Intelligent sowing and fertilization control system and control method

Abstract

The present invention relates to the field of intelligent agricultural technology, specifically to an intelligent sowing and fertilization control system and control method, the system includes a crop layout optimization module, a sowing spacing analysis module, a fertilizer ratio calculation module, a fertilization schedule planning module, an operation path calculation module, and a control parameter optimization module. In the present invention, by analyzing farmland environmental information and matching crop types and sowing layouts, the crop planting density is calculated, the growth conditions and expected yields of crops are improved, and the fertilizer ratio and dosage are analyzed in combination with changes in soil and crop requirements, the waste of resources and environmental pollution are reduced, the growth stage and meteorological conditions of crops are analyzed, the fertilization schedule is planned, nutrient waste and environmental burden are reduced, the sowing and fertilization paths are calculated considering the planting efficiency, the interference with crop growth is reduced, the control parameters are adjusted by analyzing the actual yield, the output and quality of agricultural production are improved, and the improvement of production efficiency and environmental sustainability is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent agriculture, and in particular to an intelligent sowing and fertilization control system and a control method. Background Art

[0002] The field of smart agricultural technology aims to use sensors, data analysis and automated control to improve agricultural production efficiency, quality and sustainability. Through the Internet of Things, artificial intelligence and big data analysis, multiple technologies can be used to monitor and analyze farmland environment, crop growth status and resource utilization efficiency in real time, control planting activities and agricultural operations, optimize planting management and fertilization strategies, reduce negative impacts on soil, water resources and the environment, increase agricultural product output and quality, and achieve sustainable agricultural development.

[0003] Among them, the intelligent sowing and fertilization control system aims to control the crop planting environment and nutrient supply through automated sowing and fertilization processes, optimize growth conditions and expected yields, improve the growth efficiency and quality of crops, and reduce resource consumption and environmental pollution. Through sensor networks and data analysis systems, it monitors soil nutrient status, climate change and crop growth indicators in real time, and adjusts sowing and fertilization strategies based on real-time data, optimizes agricultural production processes, and makes agricultural practices conform to sustainable development.

[0004] Traditional sowing and fertilization control methods lack analysis of farmland environmental information and cannot fully realize the dynamic use of data, resulting in crop layout and nutrient supply strategies that cannot respond to environmental changes and the actual needs of crop growth in a timely manner. They cannot accurately adjust the amount and ratio of fertilizers to match the real-time changing nutrient status in the soil, resulting in excessive and insufficient nutrients, affecting crop growth and yield, increasing environmental pressure, and having poor ability to calculate sowing and fertilization paths. They are difficult to adapt to obstacles and irregular shapes in farmland, limiting operational efficiency and leading to waste of resources and poor efficiency during the operation process. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an intelligent sowing and fertilization control system and control method.

[0006] In order to achieve the above object, the present invention adopts the following technical scheme, an intelligent sowing and fertilization control system comprises:

[0007] The crop layout optimization module analyzes soil and water conditions based on farmland environmental information, analyzes the sowing layout, matches crop types for multiple farmland locations, and generates sowing layout calculation results;

[0008] The sowing spacing analysis module calculates the sowing density, including sowing position, spacing and direction, based on the sowing layout calculation result and according to the crop growth conditions and farmland environment, and generates sowing density assessment information;

[0009] The fertilizer ratio calculation module analyzes the fertilizer ratio and dosage required by the crop based on the sowing density assessment information, combined with soil conditions and crop types, and generates a crop demand analysis result;

[0010] The fertilization schedule planning module analyzes the growth stage and meteorological conditions of the crops based on the crop demand analysis results, identifies the fertilization time window for the target crops, and generates a farmland fertilization schedule;

[0011] The operation path calculation module calculates the sowing path according to the farmland fertilization schedule and sowing density assessment information, considers the farmland environment and sowing layout, analyzes the impact of the fertilization path on crop growth, calculates the fertilization path, and generates a farmland operation planning path;

[0012] The control parameter optimization module is based on the farmland operation planning path, analyzes the output of the farmland, adjusts the sowing layout, fertilizer dosage, and sowing and fertilization route, and generates sowing and fertilization control parameters.

[0013] As a further scheme of the present invention, the sowing layout calculation results include soil type matching information, crop adaptability evaluation results, and water resource utilization efficiency information; the sowing density evaluation information includes sowing position calculation parameters, spacing efficiency evaluation data, and crop spacing impact analysis results; the crop demand analysis results include fertilizer type selection results, dosage calculation information, and fertilizer ratio calculation results; the farmland fertilization schedule includes meteorological condition adaptability information, growth stage fertilization time window, and crop response time prediction data; the farmland operation planning path includes an operation priority list, a fertilization efficiency path, and a sowing path distribution map; the sowing and fertilization control parameters include output prediction information, sowing layout adjustment parameters, and fertilizer dosage and time adjustment parameters.

