Soil data processing method and system combined with demand analysis

Abstract

The invention relates to a demand analysis-combined soil data processing method and system, and relates to the field of data processing, and the method comprises the steps: detecting target land soil characteristic parameters and target seed demand parameters, randomly configuring a soil adjustment scheme, carrying out the integrated prediction, and carrying out the error compensation based on a data sample occurrence rate and a historical adjustment error rate. Finally, an optimal soil adjustment scheme is obtained according to optimization of the soil nutrient fitness and the soil gap fitness, the technical problem that a soil management adjustment method lacks accurate consideration of different crop demand differences and systematic prediction and optimization means is solved, and the purposes that seed demands can be accurately matched, and the adjustment accuracy is improved are achieved. And the pertinence and effectiveness of soil adjustment are improved.

Description

Technical Field

[0001] This invention relates to the field of data processing, and in particular to a soil data processing method and system that incorporates demand analysis. Background Technology

[0002] In agricultural production, soil serves as the foundation for plant growth, and its quality and characteristics significantly impact crop growth and development. Traditional soil management and conditioning methods often rely on experience or simple soil tests, lacking specific consideration for the diverse needs of different crops, especially specific seeds. With the continuous development of modern agricultural technology, the demands for precision and scientific rigor in soil management and conditioning are increasing. On the one hand, different crops have varying requirements for soil nutrients and physical properties. For example, some crops may prefer nitrogen-rich soils, while others may require higher phosphorus or potassium content. Simultaneously, the physical characteristics of crop seeds, such as seed size and shape, also influence their need for soil gaps, thus affecting seed germination and growth. Therefore, the specific needs of the target crop must be fully considered when developing soil conditioning programs. On the other hand, existing soil conditioning methods often lack systematic predictive and optimization tools. Agricultural technicians typically rely on limited soil test data and experience to determine how to adjust the soil, a method that is not only inefficient but also struggles to guarantee the accuracy and effectiveness of the conditioning results. Summary of the Invention

[0003] This invention addresses the technical problem in existing soil management adjustment methods that lack precise consideration of the differences in the needs of different crops and systematic prediction and optimization methods, by providing a soil data processing method and system that combines demand analysis.

[0004] The technical solution of the present invention to solve the above-mentioned technical problems is as follows: In a first aspect, the present invention provides a soil data processing method incorporating demand analysis. The method includes: detecting soil within a target land area to obtain soil characteristic parameters, and acquiring the soil nutrient requirements parameters and seed characteristic parameter distributions for the target seeds, wherein the soil characteristic parameters include soil gap parameters and soil nutrient parameters; randomly configuring a soil adjustment scheme, and performing integrated soil adjustment prediction based on the soil characteristic parameters to obtain a predicted set of soil gap parameters and a predicted set of soil nutrient parameters; compensating for sample errors in the predicted set of soil gap parameters and the predicted set of soil nutrient parameters based on the data sample occurrence rate of the soil characteristic parameters and the soil adjustment scheme in the integrated adjustment prediction, combined with the historical adjustment error rate of the soil adjustment scheme, to obtain a predicted distribution of soil gap parameters and a predicted distribution of soil nutrient parameters; calculating soil nutrient fitness based on the predicted distribution of soil nutrient parameters and the required soil nutrient parameters, calculating soil gap fitness based on the seed characteristic parameter distribution and the predicted distribution of soil gap parameters, performing soil adjustment optimization, and obtaining the optimal soil adjustment scheme as the soil data processing result.

[0005] Secondly, this invention provides a soil data processing system incorporating demand analysis. The system includes: a basic detection module for detecting soil within a target land area, obtaining soil characteristic parameters, and acquiring the soil nutrient requirements and seed characteristic parameter distributions for the target seeds, wherein the soil characteristic parameters include soil gap parameters and soil nutrient parameters; an adjustment prediction module for randomly configuring soil adjustment schemes, performing integrated soil adjustment predictions based on the soil characteristic parameters, and obtaining a predicted set of soil gap parameters and a predicted set of soil nutrient parameters; an error compensation module for compensating for sample errors in the predicted set of soil gap parameters and the predicted set of soil nutrient parameters based on the data sample occurrence rate of the soil characteristic parameters and the soil adjustment scheme in the integrated adjustment prediction, combined with the historical adjustment error rate of the soil adjustment scheme, and obtaining the predicted distribution of soil gap parameters and the predicted distribution of soil nutrient parameters; and an adjustment optimization module for calculating soil nutrient fitness based on the predicted distribution of soil nutrient parameters and the required soil nutrient parameters, calculating soil gap fitness based on the seed characteristic parameter distribution and the predicted distribution of soil gap parameters, performing soil adjustment optimization, and obtaining the optimal soil adjustment scheme as the soil data processing result.

[0006] The beneficial effects of this invention are: by detecting the soil characteristic parameters of the target land and the target seed requirement parameters, randomly configuring soil adjustment schemes and performing integrated predictions, then performing error compensation based on the occurrence rate of data samples and the historical adjustment error rate, and finally optimizing the optimal soil adjustment scheme based on soil nutrient adaptability and soil gap adaptability, it can accurately match seed requirements and improve the pertinence and effectiveness of soil adjustment. Attached Figure Description

[0007] Figure 1 This is a flowchart illustrating a soil data processing method that incorporates requirements analysis, as provided by the present invention.

[0008] Figure 2 This is a schematic diagram of the structure of a soil data processing system that incorporates demand analysis, as provided by the present invention.

[0009] Explanation of reference numerals in the attached diagram: Basic detection module 11, Adjustment prediction module 12, Error compensation module 13, Adjustment optimization module 14. Detailed Implementation

[0010] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0011] In the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0012] In the description of this invention, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed herein.

[0013] Example 1:

[0014] like Figure 1 As shown, this embodiment of the invention provides a soil data processing method that incorporates demand analysis, the method comprising: S10: Detect the soil in the target land, obtain soil characteristic parameters, and obtain the soil nutrient parameters required by the target seeds and the distribution of seed characteristic parameters, wherein the soil characteristic parameters include soil gap parameters and soil nutrient parameters.

[0015] For example, the target land refers to the land area undergoing analysis. The core of comprehensive soil testing within the target land lies in obtaining characteristic soil parameters, specifically soil porosity parameters and soil nutrient parameters. Soil porosity parameters reflect the physical structure characteristics of the soil, such as soil compaction and porosity, which have a significant impact on seed germination and root growth. Soil nutrient parameters, on the other hand, encompass the content of various nutrients in the soil, such as nitrogen, phosphorus, and potassium, which are indispensable nutrient sources for seed growth.

[0016] At the same time, in order to develop more precise soil conditioning plans, it is also necessary to obtain the soil nutrient requirements of the target seeds. These parameters are determined based on the seeds' growth habits and physiological needs, reflecting the specific requirements of the seeds for soil nutrients at different growth stages. By collecting and analyzing these parameters, we can more accurately understand the actual soil nutrient requirements of the seeds, thereby guiding subsequent soil conditioning work.

