complete when the state transition probabilities are essentially stable. The resulting planting cycle-soil fertility change prediction model is output. Through this training, the generated planting cycle-soil fertility change prediction model can predict how soil fertility changes under different fertilization conditions and planting cycles, providing accurate guidance for planting work.

[0051] Furthermore, the fertilization guidance module 50 described in this application embodiment is also used to perform the following steps:

[0052] The planting cycle-soil fertility change prediction model is driven to make predictions and obtain the probability that the soil fertility will be less than the preset soil fertility threshold in each future planting cycle; the planting cycle in which the probability reaches the expected probability is output as the predicted planting cycle.

[0053] Specifically, the fertilization guidance module 50 drives the planting cycle-soil fertility change prediction model, using a previously trained model to simulate future planting conditions and predict soil fertility changes at each planting cycle. For example, it can predict the trend of soil fertility changes at different points in time, such as the first planting cycle and the second planting cycle.

[0054] This planting cycle-soil fertility change prediction model outputs the probability that soil fertility will fall below a preset threshold in each future planting cycle, thereby assessing the risk of insufficient soil fertility at each point in time. An expected probability is set; only when the probability of insufficient soil fertility in a particular planting cycle reaches or exceeds this expected value will the cycle be further flagged or output as a potentially high-risk cycle. Planting cycles with probabilities reaching the expected probability are output as predicted planting cycles. These predicted planting cycles require fertilization to increase soil fertility, thereby meeting the nutrient requirements of the target vegetable during its cultivation.

[0055] The fertilization guidance module 50 uses the prediction results of the planting cycle-soil fertility change prediction model to identify the planting cycle targets that need fertilization adjustments, thereby guiding growers to increase fertilizer supply or adjust planting plans to achieve refined management in the planting process.

[0056] Furthermore, the historical planting cycle determination module 10 described in this application embodiment is also used to perform the following steps:

[0057] The target vegetable is obtained from multiple growth nodes based on each planting cycle; and the fertilization record information and soil record information of each growth node are obtained separately; based on the multiple growth nodes corresponding to each historical planting cycle, the fertilization record information and soil record information of each growth node are obtained to obtain the updated Markov chain distribution.

[0058] Specifically, based on the existing historical planting cycles, the fertilization and soil data records for each key time point (i.e., growth node) in the vegetable growth process are further refined, and these refined data are integrated into the prediction model to improve the accuracy and precision of the model and achieve refined prediction of vegetable growth nodes.

[0059] This method acquires multiple growth nodes for the target vegetable in each planting cycle. For example, a tomato planting cycle may include different growth nodes such as sowing, germination, flowering, and fruiting. Each growth node is broken down, and fertilization and soil records for each node are obtained separately. Using the fertilization and soil data of these nodes, the soil state of each node is treated as a state in a Markov chain. The fertilization behavior of each node is used as an incentive variable to progressively transition to the soil state of the next stage, thereby updating the original Markov chain distribution. For example, soil changes after fertilization at the sowing stage will affect the germination stage, and fertilization at the flowering stage will further change soil fertility. The original Markov chain model only relied on the overall fertilization and soil data of each planting cycle to predict fertility changes. With the addition of each growth node, the model can make more detailed predictions of soil fertility changes at each key time point.

[0060] For example, a tomato growing cycle includes four growth stages: sowing, germination, flowering, and fruiting. Fertilization and soil record information for each stage is as follows:

[0061] Sowing period: Nitrogen fertilizer was applied, which increased the nitrogen content in the soil and kept the pH value stable.

[0062] Germination period: Phosphate fertilizer was applied, which increased the phosphorus content in the soil.

[0063] Flowering period: Potassium fertilizer was applied, which increased the potassium content in the soil but decreased the nitrogen content.

[0064] Fruiting period: No fertilizer is applied, and soil fertility gradually declines.

