An agricultural planting operation and maintenance management system based on a cloud platform

Abstract

The application relates to the technical field of agricultural management, in particular to an agricultural planting operation and management system based on a cloud platform, which comprises a bottom data image module, a standard demand superposition module, a real-time environment correction module and a penetrating reading control module. The bottom data image module collects soil nutrients to construct a background attribute set and solidifies the background attribute set into a bottom read-only image. The standard demand superposition module generates a standard fertilizer demand time sequence, encapsulates the standard fertilizer demand time sequence into an intermediate layer read-only image and superimposes the intermediate layer read-only image to generate a composite static view. The real-time environment correction module calculates a metabolic deviation coefficient based on temperature and radiation, writes the metabolic deviation coefficient into a mounted storage layer and generates a dynamic environment correction layer. The penetrating reading control module penetrates and extracts data to calculate net fertilizer demand and generates a fertilization control signal. In the application, a reference is established by constructing a composite static view, data layer fusion is realized by combining a dynamic environment correction layer, net fertilizer demand is accurately calculated by using a penetrating reading mechanism, a fertilization strategy is corrected in real time, manual input lag and errors are eliminated, and the adaptability and control precision of agricultural resource scheduling are improved.

Description

Technical Field

[0001] This invention relates to the field of agricultural management technology, and in particular to an agricultural planting operation and maintenance management system based on a cloud platform. Background Technology

[0002] This invention relates to the field of agricultural management technology, specifically the comprehensive technology of monitoring, allocating resources, and maintaining data throughout the entire agricultural production process using information technology. Traditional agricultural planting and operation management systems rely on manual field inspections and paper-based records of crop sowing times, fertilizer types, and irrigation amounts. Alternatively, operators in offices use standalone computers to input soil temperature and humidity data from handheld sensors into spreadsheet software installed on their local hard drives. All production data is stored as physical documents or offline files in specific filing cabinets or computer terminals.

[0003] Traditional agricultural planting and operation management relies on regular manual inspections and paper-based records. Data is read from handheld instruments and entered into local hard drives via keyboards. This results in production data being stored in physical documents or offline files on specific terminals, creating isolated islands of agricultural information. This makes it difficult to achieve real-time data sharing and synchronous updates, and data transmission and processing are severely lagging. Managers can only make decisions based on historical static data and cannot respond promptly to instantaneous changes in the crop growth environment. The manual transcription process is prone to human error and data backtracking is difficult, hindering in-depth correlation analysis between soil background properties and crop nutrient requirements. Consequently, resource scheduling instructions such as fertilization and irrigation lack precise basis, severely reducing the efficiency and response speed of agricultural production management. Summary of the Invention

[0004] The purpose of this invention is to address the shortcomings of existing technologies by proposing a cloud-based agricultural planting operation and maintenance management system.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: an agricultural planting operation and maintenance management system based on a cloud platform, the system comprising:

[0006] The underlying data mirroring module collects soil nitrogen, phosphorus, and potassium content and constructs a soil background attribute set, maps the soil background attribute set into a binary file set, and solidifies the binary file set into an underlying read-only mirror file;

[0007] The standard demand overlay module obtains crop varieties and yields, generates theoretical nitrogen, phosphorus and potassium values ​​and constructs a standard fertilizer requirement time series, encapsulates the standard fertilizer requirement time series as an intermediate layer read-only image file and overlays it onto the bottom layer read-only image file to generate a composite static view.

[0008] The real-time environment correction module acquires temperature and radiation, sets a temperature threshold, compares the temperature with the temperature threshold and calculates the metabolic rate deviation coefficient, mounts a read-write data storage layer on the composite static view and writes the metabolic rate deviation coefficient to generate a dynamic environment correction layer.

[0009] The penetrating reading control module extracts the metabolic rate deviation coefficient, the theoretical nitrogen, phosphorus, and potassium values, and the soil background attribute set from the dynamic environment correction layer. It calculates the product of the theoretical nitrogen, phosphorus, and potassium values ​​and the metabolic rate deviation coefficient, and subtracts the soil background attribute set to generate the net fertilizer requirement value, thus generating a fertilization control signal.

[0010] As a further aspect of the present invention, the specific functional implementation of the underlying data mirroring module is as follows:

[0011] The data acquisition and analysis submodule acquires the soil nitrogen, phosphorus and potassium content through an electrochemical sensor array deployed in farmland, uses the Kriging interpolation algorithm to perform spatial smoothing on the sampling point data, eliminates measurement noise and completes the data of unsampled areas, and constructs the soil background attribute set containing the nutrient distribution characteristics of the entire region.

[0012] The binary stream mapping submodule traverses each attribute node in the soil background attribute set, converts the floating-point nutrient concentration data into a fixed-length binary encoding format, and reassembles the encoding into a continuous bit stream according to the grid order of geographic coordinates to generate the binary file set.

[0013] The read-only image solidification submodule calls the file system driver to write the binary file set into the protected sector of the non-volatile storage medium and sets the read-only attribute bit to prohibit overwrite or modification operations, thereby generating the underlying read-only image file.

[0014] As a further aspect of the present invention, the specific function of the standard requirement overlay module is as follows:

[0015] The theoretical numerical generation submodule analyzes the crop variety and yield to determine the growth cycle characteristics of the target crop, queries the agronomic knowledge graph to obtain the ideal nutrient absorption curves of the crop at different growth stages, and calculates and generates the theoretical nitrogen, phosphorus and potassium values ​​corresponding to each growth stage in combination with the target yield setting.