[0017] Furthermore, to comprehensively assess the soil's physical support capacity for seed growth, it is necessary to measure the size of the target seeds and construct a distribution of seed characteristic parameters accordingly. Specifically, multiple seeds can be randomly sampled, their size parameters measured, and the size distribution characteristics analyzed. For example, some large seeds may require looser soil gaps to provide sufficient growing space, while small seeds may require a denser soil structure to provide stable support. Constructing a distribution of seed characteristic parameters allows for a more precise understanding of the seeds' needs for soil gaps, thereby further improving the targeting and effectiveness of soil conditioning.

[0018] In summary, by testing the soil in the target land, obtaining soil characteristic parameters, and collecting the soil nutrient requirements and seed characteristic parameter distribution of the target seeds, a scientific basis can be provided for the subsequent formulation of precise and effective soil adjustment plans.

[0019] S20: Randomly configure a soil adjustment scheme, combine the soil characteristic parameters to perform integrated soil adjustment prediction, and obtain a predicted set of soil gap parameters and a predicted set of soil nutrient parameters.

[0020] Furthermore, the randomized soil conditioning scheme involves generating multiple possible soil conditioning schemes based on soil characteristic parameters within the target land, such as soil gap parameters and soil nutrient parameters, as well as the growth requirements of the target seeds. These schemes may include different combinations of parameters such as the degree of soil loosening, fertilizer type and quantity, aiming to explore the optimal soil conditions that can meet the growth requirements of the seeds.

[0021] Subsequently, based on the configured soil adjustment schemes, integrated prediction technology was used to simulate and predict these schemes. In this process, soil characteristic parameters and adjustment schemes were used as inputs, and multiple soil adjustment prediction paths were integrated to simulate the changes in soil gaps and nutrient parameters after the implementation of different schemes. Integrated prediction technology can comprehensively consider the influence of multiple factors, improving the accuracy and reliability of predictions. For example, in a specific scheme, relatively lenient soil loosening parameters and nitrogen-rich fertilization parameters might be set. Through integrated prediction, the predicted set of soil gap parameters and soil nutrient parameters after the implementation of this scheme can be obtained. These parameter sets describe in detail the range of changes in soil gaps and the content distribution of various nutrients in the soil, providing an important basis for subsequent optimization analysis.

[0022] In summary, randomly configuring soil adjustment schemes and combining them with soil characteristic parameters for integrated soil adjustment prediction is a key step in exploring the optimal soil adjustment scheme and meeting the needs of seed growth. This process, by simulating and predicting soil changes under different schemes, provides strong data support for subsequent optimization analysis.

[0023] S30: Based on the occurrence rate of data samples of the soil characteristic parameters and soil adjustment scheme in the integrated adjustment prediction, and combined with the historical adjustment error rate of the soil adjustment scheme, sample error compensation is performed on the predicted soil gap parameter set and the predicted soil nutrient parameter set to obtain the predicted soil gap parameter distribution and the predicted soil nutrient parameter distribution.

[0024] In detail, to further improve the accuracy and practicality of the prediction results, a sample error compensation strategy is adopted. This step is based on two core elements: the occurrence rate of soil characteristic parameters and soil adjustment schemes in the integrated adjustment prediction data, and the historical adjustment error rate of the soil adjustment schemes.

[0025] Specifically, the first focus is on the occurrence rate of data samples in the integrated prediction, which reflects the representativeness and weight of different soil characteristic parameters and adjustment schemes in the prediction model. Statistical analysis reveals which soil conditions and adjustment strategies have been more common in past predictions, allowing for the allocation of higher attention and weight to them. This approach helps improve the predictive model's adaptability to common soil conditions and adjustment needs.

[0026] Simultaneously, the historical adjustment error rate of the soil adjustment scheme is considered. The historical adjustment error rate is calculated based on the difference between past actual adjustment results and predicted results, reflecting the accuracy and reliability of the prediction model in practical applications. Introducing this parameter allows for more precise correction and compensation of the prediction results.

[0027] Specifically, sample error compensation is performed on the predicted soil gap parameter set and the predicted soil nutrient parameter set based on the data sample occurrence rate and historical adjustment error rate. The prediction results are fine-tuned through complex mathematical calculations and statistical analysis to reduce the difference between predicted and actual values. The compensated prediction result is no longer a single numerical point, but a parameter range containing multiple possible values. This range encompasses both the uncertainty of the predicted values ​​and reflects the possible variation range of the soil adjustment scheme in practical applications.

[0028] For example, when predicting soil gap parameters under a specific soil adjustment scheme, an initial predicted value may be obtained. However, considering the impact of data sample occurrence rate and historical adjustment error rate, this predicted value will be compensated to obtain a broader prediction range. This range not only includes the initial predicted value but also covers other possible values ​​of soil gap parameters, thus providing more comprehensive and accurate prediction information.

[0029] In summary, by compensating for sample errors in the predicted soil gap parameter set and the predicted soil nutrient parameter set, we can obtain more accurate and practical predicted soil gap parameter distributions and predicted soil nutrient parameter distributions. These parameter distributions not only reflect the impact of soil adjustment schemes on soil conditions, but also provide strong data support for subsequent optimization decisions.

[0030] S40: Based on the predicted distribution of soil nutrient parameters and the required soil nutrient parameters, calculate the soil nutrient fitness; based on the seed characteristic parameter distribution and the predicted distribution of soil gap parameters, calculate the soil gap fitness; perform soil adjustment and optimization to obtain the optimal soil adjustment scheme, which is used as the soil data processing result.

[0031] Specifically, the optimal soil conditioning scheme is ultimately determined through calculation and optimization strategies. The core of this step lies in calculating soil nutrient fitness and soil interstitial fitness. First, a comparative analysis is conducted between the predicted distribution of soil nutrient parameters and the required soil nutrient parameters. Mathematical algorithms are then used to quantify the degree to which the predicted soil nutrient parameters meet the growth requirements of the target seeds; this is the soil nutrient fitness. This indicator directly reflects the effectiveness of the soil conditioning scheme in providing nutrients. For example, if the content of elements such as nitrogen, phosphorus, and potassium in the predicted soil nutrient parameter distribution highly matches the requirements of the target seeds, then the soil nutrient fitness of the scheme will be correspondingly high.

[0032] Simultaneously, the degree of matching between soil gaps and seed characteristics must be considered. By comparing the distribution of seed characteristic parameters with the predicted distribution of soil gap parameters, the physical support capacity of soil gaps for seed growth can be assessed, i.e., soil gap fitness. This step fully considers the needs of seed size, shape, and other physical characteristics for soil gaps. For example, if the predicted distribution of soil gap parameters can provide suitable growth space for seeds of different sizes, ensuring sufficient contact between seeds and soil, thereby improving seed germination rate and growth rate, then the soil gap fitness of this scheme will be high.

[0033] After obtaining the soil nutrient fitness and soil gap fitness, an optimization algorithm is used to iteratively optimize the soil conditioning scheme. This process continuously tries different combinations of soil conditioning parameters to find a scheme that performs well in both soil nutrient and gap fitness aspects. Finally, when the optimization algorithm converges to a specific scheme, it is determined as the optimal soil conditioning scheme and output as the result of soil data processing.