[0065] Based on the data from each node, the soil state of each node is treated as a state in a Markov chain. Using the fertilization behavior of each node as an incentive variable, the soil state is progressively transitioned to the next stage. Ultimately, through the updated Markov chain distribution, the changes in soil fertility at each growth node in the next planting cycle are more accurately predicted, and more precise fertilization recommendations are provided.

[0066] Furthermore, the historical planting cycle determination module 10 described in this application embodiment is also used to perform the following steps:

[0067] Obtain the soil fertility metabolism curve; based on the soil fertility metabolism curve, obtain the step size that limits the number of historical planting cycles.

[0068] Specifically, the historical planting cycle determination module 10 uses soil fertility metabolism curves to further analyze historical planting data and determine the historical planting cycle step size in order to obtain accurate and reliable model training data.

[0069] Soil fertility metabolism curves refer to the changing trends of soil fertility over different time periods. These curves can be obtained by depicting the dynamic changes in soil fertility influenced by various factors such as fertilization practices, rainfall, and crop growth. For example, sensors can be used to monitor the long-term changes in the content of nutrients such as nitrogen, phosphorus, and potassium in the soil, and this data can be plotted as a time series curve to show the dynamic changes in soil fertility. Typical patterns of soil fertility change can be identified through soil fertility metabolism curves.

[0070] Obtain soil fertility metabolism curves and analyze the trends in soil fertility over time to identify key time points where soil fertility rises, stabilizes, or declines in different planting cycles. Based on the metabolism curve analysis results, assess which historical planting cycles are most important for the current analysis, and set an appropriate historical data analysis period or span (step size) to limit the number of planting cycles to be analyzed, avoid processing excessive data, optimize computational resources, and focus the analysis on the most relevant planting cycles.

[0071] If the metabolic curve shows significant changes in soil fertility between certain cycles, indicating drastic changes, a smaller step size can be chosen to perform detailed analysis cycle by cycle. Conversely, if the metabolic curve shows minimal changes in soil fertility between certain cycles, indicating stable changes, a larger step size can be chosen to skip certain cycles without detailed analysis. By limiting the step size based on the number of historical planting cycles, computational resources can be allocated rationally, focusing on analyzing data from important cycles. This ensures the accuracy of the prediction model while avoiding unnecessary computational burden.

[0072] In summary, the intelligent fertilization system driven by vegetable nutrient requirement analysis provided in this application has the following technical effects:

[0073] The historical planting cycle determination module 10 acquires the soil area where the target vegetable is planted and determines the historical planting cycle of the soil area, providing a data foundation for subsequent fertilization decisions. The historical record collection module 20 collects fertilization record information and soil record information corresponding to each planting cycle, providing comprehensive data support for model training. The prediction model training module 30 trains the model based on the fertilization record information and the soil record information using a Markov chain, generating an accurate planting cycle-soil fertility change prediction model to avoid frequent soil sampling before planting and reduce operating costs. The soil fertility matching module 40 acquires the nutrient requirement data of the target vegetable, performs soil fertility matching based on the nutrient requirement data, outputs a preset soil fertility threshold, and thus accurately controls the amount of fertilizer used, avoiding over- or under-fertilization. The fertilization guidance module 50 drives the planting cycle-soil fertility change prediction model, outputs predicted planting cycles that are lower than the preset soil fertility threshold, and provides soil fertility reminders based on the predicted planting cycles to guide the grower's fertilization operations, ensuring that the soil fertility level is always within the optimal range for the growth of the target crop.

[0074] In summary, this application, through the collection and analysis of historical planting and fertilization data, utilizes predictive models to anticipate changes in soil fertility in advance, and combines this with the nutrient requirements of vegetables to provide intelligent fertilization matching and guidance, ensuring that crops receive adequate nutrients. At the same time, it avoids the complex operation of frequently collecting soil fertility data in the traditional fertilization process, significantly improving the accuracy and efficiency of fertilization, and greatly enhancing the efficiency and scientific nature of agricultural production.