[0016] The time series construction submodule discretizes the theoretical nitrogen, phosphorus and potassium values ​​in days, and smooths the differences in nutrient requirements between adjacent time points through cubic spline interpolation algorithm to construct the standard fertilizer requirement time series containing the daily fertilizer requirement for the entire growth cycle.

[0017] The view overlay generation submodule encapsulates the standard required time series into an independent read-only file system image and uses it as the intermediate layer read-only image file. It then uses union file system technology to overwrite and mount the underlying read-only image file in read-only mode to generate the composite static view.

[0018] As a further aspect of the present invention, the construction process of the standard fertilizer demand time series specifically includes:

[0019] Key phenological nodes in the crop growth model were obtained, and the start and end times of each stage, including tillering, jointing, heading, and grain-filling stages, were extracted.

[0020] Based on the duration of each phenological period, the theoretical nitrogen, phosphorus, and potassium values ​​are allocated to the corresponding time periods, and a growth rate adjustment factor is introduced to weight the daily values ​​within each time period.

[0021] The generated sequence data is normalized and a timestamp index is added to establish a mapping relationship between the time dimension and the fertilizer demand value, thereby generating the standard fertilizer demand time series.

[0022] As a further aspect of the present invention, the specific function of the real-time environment correction module is as follows:

[0023] The environmental monitoring and comparison submodule monitors the temperature and radiation in the farmland in real time through the Internet of Things weather station, obtains the preset optimal temperature range for crop photosynthesis as the temperature threshold, and judges whether the actual temperature deviates from the optimal range.

[0024] The deviation coefficient calculation submodule, when the actual temperature exceeds the temperature threshold, combines the current photosynthetically active radiation intensity, calls the crop metabolic response model to calculate the degree to which the photosynthetic rate is affected by temperature stress or radiation promotion, and quantifies and generates the metabolic rate deviation coefficient.

[0025] The dynamic layer is mounted and written to the submodule. A volatile storage space that supports random read and write is initialized at the top layer of the composite static view as the read and write data storage layer. The metabolic rate deviation coefficient is written to this layer in real time using the copy-on-write mechanism to generate the dynamic environment correction layer.

[0026] As a further aspect of the present invention, the calculation process of the metabolic rate deviation coefficient specifically includes:

[0027] Acquire the monitored real-time temperature values, photosynthetically active radiation intensity, and standard growth reference temperature;

[0028] Based on the modified form of the Arrhenius equation, the metabolic rate deviation coefficient is calculated using the following formula:

[0029] ;

[0030] in, This represents the metabolic rate deviation coefficient. The activation energy constant representing the enzyme-catalyzed reaction in crops. Represents the ideal gas constant. This represents the standard growth reference temperature. This represents the real-time temperature value. Represents the radiation sensitivity modulator. This represents the photosynthetically active radiation intensity. This represents the baseline value for basic radiation intensity.

[0031] As a further aspect of the present invention, the specific function of the penetration reading control module is as follows:

[0032] The data penetration extraction submodule utilizes the penetration reading mechanism of the union file system to prioritize reading the metabolic rate deviation coefficient from the dynamic environment correction layer. If the reading fails, it backtracks to the lower layer and directly reads the corresponding theoretical nitrogen, phosphorus, and potassium values ​​and the soil background attribute set from the lower layer image.

[0033] The net fertilizer requirement calculation submodule inputs the read data into the nutrient balance algorithm model, performs weighted calculation processing, and obtains the net fertilizer requirement value that reflects the actual needs of crops under the current environmental pressure.

[0034] The signal conversion and generation submodule maps the net fertilizer requirement value to the action parameters of the fertilizer application actuator, and outputs a pulse width modulation waveform through the digital-to-analog conversion interface to generate the fertilizer application control signal.

[0035] As a further aspect of the present invention, the calculation process for the net fertilizer requirement specifically includes:

[0036] Obtain the theoretical values ​​of nitrogen, phosphorus, and potassium from the theoretical nitrogen, phosphorus, and potassium values, and simultaneously obtain the corresponding soil background content values;

[0037] The net fertilizer requirement is calculated using the following formula:

[0038] ;

[0039] in, This represents the net fertilizer requirement. This represents the theoretical nitrogen, phosphorus, and potassium values. This represents the metabolic rate deviation coefficient. Nutrient content values ​​representing the aforementioned soil background properties. The coefficient representing the effective utilization rate of soil nutrients. This represents the compensation increment value set due to leaching loss.

[0040] As a further aspect of the present invention, the process of generating the fertilization control signal specifically includes:

[0041] Obtain the net fertilizer requirement value and the rated flow parameters of the fertilizer pipeline, and calculate the opening time of the fertilizer valve required to meet the fertilizer requirement;

[0042] Convert the on duration into the corresponding duty cycle value, and configure the timer register to generate a square wave signal with a specific frequency and duty cycle;

[0043] The square wave signal is amplified by an opto-isolation circuit to output the fertilization control signal.

[0044] As a further aspect of the present invention, the security verification process before the fertilization control signal is generated specifically includes:

[0045] Obtain historical fertilization records and the current leaf area index of the crop to calculate the safe threshold for the total cumulative fertilization amount;

[0046] The net fertilizer requirement is compared with the safety threshold. If the threshold is exceeded, an alarm is triggered and the output is automatically cut off. If the threshold is not exceeded, the fertilization control signal is allowed to be generated.