[0034] In summary, by accurately calculating soil nutrient adaptability and soil gap adaptability, and combining this with optimization algorithms, the optimal soil adjustment scheme that meets the growth needs of the target seeds can be determined. This scheme not only improves the soil's nutrient supply capacity but also ensures sufficient contact between the seeds and the soil, laying a solid foundation for the healthy growth of the seeds.

[0035] In a preferred embodiment, the soil within the target land is tested to obtain soil characteristic parameters, and the required soil nutrient parameters and seed characteristic parameter distribution for the target seeds are obtained. This includes: testing the soil within the target land to obtain soil gap parameters and soil nutrient parameters, and integrating them to obtain soil characteristic parameters; collecting the required soil nutrient parameters for the target seeds; randomly sampling and measuring the size of the target seeds to obtain multiple seed size parameters; and constructing a seed characteristic parameter distribution based on the multiple seed size parameters.

[0036] Preferably, the purpose of testing the soil in the target land is to obtain detailed characteristic parameters of the soil, including soil porosity parameters and soil nutrient parameters. Soil porosity parameters mainly describe the physical structural characteristics of the soil, such as porosity and compaction, which are crucial for seed growth space and root development. Soil nutrient parameters cover the content of various nutrients in the soil, such as nitrogen, phosphorus, and potassium, which are indispensable for normal seed growth. To obtain these parameters, professionals use advanced soil testing technologies and equipment to take multiple samples from the target land, and then use laboratory analysis methods to accurately determine the soil porosity and nutrient content of each sample. Finally, by integrating these test data, a comprehensive set of soil characteristic parameters can be obtained, providing a basis for subsequent analysis and adjustments.

[0037] At the same time, in order to develop a more precise soil conditioning plan, it is also necessary to obtain the soil nutrient requirements of the target seeds. These parameters are usually determined based on the seed's growth habits and physiological needs, reflecting the specific requirements of the seeds for soil nutrients at different growth stages. Specific information can be obtained from materials provided by seed suppliers or through experimental measurements.

[0038] In addition, to assess the soil's physical support capacity for seed growth, the size of the target seeds needs to be measured. Multiple seeds are randomly sampled, and their size parameters, such as diameter and length, are obtained using measuring tools. Then, based on these size parameters, statistical methods are used to construct a distribution of seed characteristic parameters. This distribution describes the distribution patterns and characteristics of seed size, helping to understand the actual needs of seeds for soil gaps. For example, if the target seeds are large legumes, they require relatively loose soil gaps to provide sufficient growing space. In this case, by measuring the soil gap parameters in the target land, and combining this with the soil nutrient parameters required by legume seeds and the distribution of seed size characteristic parameters, a more scientific and reasonable soil adjustment plan can be formulated, such as increasing soil looseness and supplementing necessary nutrients to meet the growth needs of legume seeds.

[0039] In a preferred embodiment, a soil adjustment scheme is randomly configured, and integrated soil adjustment prediction is performed in conjunction with the soil characteristic parameters to obtain a predicted set of soil gap parameters and a predicted set of soil nutrient parameters. This includes: obtaining a soil adjustment scheme space and randomly configuring a soil adjustment scheme; calling a constructed integrated soil adjustment prediction path, wherein the integrated soil adjustment prediction path includes multiple soil adjustment prediction paths; inputting the soil adjustment scheme and soil characteristic parameters into the integrated soil adjustment prediction path, performing integrated soil adjustment prediction, and outputting the predicted set of soil gap parameters and the predicted set of soil nutrient parameters.

[0040] Specifically, to achieve accurate exploration and prediction of soil adjustment schemes, it is first necessary to define the possible value range of soil adjustment schemes, i.e., to obtain the soil adjustment scheme space. This space encompasses a set of combinations of various adjustment parameters, such as soil loosening depth, fertilizer type and ratio, and irrigation water volume. Based on this space, a random sampling algorithm is used to randomly configure soil adjustment schemes from the parameter combination set, generating multiple samples of adjustment strategies with differences. These samples represent possible choices of different adjustment directions and intensities.

[0041] Subsequently, a pre-constructed integrated soil adjustment prediction pathway is invoked. This integrated pathway is not a single prediction model, but rather a fusion of multiple soil adjustment prediction pathways based on different principles and employing different data characteristics. Each prediction pathway simulates the soil adjustment effect from different dimensions. For example, some pathways focus on predicting changes in soil physical structure, modeling the impact mechanism of soil loosening parameters on soil gaps; others focus on predicting changes in soil chemical properties, constructing nutrient transformation and migration models based on fertilization parameters and basic soil nutrient data. These pathways complement each other, collectively forming a comprehensive and multifaceted prediction system.

[0042] In the prediction phase, randomly configured soil adjustment schemes and previously obtained soil characteristic parameters are imported as input data into the integrated soil adjustment prediction path. Each prediction path processes and calculates the input parameters according to its own algorithm logic, simulating the dynamic changes in the soil after the implementation of different adjustment schemes. Finally, the output results of each path are integrated and optimized through ensemble prediction technology, outputting a predicted set of soil gap parameters and a predicted set of soil nutrient parameters.

[0043] For example, when predicting soil conditioning for a target plot of land with heavy clay soil and uneven nutrient distribution, a randomly configured soil conditioning scheme might include combinations of parameters such as deep loosening, increased application of organic fertilizer, and phosphorus and potassium fertilizer. The physical structure prediction path within the integrated soil conditioning prediction pathway predicts the adjusted set of soil gap parameters based on inputs such as soil gap parameters and loosening depth. This set may include predicted values ​​for indicators such as porosity and permeability at different soil depths. The chemical property prediction path predicts the set of soil nutrient parameters based on soil nutrient parameters and fertilization parameters, covering the changes in the content of elements such as nitrogen, phosphorus, and potassium at different soil layers. These prediction results provide a scientific basis for subsequent soil conditioning optimization and help determine the most suitable soil conditioning scheme.

[0044] In a preferred embodiment, the construction steps of the integrated soil adjustment prediction path include: collecting a set of sample soil characteristic parameters and a set of sample soil adjustment schemes based on historical soil adjustment data, and collecting the gap and nutrient parameters of the adjusted soil under different sample soil characteristic parameters and sample soil adjustment schemes to obtain a set of sample predicted soil gap parameters and a set of sample predicted soil nutrient parameters; combining the set of sample soil characteristic parameters, the set of sample soil adjustment schemes, the set of sample predicted soil gap parameters, and the set of sample predicted soil nutrient parameters to obtain a soil adjustment prediction sample set; performing multiple data partitioning with replacement on the soil adjustment prediction sample set to obtain multiple sets of soil adjustment prediction training data; constructing multiple soil adjustment prediction paths based on deep learning, and supervising training to convergence using the multiple sets of soil adjustment prediction training data to obtain an integrated soil adjustment prediction path.