[0014] As a further solution of the present invention, the crop layout optimization module includes:

[0015] The soil condition assessment submodule analyzes soil texture and nutrient content based on farmland environmental information, identifies soil type, assesses the content of various trace elements such as nitrogen, phosphorus and potassium, and obtains soil type analysis results;

[0016] The water source condition analysis submodule analyzes the distribution and quality of farmland water sources based on the soil type analysis results, evaluates the impact of multiple water source locations on crop growth, and generates water source location evaluation results;

[0017] The crop type matching submodule analyzes the adaptability of various crops to soil and water sources based on the water source location assessment result, matches crop types to the locations of multiple farmlands, and obtains a sowing layout calculation result.

[0018] As a further solution of the present invention, the sowing spacing analysis module includes:

[0019] The growth condition assessment submodule analyzes the farmland environment and crop growth conditions, including soil type, water distribution, and climate characteristics, based on the sowing layout calculation results, and generates environmental parameter analysis results;

[0020] The spatial efficiency analysis submodule calculates the required sowing density for a variety of crops, including spacing, position, and direction, based on the environmental parameter analysis results, taking into account the mechanized operation efficiency and crop type, and adopts a branch and bound algorithm to generate crop density calculation results;

[0021] The planting spacing calculation submodule calculates the density and layout parameters of multiple crops when they are planted together based on the crop density calculation results, taking into account the conditions of multiple farmlands and sowing requirements, and generates sowing density evaluation information.

[0022] As a further solution of the present invention, the branch and bound algorithm is according to the formula:

[0023]

[0024] Calculate the sowing density, where Z is the objective function, min is the minimization operation, j is the index of the crop, i is the index of the path, and c j is the unit cost of growing the jth crop, x j is the sowing density of the jth crop, s j is the soil quality factor associated with the jth crop, w j is the weather adaptability associated with the jth crop, p i is the cost of walking the i-th path, y i is a binary decision variable, v i is the mechanical suitability associated with the ith path, e i is the energy efficiency associated with the ith path, m is the total number of crop types, and n is the estimated number of paths.

[0025] As a further solution of the present invention, the fertilizer ratio calculation module includes:

[0026] The nutrient requirement calculation submodule analyzes the fertilizer requirements of various crops based on the sowing density assessment information, soil conditions and crop types, and obtains crop fertilizer requirement data;

[0027] The soil nutrient assessment submodule assesses the current soil nutrient status based on the crop fertilizer demand data and the farmland environment, and generates real-time status assessment data;

[0028] The dosage ratio analysis submodule calculates fertilizer ratios and dosage parameters for a variety of crops based on the real-time status evaluation data and the fertilizer requirements of the crops to obtain crop demand analysis results.

[0029] As a further solution of the present invention, the fertilization schedule planning module includes:

[0030] The crop growth monitoring submodule identifies the growth stage of the crop and analyzes the nutrient types required for multiple growth stages based on the crop demand analysis results and the crop type, and obtains growth stage record information;

[0031] The environmental pattern analysis submodule monitors the meteorological conditions in real time based on the growth stage recorded information, and predicts the temperature and humidity change trends and periodic patterns in combination with the geographical location to generate meteorological condition assessment results;

[0032] The time window identification submodule analyzes and identifies the time windows for fertilizing various crops based on the meteorological condition assessment results, takes into account crop needs and meteorological changes, formulates a fertilization schedule, and obtains a farmland fertilization schedule.

[0033] As a further solution of the present invention, the operation path calculation module includes:

[0034] The shape feature analysis submodule collects and analyzes farmland environmental information, including soil moisture, obstacles, and farmland shape, based on the farmland fertilization schedule and sowing density assessment information, and generates farmland feature recognition information;

[0035] The planting trajectory design submodule calculates the farmland sowing path based on the farmland feature recognition information, combined with the farmland sowing layout, and considering the efficiency and feasibility of the path, and generates a sowing path calculation result;

[0036] The fertilization path analysis submodule analyzes the impact of the fertilization path on crop growth based on the sowing path calculation results, calculates the farmland fertilization path, and generates a farmland operation planning path.

[0037] As a further solution of the present invention, the control parameter optimization module includes:

[0038] The output data evaluation submodule analyzes the output data of the farmland based on the farmland operation planning path, evaluates the current sowing layout and fertilization effect, and generates output efficiency analysis results;

[0039] The farmland layout adjustment submodule adjusts the sowing layout and fertilizer dosage to match various farmland conditions and crop requirements based on the output efficiency analysis results, and generates layout analysis adjustment results;

[0040] The operation parameter adjustment submodule adjusts the control parameters of the sowing and fertilization route based on the layout analysis adjustment result, including the sowing speed, depth, spacing, and fertilizer concentration, and generates the sowing and fertilization control parameters.

[0041] An intelligent sowing and fertilization control method is implemented based on the intelligent sowing and fertilization control system, and comprises the following steps:

[0042] S1: Collect farmland environmental information, including soil texture and water source data, match crop types for multiple farmland locations, optimize crop layout, and generate adaptive layout parameters;

[0043] S2: using the adaptive layout parameters, taking into account soil and water conditions, analyzing and calculating the sowing density, position and spacing of multiple crops, and generating density spacing analysis results;

[0044] S3: Analyze the fertilizer ratio and dosage required by various crops based on the density spacing analysis results and the crop growth requirements, identify the fertilization time window of the target crops and generate fertilization demand analysis information based on the crop growth stage and meteorological conditions;

[0045] S4: Based on the fertilization demand analysis information and the density spacing analysis results, considering the farmland environment and sowing layout, designing sowing and fertilization paths, analyzing the impact of the paths on crop growth, and generating path analysis planning parameters;

[0046] S5: Analyze farmland output data based on the path analysis planning parameters, adjust sowing layout, fertilizer dosage and path parameters, optimize crop yield and growth quality, and generate sowing and fertilization control parameters.

