Cultivated land resource quality optimization method and device under multi-source data analysis

Abstract

The invention discloses a cultivated land resource quality optimization method and device under multi-source data analysis, and relates to the technical field of cultivated land resource optimization, and the method comprises the steps: obtaining a target cultivated land attribute, constructing a quality relation matrix of a first matrix containing a cultivated land quality main control factor and a second matrix of a quality reduction driving mechanism, and generating an optimization strategy; a cyclic structure strategy generator based on a built-in conditional probability matrix dynamically generates, adjusts and optimizes a strategy in combination with a quality matrix of real-time information collection; and according to a quality optimization strategy, performing staged resource management and optimized acceptance on the target cultivated land. The technical problems that in the prior art, a systematic quantification and dynamic adjustment mechanism for multi-factor complex association is lacked, and complex changes of actual cultivated land resources are difficult to accurately adapt are solved, and the technical effects of accuracy and dynamic adaptability of cultivated land quality optimization are achieved through a multi-source data analysis and feedback optimization mechanism.

Description

Technical Field

[0001] The present invention relates to the technical field of cultivated land resource optimization, and particularly relates to a method and device for optimizing the quality of cultivated land resources under multi-source data analysis. Background Art

[0002] Cultivated land resources are an important foundation for agricultural production, and their quality is directly related to food security, ecological environment protection and economic development. However, with global climate change, soil degradation, overdevelopment and the widespread existence of unreasonable agricultural cultivation methods, the quality of cultivated land is facing a serious threat of decline.

[0003] Traditional cultivated land quality optimization methods usually rely on a single data source (such as soil monitoring data or climate data), lacking comprehensive support from multi-source data, resulting in insufficient adaptability and scientificity of optimization strategies. In addition, existing methods mostly adopt static analysis and empirical decision-making methods, making it difficult to reflect the dynamic changes and complexity of cultivated land quality in real time. Especially in the face of a changing climate and variable soil properties, there is a lack of an effective adjustment mechanism, which affects the optimization effect. Summary of the Invention

[0004] This application provides a method and device for optimizing the quality of cultivated land resources under multi-source data analysis, which are used to solve the technical problem that the existing technology lacks a systematic quantification and dynamic adjustment mechanism for complex associations of multiple factors and is difficult to accurately adapt to the complex changes of actual cultivated land resources.

[0005] In the first aspect of this application, a method for optimizing the quality of cultivated land resources under multi-source data analysis is provided. The method includes: obtaining target cultivated land attributes and mining a quality relationship matrix, where the quality relationship matrix includes a first matrix based on the main control factors of cultivated land quality and a second matrix based on the driving mechanism of cultivated land quality decline; based on the quality relationship matrix, constructing a strategy generator, where the strategy generator is built-in with a conditional probability matrix, and the probability matrix is used for strategy generation constraints, and the strategy generator is a cyclic structure; collecting information on the target cultivated land to determine a real-time quality matrix, transmitting it to the strategy generator, generating an optimization strategy under the constraint of the conditional probability matrix, and performing feedback optimization based on grey relational projection analysis to determine a quality optimization strategy; based on the quality optimization strategy, managing the cultivated land resources of the target cultivated land.

[0006] In the second aspect of the present application, a device for optimizing the quality of cultivated land resources under multi-source data analysis is provided. The device includes: a quality relationship matrix mining module for obtaining target cultivated land attributes and mining a quality relationship matrix, where the quality relationship matrix includes a first matrix based on the main control factors of cultivated land quality and a second matrix based on the driving mechanism of cultivated land quality decline; a policy generator construction module for constructing a policy generator based on the quality relationship matrix, where the policy generator has a conditional probability matrix built in, and the probability matrix is used for policy generation constraint, and the policy generator is a cyclic structure; an optimized policy generation module for collecting information on the target cultivated land, determining a real-time quality matrix, transmitting it to the policy generator, generating an optimized policy under the constraint of the conditional probability matrix, and performing feedback optimization based on grey relational projection analysis to determine a quality optimization policy; and a cultivated land resource management module for managing the cultivated land resources of the target cultivated land based on the quality optimization policy.