[0045] Furthermore, constructing an integrated soil adjustment prediction path requires data collection, integration, segmentation, and model training. First, relying on a historical soil adjustment database, the system collects a set of characteristic parameters for sample soils, covering key indicators such as soil texture (e.g., the proportion of clay, silt, and sand), initial nutrient content (e.g., organic matter, nitrogen, phosphorus, and potassium concentrations), and pH. Simultaneously, it collects a set of soil adjustment schemes for the samples, including fertilizer types (e.g., nitrogen, phosphorus, and compound fertilizers), fertilizer application rates, irrigation frequency, and soil loosening depth. Based on this, for each sample's soil characteristic parameters and the soil after the implementation of the corresponding adjustment scheme, the system collects the soil's porosity and nutrient parameters, such as soil porosity, aeration, and dynamic changes in nitrogen, phosphorus, and potassium. These are then integrated to form a set of predicted soil porosity parameters and a set of predicted soil nutrient parameters for the samples. Subsequently, the sample soil characteristic parameter set, sample soil adjustment scheme set, sample predicted soil gap parameter set, and sample predicted soil nutrient parameter set are associated and combined to construct a soil adjustment prediction sample set. This sample set fully records the mapping relationship between different initial soil states, adjustment strategies, and adjustment effects, providing a data foundation for subsequent model training.

[0046] To improve the model's generalization ability and stability, the soil adjustment prediction sample set was split multiple times with replacement. Specifically, in each split, a certain proportion of the data was randomly selected from the sample set as training data, and the remaining data was used as validation or test data. This process was repeated until multiple independent and representative soil adjustment prediction training datasets were obtained.

[0047] Next, based on a deep learning framework, multiple soil adjustment prediction paths with different network structures or hyperparameter configurations are constructed. These paths may include convolutional neural networks (CNNs) to capture the spatial correlation of soil feature parameters; recurrent neural networks (RNNs) or their variants (such as LSTM and GRU) to process time-series data such as fertilization frequency; and fully connected neural networks to integrate multi-source information and output prediction results. Each prediction path is trained under supervision using multiple sets of soil adjustment prediction training data. The network weights are continuously adjusted using the backpropagation algorithm until the loss function of the model on the training and validation sets converges to a stable state, ultimately obtaining an integrated soil adjustment prediction path. For example, in the adjustment prediction of a specific acidic soil, the integrated prediction path can comprehensively consider parameters such as initial soil pH, fertilizer type and amount, and accurately predict the changing trends of soil gaps and nutrient parameters after adjustment, providing a scientific basis for soil improvement.

[0048] In a preferred embodiment, based on the occurrence rate of the soil characteristic parameters and soil adjustment schemes in the integrated adjustment prediction data samples, combined with the historical adjustment error rate of the soil adjustment schemes, sample error compensation is performed on the predicted soil gap parameter set and the predicted soil nutrient parameter set to obtain the predicted soil gap parameter distribution and the predicted soil nutrient parameter distribution. This includes: obtaining the average prediction accuracy rate of the integrated soil adjustment prediction path test and calculating the prediction error rate; extracting the occurrence proportion of the soil characteristic parameters and soil adjustment schemes in the soil adjustment prediction sample set to obtain the soil characteristic occurrence coefficient and adjustment scheme occurrence coefficient, and extracting and calculating the average soil characteristic occurrence coefficient and average adjustment scheme occurrence coefficient of other sample soil characteristic parameters and sample soil adjustment schemes; respectively Calculate the ratio of the average soil characteristic occurrence coefficient and the average adjustment scheme occurrence coefficient to the soil characteristic occurrence coefficient and the adjustment scheme occurrence coefficient, and calculate the mean to obtain the data sample occurrence rate; use the data sample occurrence rate to correct the prediction error rate to obtain the corrected prediction error rate; obtain the historical adjustment error rate of the soil adjustment scheme; based on the corrected prediction error rate and the historical adjustment error rate, calculate the error compensation coefficient, and perform error compensation on the predicted soil gap parameter set and the predicted soil nutrient parameter set to obtain the compensated soil gap parameter interval set and the compensated soil nutrient parameter interval set; take the intersection of the compensated soil gap parameter interval set and the compensated soil nutrient parameter interval set respectively to obtain the predicted soil gap parameter distribution and the predicted soil nutrient parameter distribution.

[0049] Preferably, in the error compensation stage of the soil data processing workflow, to improve the accuracy of prediction parameters, a systematic multi-step calculation is required. First, the integrated soil adjustment prediction path is tested and evaluated, and its average prediction accuracy is calculated using methods such as cross-validation. For example, if the accuracy of the integrated prediction path on the test set is 95%, then the prediction error rate can be calculated as 1-95%=5%. This error rate reflects the prediction deviation of the model under ideal conditions.

[0050] Subsequently, the occurrence proportions of soil characteristic parameters and soil adjustment schemes in the soil adjustment prediction sample set are extracted. For example, if the occurrence proportion of a specific soil texture (such as clay) in the sample set is 1%, then its soil characteristic occurrence coefficient is 1%; if the occurrence proportion of a certain fertilization scheme (such as a high-nitrogen fertilizer scheme) is 1%, then its adjustment scheme occurrence coefficient is 1%. Simultaneously, the average occurrence proportion of soil characteristic parameters and the average occurrence proportion of soil adjustment schemes for all samples are calculated. For example, the average occurrence proportion of all soil characteristic parameters may be 0.5%, and the average occurrence proportion of all soil adjustment schemes may be 0.5%, meaning that both the average soil characteristic occurrence coefficient and the average adjustment scheme occurrence coefficient are 0.5%.

[0051] Based on the above coefficients, the ratio of the average soil characteristic occurrence coefficient to the average soil characteristic occurrence coefficient, and the ratio of the average adjustment scheme occurrence coefficient to the average adjustment scheme occurrence coefficient are calculated, and their average is taken to obtain the data sample occurrence rate. For example, if the soil characteristic occurrence coefficient is 1% and the average soil characteristic occurrence coefficient is 0.5%, then the ratio is 0.5% / 1% = 0.5; similarly, if the adjustment scheme occurrence coefficient is 1% and the average adjustment scheme occurrence coefficient is 0.5%, then the ratio is also 0.5. The average of the two is the data sample occurrence rate, 0.5. This coefficient reflects the representativeness of the current sample in the overall sample space. The lower the data sample occurrence rate, the rarer the current sample is, and the higher the uncertainty of the prediction result.

[0052] Furthermore, the prediction error rate is corrected using the data sample occurrence rate to obtain the corrected prediction error rate. For example, if the prediction error rate is 5% and the data sample occurrence rate is 0.5, then the corrected prediction error rate is 0.5 × 5% = 2.5%. The corrected error rate comprehensively considers the impact of sample representativeness on prediction accuracy.

[0053] Simultaneously, the historical adjustment error rate of the soil conditioning scheme is obtained. This error rate is calculated based on the difference between the actual and predicted results in the past, and may be positive or negative, reflecting the systematic deviation of a specific adjustment scheme in actual application. For example, if a fertilization scheme has resulted in an average soil nutrient content that is 5% higher than the predicted value in the past, its historical adjustment error rate is +5%; if it has resulted in soil porosity that is 3% lower than the predicted value, the historical adjustment error rate is -3%.

[0054] Furthermore, based on the corrected prediction error rate and the historical adjustment error rate, an error compensation coefficient is calculated. For example, if the corrected prediction error rate is 2.5% and the historical adjustment error rate of a certain soil adjustment scheme is +5%, then the error compensation coefficient is the sum of the two, 7.5%. This coefficient is used to quantify the overall adjustment range of the prediction results.