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

[0048] In the present invention, by analyzing farmland environmental information and matching crop types and sowing layouts, crop planting density is calculated, crop growth conditions and expected yields are improved, and combined with changes in soil and crop requirements, fertilizer ratios and dosages are analyzed to reduce resource waste and reduce environmental pollution. The growth stages and meteorological conditions of crops are analyzed, fertilization schedules are planned, fertilization efficiency is optimized, nutrient waste and environmental burden are reduced, planting efficiency is considered, sowing and fertilization paths are calculated, and interference with crop growth is reduced. By analyzing actual yields, control parameters are adjusted to improve the output and quality of agricultural production, improve the ability of agricultural production to adapt to complex environmental conditions and market demands, and achieve improvements in production efficiency and environmental sustainability. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 is a system flow chart of the present invention;

[0050] Figure 2 It is a schematic diagram of the system framework of the present invention;

[0051] Figure 3 This is a flow chart of the crop layout optimization module of the present invention;

[0052] Figure 4 It is a flow chart of the sowing spacing analysis module of the present invention;

[0053] Figure 5 It is a flow chart of a fertilizer ratio calculation module of the present invention;

[0054] Figure 6 It is a flow chart of the fertilization schedule planning module of the present invention;

[0055] Figure 7 It is a flow chart of the operation path calculation module of the present invention;

[0056] Figure 8 It is a flow chart of the control parameter optimization module of the present invention;

[0057] Fig. 9 It is a schematic diagram of the method steps of the present invention. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0059] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0060] Embodiment 1

[0061] See also Figure 1 to Figure 2 The present invention provides a technical solution, an intelligent sowing and fertilization control system comprising:

[0062] The crop layout optimization module analyzes soil and water conditions based on farmland environmental information, analyzes the sowing layout, matches crop types for multiple farmland locations, and generates sowing layout calculation results;

[0063] The sowing spacing analysis module calculates the sowing density, including sowing position, spacing and direction, based on the sowing layout calculation results, according to crop growth conditions and farmland environment, and generates sowing density assessment information;

[0064] The fertilizer ratio calculation module analyzes the fertilizer ratio and dosage required by crops based on the sowing density assessment information, combined with soil conditions and crop types, and generates crop demand analysis results;

[0065] The fertilization schedule planning module analyzes the growth stage and meteorological conditions of crops based on the results of crop demand analysis, identifies the fertilization time window for target crops, and generates a farmland fertilization schedule;

[0066] The operation path calculation module calculates the sowing path based on the farmland fertilization schedule and sowing density assessment information, considers the farmland environment and sowing layout, analyzes the impact of the fertilization path on crop growth, calculates the fertilization path, and generates the farmland operation planning path;

[0067] The control parameter optimization module is based on the farmland operation planning path. By analyzing the output of the farmland, it adjusts the sowing layout, fertilizer dosage, and sowing and fertilization route to generate sowing and fertilization control parameters.

[0068] The sowing layout calculation results include soil type matching information, crop adaptability evaluation results, and water resource utilization efficiency information. The sowing density evaluation information includes sowing position calculation parameters, spacing efficiency evaluation data, and crop spacing impact analysis results. The crop demand analysis results include fertilizer type selection results, dosage calculation information, and fertilizer ratio calculation results. The farmland fertilization schedule includes meteorological condition adaptability information, growth stage fertilization time window, and crop response time prediction data. The farmland operation planning path includes an operation priority list, a fertilization efficiency path, and a sowing path distribution map. The sowing and fertilization control parameters include output prediction information, sowing layout adjustment parameters, and fertilizer dosage and time adjustment parameters.

[0069] See also Figure 2 and Figure 3 , the crop layout optimization module includes:

[0070] The soil condition assessment submodule analyzes soil texture and nutrient content based on farmland environmental information, identifies soil type, and assesses the content of various trace elements such as nitrogen, phosphorus, and potassium. The specific process of obtaining soil type analysis results is as follows;

[0071] In the soil condition assessment submodule, based on the farmland environmental information, soil samples are collected and analyzed, including soil particle size analysis, organic matter content and trace element determination, to assess soil texture and nutrient content. Each soil is classified, and the content of nitrogen, phosphorus, potassium and multiple trace elements is assessed. The soil texture and nutrient assessment model is used, and the formula is: Where S is the soil texture and nutrient score, c i is the weight of the i-th element, x i is the content of element i, y iis the ideal content of element i in the target soil type, f(x i ,y i ) is a scoring function that calculates a score based on the difference between the actual content and the ideal content, identifies the soil type, and generates a soil type analysis result.