[0047] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0048] In this invention, a read-only image of the soil nitrogen, phosphorus, and potassium content is constructed and superimposed with a standard fertilizer requirement time series generated based on crop varieties. This creates a composite static view that includes background attributes and theoretical requirements, establishing a stable data reference benchmark. The metabolic rate deviation coefficient is calculated by combining real-time temperature and radiation data. Dynamic environmental parameters are written into the mounted read-write data storage layer, achieving hierarchical management and fusion of static basic data and dynamic environmental data. A penetrating reading mechanism is used to extract multi-layer data, automatically calculate the product of theoretical values ​​and deviation coefficients, and subtract background attributes to obtain accurate net fertilizer requirements. Under the premise of ensuring the consistency of basic data, the fertilization strategy is corrected in real time, completely eliminating the lag and error of manual data entry, and significantly improving the environmental adaptability and control accuracy of agricultural resource scheduling. Attached Figure Description

[0049] Figure 1 This is a schematic diagram of the principle of an agricultural planting operation and maintenance management system based on a cloud platform according to the present invention.

[0050] Figure 2 This is a flowchart illustrating the construction process of the underlying read-only image of this invention.

[0051] Figure 3 This is a flowchart illustrating the process of generating a composite static view according to the present invention.

[0052] Figure 4 This is a flowchart of the dynamic environment correction layer generation process of the present invention;

[0053] Figure 5 This is a flowchart of the fertilization control signal generation process of the present invention. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of this invention clearer, the software-based technical solution is described in detail below with reference to system architecture diagrams and embodiments. It should be understood that the specific embodiments described herein are only for explaining the technical solutions of this invention and do not constitute a limitation on the scope of protection.

[0055] In the description of this invention, the system architecture relationships or data processing flows indicated by terms such as "layer," "module," "interface," "data flow," "client," and "server" are all defined based on the architecture diagram or flowchart corresponding to the embodiments. This way of describing is only used to clearly illustrate the logical relationships between the elements in the technical solution, and not to limit the physical deployment form. The term "multiple" includes two or more technical units, including but not limited to multiple data nodes, processing threads, service instances, or functional components and other scalable elements. The specific number is determined according to the actual business scenario and needs to be specifically specified.

[0056] Please see Figure 1 and Figure 2 This invention provides a technical solution: an agricultural planting operation and maintenance management system based on a cloud platform, comprising:

[0057] The underlying data mirroring module collects soil nitrogen, phosphorus and potassium content and constructs a soil background attribute set, maps the soil background attribute set into a binary file set, and solidifies the binary file set into an underlying read-only mirror file.

[0058] The specific functional implementation of the underlying data mirroring module is as follows:

[0059] The data acquisition and analysis submodule obtains soil nitrogen, phosphorus and potassium content through an electrochemical sensor array deployed in farmland, uses the Kriging interpolation algorithm to perform spatial smoothing on the sampling point data, eliminates measurement noise and completes the data of unsampled areas, and constructs a soil background attribute set containing the nutrient distribution characteristics of the entire region.

[0060] The binary stream mapping submodule iterates through each attribute node in the soil background attribute set, converts the floating-point nutrient concentration data into a fixed-length binary encoding format, and reassembles the encoding into a continuous bit stream according to the grid order of geographic coordinates to generate a binary file set.

[0061] The read-only image solidification submodule calls the file system driver to write the binary file set to the protected sectors of the non-volatile storage medium and sets the read-only attribute bit to prevent overwrite or modification operations, generating the underlying read-only image file.

[0062] The data acquisition and analysis submodule performs data acquisition tasks through an electrochemical sensor array deployed in the farmland area. In this embodiment, a 50-mu standardized wheat demonstration field was selected as the data acquisition target. The field was divided into 10m × 10m grid units, with a total of 330 monitoring nodes. Each monitoring node is equipped with a high-precision ion-selective electrode (ISE) sensor, with the sensor probe buried in the active root layer of the crop (20cm underground). After the system is powered on, the microcontroller reads the millivolt-level potential difference signal output by the sensor at a frequency of 50Hz through the ADC channel. Based on the Nernst Equation, the potential difference is mapped to the molar concentration of nitrogen (N), phosphorus (P), and potassium (K) ions in the soil. The acquisition controller performs filtering operations on 50 sets of data continuously acquired from a single point, removing the maximum and minimum values, and calculates the arithmetic mean of the remaining data as the measured nutrient content of that grid point. For unsampled blank areas caused by terrain obstacles or equipment failure, the system calls the Kriging interpolation algorithm engine. The algorithm first calculates the semivariogram values ​​among known sampling points, constructs a semivariogram model (using a spherical model), and determines the nugget value, sill value, and range parameter. Then, using the unknown point as the center, it searches for effective sampling points in the neighborhood, constructs a system of linear equations to solve for the weighting coefficients, and calculates the nutrient estimate for the unknown point using a weighted summation method, thereby generating a complete set of soil background attributes covering the entire region.

[0063] The aforementioned Kriging interpolation algorithm is a spatial interpolation method based on geostatistics. Its core lies in using the original data of regionalized variables and the structural characteristics of the variogram to make unbiased optimal estimates of the attribute values ​​of unsampled points, which can effectively reflect the spatial correlation of geographical attributes.

