An intelligent control method for water-fertilizer coupling carbon effect

Abstract

The present invention relates to the technical field of farmland water and fertilizer regulation, and discloses a method for intelligent regulation of water-fertilizer coupled carbon effects. The method first acquires farmland environmental perception information, analyzes it, constructs a water-fertilizer carbon coupling scenario, and determines an initial regulation parameter set. The method then acquires dynamic adjustment operations fed back by users to determine a regulation adjustment information set. The regulation adjustment information set is then hierarchically decomposed, classified, and statistically analyzed to determine a target regulation scheme. Finally, a supplier resource information set is obtained, and a targeted regulation execution plan is determined and output based on this information. This method constructs a scenario feature model based on multiple factors, identifies user preferences through interactive simulation, evaluates parameter stability from a physical and biochemical perspective, and optimizes resource allocation based on historical supplier data. This method achieves intelligent and precise regulation of farmland water and fertilizer, improves regulation efficiency and resource utilization, and reduces the impact of carbon effects. The method is suitable for the field of farmland water and fertilizer management.

Description

Technical Field

[0001] The present invention relates to the technical field of farmland water and fertilizer regulation, and specifically to an intelligent regulation method for water-fertilizer coupled carbon effect. Background Art

[0002] In agricultural production, farmland water and fertilizer management plays a vital role in crop growth and yield improvement. With the increasing severity of global climate change, the carbon impact of agricultural production has gradually become a focus of attention. Traditional methods of regulating farmland water and fertilizer have many shortcomings and cannot meet the requirements of modern agriculture for high efficiency, precision, and low carbon emissions.

[0003] In terms of control precision, traditional methods often rely on experience or simple indicators, failing to fully consider the complexity and dynamic nature of the farmland environment. Factors such as soil moisture, crop growth cycles, and spatial location interact with each other, forming a complex coupling relationship. Traditional methods struggle to comprehensively and deeply analyze and integrate these factors, resulting in a lack of scientific and accurate determination of control parameters, making precise control difficult.

[0004] Traditional methods lack effective interactive mechanisms to address user needs, preventing them from obtaining timely feedback based on actual conditions and making dynamic adjustments. During actual operations, users may request adjustments to control plans based on factors such as crop growth conditions and weather changes. However, traditional methods struggle to quickly respond to these requests, resulting in poor adaptability.

[0005] Traditional methods for evaluating the stability of parameter combinations also have significant flaws. They often focus solely on the effects of individual parameters, while ignoring the interactions between parameter combinations and their physical and biochemical stability. In real farmland environments, the stability of parameter combinations directly impacts the durability and reliability of regulatory effects. Traditional methods are unable to conduct a comprehensive and systematic stability assessment of parameter combinations, which can easily lead to unstable regulatory effects and even adversely affect crop growth and the farmland ecosystem.

[0006] When formulating control plans, traditional methods struggle to comprehensively consider multiple factors, including the control cycle, crop growth cycle, and resource depletion. Crop growth cycles vary across farmland, and control cycles need to be rationally divided based on actual conditions. Resource depletion during the control process also needs to be considered to develop a scientific and rational control plan. However, traditional methods lack effective data statistics and analytical tools, making it difficult to comprehensively consider these factors, resulting in a lack of systematic and scientific control plan development.

[0007] Furthermore, traditional approaches to resource supply management fail to fully leverage supplier information, making it difficult to scientifically select and optimize supplier allocation. Factors such as a supplier's historical cooperation record, total supply volume, cost, quality compliance rate, and contract performance risk are all important factors in selecting suppliers. However, traditional approaches lack the ability to effectively integrate and analyze this information, resulting in low efficiency and quality in resource supply, and increased regulatory costs and risks.

[0008] Traditional methods of farmland water and fertilizer regulation have obvious deficiencies in accuracy, flexibility, stability assessment, plan formulation, and resource supply management. There is an urgent need for a method that can comprehensively consider multiple factors and achieve intelligent regulation to improve the efficiency and quality of farmland water and fertilizer management, reduce carbon emissions, and achieve sustainable agricultural development. Summary of the Invention

[0009] The purpose of the present invention is to provide a method for intelligently controlling the carbon effect of water-fertilizer coupling to solve the problems raised in the above background technology.

[0010] To achieve the above objectives, the present invention provides the following technical solution: a method for intelligently controlling the carbon effect of water-fertilizer coupling, the method comprising:

[0011] Acquire farmland environmental perception information, analyze the farmland environmental perception information, construct a water-fertilizer-carbon coupling effect scenario, and determine and output an initial control parameter set;

[0012] Obtaining dynamic adjustment operations based on user feedback of the initial control parameter set and determining a control adjustment information set;

[0013] Analyzing the control and adjustment information set, performing hierarchical decomposition and classification statistics on the control and adjustment information set, and determining a target control plan;

[0014] Obtain a supplier resource information set, and based on the supplier resource information set and according to the target control scheme, determine and output a targeted control execution plan.

[0015] Preferably, the analyzing the farmland environmental perception information, constructing a water-fertilizer-carbon coupling scenario, and determining and outputting an initial control parameter set include:

[0016] parsing the farmland environmental perception information to extract a soil moisture feature word set, crop growth cycle nodes, and farmland spatial positioning coordinates;

[0017] Analyze the soil moisture feature word set to determine the associated impact weight and standard action score corresponding to each feature word;

[0018] Determining a critical time period for crop water and fertilizer requirements based on the crop growth cycle nodes, and determining a time series influencing factor based on the crop growth cycle nodes and the critical time period for crop water and fertilizer requirements;

[0019] Constructing a scene feature model according to the association impact weight, the standard action score, the temporal impact factor and the farmland spatial positioning coordinates;

[0020] According to the scene feature model, a matching search is performed on the preset control parameter database to determine and output the initial control parameter set.

[0021] Preferably, the scene feature model is constructed based on the associated influence weight, the standard action score, the temporal influence factor and the farmland spatial positioning coordinates, specifically: the intensity of the effect of the comprehensive associated influence weight on the feature word, the contribution of the standard action score to the coupling effect, the correction coefficient of the temporal influence factor to the time period matching, and the adaptation dimension of the farmland spatial positioning coordinates to regional differences, and the scene feature model is formed through multi-dimensional feature fusion.

[0022] Preferably, obtaining the dynamic adjustment operation fed back by the user based on the initial control parameter set to determine the control adjustment information set includes:

[0023] Based on the initial control parameter set, an interactive simulation control interface is provided to the user, and the water-fertilizer-carbon coupling effect is simulated in real time based on the operation path data fed back by the user;

[0024] Based on the operation path data, identifying the user's potential preference parameters through path pattern analysis, dynamically adjusting the priority ranking of the initial parameters, and generating parameter combination information;

[0025] Analyze the parameter combination information, evaluate the stability of the parameter combination, determine the parameter stability state information, and feedback the corresponding parameter adjustment suggestions to the user, and receive the user's confirmation instruction;

[0026] According to the user confirmation instruction, a control adjustment information set is determined.