[0007] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0008] A method and device for optimizing the quality of cultivated land resources under multi-source data analysis provided in the present application relate to the technical field of cultivated land resource optimization. By constructing a quality relationship matrix of the main control factors of cultivated land quality and the decline driving mechanism, combining a policy generator with a built-in conditional probability matrix, an optimized policy is dynamically generated, and based on real-time quality matrix information collection and grey relational projection analysis, feedback optimization adjustment is realized. According to the optimized policy, phased management and acceptance of the target cultivated land are carried out to ensure efficient utilization of resources and achievement of the optimization goal. The technical problem that the prior art lacks a systematic quantification and dynamic adjustment mechanism for complex correlations of multiple factors and is difficult to accurately adapt to the complex changes of actual cultivated land resources is solved, and the technical effect of realizing the accuracy and dynamic adaptability of cultivated land quality optimization through multi-source data analysis and feedback optimization mechanism is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings without creative efforts based on these drawings.

[0010] Figure 1 It is a schematic flowchart of a method for optimizing the quality of cultivated land resources under multi-source data analysis provided by an embodiment of the present application;

[0011] Figure 2Schematic structural diagram of an arable land resource quality optimization device provided by an embodiment of the present application.

[0012] Explanation of reference numerals: Quality relationship matrix mining module 11, strategy generator construction module 12, optimization strategy generation module 13, arable land resource management module 14. Detailed implementation manners

[0013] The present application provides a method and device for optimizing the quality of arable land resources under multi-source data analysis, which are used to solve the technical problem that the existing technology lacks a systematic quantification and dynamic adjustment mechanism for complex associations of multiple factors and is difficult to accurately adapt to the complex changes of actual arable land resources.

[0014] Next, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0015] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above accompanying drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or server that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products, or devices.

[0016] Embodiment 1, as Figure 1 shown, the present application provides a method for optimizing the quality of arable land resources under multi-source data analysis, and the method includes:

[0017] P10: Obtain the target arable land attributes and mine the quality relationship matrix, where the quality relationship matrix includes a first matrix based on the main control factors of arable land quality and a second matrix based on the driving mechanism of arable land quality decline.

[0018] Specifically, the attributes of the target cultivated land are obtained and analyzed. The attributes of cultivated land can be divided into various types according to different geographical regions and agricultural conditions, such as black soil, dry land in the north, paddy fields in the south, dry land in the south, facility agricultural land, saline-alkali cultivated land, etc. There are significant differences in the quality performance and utilization methods of each type of cultivated land. Therefore, for different types of cultivated land, personalized quality analysis and optimization must be carried out.

[0019] To effectively describe each element of cultivated land quality and reveal their interrelationships, a quality relationship matrix is constructed. This matrix consists of two parts: the first part is the first matrix based on the main control factors of cultivated land quality, and the second part is the second matrix based on the driving mechanism of cultivated land quality decline.

[0020] Among them, the first matrix, that is, the main control factor matrix of cultivated land quality, is mainly constructed based on the core elements affecting cultivated land quality, including factors such as tillage layer texture, pH value, organic matter content, and trace element content. The tillage layer texture refers to the proportion of different particles in the soil (such as sand, loam, clay, etc.), which determines the soil's water retention capacity, air permeability, and nutrient supply capacity. The pH value affects the acidity and alkalinity of the soil and directly affects the absorption of nutrients by crops and the activity of microorganisms. The organic matter content is closely related to the fertility of the soil and is the basis of soil health, while the trace element content (such as boron, zinc, copper, etc.) is an important component required for crop growth and affects the nutritional status and disease and pest resistance of crops. By comprehensively analyzing these main control factors, a basic matrix of cultivated land quality can be formed, revealing the basic composition of cultivated land quality.

[0021] The second matrix, that is, the driving mechanism matrix of cultivated land quality decline, is used to describe and quantify various driving factors that lead to the decline of cultivated land quality. These factors may be caused by natural environmental changes (such as drought, excessive precipitation) or human activities (such as unreasonable tillage, improper fertilization, over-tillage, etc.). For example, over-tillage may lead to soil degradation, such as tillage layer compaction and organic matter loss; improper fertilization will cause nutrient imbalance in the soil, thereby reducing the production capacity of cultivated land. By analyzing these driving mechanisms, the potential causes of cultivated land quality decline can be revealed, providing a basis for subsequent optimization strategies.