[0055] Finally, error compensation coefficients are used to compensate for errors in the predicted soil gap parameter set and the predicted soil nutrient parameter set. For example, if a predicted soil gap parameter is 30% and the error compensation coefficient is ±7.5%, then the compensated soil gap parameter interval is [30%×(1-7.5%), 30%×(1+7.5%)]=[27.75%, 32.25%]. Similarly, if a predicted soil nutrient parameter is 100mg / kg, the compensated soil nutrient parameter interval is [100mg / kg×(1-7.5%), 100mg / kg×(1+7.5%)]=[92.5mg / kg, 107.5mg / kg]. By taking the intersection of the compensated soil gap parameter interval set and the compensated soil nutrient parameter interval set respectively, the distributions of the predicted soil gap parameter and the predicted soil nutrient parameter are finally obtained. For example, if the compensated soil gap parameter ranges for a certain soil under multiple adjustment schemes are [25%, 30%] and [28%, 33%], then its predicted soil gap parameter distribution is the intersection of the two [28%, 30%]. This distribution provides a more reliable parameter range for subsequent soil adjustment and optimization.

[0056] In a preferred embodiment, obtaining the historical adjustment error rate of the soil adjustment scheme includes: searching within the soil adjustment data of the historical period according to the soil adjustment scheme to obtain multiple soil adjustment data, wherein each soil adjustment data includes an average predicted soil characteristic parameter and an actual adjusted soil characteristic parameter; and calculating the average deviation of the actual adjusted soil characteristic parameter from the average predicted soil characteristic parameter based on the multiple soil adjustment data to obtain the historical adjustment error rate.

[0057] Furthermore, obtaining historical adjustment error rates is a crucial step in the error assessment process of soil conditioning programs. Specifically, a systematic search needs to be conducted in a historical database based on the target soil conditioning program. This database stores various soil conditioning operations implemented in different time periods and their corresponding data records. By setting specific search criteria, such as parameters related to the adjustment program, such as fertilizer type, fertilizer amount, irrigation strategy, and soil loosening depth, multiple soil conditioning data matching the target program can be accurately located. For example, if the target program is "apply 20 kg of nitrogen fertilizer and 15 kg of phosphorus fertilizer per acre, and loosen the soil to a depth of 30 cm," the search process will filter out all historical adjustment records with the same or similar fertilizer ratios and soil loosening depths.

[0058] Each retrieved soil adjustment data point contains two core parameter sets: average predicted soil characteristic parameters and actual adjusted soil characteristic parameters. The average predicted soil characteristic parameters are generated based on historical model predictions and reflect the expected trends in soil characteristic parameters (such as soil nutrient content, pH, and porosity) under a specific adjustment scheme. The actual adjusted soil characteristic parameters are obtained through field sampling and laboratory analysis, representing the true state of soil characteristic parameters after the implementation of the adjustment scheme. For example, a data point might show that under a specific adjustment scheme, the average predicted value for soil organic matter content is 2.5%, while the actual measured value after adjustment is 2.2%.

[0059] Finally, based on multiple soil adjustment data points, the average deviation of the actual adjusted soil characteristic parameters from the average predicted soil characteristic parameters is further calculated to quantify the historical adjustment error rate. The specific calculation process is as follows: for each data point, the deviation between the actual and predicted values ​​(such as absolute or relative deviation) is calculated, and the arithmetic mean of all deviations is taken to obtain the historical adjustment error rate. For example, if 10 relevant data points are retrieved, and the actual and predicted values ​​of soil organic matter content deviate from the predicted values ​​by -0.1%, +0.2%, and -0.3%, respectively, the historical adjustment error rate for that characteristic parameter can be obtained by summing these deviations and dividing by the number of data points. Similarly, the historical adjustment error rate can be calculated separately for other soil characteristic parameters. The final obtained historical adjustment error rate can objectively reflect the systematic deviation of a specific soil adjustment scheme in historical applications, providing a key basis for subsequent error compensation and scheme optimization.

[0060] In a preferred embodiment, soil nutrient fitness is calculated based on the predicted soil nutrient parameter distribution and the required soil nutrient parameters; soil gap fitness is calculated based on the seed characteristic parameter distribution and the predicted soil gap parameter distribution; and soil adjustment optimization is performed to obtain the optimal soil adjustment scheme. This includes: extracting the median value of the predicted soil nutrient parameter distribution, calculating the nutrient deviation amplitude from the required soil nutrient parameters, and calculating the soil nutrient fitness; extracting the intersection of the seed characteristic parameter distribution and the predicted soil gap parameter distribution, calculating the overlap ratio with the seed characteristic parameter distribution as the soil gap fitness; and performing soil adjustment optimization based on the soil nutrient fitness and soil gap fitness to obtain the optimal soil adjustment scheme.

[0061] In detail, during the soil conditioning and optimization process, to accurately determine the optimal soil conditioning scheme that meets the growth needs of crops, it is necessary to comprehensively consider the adaptability of soil nutrients and gaps. First, focus on calculating soil nutrient adaptability. Extract the median value from the predicted distribution of soil nutrient parameters. This median value can be regarded as a representative of the central tendency of the predicted nutrient parameters, reflecting the expected level of soil nutrient content under a specific soil conditioning scheme. For example, if the median value of the predicted soil nitrogen content distribution is 120 mg / kg, and the nitrogen content in the crop's required soil nutrient parameters is set at 100 mg / kg, then the nutrient deviation is obtained by calculating the absolute difference between the two and dividing it by the required soil nutrient parameters. That is, the nutrient deviation range is |(120-100)| / 100=20%. This deviation range directly reflects the degree of deviation between the predicted nutrient parameters and the required nutrient parameters. Based on this deviation range, combined with the preset fitness calculation rules (such as the smaller the deviation range, the higher the fitness), the soil nutrient fitness can be calculated. The higher the fitness value, the closer the predicted soil nutrient parameters are to the crop requirements, and the stronger the suitability of the soil nutrient conditions for crop growth.

[0062] Next, soil porosity fitness is calculated by intersecting the distribution of seed characteristic parameters with the predicted distribution of soil porosity parameters to determine the range of parameters covered by both. For example, if the suitable soil porosity range in the seed characteristic parameter distribution is 40%-50%, while the porosity range in the predicted soil porosity parameter distribution is 35%-55%, then the intersection is 40%-50%. Subsequently, the overlap ratio between the intersection range and the seed characteristic parameter distribution is calculated as a quantitative indicator of soil porosity fitness. For example, if the complete range of suitable porosity in the seed characteristic parameter distribution spans 15% (40%-55%, assuming a lower limit of 40% is the suitable lower limit, and an upper limit of 55% exceeds actual needs and is only for illustrative purposes; the actual range should be based on the suitable range), and the intersection range spans 10%, then the overlap ratio is 10% / 15%≈66.7% (this is only to illustrate the calculation logic; the actual calculation needs to be accurate based on the suitable range of the seeds). The higher the overlap ratio, the better the predicted soil gap parameters can meet the requirements of seed germination and growth for soil structure, and the higher the soil gap adaptability.