[0027] Preferably, analyzing the parameter combination information, evaluating the parameter combination stability, and determining parameter stability state information includes:

[0028] Extracting the total number of parameters, parameter scope, combined parameter core value, action position vector of each parameter, and parameter type attribute based on the parameter combination information;

[0029] Determining a parameter combination tolerance threshold, a basic action amount, a basic impact rate, and a basic action area of ​​each parameter according to the parameter type attribute of each parameter;

[0030] Based on the parameter action range, the core value of the combined parameter and the total amount of the parameters, a physical stability determination condition is constructed according to the basic action amount and the action position vector of each parameter;

[0031] Determining the expected duration of the regulation effect based on the crop growth cycle nodes and the crop's key water and fertilizer demand periods;

[0032] Based on the parameter combination tolerance threshold and the expected duration of the regulatory effect, and according to the basic impact rate and the basic effect area of ​​each parameter, a biochemical stability determination condition is constructed;

[0033] According to the physical stability determination condition and the biochemical stability determination condition, it is determined whether the physical stability or biochemical stability corresponding to the current parameter combination meets the requirements, and a determination result is determined as the parameter stability state information.

[0034] Preferably, based on the parameter action range, the combined parameter core value and the parameter total amount, according to the basic action amount and the action position vector of each parameter, a physical stability judgment condition is constructed, specifically: the adaptability of the comprehensive parameter action range to spatial coverage, the proximity of the combined parameter core value to the overall goal, the sufficiency of the parameter total amount to resource matching, and the distribution balance of the basic action amount and the action position vector are considered to form a physical stability judgment condition; based on the parameter combination tolerance threshold and the expected regulation action duration, according to the basic impact rate and the basic action area of ​​each parameter, a biochemical stability judgment condition is constructed, specifically: the safety of the system load is considered by the comprehensive parameter combination tolerance threshold, the rationality of the expected regulation action duration to the time matching, and the synergy of the basic impact rate and the basic action area are considered to form a biochemical stability judgment condition.

[0035] Preferably, the analyzing the control and adjustment information set, performing hierarchical decomposition and classification statistics on the control and adjustment information set, and determining a target control scheme includes:

[0036] According to the control adjustment information set, a target parameter type set and a target control auxiliary material set are counted;

[0037] According to the control cycle set by the management party, a number of control execution batches are divided according to the crop growth cycle nodes corresponding to different farmlands in the control adjustment information set, and a control batch information set is determined;

[0038] Based on the control batch information set, the target parameter type set is parsed, and the control redundancy corresponding to each type parameter in each control execution batch is determined according to the loss ratio corresponding to each type parameter in the target parameter type set in the historical control information;

[0039] The target control scheme is constructed according to the target control auxiliary material set, the control batch information set and the control redundancy.

[0040] Preferably, the determining and outputting of a targeted control execution plan based on the supplier resource information set and according to the target control scheme includes:

[0041] Based on the supplier resource information set, the target control scheme is parsed to determine a number of target suppliers corresponding to each type parameter in the target control scheme;

[0042] Extract the historical cooperation records corresponding to each target supplier based on the supplier resource information set, so as to determine the historical total supply volume, historical total supply cost, historical quality compliance rate, and historical performance risk of the current management party under the corresponding target supplier for each type of parameter;

[0043] Based on the historical total supply volume, the historical total supply cost, the historical quality compliance rate and the historical performance risk of each type parameter under the corresponding target supplier, comprehensive cost optimization processing is performed on each type parameter to determine the optimal supplier corresponding to each type parameter, thereby constructing and outputting the targeted regulation execution plan.

[0044] Preferably, the comprehensive cost optimization processing is performed on each type parameter according to the historical total supply volume, the historical total supply cost, the historical quality compliance rate and the historical performance risk of each type parameter under the corresponding target supplier, specifically: comprehensively considering the cost efficiency of the historical total supply cost and the historical total supply volume on the preset cost impact weight, the quality assurance degree of the historical quality compliance rate on the preset quality impact weight, and the reliability degree of the historical performance risk on the preset risk impact weight, and determining the optimal supplier through multi-dimensional evaluation.

[0045] Preferably, after constructing and outputting the targeted regulation execution plan, it also includes: obtaining resource consumption monitoring data during the regulation execution process, parsing the resource consumption monitoring data, and counting the deviation value between the actual total supply volume and the target total supply volume, the difference between the actual supply cost and the target supply cost, and the fluctuation value between the actual quality compliance rate and the historical quality compliance rate; based on the deviation value, difference value and fluctuation value, dynamically correcting the historical cooperation records in the supplier resource information set to form an updated supplier resource information set.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] By acquiring and analyzing farmland environmental perception information, this method constructs water-fertilizer-carbon coupling scenarios and subsequently determines an initial set of control parameters. This process fully considers multiple factors, including soil moisture feature word sets, crop growth cycle nodes, and farmland spatial coordinates. This makes the initial control parameter set more scientific and targeted, better adapted to the actual farmland environment, and lays the foundation for precise control.

[0048] When obtaining dynamic adjustment operations based on user feedback from the initial control parameter set, the system provides an interactive simulation control interface to simulate the effects of water-fertilizer-carbon coupling in real time, identify users' potential preferred parameters, and dynamically adjust the priority ranking of initial parameters. This interactive mechanism enables the control scheme to be flexibly adjusted according to the user's actual needs and on-site conditions, improving the adaptability of the control scheme and user satisfaction. At the same time, when parsing parameter combination information and evaluating its stability, judgment conditions are constructed from both physical and biochemical levels, comprehensively considering factors such as the total number of parameters, scope of action, core value, type attributes, and crop growth cycle, ensuring the stability and reliability of the parameter combination in actual application, thereby ensuring the durability and effectiveness of the control effect.

[0049] When determining the target control plan, the control adjustment information set is hierarchically broken down and classified, taking into account factors such as the target parameter type set, the set of control auxiliary materials, the control cycle, and the points in the crop growth cycle. The control execution batches are then divided and the control redundancy is determined. This systematic plan-making approach can better adapt to the actual conditions of different farmlands, improve the scientific nature and operability of the control plan, and ensure the orderly execution of the control tasks.

[0050] When determining a targeted regulation execution plan based on supplier resource information, we analyze suppliers' historical cooperation records, including factors such as total supply volume, total cost, quality compliance rate, and contract performance risk, and then perform comprehensive cost optimization on each type of parameter to determine the optimal supplier. This process enables the scientific selection and optimal allocation of supplier resources, improves the efficiency and quality of resource supply, reduces regulation costs and risks, and ensures the smooth implementation of regulation plans.