[0072] The water source condition analysis submodule analyzes the distribution and quality of farmland water sources based on the soil type analysis results, and evaluates the impact of multiple water source locations on crop growth. The specific process of generating water source location evaluation results is as follows;

[0073] In the water source condition analysis submodule, based on the soil type analysis results, the geographical distribution and water quality of water sources are studied, including the pH value, salinity, and distance of water sources from farmland. Each water source location is evaluated, and the compatibility of surrounding soil types and the degree of support for crop growth are analyzed. The water source assessment model is used, and the formula is: Among them, W is the water source condition score, p j is the weight of the jth water source location, z j is the water quality index of water source j, v j is the crop growth demand corresponding to water source j, g(z j , v j ) is a function that calculates a score based on the match between water quality and crop requirements to generate a water source location assessment result.

[0074] The crop type matching submodule analyzes the adaptability of various crops to soil and water sources based on the water source location assessment results, matches crop types for the locations of multiple farmlands, and obtains the sowing layout calculation results. The specific process is as follows;

[0075] In the crop type matching submodule, based on the water source location assessment results, the growth condition requirements of various crops are analyzed, including the dependence on soil type and water source quality, integrating the crop growth cycle, economic value and market demand, and evaluating the adaptability to soil and water sources. The crop matching model is used, and the formula is: Among them, C is the crop matching score, q k is the importance weight of the kth crop, r k is the dependence of crop k on soil, s k is the dependence of crop k on water quality, t k is the economic and ecological value of crop k, h(r k ,s k , t k ) is a scoring function that allocates suitable farmland locations based on crop demand and potential value to obtain the sowing layout calculation result.

[0076] See also Figure 2 and Figure 4, the sowing spacing analysis module includes:

[0077] The growth condition assessment submodule analyzes the farmland environment and crop growth conditions, including soil type, water distribution, and climate characteristics, based on the sowing layout calculation results. The specific process of generating environmental parameter analysis results is as follows:

[0078] In the growth condition assessment submodule, based on the calculation results of the sowing layout, the geographic information system is used to map the environmental factors of the farmland area, including the analysis of soil type, water distribution and climate characteristics, collect and integrate multi-source environmental data, evaluate the permeability and water retention of the soil, and conduct statistical analysis on the climate conditions, including temperature, rainfall, and sunshine duration. The environmental suitability assessment model is adopted, and the formula is Among them, E s is the total score of environmental suitability, T s is the soil suitability score, W s is the moisture suitability score, C s It is the climate suitability score. Each indicator is obtained through corresponding measurements to generate environmental parameter analysis results.

[0079] The spatial efficiency analysis submodule uses a branch-and-bound algorithm based on the environmental parameter analysis results, taking into account the mechanized operation efficiency and crop type, to calculate the required sowing density for a variety of crops, including spacing, position, and direction. The specific process of generating crop density calculation results is as follows;

[0080] In the spatial efficiency analysis submodule, based on the results of environmental parameter analysis, combined with the spatial requirements of mechanized operations and the target requirements of crop growth, an optimization algorithm is used to calculate the crop sowing density, including analyzing the minimum soil volume and sunlight requirements required for crop root development, and using a spatial configuration optimization model to calculate the spacing, position and direction of crop sowing to generate crop density calculation results.

[0081] Branch and bound algorithm, according to the formula:

[0082]

[0083] Calculate the sowing density, where Z is the objective function, which represents the weighted sum of the total cost and the value to be minimized. Min is the minimization operation, which is used to capture the parameter configuration that makes the objective function Z reach the lowest value. j is the index of the crop, from 1 to m, used for iterative calculation of crop associations. i is the index of the path, from 1 to n, used for iterative calculation of path associations. c j is the unit cost of growing the jth crop, x j is the sowing density of the jth crop, indicating the area and quantity of the target crop planted, s jis the soil quality factor associated with the jth crop, adjusting the planting cost to reflect the soil condition, w j is the weather adaptability associated with the jth crop, adjusting the cost to reflect the impact of weather on crop growth, p i is the cost of walking the i-th path, y i is a binary decision variable, indicating whether to choose the i-th path, v i is the suitability of the machine associated with the ith path, and the path cost is adjusted to reflect the suitability of the machine on that path, e i is the energy efficiency associated with the ith path, the path cost is adjusted to reflect the energy consumption, m is the total number of crop types, and n is the estimated number of paths.

[0084] The specific execution process of the formula is as follows:

[0085] Define the seeding density x j 、Path selection y i , planting cost j and path cost p i Multiple key variables, and soil quality j 、Weather adaptability j 、Mechanical suitability i and energy efficiency i Multiple adjustment factors are taken into account to ensure that the sowing area meets the land utilization requirements, the path selection is suitable for machinery passage and meets energy efficiency standards, and all variable combinations are searched through the branch and bound method to calculate the sowing density and path configuration to optimize resource utilization and cost-effectiveness.