[0064] The binary stream mapping submodule initiates a memory traversal program, sequentially reading the data of each attribute node in the soil background attribute set according to the grid scanning order from the northwest corner (0,0) to the southeast corner (x,y) in the geographic coordinate system. For the three floating-point concentration values ​​(unit: mg / kg) of nitrogen, phosphorus, and potassium contained in each node, the system follows the IEEE 754 single-precision floating-point standard to convert them into 32-bit binary codes. For example, if the available nitrogen content of a node is 45.625 mg / kg, the system converts it to hexadecimal representation 0x42368000, and then maps it to the binary sequence 01000010001101101000000000000000. The program allocates a contiguous memory buffer, concatenates the converted binary codes end-to-end in the order of "Grid_ID-N_Code-P_Code-K_Code", without adding any delimiters or metadata headers, forming a compact pure binary bit stream. This process eliminates the parsing overhead associated with JSON or XML formats, ensuring efficient data transmission at the underlying level.

[0065] The read-only image solidification submodule calls the operating system kernel's file system driver (SquashFS driver) to lock a segment of physically contiguous non-volatile storage medium (a specific partition of an industrial-grade eMMC storage chip). The driver directly writes the generated binary bitstream to this partition. After writing, the system sends an instruction to the storage control register to set the write protection flag in the partition's attribute bit to 1. Subsequently, the system calculates the MD5 hash checksum of the binary file set and stores it in the partition's superblock as an integrity verification benchmark. At this point, this storage area exposes only a read-only interface to upper-layer applications. Any write operation instructions (Write, Append, Truncate) targeting this area will be directly intercepted by the kernel I / O scheduler and return a "PermissionDenied" error code, thus generating an immutable underlying read-only image file.

[0066] Table 1 shows a partial data fragment of the soil background attribute set collected and constructed by the system:

[0067] Table 1 Soil background attribute set and binary mapping table

[0068] ;

[0069] Please see Figure 1 and Figure 3 The standard demand overlay module obtains crop varieties and yields, generates theoretical nitrogen, phosphorus and potassium values ​​and constructs a standard fertilizer requirement time series, encapsulates the standard fertilizer requirement time series as an intermediate layer read-only image file and overlays it onto the bottom layer read-only image file to generate a composite static view.

[0070] The specific functional implementation of the standard requirement overlay module is as follows:

[0071] The theoretical numerical generation submodule analyzes crop varieties and yields to determine the growth cycle characteristics of the target crop, queries the agronomic knowledge graph to obtain the ideal nutrient absorption curves of the crop at different growth stages, and calculates and generates the theoretical nitrogen, phosphorus and potassium values ​​corresponding to each growth stage in combination with the target yield setting.

[0072] The time series construction submodule discretizes the theoretical nitrogen, phosphorus and potassium values ​​in days, and smooths the differences in nutrient requirements between adjacent time points through cubic spline interpolation algorithm to construct a standard fertilizer requirement time series that includes the daily fertilizer requirement for the entire growth cycle.

[0073] The construction process of the standard fertilizer requirement time series includes the following:

[0074] Key phenological nodes in the crop growth model were obtained, and the start and end times of each stage, including tillering, jointing, heading, and grain-filling stages, were extracted.

[0075] Based on the duration of each phenological period, the theoretical nitrogen, phosphorus, and potassium values ​​are allocated to the corresponding time periods, and a growth rate adjustment factor is introduced to weight the daily values ​​within each time period.

[0076] The generated sequence data is normalized and a timestamp index is added to establish a mapping relationship between the time dimension and the fertilizer demand value, thereby generating a standard fertilizer demand time series.

[0077] The view overlay generation submodule encapsulates the standard required time series into an independent read-only file system image and uses it as an intermediate read-only image file. It then uses union file system technology to overwrite and mount the underlying read-only image file in read-only mode to generate a composite static view.

[0078] The theoretical numerical generation submodule receives the crop variety parameter "Winter Wheat - Jingdong 22" and the target yield setting "600 kg / mu" input by the user. The system kernel analyzes the genotype characteristics of the variety and determines its entire growth period to be 230 days. Subsequently, the program accesses the locally integrated agronomic knowledge graph database through SQL query commands to retrieve the nutrient absorption coefficients of the variety at different growth stages (greening stage, jointing stage, heading stage, and grain-filling stage). Based on the product relationship between the target yield and the nutrient absorption coefficient, the system calculates the total fertilizer requirement for each stage. For example, if the knowledge graph data shows that "Jingdong 22" requires 3.0 kg of pure nitrogen to produce 100 kg of grain, then the total nitrogen requirement for the entire growth period corresponding to a yield of 600 kg is 18.0 kg. The system further decomposes this total according to the distribution ratio of each growth stage (jointing stage accounts for 40%), resulting in a theoretical total nitrogen requirement of 7.2 kg at the jointing stage. Similarly, the theoretical total requirements of phosphorus and potassium at each stage are calculated, generating a set of theoretical nitrogen, phosphorus, and potassium values ​​for each stage.

[0079] The time-series construction submodule performs the discretization task of the time dimension. The system first extracts key phenological nodes from the crop growth model and defines the time span of each stage. The greening stage is set as February 20th to March 10th (20 days), and the jointing stage as March 11th to April 5th (26 days). For the total nitrogen requirement of 7.2 kg during the jointing stage, the system introduces a growth rate factor (GRF). The GRF exhibits a normal distribution characteristic, simulating the rapid growth of the crop in the middle of the stage. The system uses a cubic spline interpolation algorithm, with the average daily fertilizer requirement at the start, end, and midpoint of the stage as control points, to construct a smooth daily fertilizer requirement curve function. Each day during the jointing period Substitute into function The algorithm calculates the specific fertilizer requirement for each day, ensuring that the total integral over 26 days is strictly equal to 7.2 kg. For the boundary between adjacent growth stages (March 10th and March 11th), the algorithm performs boundary smoothing to eliminate abrupt changes.