[0063] Finally, soil adjustment and optimization are carried out based on the calculated soil nutrient fitness and soil gap fitness. Specifically, the fitness values ​​of both are incorporated into a comprehensive evaluation system. Weighted summation or other optimization algorithms are performed by setting weights (e.g., assigning different weights according to the crop's sensitivity to nutrients and gaps) to select the soil adjustment scheme that achieves the best balance in both nutrient and gap aspects. For example, if the nutrient fitness weight is 0.6 and the gap fitness weight is 0.4, and a certain soil adjustment scheme has a nutrient fitness of 0.8 and a gap fitness of 0.7, then its comprehensive fitness is 0.6 × 0.8 + 0.4 × 0.7 = 0.76. By performing similar calculations and comparisons on multiple different soil adjustment schemes, the scheme with the highest comprehensive fitness is selected as the optimal soil adjustment scheme. This scheme can maximally meet the crop's needs for soil nutrients and gaps, creating an ideal soil environment for crop growth.

[0064] In a preferred embodiment, soil adjustment optimization is performed based on the soil nutrient fitness and soil gap fitness to obtain the optimal soil adjustment scheme, including: weighting the soil nutrient fitness and soil gap fitness to obtain the soil adjustment fitness; continuing to randomly configure the soil adjustment scheme and calculate the soil adjustment fitness, performing soil adjustment optimization until optimization convergence, and outputting the optimal soil adjustment scheme with the largest soil adjustment fitness.

[0065] Specifically, to accurately determine the optimal solution for crop growth, systematic optimization must be carried out based on soil nutrient adaptability and soil gap adaptability. First, soil nutrient adaptability and soil gap adaptability are weighted according to factors such as crop growth characteristics, varietal differences, and growth stage. For example, for crops with high nutrient requirements and high root aeration requirements, soil nutrient adaptability can be assigned a higher weight (e.g., 0.6), while soil gap adaptability can be assigned a lower weight (e.g., 0.4). Conversely, if the crop has relatively balanced soil nutrient requirements but is more sensitive to soil structure, the weights can be adjusted to 0.4 for soil nutrient adaptability and 0.6 for soil gap adaptability. The soil adjustment adaptability is obtained by multiplying the two adaptability values ​​by their respective weights and then summing them. This adaptability comprehensively reflects the suitability of a specific soil adjustment scheme for crop growth in terms of both nutrient supply and gap structure. For example, if the soil nutrient fitness corresponding to a certain soil adjustment scheme is 0.85, the soil gap fitness is 0.75, and the weight of nutrient fitness is 0.6 and the weight of gap fitness is 0.4, then its soil adjustment fitness is 0.6×0.85+0.4×0.75=0.81.

[0066] Subsequently, a random search algorithm or intelligent optimization algorithm (such as genetic algorithm, particle swarm optimization, etc.) is used to continue randomly configuring the soil adjustment scheme. Specifically, within the algorithm framework, a new set of soil adjustment parameters is randomly generated in each iteration, including fertilizer type, fertilizer amount, irrigation strategy, and soil loosening depth. These parameters together constitute a new soil adjustment scheme. Based on this scheme, the corresponding soil nutrient fitness and soil gap fitness are recalculated and weighted again to obtain a new soil adjustment fitness. For example, by randomly generating an adjustment scheme through the algorithm, adjusting the fertilizer amount to 18 kg of compound fertilizer per acre and setting the soil loosening depth to 25 cm, the distribution of soil nutrients and gap parameters is simulated and predicted according to this scheme, and then its nutrient fitness is calculated to be 0.82 and its gap fitness to be 0.78. The corresponding soil adjustment fitness is 0.6 × 0.82 + 0.4 × 0.78 = 0.804.

[0067] The process of randomly configuring the soil and calculating fitness is repeated multiple times for iterative optimization. During optimization, the algorithm filters and updates different schemes based on their fitness values, retaining schemes with higher fitness as the basis for the next generation of optimization, gradually approaching the optimal solution. For example, in genetic algorithms, new scheme populations are continuously generated through operations such as selection, crossover, and mutation, allowing the characteristics of schemes with higher fitness to be preserved and combined, while schemes with lower fitness are gradually eliminated. As the number of iterations increases, the soil adjustment fitness gradually stabilizes, reaching an optimization convergence state. At this point, the algorithm outputs the soil adjustment scheme with the highest fitness as the optimal solution. This scheme achieves the best balance in terms of both nutrients and gaps, maximizing the satisfaction of crop growth needs and providing a scientific and efficient soil adjustment strategy for agricultural production.

[0068] The soil data processing method combined with demand analysis provided in this embodiment of the invention has at least the following technical effects: 1. By detecting soil characteristic parameters of the target land and simultaneously obtaining the soil nutrient parameters required by the target seeds and the distribution of seed characteristic parameters, the soil background conditions and crop requirements are deeply integrated. Soil adjustment schemes are randomly configured and predictions are made using integrated soil adjustment prediction paths. Predicted soil gap parameter sets and nutrient parameter sets are obtained, realizing the transformation from multi-source data to accurate prediction. This provides a solid foundation for subsequent adjustments and significantly improves the scientific nature and pertinence of soil adjustment scheme formulation.

[0069] 2. By introducing the data sample occurrence rate and historical adjustment error rate, sample error compensation is performed on the prediction parameter set. The prediction error rate, feature and scheme occurrence coefficient, and data sample occurrence rate are calculated, and the error compensation coefficient is obtained by combining the historical adjustment error rate. Interval compensation is performed on the prediction parameter set, and the predicted distribution of soil gap parameters and nutrient parameters is finally obtained. This effectively reduces the prediction inaccuracy caused by sample bias and historical adjustment error, making the prediction results closer to the actual situation and providing more reliable data support for subsequent fitness calculation and scheme optimization.

[0070] 3. Based on the predicted distribution of soil nutrient parameters and demand parameters, the distribution of seed characteristic parameters, and the predicted distribution of soil gap parameters, soil nutrient fitness and soil gap fitness are calculated respectively. The soil adjustment fitness is obtained through weighted calculation. An intelligent optimization algorithm is used to continuously and randomly configure soil adjustment schemes and calculate fitness. Multiple rounds of iterative optimization are carried out until convergence, and finally the optimal scheme with the largest soil adjustment fitness is output. With crop demand as the guide, the synergistic optimization of soil nutrients and gaps is realized, which greatly improves the matching degree between soil adjustment schemes and crop growth needs, creates the best soil environment for crop growth, and powerfully promotes the precision and efficiency of agricultural production.

[0071] Example 2:

[0072] like Figure 2 As shown, based on the same inventive concept as the soil data processing method combining demand analysis provided in Embodiment 1, this embodiment of the invention also provides a soil data processing system combining demand analysis, the system comprising: The basic detection module 11 is used to detect the soil in the target land, obtain soil characteristic parameters, and acquire the soil nutrient parameters required by the target seeds and the distribution of seed characteristic parameters. The soil characteristic parameters include soil gap parameters and soil nutrient parameters.

[0073] The adjustment prediction module 12 is used to randomly configure the soil adjustment scheme, combine the soil characteristic parameters to perform integrated soil adjustment prediction, and obtain the predicted soil gap parameter set and the predicted soil nutrient parameter set.