[0086] The planting spacing calculation submodule calculates the density and layout parameters of multiple crops when they are planted together based on the crop density calculation results, taking into account the conditions and sowing requirements of multiple farmlands, and generates the sowing density assessment information in the following process:

[0087] In the planting spacing calculation submodule, based on the crop density calculation results, the environmental conditions of multiple farmlands and the sowing requirements of crops are considered, and the mutual influence between crops, including light competition and root interaction, is analyzed. The companion planting optimization model is adopted, and the formula is: Among them, P represents the optimization score of seeding layout, r j represents the planting response coefficient of the jth crop, s j Indicates the planting area, s max It represents the maximum plantable area, m represents the number of crop types, and analyzes the planting spacing and layout to match the optimal growth environment for multiple crops and generate seeding density assessment information.

[0088] See also Figure 2 and Figure 5 , the fertilizer ratio calculation module includes:

[0089] The nutrient requirement calculation submodule analyzes the fertilizer requirements of various crops based on the sowing density assessment information, soil conditions and crop types. The specific process of obtaining crop fertilizer requirement data is as follows:

[0090] In the nutrient requirement calculation submodule, the fertilizer requirements of multiple crops are calculated based on the sowing density assessment information, taking into account the fertilizer absorption rate of each crop and the existing nutrient content in the soil. The formula is F i =κ i ·(N i -O i ), where F i is the fertilizer requirement of the i-th crop, κ i is the fertilizer demand adjustment coefficient of crop i, which depends on the growth stage and variety characteristics of the crop, N i is the total nutrient required by crop i theoretically, O i The existing nutrients in the soil that can be absorbed by crop i are calculated. The difference between the nutrients required by the crop and the existing nutrients in the soil is used to obtain the amount of fertilizer to be added and the fertilizer demand data of the crop.

[0091] The soil nutrient assessment submodule evaluates the current soil nutrient status based on crop fertilizer demand data and combined with the farmland environment, and generates real-time status assessment data in the following process:

[0092] In the soil nutrient assessment submodule, soil sample analysis is used to assess the current soil nutrient status based on crop fertilizer demand data. The formula is: Among them, S t is the soil nutrient status score, λ is the upper limit adjustment coefficient of the score to adjust the sensitivity of the score, η j is the importance coefficient of nutrient j, C j Generate real-time status assessment data for the concentration of nutrients in the soil and the cumulative effect of nutrients.

[0093] The dosage ratio analysis submodule calculates fertilizer ratios and dosage parameters for various crops based on real-time status assessment data and crop fertilizer requirements, and obtains crop demand analysis results in the following specific process:

[0094] In the dosage ratio analysis submodule, based on the real-time status assessment data and the crop's demand intensity for target nutrients, the optimal fertilizer ratio and dosage are calculated. The formula is: Among them, D k is the fertilizer dosage of crop k, ξ kl is the adjustment coefficient of nutrient l for crop k, R l is the requirement of nutrient l, T lis the current available amount of nutrient l in the soil, μ is the fine-tuning parameter to avoid zero division errors, and the amount of each nutrient added is determined by adjusting the coefficient and the demand-supply ratio to optimize the fertilizer use efficiency and obtain the crop demand analysis results.

[0095] See also Figure 2 and Figure 6 , the fertilization schedule planning module includes:

[0096] The crop growth monitoring submodule identifies the growth stage of the crop and analyzes the nutrient types required for multiple growth stages based on the crop demand analysis results and the specific process of obtaining the growth stage record information according to the crop type.

[0097] In the crop growth monitoring submodule, based on the crop demand analysis results, image recognition technology is used to monitor the growth status of each crop, including leaf color, root health, and flower and fruit development. Crops at different growth stages are classified, and combined with soil test results, the nutrient requirements of crops at multiple growth stages are analyzed. The crop growth stage analysis model is used, and the formula is: Where N represents the total nutrients required by crops, α k represents the nutrient requirement coefficient for the kth growth stage, x k represents the duration of the kth stage, p represents the total number of growth stages, and the nutrient supply plans of multiple stages are analyzed to obtain the growth stage record information.

[0098] The environmental pattern analysis submodule monitors meteorological conditions in real time based on the growth stage record information, and predicts the temperature and humidity change trends and periodic patterns in combination with the geographical location. The specific process of generating meteorological condition assessment results is as follows;

[0099] In the environmental pattern analysis submodule, based on the growth stage recorded information, combined with real-time meteorological monitoring data, including satellite meteorological data and ground observation station information, climate conditions, including temperature, humidity and rainfall, are analyzed by applying the meteorological trend prediction model, the formula is C t =β0+β1·T t +β2·H t +∈ t , where C t Represents the predicted meteorological condition index, T t and H t Represent the real-time readings of temperature and humidity respectively, β0 is the intercept term of the model, representing the starting value of the predicted meteorological condition index under the baseline condition where the temperature and humidity have zero influence, β1 is the influence coefficient of temperature on the meteorological condition index, β2 is the influence coefficient of humidity on the meteorological condition index, ∈ t The error term is used to predict the temperature and humidity change trends and periodic patterns and generate meteorological condition assessment results.