[0080] After processing, the system normalizes and encapsulates the daily data, defining the data format as "timestamp_N demand_P demand_K demand". All daily data are arranged in chronological order, and an index table is created at the beginning of the file to map dates to file offsets, generating a standard demand time series.

[0081] The view overlay generation submodule creates an independent file system image (CRAMFS format) and writes the standard fertilizer requirement time series into it. Then, using the Linux kernel's OverlayFS union file system technology, the mount command is executed: `mount -t overlay overlay-olowerdir= / mnt / soil_base,upperdir= / mnt / crop_std,workdir= / work / mnt / merged_view`. This command overlays the intermediate layer image containing crop fertilizer requirement data onto the underlying image containing soil baseline data in read-only mode, logically merging them into a unified directory tree structure ` / mnt / merged_view`. At this point, when an application accesses a grid file in this directory, the system automatically presents a data view overlaid with soil properties and crop standard requirements, generating a composite static view.

[0082] The aforementioned OverlayFS union file system technology refers to a union mount file system implementation for Linux. It allows two or more directories (called layers) to be merged and presented as a unified directory view, where files in the upper-level directory will overwrite files with the same name in the lower-level directory, thereby achieving hierarchical management and view overlay.

[0083] Please see Figure 1 and Figure 4 The real-time environment correction module acquires temperature and radiation, sets a temperature threshold, compares the temperature with the temperature threshold and calculates the metabolic rate deviation coefficient, mounts a read-write data storage layer on the composite static view and writes the metabolic rate deviation coefficient to generate a dynamic environment correction layer.

[0084] The specific functions of the real-time environment correction module are as follows:

[0085] The environmental monitoring and comparison submodule monitors the temperature and radiation in the farmland in real time through the Internet of Things weather station, obtains the preset optimal temperature range for crop photosynthesis as the temperature threshold, and judges whether the actual temperature deviates from the optimal range.

[0086] The deviation coefficient calculation submodule, when the actual temperature exceeds the temperature threshold, combines the current photosynthetically active radiation intensity, calls the crop metabolic response model to calculate the degree to which the photosynthetic rate is affected by temperature stress or radiation promotion, and quantifies and generates the metabolic rate deviation coefficient.

[0087] The calculation process for the metabolic rate deviation coefficient specifically includes:

[0088] Acquire the monitored real-time temperature values, photosynthetically active radiation intensity, and standard growth reference temperature;

[0089] Based on the modified form of the Arrhenius equation, the metabolic rate deviation coefficient is calculated using the following formula:

[0090] in, This represents the metabolic rate deviation coefficient. The activation energy constant representing the enzyme-catalyzed reaction in crops. Represents the ideal gas constant. Represents the standard growth reference temperature. Represents the real-time temperature value. Represents the radiation sensitivity modulator. Represents the photosynthetically active radiation intensity. Represents the baseline value for basic radiation intensity;

[0091] The dynamic layer is mounted and written to the submodule. A volatile storage space that supports random read and write is initialized at the top layer of the composite static view as a read and write data storage layer. The metabolic rate deviation coefficient is written to this layer in real time using the copy-on-write mechanism to generate a dynamic environment correction layer.

[0092] The environmental monitoring and comparison submodule connects to the farmland micro-weather station via an RS-485 bus, polling and reading the current air temperature every 1 minute. ) and photosynthetically active radiation intensity ( The system's internal registers are preset with the optimal temperature range (18°C, 25°C) for photosynthesis during the winter wheat jointing stage. During system operation, the time was set to 14:00 on May 15th, and the system collected real-time temperatures. At 32°C, the real-time radiation intensity 1200 Logical comparison unit determination Upon confirming that the current environment exceeds the suitable range and is under high temperature and strong light stress, the deviation coefficient calculation submodule is immediately triggered.

[0093] The deviation coefficient calculation submodule quantifies changes in crop metabolic rates by invoking a modified form of the Arrhenius equation based on collected environmental variables and preset parameters. The system calculates the metabolic rate deviation coefficient using the following formula:

[0094] ;

[0095] in, The metabolic rate deviation coefficient is used to quantify the degree to which environmental stress corrects the standard nutrient uptake rate of crops. The activation energy constant representing crop enzyme-catalyzed reactions is set as follows: This reflects the sensitivity of the crop's internal biochemical reactions to temperature changes; Represents the ideal gas constant, using the standard value. ; Represents the standard growth reference temperature (Kelvin units), with a value of (Corresponding to 25°C); This represents the real-time temperature value (Kelvin units), with a range of values. (Corresponding to 32°C); This represents the radiation sensitivity adjustment factor, with values ​​ranging from [value missing]. This is used to adjust the contribution weight of the radiation enhancement term to the total bias; Represents the photosynthetically active radiation intensity, with a value of ; This represents the baseline radiation intensity, i.e., the standard radiation at the light saturation point, and its value is... .

[0096] The advantage of the formula is that by introducing the exponential term of the Arrhenius equation, it accurately simulates the nonlinear acceleration effect of temperature increase on the rate of enzyme-catalyzed reaction. At the same time, combined with the linear correction of the radiation enhancement factor, it comprehensively reflects the phenomenon of accelerated nutrient metabolism caused by the dual increase in crop respiration consumption and photosynthetic demand under high temperature and high light conditions.