[0051] Furthermore, during the control execution process, resource consumption monitoring data is obtained and historical cooperation records in the supplier resource information set are dynamically revised to form an updated supplier resource information set. This dynamic revision mechanism continuously optimizes supplier resource information, improving the accuracy and reliability of subsequent control execution plans, and achieving continuous optimization and improvement of the control process.

[0052] The method of the present invention significantly improves the accuracy, adaptability and efficiency of farmland water and fertilizer regulation through multi-dimensional information integration, scientific model construction, flexible interaction mechanism, systematic program formulation and dynamic resource management, reduces carbon emissions, and realizes efficient, precise and low-carbon management of agricultural production. It has important practical application value and broad market prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 This is a working principle diagram of the water-fertilizer coupled carbon effect intelligent control method of the present invention;

[0054] Figure 2 Flowchart determined for the initial set of control parameters;

[0055] Figure 3 Flowcharts generated for regulatory adjustment information sets;

[0056] Figure 4 Flowchart generated for target regulation scheme;

[0057] Figure 5 A flowchart generated for targeted control execution plan. DETAILED DESCRIPTION

[0058] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0059] See also Figure 1-Figure 5 The present invention relates to a method for intelligently controlling the carbon effect of water-fertilizer coupling, and the specific implementation steps are as follows:

[0060] Acquire and analyze farmland environmental sensor information, construct a water-fertilizer-carbon interaction scenario, and determine and output an initial set of control parameters. Farmland environmental sensor information can be acquired through various deployed sensors, including data on soil moisture, temperature, crop growth status, and other aspects. This information is analyzed and key features extracted to construct a scenario that reflects the interaction between water, fertilizer, and carbon. Based on this, an initial set of control parameters is determined and output.

[0061] Obtain the user's dynamic adjustment operations based on the initial control parameter set to determine the control adjustment information set. The initial control parameter set is provided to the user, who makes adjustments through the interactive interface. The system records these dynamic adjustment operations and determines the control adjustment information set.

[0062] Analyze the control and adjustment information set, perform hierarchical decomposition and classification of the control and adjustment information set, and determine the target control plan. Analyze the control and adjustment information set in depth, decompose it according to different levels, and classify and count various types of information to ultimately form a target control plan.

[0063] Obtain a supplier resource information set, and based on the supplier resource information set and the target control scheme, determine and output a targeted control execution plan. Obtain relevant supplier resource information, combine the target control scheme, select suitable suppliers from the supplier resource information set, determine a specific control execution plan, and output it.

[0064] Example 1:

[0065] This embodiment details the specific implementation method of obtaining farmland environmental perception information, parsing the information to construct a water-fertilizer-carbon coupling scenario, and determining an initial control parameter set.

[0066] Acquiring farmland environmental perception information requires the use of various sensor devices deployed throughout the farmland. These sensors come in a variety of types, including soil moisture sensors for monitoring soil moisture, which collect real-time data on water content at different depths; temperature sensors for sensing temperature, which record temperature changes in the farmland environment and soil; and image sensors for monitoring crop growth, which capture relevant information by capturing crop growth. These sensors are distributed throughout the farmland at a specific density and layout to ensure that the acquired farmland environmental perception information is comprehensive and representative, covering different areas of the farmland and various aspects of crop growth.

[0067] The acquired farmland environmental perception information is parsed. A key step in the parsing process is extracting a set of soil moisture feature words, crop growth cycle nodes, and farmland spatial positioning coordinates. Extracting the soil moisture feature word set requires analyzing and processing the data collected by the soil moisture sensor. For example, soil moisture data is compared with a preset humidity range to generate feature words such as "moist," "suitable," and "drought" that reflect the soil moisture status. The determination of crop growth cycle nodes is based on long-term observation and research of the crop growth process, combined with crop growth images captured by image sensors and other relevant growth indicator data, to determine the specific growth stage of the crop, such as the seedling stage, flowering stage, and fruiting stage. Obtaining farmland spatial positioning coordinates is relatively straightforward. The specific location of each sensor can be determined using a GPS positioning module or other positioning device installed on the sensor, thereby obtaining the farmland's spatial positioning coordinates.

[0068] After extracting the set of soil moisture feature words, an in-depth analysis is required to determine the associated impact weight and standard action score corresponding to each feature word. The determination of the associated impact weight needs to consider the degree of influence of the feature word on the water-fertilizer-carbon coupling effect. For example, the feature word "drought" may have a significant impact on crop water and nutrient absorption, thereby affecting carbon fixation and emission, so it will be assigned a higher associated impact weight; while the feature word "suitable" has a relatively small impact on the water-fertilizer-carbon coupling effect, and its associated impact weight is lower. The determination of the standard action score is based on certain industry standards or historical data, setting a score for each feature word that can quantify its contribution to the coupling effect.

[0069] Based on the identified crop growth cycle nodes, key water and nutrient requirement periods are identified. Crop water and nutrient requirements vary at different points in the crop growth cycle. For example, during the flowering and fruiting stages, water and nutrient requirements are typically highest, and these periods are identified as critical water and nutrient requirement periods. Furthermore, combining the crop growth cycle nodes and key water and fertilization requirement periods, a timing impact factor is determined. This timing impact factor is used to adjust the responsiveness of regulatory measures at different time periods, reflecting the fact that the same regulatory parameters may produce different effects at different stages of crop growth.

[0070] A scenario feature model is constructed by integrating the associated impact weights, standard action scores, temporal impact factors, and farmland spatial positioning coordinates. During this construction process, the role of each factor must be fully considered. The associated impact weights reflect the intensity of the characteristic word's influence on the water-fertilizer-carbon coupling effect, the standard action score quantifies its contribution to the coupling effect, the temporal impact factor corrects the accuracy of time period matching, and the farmland spatial positioning coordinates take into account the adaptation dimension of regional differences. By fusing these multi-dimensional features, a model is formed that can comprehensively and accurately describe the current farmland water-fertilizer-carbon coupling scenario. This multi-dimensional feature fusion method enables the scenario feature model to more accurately reflect the actual farmland conditions, providing a reliable basis for the subsequent determination of regulatory parameters.

[0071] The constructed scene feature model is used to perform a matching search against a database of preset control parameters. This database contains a large number of control parameter combinations derived from historical experience and research, corresponding to different scene features. By comparing the scene feature model with the data in the database, the control parameter combination that best matches the current scene features is found, thereby determining and outputting an initial control parameter set. This output initial control parameter set contains a preliminary control plan tailored to the current farmland environment and crop growth status, providing a foundation for subsequent control operations.