[0074] Error compensation module 13 is used to perform sample error compensation on the predicted soil gap parameter set and the predicted soil nutrient parameter set based on the occurrence rate of data samples in the integrated adjustment prediction of the soil characteristic parameters and soil adjustment scheme, combined with the historical adjustment error rate of the soil adjustment scheme, so as to obtain the predicted soil gap parameter distribution and the predicted soil nutrient parameter distribution.

[0075] The adjustment and optimization module 14 is used to calculate the soil nutrient fitness based on the predicted soil nutrient parameter distribution and the required soil nutrient parameters, calculate the soil gap fitness based on the seed characteristic parameter distribution and the predicted soil gap parameter distribution, perform soil adjustment and optimization, and obtain the optimal soil adjustment scheme as the soil data processing result.

[0076] Furthermore, the basic detection module 11 is also used to perform the following steps: The soil in the target land is tested to obtain soil gap parameters and soil nutrient parameters, and integrated to obtain soil characteristic parameters; the soil nutrient parameters required by the target seeds are collected; the target seeds are randomly sampled and their size is measured to obtain multiple seed size parameters; and a distribution of seed characteristic parameters is constructed based on the multiple seed size parameters.

[0077] Furthermore, the adjustment prediction module 12 is also used to perform the following steps: Obtain the soil adjustment scheme space and randomly configure the soil adjustment scheme; invoke the constructed integrated soil adjustment prediction path, wherein the integrated soil adjustment prediction path includes multiple soil adjustment prediction paths; The soil adjustment scheme and soil characteristic parameters are input into the integrated soil adjustment prediction path to perform integrated soil adjustment prediction, and the predicted soil gap parameter set and predicted soil nutrient parameter set are output.

[0078] Furthermore, the adjustment prediction module 12 is also used to perform the following steps: Based on historical soil adjustment data, a set of sample soil characteristic parameters and a set of sample soil adjustment schemes are collected. Furthermore, the gap and nutrient parameters of the adjusted soil under different sample soil characteristic parameters and sample soil adjustment schemes are collected to obtain a set of sample predicted soil gap parameters and a set of sample predicted soil nutrient parameters. These sets are then combined to obtain a soil adjustment prediction sample set. The soil adjustment prediction sample set is further divided with replacement multiple times to obtain multiple sets of soil adjustment prediction training data. Based on deep learning, multiple soil adjustment prediction paths are constructed, and each path is trained to convergence using the multiple sets of soil adjustment prediction training data to obtain an integrated soil adjustment prediction path.

[0079] Furthermore, the error compensation module 13 is also used to perform the following steps: The average prediction accuracy of the integrated soil adjustment prediction path is obtained, and the prediction error rate is calculated. The occurrence ratio of the soil characteristic parameters and soil adjustment schemes in the soil adjustment prediction sample set is extracted to obtain the soil characteristic occurrence coefficient and adjustment scheme occurrence coefficient. The average soil characteristic occurrence coefficient and average adjustment scheme occurrence coefficient of other sample soil characteristic parameters and sample soil adjustment schemes are extracted and calculated. The ratio of the average soil characteristic occurrence coefficient and average adjustment scheme occurrence coefficient to the soil characteristic occurrence coefficient and adjustment scheme occurrence coefficient is calculated, and the mean is calculated to obtain the data sample occurrence rate. The prediction error rate is corrected using the data sample occurrence rate to obtain the corrected prediction error rate. The historical adjustment error rate of the soil adjustment scheme is obtained. Based on the corrected prediction error rate and the historical adjustment error rate, the error compensation coefficient is calculated to compensate for the error in the predicted soil gap parameter set and the predicted soil nutrient parameter set, obtaining the compensated soil gap parameter interval set and the compensated soil nutrient parameter interval set. The intersection of the compensated soil gap parameter interval set and the compensated soil nutrient parameter interval set is taken to obtain the predicted soil gap parameter distribution and the predicted soil nutrient parameter distribution.

[0080] Furthermore, the error compensation module 13 is also used to perform the following steps: According to the soil adjustment scheme, multiple soil adjustment data are retrieved from historical soil adjustment data. Each soil adjustment data includes the average predicted soil characteristic parameter and the actual adjusted soil characteristic parameter. Based on the multiple soil adjustment data, the average deviation of the actual adjusted soil characteristic parameter from the average predicted soil characteristic parameter is calculated to obtain the historical adjustment error rate.

[0081] Furthermore, the adjustment and optimization module 14 is also used to perform the following steps: The median value of the predicted soil nutrient parameter distribution is extracted, the nutrient deviation from the required soil nutrient parameters is calculated, and the soil nutrient fitness is calculated. The intersection of the seed characteristic parameter distribution and the predicted soil gap parameter distribution is extracted, and the overlap ratio with the seed characteristic parameter distribution is calculated as the soil gap fitness. Based on the soil nutrient fitness and soil gap fitness, soil adjustment and optimization are performed to obtain the optimal soil adjustment scheme.

[0082] Furthermore, the adjustment and optimization module 14 is also used to perform the following steps: The soil nutrient fitness and soil gap fitness are weighted and calculated to obtain the soil adjustment fitness; the soil adjustment scheme is randomly configured and the soil adjustment fitness is calculated again. The soil adjustment is optimized until the optimization converges, and the optimal soil adjustment scheme with the largest soil adjustment fitness is output.

[0083] Through the foregoing detailed description of a soil data processing method incorporating demand analysis, those skilled in the art can clearly understand the soil data processing system incorporating demand analysis in this embodiment. As the system disclosed in the embodiment corresponds to the method disclosed in the embodiment, the description is relatively simple, and relevant details can be found in the method section.

[0084] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A soil data processing method in combination with demand analysis, characterized by, The method comprises: detecting the soil in the target land to obtain soil characteristic parameters, and obtaining the required soil nutrient parameters of the target seeds and the seed characteristic parameter distribution, wherein the soil characteristic parameters comprise soil gap parameters and soil nutrient parameters; randomly configuring a soil adjustment scheme, and performing integrated soil adjustment prediction combined with the soil characteristic parameters to obtain a predicted soil gap parameter set and a predicted soil nutrient parameter set; based on the data sample occurrence rate of the soil characteristic parameters and the soil adjustment scheme in the integrated adjustment prediction, and combined with the historical adjustment error rate of the soil adjustment scheme, sample error compensation is performed on the predicted soil gap parameter set and the predicted soil nutrient parameter set to obtain a predicted soil gap parameter distribution and a predicted soil nutrient parameter distribution; based on the predicted soil nutrient parameter distribution and the required soil nutrient parameters, the soil nutrient fitness is calculated and obtained, based on the seed characteristic parameter distribution and the predicted soil gap parameter distribution, the soil gap fitness is calculated and obtained, and soil adjustment optimization is performed to obtain an optimal soil adjustment scheme as the soil data processing result.