[0100] The time window identification submodule analyzes and identifies the time windows for fertilizing various crops based on the meteorological condition assessment results, taking into account crop demand and meteorological changes, and formulates a fertilization schedule. The specific process of obtaining the farmland fertilization schedule is as follows;

[0101] In the time window identification submodule, based on the meteorological condition assessment results, combined with the crop target demand and predicted climate conditions, the decision support system is used to analyze the optimal fertilization time, and the fertilization time optimization model is adopted, with the formula F d =max i∈D (γ i ·Y i ), where F d represents the optimal fertilization day, γ i It represents the meteorological suitability of the i-th day, Yi represents the contribution of the target day to crop growth, and D represents the range of calendar days considered. The optimal time window for fertilization is determined and a farmland fertilization schedule is generated.

[0102] See also Figure 2 and Figure 7 , the operation path calculation module includes:

[0103] The shape feature analysis submodule collects and analyzes farmland environmental information, including soil moisture, obstacles, and farmland shape, based on the farmland fertilization schedule and sowing density assessment information. The specific process of generating farmland feature recognition information is as follows;

[0104] In the shape feature analysis submodule, based on the farmland fertilization schedule and sowing density assessment information, various environmental information such as soil moisture, existing obstacles, and the shape and size of the farmland are collected. Through data integration and analysis, the characteristics of the farmland and potential planting restrictions are identified and classified. The formula is: Among them, H f represents the comprehensive score of farmland shape feature recognition, φ is the adjustment coefficient matching the differentiated types of farmland, ω i is the importance weight of the i-th environmental feature, h i is the measured value of feature i, s i is the standard value of feature i, ∈ is a small amount to avoid division by zero, and the impact of multiple features is evaluated through the logarithmic response function, the sensitivity to outliers is enhanced, the recognition process of farmland features is optimized, and farmland feature recognition information is generated.

[0105] The planting trajectory design submodule calculates the farmland sowing path based on the farmland feature recognition information, combined with the farmland sowing layout, and considers the efficiency and feasibility of the path. The specific process of generating the sowing path calculation result is as follows;

[0106] In the planting trajectory design submodule, the planting path is designed based on the farmland feature recognition information and combined with the farmland sowing layout. The shape of the farmland and the distribution of obstacles are considered, and the minimum cost path algorithm is used to optimize the planting route. The formula is: Among them, P seed is the total cost of the planting path, ξ j is the cost coefficient of path j, d j is the distance of path j, and the sowing efficiency is ensured by minimizing the cost of multiple path segments, taking into account the physical layout and obstacles of the farmland, and generating the sowing path calculation result.

[0107] The fertilization path analysis submodule analyzes the impact of the fertilization path on crop growth based on the sowing path calculation results, calculates the farmland fertilization path, and generates the farmland operation planning path. The specific process is as follows;

[0108] In the fertilization path analysis submodule, the fertilization path is designed based on the sowing path calculation results to optimize the fertilization coverage area and reduce the interference with crop growth. The formula is: Among them, F path is the efficiency score of the fertilization path, f(x) is the function of the fertilization efficiency on path x, L is the total length of the fertilization path, x represents the target point and position on the fertilization path, d is the differential symbol, and is the mathematical symbol representing the derivative and rate of change. It evaluates the efficiency of the fertilization path, ensures the uniformity and comprehensiveness of fertilization activities, reduces the negative impact on crop growth, and generates a farmland operation planning path.

[0109] See also Figure 2 and Figure 8 , the control parameter optimization module includes:

[0110] The output data evaluation submodule analyzes the output data of the farmland based on the farmland operation planning path, evaluates the current sowing layout and fertilization effect, and generates the output efficiency analysis results. The specific process is as follows;

[0111] In the output data evaluation submodule, based on the farmland operation planning path, the actual output data after sowing, including crop growth rate, fruit size and quantity, and harvest volume, are collected and integrated to evaluate the impact of the current sowing layout and fertilization effect on the output. The output efficiency evaluation model is adopted, and the formula is: Among them, E p represents the output efficiency, y i represents the actual output of the i-th crop, Y max Represents the theoretical maximum output, n represents the number of crop types, analyzes the efficiency of the current agricultural plan, and generates output efficiency analysis results.

[0112] The farmland layout adjustment submodule adjusts the sowing layout and fertilizer dosage to match various farmland conditions and crop requirements based on the output efficiency analysis results. The specific process of generating layout analysis and adjustment results is as follows:

[0113] In the farmland layout adjustment submodule, based on the output efficiency analysis results, the sowing layout is adjusted according to the output data of various crops and the environmental adaptability analysis, including modifying the crop spacing, row spacing, and fertilizer dosage for various farmland conditions. The layout optimization model is adopted, and the formula is L new =L old +δ·(Env opt -Env cur ), where L new Represents the adjusted layout parameters, L old represents the old layout parameters, δ represents the adjustment coefficient, Env opt and Env cur They represent the optimal environmental parameters and the current environmental parameters respectively. The sowing and fertilization strategies are adjusted according to the feedback of output efficiency to generate layout analysis adjustment results.