[0072] Throughout the implementation process, each step is closely interconnected and mutually influential. Obtaining accurate farmland environmental perception information is the foundation of all subsequent steps. Only with accurate information can the correct feature words, nodes, and coordinates be extracted. The accuracy of the scene feature model is directly related to the analysis of feature words and the determination of temporal influencing factors. The accuracy of the scene feature model, in turn, determines whether the appropriate initial control parameter set can be retrieved from the preset control parameter database.

[0073] Example 2:

[0074] This embodiment describes in detail a specific implementation method for obtaining a dynamic adjustment operation based on user feedback of an initial control parameter set and determining a control adjustment information set.

[0075] After obtaining the initial set of control parameters, the system must provide the user with an interactive simulation control interface. This interface must be designed to conform to human-computer interaction logic and be able to intuitively display the various parameters of the initial control parameter set, such as water and fertilizer application rates, application time, and carbon effect-related indicators. The interface should include parameter adjustment capabilities, allowing users to modify parameters through interactive components such as sliders, input boxes, and drop-down menus. Furthermore, the interface must present real-time user operation path data, including the order in which users adjust parameters, the specific values ​​modified, and the duration of the adjustment. This data will serve as the basis for subsequent analysis.

[0076] The system simulates the effects of water-fertilizer-carbon coupling in real time based on user feedback. This simulation is based on a constructed water-fertilizer-carbon coupling model that integrates multiple data points, including farmland environmental perception and crop growth characteristics. When users adjust a parameter, the model calculates changes in processes such as water and fertilizer migration within the soil, crop uptake and utilization of water and fertilizer, and carbon sequestration and emission. These changes are then displayed visually, using dynamic curves and charts, allowing users to intuitively understand the impact of parameter adjustments on water-fertilizer-carbon coupling.

[0077] By performing path pattern analysis on the operation path data, the user's potential preference parameters can be identified. Path pattern analysis can use data mining technology to compile statistics and summarize user operating habits and parameter adjustment tendencies. For example, if a user frequently prioritizes adjusting the amount of water and fertilizer applied but rarely changes the application time, it can be inferred that the user may be more concerned about the impact of water and fertilizer application on crop growth. By identifying these potential preference parameters, the system can dynamically adjust the priority ranking of the initial parameters. The priority ranking is adjusted based on factors such as the degree of influence of the user's preferred parameters on the water-fertilizer-carbon coupling effect and the frequency of user operations. Parameters that the user is more concerned about are ranked higher, allowing for the subsequent generation of parameter combination information that better meets user needs.

[0078] After generating the parameter combination information, it needs to be parsed and the stability of the parameter combination evaluated. The parsing process mainly extracts the characteristics of each parameter in the parameter combination, such as the total number of parameters, the range of parameter effects, the core value of the combination parameters, the action position vector of each parameter, and the parameter type attributes. The parameter type attributes include whether the parameter belongs to the water and fertilizer category, the carbon effect category, or other auxiliary categories. Based on the parameter type attributes, the parameter combination tolerance threshold, the basic effect amount of each parameter, the basic impact rate, and the basic effect area are determined. The parameter combination tolerance threshold refers to the range within which the parameter combination can function stably in the farmland environment without causing adverse effects; the basic effect amount and other parameters are basic parameter attributes determined based on historical data and farmland characteristics.

[0079] When evaluating the stability of a parameter combination, first establish physical stability criteria. This requires comprehensive consideration of the adaptability of the parameter's range of action to spatial coverage, such as whether the range of water and fertilizer application covers different areas of the farmland; the convergence of the core value of the combined parameter to the overall goal, that is, whether the core goal of the parameter combination is consistent with the overall goal of farmland regulation; the adequacy of the total parameter amount to resource matching, ensuring that the total parameter amount can meet the needs of crop growth; and the balanced distribution of the basic action quantity and action position vector, ensuring that the parameter's effect is evenly distributed across the farmland space. Through the comprehensive consideration of these factors, physical stability criteria are formed to determine the physical stability of the parameter combination.

[0080] At the same time, the estimated duration of the regulatory action is determined based on the nodes of the crop growth cycle and the key water and fertilizer demand periods of the crops. The response time and duration of the crop's regulatory actions vary at different growth stages, so the estimated duration of the regulatory action needs to be determined in conjunction with specific growth cycle nodes. Based on the estimated duration of the regulatory action and the parameter combination tolerance threshold, biochemical stability determination criteria are constructed. This requires comprehensive consideration of the parameter combination tolerance threshold's safety for system load, ensuring that the parameter combination does not cause damage to the farmland ecosystem; the rationality of the estimated duration of the regulatory action for timeliness matching, so that the duration of the regulatory action matches the crop's needs; and the synergy between the basic impact rate and the basic action area, ensuring that the parameters' effects in the biochemical process are coordinated and consistent. These factors are used to construct biochemical stability determination criteria to evaluate the stability of the parameter combination at the biochemical level.

[0081] Based on the physical and biochemical stability criteria, the system determines whether the physical and biochemical stability of the current parameter combination meet the requirements, generating parameter stability information. If the parameter combination is stable at both the physical and biochemical levels, it is considered feasible. If instability factors exist, corresponding parameter adjustment suggestions are generated. These adjustment suggestions are based on the analysis of instability factors. For example, if physical stability does not meet the requirements, adjustments to the parameter range or total amount may be recommended. If biochemical stability is insufficient, optimization of the parameter's basic impact rate may be recommended.

[0082] Feedback parameter stability information and adjustment suggestions to the user, and receive confirmation from the user. This feedback must be clear and concise, allowing the user to understand the stability of the current parameter combination and the reasons and effects of the adjustment suggestions. Based on this feedback, the user can decide whether to accept the adjustment suggestions or further modify the parameters. After receiving the user's confirmation, the system determines the control adjustment information set based on the instructions. If the user accepts the adjustment suggestions, the control adjustment information set will contain the adjusted parameter combination. If the user continues to modify the parameters, simulation, analysis, and evaluation will be repeated until the user confirms, ultimately forming an accurate control adjustment information set.

[0083] Throughout the implementation process, the real-time and accuracy of the interactive simulation control interface are crucial, directly influencing users' judgment of the effects of parameter adjustments. The precision of path pattern analysis determines whether user preferences can be accurately identified, thereby generating a parameter combination that meets their needs. Furthermore, evaluating the stability of parameter combinations ensures the feasibility and effectiveness of the control scheme in practical applications. These various links work closely together to form a closed-loop interactive adjustment process, ensuring that the final set of control adjustment information better meets user needs and the actual requirements of farmland control.

[0084] Example 3:

[0085] This embodiment details a specific implementation method for parsing parameter combination information and evaluating its stability to determine parameter stable state information.