[0097] The specific calculation process is as follows:

[0098] The first step is to calculate the temperature effect index. Temperature difference term: Index section: Temperature coefficient: .

[0099] The second step is to calculate the linear term of the radiation effect. Radiation increment ratio: Emissivity: .

[0100] The third step is to calculate the total deviation coefficient. The result This indicates that under the current high temperature of 32°C and radiation intensity of 1200, the actual metabolic fertilizer requirement rate of crops is 2.28 times that under standard conditions.

[0101] Table 2 shows the calculation parameters and results of the real-time environment correction module under different environmental conditions:

[0102] Table 2 Environmental Correction Parameters and Calculation Results

[0103] ;

[0104] The dynamic layer mounting and writing submodule initializes a RAM-based TmpFS file system at the top layer of the composite static view, with a size set to 64MB, as a read-write data storage layer. The system utilizes UnionFS's Copy-On-Write (CoW) mechanism to calculate the data without modifying the underlying read-only image. The state file corresponding to that layer is written to it. At this point, the state parameters of that grid point in the file system view are dynamically updated, generating a dynamic environment correction layer.

[0105] The Copy-On-Write (CoW) mechanism mentioned above is a resource management technique that, when the system needs to modify data, does not directly overwrite the original data, but instead copies the original data to a new location for modification, thereby ensuring the integrity of the original data and the security of concurrent access.

[0106] Please see Figure 1 and Figure 5 The system penetrates the reading control module, extracts the metabolic rate deviation coefficient, theoretical nitrogen, phosphorus and potassium values ​​and soil background attribute set from the dynamic environment correction layer, calculates the product of theoretical nitrogen, phosphorus and potassium values ​​and metabolic rate deviation coefficient and subtracts the soil background attribute set to generate net fertilizer requirement value, and generates fertilization control signal.

[0107] The specific functions of the penetration reading control module are as follows:

[0108] The data penetration extraction submodule utilizes the penetration reading mechanism of the union file system to prioritize reading the metabolic rate deviation coefficient from the dynamic environment correction layer. If the reading fails, it backtracks to the lower layer and directly reads the corresponding theoretical nitrogen, phosphorus, and potassium values ​​and soil background attribute set from the lower layer image.

[0109] The net fertilizer requirement calculation submodule inputs the read data into the nutrient balance algorithm model, performs weighted calculation, and obtains a net fertilizer requirement value that reflects the actual needs of crops under the current environmental pressure.

[0110] The calculation process for net fertilizer requirement specifically includes:

[0111] Obtain the theoretical values ​​of nitrogen, phosphorus, and potassium from the theoretical nitrogen, phosphorus, and potassium values, and at the same time obtain the corresponding soil background content values;

[0112] Calculate the net fertilizer requirement using the following formula:

[0113] in, This represents the net fertilizer requirement. Represents theoretical nitrogen, phosphorus, and potassium values. This represents the metabolic rate deviation coefficient. Nutrient content values ​​representing the concentrated background properties of the soil. The coefficient representing the effective utilization rate of soil nutrients. This represents the compensation increment value set due to leaching loss;

[0114] The security verification process before the fertilization control signal is generated specifically includes:

[0115] Obtain historical fertilization records and the current leaf area index of the crop to calculate the safe threshold for the total cumulative fertilization amount;

[0116] The net fertilizer requirement is compared with the safety threshold. If the threshold is exceeded, an alarm is triggered and the output is automatically cut off. If the threshold is not exceeded, the generation of fertilizer control signals is allowed.

[0117] The signal conversion and generation submodule maps the net fertilizer requirement value to the action parameters of the fertilizer application actuator, and outputs a pulse width modulation waveform through the digital-to-analog conversion interface to generate the fertilizer application control signal;

[0118] The process of generating fertilization control signals specifically includes:

[0119] Obtain the net fertilizer requirement and the rated flow parameters of the fertilizer pipeline, and calculate the opening time of the fertilizer valve required to meet the fertilizer requirement;

[0120] Convert the on duration into the corresponding duty cycle value, and configure the timer register to generate a square wave signal with a specific frequency and duty cycle;

[0121] The square wave signal is amplified by an opto-isolation circuit to output a fertilization control signal.

[0122] The data penetration extraction submodule executes data reading instructions. The system file pointer first accesses the top level of the file system (dynamic environment correction layer) and successfully reads the latest metabolic rate deviation coefficient. Since the bottom and middle layers are read-only, the system uses the union file system's penetration mechanism to logically "penetrate" the dynamic layer and directly index to the middle layer to read the theoretical nitrogen fertilizer requirement for the current date. It also indexes down to the underlying layer to read the soil nitrogen background value for that grid. The system reads the theoretical nitrogen requirement for the jointing stage from the intermediate layer as follows: (Normalized theoretical value of irrigation solution concentration), the soil available nitrogen content read from the bottom layer is converted into liquid phase contribution value. .

[0123] The net fertilizer requirement calculation submodule feeds the extracted data into the nutrient balance algorithm model. The system calculates the net fertilizer requirement using the following formula:

[0124] ;

[0125] in, This represents the net fertilizer requirement, which is the final concentration of nutrients that needs to be injected through the integrated water and fertilizer system. The values ​​represent theoretical nitrogen, phosphorus, and potassium values; the values ​​used in this embodiment are... ; The value represents the metabolic rate deviation coefficient, which is 2.28 in this embodiment. Nutrient content values ​​representing the concentrated background properties of the soil; the values ​​used in this embodiment are... ; The effective utilization rate coefficient of soil nutrients is set as follows: This is used to reflect the limitation of root absorption by soil adsorption and microbial fixation. This represents the incremental compensation value set due to leaching loss, which is determined based on the current irrigation quota. .