[0114] The operation parameter adjustment submodule adjusts the control parameters of the sowing and fertilization route based on the layout analysis adjustment results, including the sowing speed, depth, spacing, and fertilizer concentration. The specific process of generating the sowing and fertilization control parameters is as follows;

[0115] In the operation parameter adjustment submodule, based on the layout analysis and adjustment results, the compatibility of the operation parameters of the seeding machinery and the farmland conditions is analyzed, and the parameters of the seeding and fertilization route are adjusted, including seeding speed, planting depth, crop spacing, and fertilizer application concentration. The parameter optimization model is adopted, and the formula is P opt =P cur +κ·(O target -O actual ), where P opt represents the optimized operating parameters, P cur represents the current operation parameters, κ represents the adjustment intensity, O target and O actual They represent the target operation result and the current operation result respectively, optimize the operation efficiency of sowing and fertilization, and generate sowing and fertilization control parameters.

[0116] See also Fig. 9 , an intelligent sowing and fertilization control method, the intelligent sowing and fertilization control method is executed based on the above-mentioned intelligent sowing and fertilization control system, comprising the following steps:

[0117] S1: Collect farmland environmental information, including soil texture and water source data, match crop types for multiple farmland locations, optimize crop layout, and generate adaptive layout parameters;

[0118] S2: Using adaptive layout parameters, considering soil and water conditions, analyzing and calculating the sowing density, position and spacing of multiple crops, and generating density spacing analysis results;

[0119] S3: Based on the density spacing analysis results and combined with the crop growth requirements, the fertilizer ratio and dosage required for various crops are analyzed. Combined with the growth stage and meteorological conditions of the crops, the fertilization time window of the target crops is identified to generate fertilization demand analysis information;

[0120] S4: Based on the fertilization demand analysis information and density spacing analysis results, considering the farmland environment and sowing layout, design the sowing and fertilization path, analyze the impact of the path on crop growth, and generate path analysis planning parameters;

[0121] S5: Based on the path analysis planning parameters, analyze the farmland output data, adjust the sowing layout, fertilizer dosage and path parameters, optimize the crop yield and growth quality, and generate sowing and fertilization control parameters.

[0122] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. An intelligent sowing and fertilization control system, characterized in that: The system comprises: The crop layout optimization module analyzes soil and water conditions based on farmland environmental information, analyzes the sowing layout, matches crop types for multiple farmland locations, and generates sowing layout calculation results; The specific formula for analyzing soil and water source conditions is: ， ； in, Score soil texture and nutrients, For the The weight of the element, For elements The content of For elements Ideal content in target soil types, is a scoring function that calculates the score based on the difference between the actual content and the ideal content. Score water conditions. For the The weight of the water source location, For water source water quality indicators, For water source Corresponding crop growth requirements, is a function that calculates a score based on how well the water quality matches the crop’s needs; A sowing spacing analysis module calculates the sowing density, including sowing position, spacing and direction, based on the sowing layout calculation results and according to crop growth conditions and farmland environment, and generates sowing density assessment information; A fertilizer ratio calculation module, which analyzes the fertilizer ratio and dosage required by the crop based on the sowing density assessment information, combined with soil conditions and crop types, and generates a crop demand analysis result; A fertilization schedule planning module, based on the crop demand analysis results, analyzes the growth stage and meteorological conditions of the crops, identifies the fertilization time window for the target crops, and generates a farmland fertilization schedule; An operation path calculation module calculates the sowing path according to the farmland fertilization schedule and sowing density assessment information, considers the farmland environment and sowing layout, analyzes the impact of the fertilization path on crop growth, calculates the fertilization path, and generates a farmland operation planning path; The specific formula for calculating the sowing path is: ； in, is the total cost of the planting path, For the path The cost factor, For path distance; A control parameter optimization module, based on the farmland operation planning path, adjusts the sowing layout, fertilizer dosage, and sowing and fertilization route by analyzing the output of the farmland, and generates sowing and fertilization control parameters; The control parameter optimization module includes: The output data evaluation submodule analyzes the output data of the farmland based on the farmland operation planning path, evaluates the current sowing layout and fertilization effect, and generates output efficiency analysis results; The farmland layout adjustment submodule adjusts the sowing layout and fertilizer dosage to match various farmland conditions and crop requirements based on the output efficiency analysis results, and generates layout analysis adjustment results; The operation parameter adjustment submodule adjusts the control parameters of the sowing and fertilization route based on the layout analysis adjustment result, including the sowing speed, depth, spacing, and fertilizer concentration, and generates the sowing and fertilization control parameters.

2. The intelligent sowing and fertilization control system according to claim 1 is characterized in that: The sowing layout calculation results include soil type matching information, crop adaptability evaluation results, and water resource utilization efficiency information; the sowing density evaluation information includes sowing position calculation parameters, spacing efficiency evaluation data, and crop spacing impact analysis results; the crop demand analysis results include fertilizer type selection results, dosage calculation information, and fertilizer ratio calculation results; the farmland fertilization schedule includes meteorological condition adaptability information, growth stage fertilization time window, and crop response time prediction data; the farmland operation planning path includes an operation priority list, a fertilization efficiency path, and a sowing path distribution map; the sowing and fertilization control parameters include output prediction information, sowing layout adjustment parameters, and fertilizer dosage and time adjustment parameters.