[0086] After obtaining the parameter combination information, the first step is to conduct a comprehensive analysis of it and extract key characteristic parameters from it. Specifically, it is necessary to extract the total number of parameters, that is, the sum of the number of all parameters contained in the combination; the parameter scope, which refers to the regional boundary or numerical range in which each parameter can have an impact in the farmland environment; the core value of the combination parameter, that is, the core target parameter value of the parameter combination, such as the baseline amount of water and fertilizer application or the target threshold for carbon effect regulation; the action position vector of each parameter, which is used to characterize the point of action and direction of influence of the parameter in the farmland space; and the parameter type attribute, which clarifies whether each parameter belongs to the water and fertilizer regulation category, carbon effect monitoring category, or auxiliary regulation category. The extraction of these characteristic parameters is the basis for subsequent stability assessment, and the accuracy and completeness of the extraction process must be ensured to avoid missing key information.

[0087] Based on the extracted parameter type attributes, the basic attribute values ​​related to the parameter combination are further determined. Specifically, this includes determining the parameter combination tolerance threshold, which refers to the maximum boundary value that the farmland ecosystem can withstand the parameter combination without adverse biochemical reactions or physical structure damage. Its determination needs to be combined with farmland soil characteristics, crop types, and historical control data; the basic effect of each parameter, that is, the basic impact of the parameter on the water-fertilizer-carbon coupling effect under standard farmland environmental conditions; the basic impact rate, which refers to the speed at which the parameter effect changes over time; and the basic impact area, which is the area within the farmland space that the parameter can directly affect. The determination of these basic attribute values ​​requires reference to a large amount of historical experimental data and farmland monitoring data to establish a scientific parameter library to ensure its accuracy and reliability.

[0088] Next, the physical stability criteria are constructed. This process requires comprehensive consideration of multiple factors. First, the adaptability of the parameter range to spatial coverage. For example, whether the range of water and fertilizer application parameters evenly covers different areas of the farmland, avoiding situations where some areas are overwatered and others underwatered. Second, the convergence of the core value of the combined parameters to the overall target. Specifically, whether the core value of the current parameter combination aligns with the overall goals of farmland regulation (such as crop yield targets and carbon emission reduction targets), and whether the deviation is within an acceptable range. Third, the adequacy of the total parameter amount to resource matching requires determining whether the total parameter amount can meet the water and fertilizer needs of crops during the current growth cycle and whether it matches the regulation requirements of the farmland carbon cycle. Finally, the distribution balance of the basic action quantity and the action position vector is important to ensure that the effect of each parameter is evenly distributed in space, so that the overall water, fertilizer, and carbon coupling effects of the farmland are not affected by excessive or weak local effects. By integrating these factors, a comprehensive set of physical stability criteria is formed to determine the stability of the parameter combination in the physical environment of the farmland.

[0089] While establishing the physical stability judgment conditions, it is also necessary to determine the expected duration of the regulatory effect based on the nodes of the crop growth cycle and the key water and fertilizer demand periods of the crops. Different crop growth stages, such as the seedling stage, flowering stage, and fruiting stage, have significant differences in the intensity of crop physiological activities and the characteristics of their demand for water and fertilizer. Therefore, the duration of the regulatory measures should also be adjusted accordingly. For example, during the rapid growth period of crops, the duration of the regulatory effect may need to be longer to meet their continuous water and fertilizer needs; while in the later growth period, the duration of the effect can be appropriately shortened. The determination of the expected duration of the regulatory effect requires a combination of crop growth models and historical regulatory experience to accurately calculate the duration of regulation required for each growth stage.

[0090] Based on the determined parameter combination tolerance threshold and the expected duration of the control action, biochemical stability criteria are constructed. This process also requires the integration of multiple factors. First, the parameter combination tolerance threshold must ensure the system's safety. This ensures that the parameter combination will not exceed the biochemical carrying capacity of the farmland ecosystem during the expected duration of the control action, thereby avoiding adverse effects on soil microbial communities, crop roots, and other factors. Second, the rationality of the expected duration of the control action in terms of time effectiveness must be considered. Specifically, whether the control action duration matches the physiological needs of the crop during that growth stage and whether it can maintain its effect during critical periods of water and fertilizer demand. Finally, the synergy between the basic impact rate and the basic effect area must be ensured. This ensures that the parameter effect rate is coordinated with its effect area. For example, if the effect rate of water and fertilizer application parameters is too fast while the effect area is too small, excessive water and fertilizer accumulation may occur locally, leading to problems such as soil compaction or crop root burn. By integrating these factors, biochemical stability criteria are formed to assess the stability of the parameter combination in the farmland biochemical environment.

[0091] After completing the construction of the physical and biochemical stability judgment conditions, the stability of the current parameter combination begins to be judged. The characteristic parameters of the parameter combination are substituted into the physical stability judgment conditions, and the parameter range, core value, total amount, and the distribution of the basic action quantity and position vector are checked one by one to see if they meet the requirements, and to determine whether its physical stability meets the standards. Similarly, the tolerance threshold, expected duration of the regulatory effect, basic impact rate, and area of ​​effect of the parameter combination are substituted into the biochemical stability judgment conditions to assess whether its biochemical stability meets the standards. Through a comprehensive judgment of physical and biochemical stability, the final judgment result is obtained. This result is the parameter stability status information, which specifically includes whether the parameter combination is stable, the specific factors of instability, and the possible degree of impact.

[0092] Throughout the entire implementation process, accurate extraction of parameter characteristics is fundamental, scientifically establishing physical and biochemical stability criteria is crucial, and accurate determination of the stable state is the ultimate goal. Each link is closely interconnected, and omissions in any one of them can lead to deviations in the stability assessment results. For example, inaccurate extraction of parameter ranges can lead to misjudgment of physical stability criteria; and inappropriate determination of the estimated duration of regulatory action can affect the accuracy of biochemical stability criteria.

[0093] Example 4:

[0094] This embodiment details the specific implementation method of parsing the control adjustment information set and performing hierarchical decomposition, classification and statistics on it to determine the target control solution.

[0095] After obtaining the control and adjustment information set, it is necessary to perform statistical analysis on the information therein to determine the target parameter type set and the target control auxiliary material set. For example, assuming that the control and adjustment information set contains water and fertilizer control parameters for a certain farmland, such as nitrogen fertilizer application amount, phosphorus fertilizer application amount, irrigation water volume, etc., these belong to the target parameter type set; and the auxiliary materials that may be needed during the control process, such as organic fertilizer for improving soil structure, sensor equipment for monitoring carbon effects, etc., constitute the target control auxiliary material set. During the statistical process, the various parameters and auxiliary materials in the control and adjustment information set need to be classified and sorted to ensure that no key information is missed.