[0022] By combining these two matrices (the first matrix and the second matrix), the current situation and change trend of cultivated land quality can be comprehensively analyzed. This quality relationship matrix not only provides a theoretical basis for the quantitative analysis of cultivated land quality but also provides important data support and decision-making basis for the subsequent generation of optimization strategies.

[0023] Furthermore, after mining the quality relationship matrix, step P10 of the embodiment of the present application further includes:

[0024] P11a: Obtain the target cultivated land attributes, conduct agricultural big data retrieval with the region of the target cultivated land as a constraint, and call the cultivated land monitoring data of the same attributes; P12a: Traverse the cultivated land monitoring data to mine the matrix element range of the quality relationship matrix; P13a: Based on the matrix element range, perform quality optimization constraints on the target cultivated land, including natural optimization that meets the matrix element range and non-natural condition optimization that does not meet the matrix element range.

[0025] Optionally, after mining the quality relationship matrix, the accuracy of cultivated land quality optimization can be further improved. First, for the specific attributes of the target cultivated land (such as black soil, dry land in the north, paddy fields in the south, etc.), based on its regional characteristics (including climate, soil type, water resources, etc.), conduct retrieval and analysis of agricultural big data. By calling the historical monitoring data of cultivated land with the same attributes, the long-term quality change trend and important characteristics of similar cultivated land can be obtained, such as soil nutrient levels, typical crop planting conditions and success rates. These data provide an important reference benchmark for the target cultivated land, helping to clarify the potential upper limit and limitation range that can be achieved by the current natural conditions of the cultivated land before generating optimization strategies.

[0026] Next, comprehensively traverse the called cultivated land monitoring data to mine the matrix element range of the quality relationship matrix, that is, the general state range of the local cultivated land under natural conditions. The core goal of this step is to analyze whether the characteristics of the target cultivated land can meet the optimization requirements. The matrix element range is determined by factors such as local climate conditions, soil fertility, and water resource status. For example, in dry land in the north, the natural conditions are usually not suitable for growing tropical fruits in the south, and additional artificial environment optimization (such as greenhouse cultivation) is required to achieve higher production goals. By traversing the monitoring data, it is possible to identify which indicators of the target cultivated land exceed the local general range and further determine whether additional technical support is needed for optimization.

[0027] Finally, based on the mined matrix element range, perform constraints on the quality optimization of the target cultivated land. The optimization methods can be divided into two categories: natural optimization and non-natural condition optimization. For indicators that can meet the requirements through natural condition adjustment (such as fertilization, irrigation, or soil improvement), that is, indicators that meet the matrix element range, adopt natural optimization strategies. For example, improve the cultivated land quality by increasing the organic matter content or improving the soil structure. For indicators that do not meet the matrix element range, external technical means need to be introduced, such as adjusting the temperature and humidity in the greenhouse, controlling the water supply with a precision irrigation system, and supplementing light artificially to make up for insufficient light, to break through the limitations of natural conditions. This distinction of optimization strategies can ensure the maximization of resource utilization efficiency and provide practical solutions for specific planting needs.

[0028] Through the above steps, the precise optimization constraints on cultivated land quality can be systematically completed, which not only gives full play to the potential of natural conditions but also flexibly supplements artificial technical means, providing a scientific basis for cultivated land resource management and efficient utilization.

[0029] P20: Based on the quality relationship matrix, construct a strategy generator, where the strategy generator is built-in with a conditional probability matrix, and the probability matrix is used to perform strategy generation constraints, and the strategy generator is a cyclic structure.

[0030] Furthermore, to construct a strategy generator, step P20 of the embodiment of the present application further includes:

[0031] P21: Traverse the quality main control factors, call the cultivated land resource optimization samples for factor-by-factor decomposition, and determine N groups of optimization samples, where the N groups of optimization samples correspond one-to-one to the quality main control factors; P22: Traverse the N groups of optimization samples, perform within-group co-reference fitting to determine a baseline adjustment plan, where co-reference fitting refers to fitting the optimization samples in the same way; P23: Incorporate the baseline adjustment plan into the strategy generator, and based on the cultivated land resource optimization samples, perform supervised training on the strategy generator.