[0075] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily 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 this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An intelligent fertilization system driven by vegetable nutrient requirement analysis, characterized in that, The system includes: A historical planting cycle determination module is used to obtain the soil area where the target vegetable is planted and determine the historical planting cycle of the soil area. The historical record acquisition module is used to collect fertilization record information and soil record information corresponding to each planting cycle. A prediction model training module is used to train the model based on the fertilization record information and the soil record information to generate a planting cycle-soil fertility change prediction model. A soil fertility matching module is used to acquire the nutrient requirement data of the target vegetable, perform soil fertility matching based on the nutrient requirement data, and output a preset soil fertility threshold. The fertilization guidance module is used to drive the planting cycle-soil fertility change prediction model, output the predicted planting cycle that is less than the preset soil fertility threshold, and provide soil fertility reminders based on the predicted planting cycle. The prediction model training module is also used to perform the following steps: Establish a Markov chain distribution between each historical planting cycle, the fertilization record information, and the soil record information, wherein the fertilization record information is the incentive variable and the soil record information is the transition variable; Input the nutrient requirement data of the target vegetable, perform initial matching and evaluation on the soil record information, and obtain soil fertility tags; Based on the Markov chain distribution and the soil fertility label, a state transition training is performed to generate a planting cycle-soil fertility change prediction model. The fertilization guidance module is also used to perform the following steps: The planting cycle-soil fertility change prediction model is driven to make predictions and obtain the probability that the soil fertility will be less than the preset soil fertility threshold in each future planting cycle. The planting round in which the probability reaches the expected probability is output as the predicted planting round; The historical planting cycle determination module is also used to perform the following steps: The target vegetable is obtained based on multiple growth nodes in each planting cycle; It also separates and obtains fertilization records and soil records for each growth node; Based on multiple growth nodes corresponding to each historical planting cycle, and the fertilization record information and soil record information of each growth node, the updated Markov chain distribution is obtained.

2. The intelligent fertilization system driven by vegetable nutrient requirement analysis as described in claim 1, characterized in that, After obtaining the soil area for planting the target vegetables, the system is also used to perform the following steps: Access the digital soil management system to obtain the location of the soil area; Based on the location of the soil area, determine whether the target vegetable has been continuously planted in the historical planting cycles of the soil area. If the target vegetable has been continuously planted in the soil area, obtain the global training instruction. According to the global training instructions, a global model is trained on the fertilization record information and the soil record information to generate a planting cycle-soil fertility change prediction model.

3. The intelligent fertilization system driven by vegetable nutrient requirement analysis as described in claim 2, characterized in that, The system is also used to perform the following steps: If the target vegetable is not continuously planted in the soil area, the soil area is divided according to the type of vegetable planted to obtain multiple soil sub-regions, wherein each soil sub-region corresponds to the planting of the same type of vegetable; Based on the multiple soil sub-regions, obtain multiple fertilization record information and multiple soil record information; Training is performed based on the multiple fertilization records and multiple soil records to output multiple planting cycle-soil fertility change prediction models; Based on the multiple planting cycle-soil fertility change prediction models, regional fertilization is carried out in the multiple soil sub-regions.

4. The intelligent fertilization system driven by vegetable nutrient requirement analysis as described in claim 3, characterized in that, The system is also used to perform the following steps: Obtain the total planting area of ​​the soil region; Obtain the planting area of ​​multiple regions corresponding to the multiple soil sub-regions; Calculate the proportion coefficient of the planting area of ​​the multiple regions to the total planting area, retain N soil sub-regions that are greater than or equal to the preset proportion coefficient, and output N planting cycle-soil fertility change prediction models, where N is a positive integer greater than 1.

5. The intelligent fertilization system driven by vegetable nutrient requirement analysis as described in claim 1, characterized in that, The historical planting cycle determination module is also used to perform the following steps: Obtain soil fertility metabolism curves; Based on the soil fertility metabolism curve, obtain the step size that limits the number of historical planting cycles.

Images