[0096] Based on the control cycle set by the management, combined with the crop growth cycle nodes corresponding to different fields within the control adjustment information set, control execution batches are divided and a control batch information set is determined. For example, the management may set a control cycle of one month, but different fields may have crops at different growth cycle nodes, with some crops in the seedling stage and others in the flowering stage. For fields in the seedling stage, the control requirements may primarily focus on promoting root growth, requiring more nitrogen fertilizer and adequate water. Fields in the flowering stage, on the other hand, may prioritize the supply of phosphorus and potassium fertilizers and stable watering. Therefore, control execution can be divided into multiple batches based on these different growth cycle nodes. For example, fields in the seedling stage could be the first batch to be controlled, and fields in the flowering stage the second. For each batch, specific control time, key control parameters, and other information could be determined to form a control batch information set.

[0097] After determining the control batch information set, the target parameter type set is parsed based on the set. Taking the nitrogen fertilizer application amount as an example, it is necessary to analyze the corresponding loss ratio in the historical control information. The historical control information records the actual absorption and utilization of nitrogen fertilizer after application and the loss situation in similar growth cycle nodes and farmland environments in the past, such as losses caused by leaching, volatilization, etc. By analyzing these historical data, the loss ratio of the parameter under the current control batch is determined. For example, historical data shows that the loss ratio of nitrogen fertilizer is about 30% in the seedling stage of crops. Then, in the current control batch, for farmland in the seedling stage, when determining the amount of nitrogen fertilizer applied, it is necessary to consider this 30% loss ratio to ensure that the amount of nitrogen actually absorbed by the crop meets the demand.

[0098] Based on the control redundancy corresponding to each parameter type within each control execution batch, combined with the target control auxiliary material set and the control batch information set, a target control plan is constructed. Continuing with the above example, for the first batch of farmland in the seedling stage, the nitrogen fertilizer application amount in the target parameter type set, taking into account a 30% loss rate, results in a control redundancy of 30%. Assuming the original plan was to apply 100 kg of nitrogen fertilizer, after accounting for the redundancy, the actual amount required is 100 + 100 × 30% = 130 kg. Furthermore, the organic fertilizer in the target control auxiliary material set needs to be applied at a specific time, either simultaneously with or after the nitrogen fertilizer application, based on the schedule in the control batch information set. The specific amount to be applied is determined. Combining these parameter adjustments, the use of auxiliary materials, and the control batch schedule information forms the target control plan.

[0099] When developing a targeted control plan, it's important to pay attention to the connection and coordination between different control batches. For example, after the first batch of controls is completed, the effectiveness of the controls needs to be evaluated. The results of this evaluation may affect the control parameters and auxiliary material usage of subsequent batches. Furthermore, the materials in the target control auxiliary material set must be purchased and allocated in advance based on the control batch information set to ensure sufficient supplies when the controls are implemented.

[0100] Furthermore, the determination of regulatory redundancy should be based not only on historical loss rates but also on the specific environmental conditions of the current farmland, such as soil texture and climate. If the soil's ability to retain water and fertilizer is poor, this may result in a higher nitrogen loss rate than the historical average. In this case, the regulatory redundancy should be increased accordingly. Conversely, if soil conditions are favorable, the loss rate may be lower, and the regulatory redundancy can be appropriately reduced.

[0101] For materials included in the target control auxiliary material set, such as sensor equipment, the control plan must clearly specify their installation location, installation time, and monitoring frequency. The installation location should be determined based on the spatial positioning coordinates of the farmland and the parameter action position vector to ensure accurate monitoring of the effects of the control parameters and changes in carbon impact.

[0102] Throughout the implementation process, from statistically analyzing the target parameter type set and the target control auxiliary material set, to dividing the control execution batches, and then to determining the control redundancy, each step needs to be closely integrated with the actual farmland conditions and historical data to ensure that the constructed target control scheme is scientific and operational. For example, when dividing the control batches, it is not enough to just rely on the crop growth cycle nodes, but also to consider factors such as the geographical location of the farmland and irrigation conditions to avoid poor control effects due to unreasonable batch division. At the same time, when determining the control redundancy, it is necessary to fully analyze the reliability of the historical loss data and make adjustments based on the actual situation of the current farmland to ensure that the control parameters can meet the needs of crop growth and carbon effect control.

[0103] Example 5:

[0104] This embodiment details the specific implementation method of determining and outputting a targeted control execution plan based on the supplier resource information set and the target control scheme, as well as the dynamic correction process after the control is executed.

[0105] Assume that the target control plan includes parameters such as nitrogen fertilizer, phosphate fertilizer, irrigation water, and carbon monitoring equipment. When determining the targeted control execution plan, the target control plan is parsed based on the supplier resource information set to determine the target suppliers corresponding to each type of parameter. For example, for nitrogen fertilizer parameters, the supplier resource information set may record three suppliers, A, B, and C, among which supplier A provides granular urea, supplier B provides liquid nitrogen fertilizer, and supplier C provides slow-release nitrogen fertilizer; the phosphate fertilizer parameters correspond to two suppliers, D and E, where supplier D specializes in producing high-purity supercalcium phosphate and supplier E mainly produces diammonium phosphate; the irrigation water parameters may involve the local reservoir manager F and the groundwater supplier G; the carbon monitoring equipment parameters correspond to suppliers H and I, where supplier H's equipment has higher accuracy and supplier I's equipment has lower cost.

[0106] The historical cooperation records of each target supplier were extracted from the supplier resource information set, including historical supply volume, historical supply cost, historical quality compliance rate, and historical performance risk. For example, nitrogen fertilizer supplier A's historical cooperation records show that over the past three years, it supplied a total of 500 tons of granular urea to the management party at a historical total supply cost of 1.5 million yuan, a historical quality compliance rate of 95%, and a historical performance risk level of low (specifically, no delivery delays or quantity shortages). Supplier B's historical supply volume was 300 tons, with a total cost of 900,000 yuan, a quality compliance rate of 90%, and a performance risk level of medium (with two delivery delays). Supplier C's historical supply volume was 200 tons, with a total cost of 800,000 yuan, a quality compliance rate of 98%, and a performance risk level of low.

[0107] Based on the historical total supply volume, historical total supply cost, historical quality compliance rate, and historical performance risk of each type parameter under the corresponding target supplier, a comprehensive cost optimization process is performed to determine the optimal supplier. Assume that the management party presets a cost impact weight of 0.4, a quality impact weight of 0.3, and a risk impact weight of 0.3. For the nitrogen fertilizer parameters, the comprehensive score of each supplier is calculated: Supplier A has a cost efficiency of 1.5 million yuan / 500 tons (3,000 yuan / ton), a quality assurance level of 95%, and a performance reliability score corresponding to low risk (for example, low risk is set to 90 points, medium risk is 70 points, and high risk is 50 points). The comprehensive score is 0.4×(1-0.3 / 0.3) (assuming the baseline cost efficiency is 3,000 yuan / ton. This is an example logic and can actually be normalized) + 0.3×95% + 0.3×90 points, converted to a percentage; Supplier B has a cost efficiency of 900,000 yuan / 300 tons (3,000 yuan / ton), a quality assurance level of 90%, and a performance reliability score of 70 points. The comprehensive score is calculated with the same weights; Supplier C has a cost efficiency of 800,000 yuan / 200 tons (4,000 yuan / ton), a quality assurance level of 98%, and a performance reliability score of 90 points. In the comprehensive score, the cost efficiency score may be lower because it is higher than the baseline value, but the quality and risk scores are higher. Through multi-dimensional evaluation, Supplier A was ultimately determined to be the optimal supplier of nitrogen fertilizer parameters due to its balanced performance in terms of cost and risk, and its high quality compliance rate.