[0032] Specifically, by constructing a strategy generator based on the quality relationship matrix, the intelligence and systematization of cultivated land resource quality optimization are realized. The core of the strategy generator lies in the built-in conditional probability matrix, which is used to constrain and guide the strategy generation process. At the same time, a cyclic structure is adopted to continuously optimize the strategy generation to ensure that the output results meet the optimization objectives.

[0033] In the process of constructing the strategy generator, it is first necessary to conduct a one-by-one traversal and analysis of the quality main control factors in the quality relationship matrix. The quality main control factors include the core indicators of cultivated land quality, such as tillage layer texture, pH value, organic matter content, etc. Each factor is directly related to the optimization direction of cultivated land quality. For each main control factor, call the cultivated land resource optimization sample library and perform correlation analysis between the main control factor and the sample data. The optimization sample library stores a large number of practically verified optimization cases. For example, the impact of different doses of fertilization on soil organic matter and the effects of different acid-base regulators on soil pH value. Through this factor-by-factor decomposition process, the optimization samples are grouped into N groups of optimization samples, and each group of optimization samples corresponds to a main control factor. This grouping method ensures that the optimization strategy for each main control factor is data-driven, can cover its specific range of variation, and provides sufficient support for the precise design of the strategy generator.

[0034] After completing the sample grouping, it is necessary to conduct in-depth analysis on the optimized samples in each group. By using the within-group co-reference fitting method, the inherent regularity of the sample data can be extracted. Within-group co-reference fitting refers to analyzing the relationship between the sample data with different optimization amplitudes under the same optimization method, and then determining the optimization baseline and adjustment rules. For example, under the optimization method of adjusting the soil pH value, different dosages of the regulator may correspond to different effects. By fitting these sample data, the following information can be extracted: the baseline adjustment plan, that is, the best basic adjustment strategy under this optimization method. For example, the target range of the pH value and the recommended dosage value. The linear adjustment relationship, that is, analyzing the effects of different amplitudes of the optimization method and establishing a mathematical model (such as a linear or non-linear relationship) between the optimization amplitude and its effect. For example, clarifying the degree of influence of the application amount of each unit of the regulator on the change of the pH value.

[0035] These fitting results not only provide reference values for optimization, but also construct an elastic space for optimizations with different amplitudes. Finally, the baseline adjustment plan and the linear adjustment relationship together serve as the core output of the within-group fitting, providing standardized optimization parameters for the strategy generator.

[0036] After extracting the baseline adjustment plan, the baseline adjustment plan and the linear adjustment relationship of each group of optimized samples are built into the strategy generator as its core rule module. Subsequently, combined with all the cultivated land resource optimization samples, the strategy generator is supervised and trained. The supervised training iteratively adjusts the conditional probability matrix in the strategy generator by gradually inputting the optimization samples and their corresponding target values. The role of the conditional probability matrix is to constrain the output of the strategy generator so that the generated strategy conforms to the actual optimization logic and effect. At the same time, during the training process, the strategy generator will use its loop structure to verify and adjust the generated strategy, and further optimize its internal parameters through comparative analysis with the sample target values. This training method ensures that the strategy generator can continuously learn and generate efficient strategies that meet the optimization requirements according to the input cultivated land characteristics, ultimately improving the intelligence and accuracy of cultivated land resource management.

[0037] P30: Collect information on the target cultivated land, determine the real-time quality matrix, transmit it to the said strategy generator, generate an optimization strategy under the constraint of the conditional probability matrix, and perform feedback optimization based on grey relational projection analysis to determine the quality optimization strategy.

[0038] Furthermore, step P30 of the embodiment of the present application further includes:

[0039] P31: Obtain the real-time quality matrix and the ideal quality matrix of the target cultivated land, measure the matrix difference, and determine the optimization objective; P32: Input the optimization objective into the strategy generator, and based on the conditional probability matrix, determine multiple single-factor strategies, and combine them to determine the first optimization strategy; P33: Take the first optimization strategy as the benchmark, perform generation feedback optimization until the preset number of iterations is met, and output the quality optimization strategy.

[0040] It should be understood that real-time information of the target cultivated land is collected to form a real-time quality matrix, and an optimization strategy is generated through a strategy generator. At the same time, feedback optimization is realized based on grey relational projection analysis, and finally the quality optimization strategy is determined.