[0126] The specific calculation process is as follows: The results indicate that although there is a certain stock in the soil, the system still needs additional replenishment due to accelerated metabolism (demand surge to 11.4) and limited soil utilization (only 6.0 can be provided). The nitrogen concentration is set to meet the real-time needs of the crop.

[0127] The safety verification process before the fertilization control signal is generated is initiated. The system retrieves the cumulative total fertilization amount for this field this quarter from the database. Meanwhile, the current leaf area index (LAI) measured using a spectral camera is 3.5. Based on model calculations, the safe threshold for the total cumulative fertilization amount during the current growth stage is [value missing]. The system predicts the cumulative total amount after this fertilization will be... ,determination The signal generation is permitted as it does not exceed the safety threshold.

[0128] The signal conversion and generation submodule will convert the net fertilizer requirement value. This is mapped to the execution parameters of the fertilizer pump. The rated fertilizer suction flow rate of the Venturi fertilizer injector is known to be... The main pipeline water flow rate is To achieve Based on the target concentration, the controller calculates the required mother liquor injection rate. This rate is then converted into the solenoid valve's duty cycle. The system is configured for full-speed injection corresponding to a 100% duty cycle, and the calculated target duty cycle is 35%. The system configures the microcontroller's PWM register, sets the clock frequency to 1kHz, and sets the Compare-Capture Register (CCR) value to 35% of the Automatic Reload Register (ARR) value. Upon timer overflow, a square wave signal with a 35% duty cycle is generated. This signal is electrically isolated by an optocoupler (EL817) and input to the MOSFET driver circuit for power amplification, ultimately outputting a 24V pulse-width modulated voltage to drive the fertilizer solenoid valve to open at a 35% time ratio, precisely controlling the fertilizer application rate.

[0129] The aforementioned pulse width modulation (PWM) refers to a technique that uses the digital output of a microprocessor to control analog circuits, adjusting the average power of the output signal by changing the duration (duty cycle) of the high level in the pulse sequence.

[0130] The above embodiments illustrate preferred embodiments of the present invention. Any equivalent adjustments to the technical solution based on software engineering methods are within the scope of protection, including but not limited to: implementing algorithm logic using different programming languages, refactoring functional modules into services, adjusting data interaction protocols, and optimizing resource scheduling strategies. Any implementation scheme derived from reasonable modifications to the data processing flow, service call chain, or system architecture layer without departing from the core technology of the present invention should be considered within the scope of protection of the present invention.

Claims

1. A cloud-based agricultural planting operation and maintenance management system, characterized in that, The system includes: The underlying data mirroring module collects soil nitrogen, phosphorus, and potassium content and constructs a soil background attribute set, maps the soil background attribute set into a binary file set, and solidifies the binary file set into an underlying read-only mirror file; The standard demand overlay module obtains crop varieties and yields, generates theoretical nitrogen, phosphorus and potassium values ​​and constructs a standard fertilizer requirement time series, encapsulates the standard fertilizer requirement time series as an intermediate layer read-only image file and overlays it onto the bottom layer read-only image file to generate a composite static view. The real-time environment correction module acquires temperature and radiation, sets a temperature threshold, compares the temperature with the temperature threshold and calculates the metabolic rate deviation coefficient, mounts a read-write data storage layer on the composite static view and writes the metabolic rate deviation coefficient to generate a dynamic environment correction layer. The calculation process for the metabolic rate deviation coefficient specifically includes: Acquire the monitored real-time temperature values, photosynthetically active radiation intensity, and standard growth reference temperature; Based on the modified form of the Arrhenius equation, the metabolic rate deviation coefficient is calculated using the following formula: ； in, This represents the metabolic rate deviation coefficient. The activation energy constant representing the enzyme-catalyzed reaction in crops. Represents the ideal gas constant. This represents the standard growth reference temperature. This represents the real-time temperature value. Represents the radiation sensitivity modulator. This represents the photosynthetically active radiation intensity. Represents the baseline value for basic radiation intensity; The penetrating reading control module extracts the metabolic rate deviation coefficient, the theoretical nitrogen, phosphorus, and potassium values, and the soil background attribute set from the dynamic environment correction layer. It calculates the product of the theoretical nitrogen, phosphorus, and potassium values ​​and the metabolic rate deviation coefficient, and subtracts the soil background attribute set to generate the net fertilizer requirement value, thus generating a fertilization control signal.

2. The cloud-based agricultural planting operation and maintenance management system according to claim 1, characterized in that, The specific functional implementation of the underlying data mirroring module is as follows: The data acquisition and analysis submodule acquires the soil nitrogen, phosphorus and potassium content through an electrochemical sensor array deployed in farmland, uses the Kriging interpolation algorithm to perform spatial smoothing on the sampling point data, eliminates measurement noise and completes the data of unsampled areas, and constructs the soil background attribute set containing the nutrient distribution characteristics of the entire region. The binary stream mapping submodule traverses each attribute node in the soil background attribute set, converts the floating-point nutrient concentration data into a fixed-length binary encoding format, and reassembles the encoding into a continuous bit stream according to the grid order of geographic coordinates to generate the binary file set. The read-only image solidification submodule calls the file system driver to write the binary file set into the protected sector of the non-volatile storage medium and sets the read-only attribute bit to prohibit overwrite or modification operations, thereby generating the underlying read-only image file.