[0108] Similarly, let's evaluate suppliers D and E for phosphate fertilizer parameters: Assume that supplier D's historical total supply cost is 800,000 yuan / 200 tons (4,000 yuan / ton), with a 98% quality compliance rate and low contract performance risk. Supplier E's cost is 600,000 yuan / 200 tons (3,000 yuan / ton), with a 92% quality compliance rate and medium contract performance risk. If the cost impact is weighted equally, supplier E may score higher due to its cost advantage. However, considering both quality and risk factors, supplier E may ultimately be selected as the optimal supplier for phosphate fertilizer parameters.

[0109] Regarding irrigation water parameters, Supplier F (the reservoir manager) has a historical total supply cost of 0.5 yuan per ton, with a total supply of 100,000 tons and a 100% quality compliance rate (the water source meets irrigation standards). This places the supplier at low risk. Supplier G (the groundwater supplier) has a cost of 0.8 yuan per ton, a total supply of 50,000 tons, and a 95% quality compliance rate (the groundwater mineral content sometimes exceeds standards). This places the supplier at medium risk. After comprehensive evaluation, Supplier F is selected as the optimal supplier.

[0110] Regarding carbon monitoring equipment parameters, Supplier H's equipment costs 5,000 yuan per unit, has a historical supply of 100 units, and has a 99% quality compliance rate, posing a low compliance risk. Supplier I's equipment costs 3,000 yuan per unit, has a total supply of 150 units, and has a 90% quality compliance rate, posing a medium compliance risk. If the management party prioritizes equipment accuracy, they may choose Supplier H; if they have a limited budget, they may choose Supplier I after considering all factors.

[0111] After determining the optimal supplier for each parameter type, a targeted control execution plan was constructed. This plan included: purchasing 130 kg of granular urea from nitrogen fertilizer supplier A (considering the excess after losses in Example 4), with delivery to a designated farmland warehouse three days before the first control batch; purchasing 80 kg of diammonium phosphate from phosphate fertilizer supplier E, with delivery time synchronized with the nitrogen fertilizer; requesting 1,000 tons of irrigation water from reservoir manager F, with water delivery scheduled on the day the control batch was executed; and purchasing two carbon monitoring devices from supplier H, with installation and commissioning completed one day before the control batch was executed. The execution plan also required clear contact information, acceptance criteria, payment methods, and other details for each supplier to ensure smooth control execution.

[0112] After constructing and outputting a targeted control execution plan, resource consumption monitoring data is obtained during the control execution process. For example, the actual total nitrogen fertilizer supply was 128 kg, with a deviation of -2 kg from the target supply of 130 kg. The actual supply cost was 3,840 yuan (assuming a unit price of 30 yuan / kg), compared to the target supply cost of 3,900 yuan, a difference of -60 yuan. The actual quality compliance rate was 96%, with a fluctuation of +1% compared to the historical quality compliance rate of 95%. The actual total irrigation water supply was 1,020 tons, with a deviation of +20 tons from the target of 1,000 tons. The actual cost was 510 yuan, compared to the target cost of 500 yuan, a difference of +10 yuan, and a quality compliance rate of 100%, with a fluctuation of 0%.

[0113] Based on these deviations, differences, and fluctuations, historical cooperation records in the supplier resource information set are dynamically revised. For nitrogen fertilizer supplier A, the historical total supply volume is updated to 500 + 0.0128 = 500.0128 tons (assuming the unit is uniformly tonnes), the historical total supply cost is updated to 150 + 0.384 = 1,503,840 yuan, and the historical quality compliance rate is adjusted to (95% × 500 + 96% × 0.0128) / 500.0128 ≈ 95% (due to the small increase in volume and negligible overall impact, the original value can be maintained or slightly adjusted). The performance risk is maintained at a low level due to on-time delivery and close-to-target quantity. The total historical supply of irrigation water supplier F is updated to 10+0.102=101,020 tons, and the total historical supply cost is updated to 10×0.5+0.102×0.5=50,510 yuan. The quality compliance rate remains at 100%. The performance risk is due to the actual water supply exceeding the target by 20 tons. It is necessary to analyze whether it is caused by scheduling errors. If the fluctuation is within a reasonable range, the performance risk can be maintained at a low level. Otherwise, the risk assessment needs to be adjusted.

[0114] This dynamically revised supplier resource information set will serve as a reference for the formulation of subsequent regulatory plans, ensuring that historical cooperation records are more aligned with actual conditions and improving the accuracy of future supplier selection. For example, if Supplier F's actual water supply exceeded its target during this regulation without any adverse impact, its supply capacity might be considered more stable in subsequent assessments, and its contract performance risk score might be appropriately increased. If Supplier E's actual phosphate fertilizer quality compliance rate is higher than historical levels, its quality compliance rate record might be adjusted upwards, making it more competitive in future comprehensive assessments.

[0115] During the entire implementation process, the selection of suppliers needs to comprehensively consider the matching degree between historical data and current regulation needs. The formulation of the implementation plan needs to be detailed to specific factors such as time, quantity, and location. The collection and analysis of resource consumption monitoring data must be timely and accurate. The dynamic correction process needs to be reasonably adjusted based on objective data to ensure the timeliness and pertinence of the supplier's resource information set, thereby forming a closed-loop regulation and execution management system and improving the overall efficiency and reliability of water-fertilizer coupled carbon effect regulation.