2. The soil data processing method in connection with requirement analysis according to claim 1, characterized in that, detecting the soil in the target land to obtain soil characteristic parameters, and obtaining the required soil nutrient parameters of the target seeds and the seed characteristic parameter distribution, comprising: detecting the soil in the target land to obtain soil gap parameters and soil nutrient parameters, and integrating to obtain soil characteristic parameters; collecting the required soil nutrient parameters of the target seeds; randomly sampling and detecting the size of the target seeds to obtain a plurality of seed size parameters; based on the plurality of seed size parameters, the seed characteristic parameter distribution is constructed.

3. The soil data processing method in conjunction with requirement analysis according to claim 1, characterized in that, randomly configuring a soil adjustment scheme, and performing integrated soil adjustment prediction combined with the soil characteristic parameters to obtain a predicted soil gap parameter set and a predicted soil nutrient parameter set, comprising: obtaining a soil adjustment scheme space, and randomly configuring a soil adjustment scheme; calling the constructed integrated soil adjustment prediction path, wherein the integrated soil adjustment prediction path comprises a plurality of soil adjustment prediction paths; inputting the soil adjustment scheme and the soil characteristic parameters into the integrated soil adjustment prediction path to perform integrated soil adjustment prediction, and outputting the predicted soil gap parameter set and the predicted soil nutrient parameter set.

4. The soil data processing method in connection with requirement analysis according to claim 3, characterized by, The construction steps of the integrated soil adjustment prediction path comprise: based on the adjustment history data of the soil, a sample soil characteristic parameter set and a sample soil adjustment scheme set are collected, and the gap and nutrient parameters of the adjusted soil under different sample soil characteristic parameters and sample soil adjustment schemes are collected to obtain a sample predicted soil gap parameter set and a sample predicted soil nutrient parameter set; combining the sample soil characteristic parameter set, the sample soil adjustment scheme set, the sample predicted soil gap parameter set and the sample predicted soil nutrient parameter set to obtain a soil adjustment prediction sample set; performing multiple data division with replacement on the soil adjustment prediction sample set to obtain multiple soil adjustment prediction training data; based on deep learning, a plurality of soil adjustment prediction paths are constructed, and the multiple soil adjustment prediction training data are supervised and trained to convergence respectively to obtain an integrated soil adjustment prediction path.

5. The soil data processing method in connection with requirement analysis according to claim 3, characterized by, According to the data sample occurrence rate of the soil characteristic parameters and the soil adjustment scheme in the integrated adjustment prediction, in combination with the historical adjustment error rate of the soil adjustment scheme, sample error compensation is performed on the predicted soil gap parameter set and the predicted soil nutrient parameter set to obtain a predicted soil gap parameter distribution and a predicted soil nutrient parameter distribution, including: An average prediction accuracy rate of the integrated soil adjustment prediction path is obtained, and a prediction error rate is calculated and obtained; The occurrence proportion of the soil characteristic parameters and the soil adjustment scheme in the soil adjustment prediction sample set is extracted to obtain a soil characteristic occurrence coefficient and an adjustment scheme occurrence coefficient, and the average soil characteristic occurrence coefficient and the average adjustment scheme occurrence coefficient of other sample soil characteristic parameters and sample soil adjustment schemes are extracted and calculated; The ratio of the average soil characteristic occurrence coefficient and the average adjustment scheme occurrence coefficient to the soil characteristic occurrence coefficient and the adjustment scheme occurrence coefficient is calculated respectively, and the mean value is calculated to obtain a data sample occurrence rate; The prediction error rate is corrected and calculated by using the data sample occurrence rate to obtain a corrected prediction error rate; The historical adjustment error rate of the soil adjustment scheme is obtained; According to the corrected prediction error rate and the historical adjustment error rate, an error compensation coefficient is calculated to perform error compensation on the predicted soil gap parameter set and the predicted soil nutrient parameter set to obtain a compensated soil gap parameter interval set and a compensated soil nutrient parameter interval set; The intersection of the compensated soil gap parameter interval set and the compensated soil nutrient parameter interval set is taken respectively to obtain a predicted soil gap parameter distribution and a predicted soil nutrient parameter distribution.

6. The soil data processing method in connection with requirement analysis according to claim 5, characterized by, The historical adjustment error rate of the soil adjustment scheme is obtained, including: According to the soil adjustment scheme, the soil adjustment data in the historical time is searched to obtain a plurality of soil adjustment data, wherein each soil adjustment data includes an average predicted soil characteristic parameter and an actual adjusted soil characteristic parameter; According to the plurality of soil adjustment data, the average amplitude of the actual adjusted soil characteristic parameter deviating from the average predicted soil characteristic parameter is calculated to obtain a historical adjustment error rate.

7. The soil data processing method in conjunction with requirement analysis according to claim 1, characterized in that, According to the predicted soil nutrient parameter distribution and the required soil nutrient parameter, a soil nutrient fitness is calculated and obtained, according to the seed characteristic parameter distribution and the predicted soil gap parameter distribution, a soil gap fitness is calculated and obtained, and soil adjustment optimization is performed to obtain an optimal soil adjustment scheme, including: The median value of the predicted soil nutrient parameter distribution is extracted, the nutrient deviation amplitude of the required soil nutrient parameter is calculated, and the soil nutrient fitness is calculated and obtained; The intersection of the seed characteristic parameter distribution and the predicted soil gap parameter distribution is extracted, and the coincidence proportion of the seed characteristic parameter distribution is calculated as the soil gap fitness; According to the soil nutrient fitness and the soil gap fitness, soil adjustment optimization is performed to obtain an optimal soil adjustment scheme.

8. The soil data processing method in conjunction with requirement analysis according to claim 7, characterized in that, According to the soil nutrient fitness and the soil gap fitness, soil adjustment optimization is performed to obtain an optimal soil adjustment scheme, including: The soil nutrient fitness and the soil gap fitness are weighted and calculated to obtain a soil adjustment fitness; Continue to randomly configure the soil adjustment scheme and calculate the soil adjustment fitness, perform soil adjustment optimization until optimization convergence is reached, and output the optimal soil adjustment scheme with the maximum soil adjustment fitness.

9. A soil data processing system incorporating requirements analysis, characterized by, A soil data processing method for implementing the demand analysis, the system comprising: a basic detection module for detecting the soil in the target land, obtaining soil characteristic parameters, and acquiring demand soil nutrient parameters and seed characteristic parameter distribution of the target seed, wherein the soil characteristic parameters include soil gap parameters and soil nutrient parameters; an adjustment prediction module for randomly configuring a soil adjustment scheme, performing integrated soil adjustment prediction in combination with the soil characteristic parameters, and obtaining a predicted soil gap parameter set and a predicted soil nutrient parameter set; an error compensation module for performing sample error compensation on the predicted soil gap parameter set and the predicted soil nutrient parameter set according to the data sample occurrence rate of the soil characteristic parameters and the soil adjustment scheme in integrated adjustment prediction, and combining the historical adjustment error rate of the soil adjustment scheme to obtain a predicted soil gap parameter distribution and a predicted soil nutrient parameter distribution; an adjustment optimization module for calculating soil nutrient fitness based on the predicted soil nutrient parameter distribution and the demand soil nutrient parameters, calculating soil gap fitness based on the seed characteristic parameter distribution and the predicted soil gap parameter distribution, performing soil adjustment optimization, and obtaining an optimal soil adjustment scheme as a soil data processing result.

Images