3. The cloud-based agricultural planting operation and maintenance management system according to claim 2, characterized in that, The specific functional implementation of the standard requirement overlay module is as follows: The theoretical numerical generation submodule analyzes the crop variety and yield to determine the growth cycle characteristics of the target crop, queries the agronomic knowledge graph to obtain the ideal nutrient absorption curves of the crop at different growth stages, and calculates and generates the theoretical nitrogen, phosphorus and potassium values ​​corresponding to each growth stage in combination with the target yield setting. The time series construction submodule discretizes the theoretical nitrogen, phosphorus and potassium values ​​in days, and smooths the differences in nutrient requirements between adjacent time points through cubic spline interpolation algorithm to construct the standard fertilizer requirement time series containing the daily fertilizer requirement for the entire growth cycle. The view overlay generation submodule encapsulates the standard required time series into an independent read-only file system image and uses it as the intermediate layer read-only image file. It then uses union file system technology to overwrite and mount the underlying read-only image file in read-only mode to generate the composite static view.

4. The cloud-based agricultural planting operation and maintenance management system according to claim 3, characterized in that, The construction process of the standard fertilizer requirement time series specifically includes: Key phenological nodes in the crop growth model were obtained, and the start and end times of each stage, including tillering, jointing, heading, and grain-filling stages, were extracted. Based on the duration of each phenological period, the theoretical nitrogen, phosphorus, and potassium values ​​are allocated to the corresponding time periods, and a growth rate adjustment factor is introduced to weight the daily values ​​within each time period. The generated sequence data is normalized and a timestamp index is added to establish a mapping relationship between the time dimension and the fertilizer demand value, thereby generating the standard fertilizer demand time series.

5. The cloud-based agricultural planting operation and maintenance management system according to claim 4, characterized in that, The specific functions of the real-time environment correction module are as follows: The environmental monitoring and comparison submodule monitors the temperature and radiation in the farmland in real time through the Internet of Things weather station, obtains the preset optimal temperature range for crop photosynthesis as the temperature threshold, and judges whether the actual temperature deviates from the optimal range. The deviation coefficient calculation submodule, when the actual temperature exceeds the temperature threshold, combines the current photosynthetically active radiation intensity, calls the crop metabolic response model to calculate the degree to which the photosynthetic rate is affected by temperature stress or radiation promotion, and quantifies and generates the metabolic rate deviation coefficient. The dynamic layer is mounted and written to the submodule. A volatile storage space that supports random read and write is initialized at the top layer of the composite static view as the read and write data storage layer. The metabolic rate deviation coefficient is written to this layer in real time using the copy-on-write mechanism to generate the dynamic environment correction layer.

6. The cloud-based agricultural planting operation and maintenance management system according to claim 1, characterized in that, The specific functions of the penetration reading control module are as follows: The data penetration extraction submodule utilizes the penetration reading mechanism of the union file system to prioritize reading the metabolic rate deviation coefficient from the dynamic environment correction layer. If the reading fails, it backtracks to the lower layer and directly reads the corresponding theoretical nitrogen, phosphorus, and potassium values ​​and the soil background attribute set from the lower layer image. The net fertilizer requirement calculation submodule inputs the read data into the nutrient balance algorithm model, performs weighted calculation processing, and obtains the net fertilizer requirement value that reflects the actual needs of crops under the current environmental pressure. The signal conversion and generation submodule maps the net fertilizer requirement value to the action parameters of the fertilizer application actuator, and outputs a pulse width modulation waveform through the digital-to-analog conversion interface to generate the fertilizer application control signal.

7. The cloud-based agricultural planting operation and maintenance management system according to claim 6, characterized in that, The calculation process for the net fertilizer requirement specifically includes: Obtain the theoretical values ​​of nitrogen, phosphorus, and potassium from the theoretical nitrogen, phosphorus, and potassium values, and simultaneously obtain the corresponding soil background content values; The net fertilizer requirement is calculated using the following formula: ； in, This represents the net fertilizer requirement. This represents the theoretical nitrogen, phosphorus, and potassium values. This represents the metabolic rate deviation coefficient. Nutrient content values ​​representing the aforementioned soil background properties. The coefficient representing the effective utilization rate of soil nutrients. This represents the compensation increment value set due to leaching loss.

8. The cloud-based agricultural planting operation and maintenance management system according to claim 7, characterized in that, The process of generating the fertilization control signal specifically includes: Obtain the net fertilizer requirement value and the rated flow parameters of the fertilizer pipeline, and calculate the opening time of the fertilizer valve required to meet the fertilizer requirement; Convert the on duration into the corresponding duty cycle value, and configure the timer register to generate a square wave signal with a specific frequency and duty cycle; The square wave signal is amplified by an opto-isolation circuit to output the fertilization control signal.

9. The cloud-based agricultural planting operation and maintenance management system according to claim 8, characterized in that, The security verification process before the fertilization control signal is generated specifically includes: Obtain historical fertilization records and the current leaf area index of the crop to calculate the safe threshold for the total cumulative fertilization amount; The net fertilizer requirement is compared with the safety threshold. If the threshold is exceeded, an alarm is triggered and the output is automatically cut off. If the threshold is not exceeded, the fertilization control signal is allowed to be generated.

Images