3. The intelligent sowing and fertilization control system according to claim 1 is characterized in that: The crop layout optimization module includes: The soil condition assessment submodule analyzes soil texture and nutrient content based on farmland environmental information, identifies soil type, assesses the content of various trace elements such as nitrogen, phosphorus and potassium, and obtains soil type analysis results; A water source condition analysis submodule analyzes the distribution and quality of farmland water sources based on the soil type analysis results, evaluates the impact of multiple water source locations on crop growth, and generates water source location evaluation results; The crop type matching submodule analyzes the adaptability of various crops to soil and water sources based on the water source location assessment result, matches the crop types for the locations of multiple farmlands, and obtains a sowing layout calculation result.

4. The intelligent sowing and fertilization control system according to claim 1 is characterized in that: The sowing spacing analysis module includes: A growth condition assessment submodule analyzes the farmland environment and crop growth conditions, including soil type, water distribution, and climate characteristics, based on the sowing layout calculation results, and generates environmental parameter analysis results; The spatial efficiency analysis submodule calculates the required sowing density for a variety of crops, including spacing, position, and direction, based on the environmental parameter analysis results, taking into account the mechanized operation efficiency and crop type, and adopts a branch and bound algorithm to generate crop density calculation results; The planting spacing calculation submodule calculates the density and layout parameters of multiple crops when they are planted together based on the crop density calculation results and taking into account the conditions and sowing requirements of multiple farmlands, and generates sowing density evaluation information.

5. The intelligent sowing and fertilization control system according to claim 4 is characterized in that: The branch and bound algorithm is based on the formula: Calculate the seeding density, where is the objective function, To minimize operations, is the index of the crop, is the index of the path, To plant the The unit cost of growing crops, For the The sowing density of crops, For the Soil quality factors associated with different crops, For the The weather adaptability of crops, To pass the The cost of the path, is a binary decision variable, For the The mechanical suitability of the pathways involved, For the The energy efficiency associated with each path, is the total number of crop types, is the estimated number of paths.

6. The intelligent sowing and fertilization control system according to claim 1 is characterized in that: The fertilizer ratio calculation module comprises: A nutrient requirement calculation submodule analyzes fertilizer requirements of various crops based on the sowing density assessment information, soil conditions and crop types, and obtains crop fertilizer requirement data; The soil nutrient assessment submodule assesses the current soil nutrient status based on the crop fertilizer demand data and the farmland environment, and generates real-time status assessment data; The dosage ratio analysis submodule calculates fertilizer ratios and dosage parameters for a variety of crops based on the real-time status evaluation data and the fertilizer requirements of the crops to obtain crop demand analysis results.

7. The intelligent sowing and fertilization control system according to claim 1 is characterized in that: The fertilization schedule planning module includes: The crop growth monitoring submodule identifies the growth stage of the crop and analyzes the nutrient types required for multiple growth stages based on the crop demand analysis results and the crop type, thereby obtaining growth stage record information; The environmental pattern analysis submodule monitors the meteorological conditions in real time based on the growth stage recorded information, predicts the temperature and humidity change trend and periodic pattern in combination with the geographical location, and generates meteorological condition assessment results; The time window identification submodule analyzes and identifies the time windows for fertilizing various crops based on the meteorological condition assessment results, considers crop demand and meteorological changes, formulates a fertilization schedule, and obtains a farmland fertilization schedule.

8. The intelligent sowing and fertilization control system according to claim 1 is characterized in that: The operation path calculation module includes: The shape feature analysis submodule collects and analyzes farmland environmental information, including soil moisture, obstacles, and farmland shape, based on the farmland fertilization schedule and seeding density assessment information, and generates farmland feature recognition information; The planting trajectory design submodule calculates the farmland sowing path based on the farmland feature recognition information, combined with the farmland sowing layout, and considering the efficiency and feasibility of the path, and generates a sowing path calculation result; The fertilization path analysis submodule analyzes the impact of the fertilization path on crop growth based on the sowing path calculation results, calculates the farmland fertilization path, and generates a farmland operation planning path.

9. An intelligent sowing and fertilization control method, characterized in that: The intelligent sowing and fertilization control system according to any one of claims 1 to 8 is used for implementation, comprising the following steps: Collect farmland environmental information, including soil texture and water source data, match crop types for multiple farmland locations, optimize crop layout, and generate adaptive layout parameters; Utilizing the adaptive layout parameters, taking into account soil and water conditions, analyzing and calculating the sowing density, position and spacing of multiple crops, and generating density spacing analysis results; According to the density spacing analysis results, combined with the crop growth requirements, the fertilizer ratios and dosages required by various crops are analyzed, and the fertilization time window of the target crops is identified in combination with the growth stage and meteorological conditions of the crops, so as to generate fertilization demand analysis information; Based on the fertilization demand analysis information and density spacing analysis results, considering the farmland environment and sowing layout, designing sowing and fertilization paths, analyzing the impact of the paths on crop growth, and generating path analysis planning parameters; According to the path analysis planning parameters, the farmland output data is analyzed, the sowing layout, fertilizer dosage and path parameters are adjusted, the crop yield and growth quality are optimized, and the sowing and fertilization control parameters are generated.

Images