[0116] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "includes," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0117] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A method for intelligently controlling the carbon effect of water-fertilizer coupling, characterized in that: include: Acquire farmland environmental perception information, analyze the farmland environmental perception information, construct a water-fertilizer-carbon coupling effect scenario, and determine and output an initial control parameter set; Obtaining dynamic adjustment operations based on user feedback of the initial control parameter set and determining a control adjustment information set; Analyzing the control and adjustment information set, performing hierarchical decomposition and classification statistics on the control and adjustment information set, and determining a target control plan; Acquire a supplier resource information set, and determine and output a targeted regulation execution plan based on the supplier resource information set and the target regulation scheme; The analyzing of the farmland environmental perception information, constructing a water-fertilizer-carbon coupling scenario, and determining and outputting an initial control parameter set include: parsing the farmland environmental perception information to extract a soil moisture feature word set, crop growth cycle nodes, and farmland spatial positioning coordinates; Analyze the soil moisture feature word set to determine the associated impact weight and standard action score corresponding to each feature word; Determining a critical time period for crop water and fertilizer requirements based on the crop growth cycle nodes, and determining a time series influencing factor based on the crop growth cycle nodes and the critical time period for crop water and fertilizer requirements; Constructing a scene feature model according to the association impact weight, the standard action score, the temporal impact factor and the farmland spatial positioning coordinates; According to the scene feature model, a matching search is performed on a preset control parameter database to determine and output the initial control parameter set; The obtaining of the dynamic adjustment operation based on the feedback of the user on the initial control parameter set and determining the control adjustment information set includes: Based on the initial control parameter set, an interactive simulation control interface is provided to the user, and the water-fertilizer-carbon coupling effect is simulated in real time based on the operation path data fed back by the user; Based on the operation path data, identifying the user's potential preference parameters through path pattern analysis, dynamically adjusting the priority ranking of the initial parameters, and generating parameter combination information; Analyze the parameter combination information, evaluate the stability of the parameter combination, determine the parameter stability state information, and feedback the corresponding parameter adjustment suggestions to the user, and receive the user's confirmation instruction; Determining a control adjustment information set according to the user confirmation instruction; The analyzing the parameter combination information, evaluating the parameter combination stability, and determining the parameter stability state information includes: Extracting the total number of parameters, parameter scope, combined parameter core value, action position vector of each parameter, and parameter type attribute based on the parameter combination information; Determining a parameter combination tolerance threshold, a basic action amount, a basic impact rate, and a basic action area of ​​each parameter according to the parameter type attribute of each parameter; Based on the parameter action range, the core value of the combined parameter and the total amount of the parameters, a physical stability determination condition is constructed according to the basic action amount and the action position vector of each parameter; Determining the expected duration of the regulation effect based on the crop growth cycle nodes and the crop's key water and fertilizer demand periods; Based on the parameter combination tolerance threshold and the expected duration of the regulatory effect, and according to the basic impact rate and the basic effect area of ​​each parameter, a biochemical stability determination condition is constructed; According to the physical stability determination condition and the biochemical stability determination condition, determining whether the physical stability or biochemical stability corresponding to the current parameter combination meets the requirements, and determining a determination result as the parameter stability state information; The step of analyzing the control and adjustment information set, performing hierarchical decomposition, classification, and statistics on the control and adjustment information set, and determining a target control plan includes: According to the control adjustment information set, a target parameter type set and a target control auxiliary material set are counted; According to the control cycle set by the management party, a number of control execution batches are divided according to the crop growth cycle nodes corresponding to different farmlands in the control adjustment information set, and a control batch information set is determined; Based on the control batch information set, the target parameter type set is parsed, and the control redundancy corresponding to each type parameter in each control execution batch is determined according to the loss ratio corresponding to each type parameter in the target parameter type set in the historical control information; The target control scheme is constructed according to the target control auxiliary material set, the control batch information set and the control redundancy.

2. The method for intelligently controlling the carbon effect of water-fertilizer coupling according to claim 1, characterized in that: The scene feature model is constructed based on the association influence weight, the standard action score, the temporal influence factor and the farmland spatial positioning coordinates, specifically: the effect strength of the comprehensive association influence weight on the feature word, the contribution degree of the standard action score to the coupling effect, the correction coefficient of the temporal influence factor to the time period matching, and the adaptation dimension of the farmland spatial positioning coordinates to regional differences, and the scene feature model is formed through multi-dimensional feature fusion.

3. The method for intelligently controlling the carbon effect of water-fertilizer coupling according to claim 1, characterized in that: Based on the parameter action range, the core value of the combined parameter and the total amount of the parameters, according to the basic action amount and the action position vector of each parameter, a physical stability judgment condition is constructed, specifically: the adaptability of the comprehensive parameter action range to the spatial coverage, the convergence of the core value of the combined parameter to the overall goal, the sufficiency of the total amount of parameters to the resource matching, and the distribution balance of the basic action amount and the action position vector, to form a physical stability judgment condition; based on the parameter combination tolerance threshold and the expected regulation action time, according to the basic impact rate and the basic action area of ​​each parameter, a biochemical stability judgment condition is constructed, specifically: the safety of the comprehensive parameter combination tolerance threshold to the system load, the rationality of the expected regulation action time to the time matching, and the synergy of the basic impact rate and the basic action area, to form a biochemical stability judgment condition.

4. The method for intelligently controlling the carbon effect of water-fertilizer coupling according to claim 1, wherein based on the supplier resource information set and according to the target control scheme, a targeted control execution plan is determined and outputted, characterized in that: include: Based on the supplier resource information set, the target control scheme is parsed to determine a number of target suppliers corresponding to each type parameter in the target control scheme; Extract the historical cooperation records corresponding to each target supplier based on the supplier resource information set, so as to determine the historical total supply volume, historical total supply cost, historical quality compliance rate, and historical performance risk of the current management party under the corresponding target supplier for each type of parameter; Based on the historical total supply volume, the historical total supply cost, the historical quality compliance rate and the historical performance risk of each type parameter under the corresponding target supplier, comprehensive cost optimization processing is performed on each type parameter to determine the optimal supplier corresponding to each type parameter, thereby constructing and outputting the targeted regulation execution plan.

5. The method for intelligently controlling the carbon effect of water-fertilizer coupling according to claim 4, characterized in that: According to the historical total supply volume, the historical total supply cost, the historical quality compliance rate and the historical performance risk of each type parameter under the corresponding target supplier, a comprehensive cost optimization process is performed on each type parameter, specifically: the cost efficiency of the historical total supply cost and the historical total supply volume is comprehensively considered based on the preset cost impact weight, the quality assurance level of the historical quality compliance rate is considered based on the preset quality impact weight, and the reliability level of the historical performance risk is considered based on the preset risk impact weight, and the optimal supplier is determined through a multi-dimensional evaluation.

6. The method for intelligently controlling the carbon effect of water-fertilizer coupling according to claim 4, characterized in that: After constructing and outputting the targeted regulation execution plan, it also includes: obtaining resource consumption monitoring data during the regulation execution process, parsing the resource consumption monitoring data, and counting the deviation value between the actual total supply and the target total supply, the difference between the actual supply cost and the target supply cost, and the fluctuation value between the actual quality compliance rate and the historical quality compliance rate; based on the deviation value, difference value and fluctuation value, dynamically correcting the historical cooperation records in the supplier resource information set to form an updated supplier resource information set.

Images