[0041] First, collect the real-time quality data of the target cultivated land to generate a real-time quality matrix. This matrix reflects the current actual quality state of the target cultivated land, including key factors such as soil structure, nutrient content, and pH value. At the same time, call the preset ideal quality matrix, which represents the quality standard of the target cultivated land under optimal conditions. By performing difference analysis on the real-time quality matrix and the ideal quality matrix, calculate the difference degree of each quality main control factor. These differences are used to determine the optimization objective. For example, for some factors (such as insufficient organic matter content), an enhanced optimization strategy is required, while for other factors (such as too high acidity or alkalinity), weakening or reverse adjustment may be needed.

[0042] Since there may be mutual influence of optimization strategies among different quality factors, for example, increasing soil organic matter may cause a slight change in pH value, the overall optimization guiding direction can be determined through quality coefficient evaluation, comprehensively considering the interactive influence among various factors. This guiding direction provides a clearer reference for subsequent strategy generation by guiding the generation probability.

[0043] Input the optimization objective into the strategy generator. The strategy generator decomposes the optimization objective factor by factor based on the conditional probability matrix to generate multiple single-factor strategies. A single-factor strategy is an independent optimization plan for a single quality main control factor. For example, increase soil organic matter by adding organic fertilizers, or adjust the soil pH value by applying acid regulators. The strategy generator judges the priority and applicability of each single-factor strategy through the conditional probability matrix to ensure a balance between technical feasibility and effect reliability of the generated strategies.

[0044] Subsequently, the strategy generator combines multiple single-factor strategies to generate the first optimization strategy. The first optimization strategy is a global optimization plan, comprehensively considering the actual needs and mutual influence of each quality main control factor. For example, in the condition of dry land in the north, it may be necessary to adjust the soil structure and water supply simultaneously, and the combination of these strategies needs to be reasonably weighed through the conditional probability matrix to avoid conflicts.

[0045] Taking the first optimization strategy as the initial benchmark, generate feedback optimization through the feedback mechanism of the strategy generator. The feedback optimization is based on real-time evaluation and grey relational projection analysis to verify and correct the effect of the generated strategy. Grey relational projection analysis can quantify the difference between the actual effect of the optimization strategy and the target, and gradually narrow the optimization gap through weight adjustment and strategy reconstruction. In each round of feedback optimization, the strategy generator iterates in combination with the real-time state of the target cultivated land and the optimization goal to adjust the strategy generation direction.

[0046] This process continues until the preset number of iterations is reached or the optimization goal is fully met, and finally, a quality optimization strategy is output. This optimization strategy fully considers the real-time condition of the target cultivated land and also combines the refined adjustment of the strategy by the feedback mechanism to ensure the scientificity and feasibility of the generated scheme.

[0047] Furthermore, for the generation of feedback optimization, step P33 of the embodiment of the present application further includes:

[0048] P33-1: Simulate the first optimization strategy and conduct grey relational projection analysis to determine the quality coefficient, where the quality coefficient includes a projection angle and a projection value. The projection angle is the direction difference from the ideal quality matrix, and the projection value is the degree of superiority or inferiority from the ideal quality matrix; P33-2: Generate the first feedback information based on the quality coefficient; P33-3: Generate and combine to determine the second optimization strategy based on the first feedback information and the conditional probability matrix.

[0049] Optionally, the specific process of generating feedback optimization can be, based on the first optimization strategy, first conduct a simulation evaluation on it and comprehensively analyze the effect of the strategy using grey relational projection analysis. Grey relational projection analysis is an important tool for evaluating the optimization strategy and is used to quantify the matching degree between the first optimization strategy and the ideal quality matrix. Specifically, this analysis generates two core indicators: the projection angle and the projection value. Among them, the projection angle describes the difference in direction between the optimization strategy and the ideal quality matrix. The smaller the projection angle, the closer the direction is to the ideal state; the projection value reflects the degree of closeness in quality superiority or inferiority between the optimization strategy and the ideal quality matrix. The higher the projection value, the closer the optimization strategy is to the target effect. Through this process, the effectiveness of the current optimization strategy and its existing deviations can be intuitively identified, providing a quantitative basis for subsequent adjustments.

[0050] Next, based on the quality coefficients (including the projection angle and projection value) obtained from the grey relational projection analysis, the first feedback information is generated. The feedback information specifically includes two aspects: one is to put forward clear direction adjustment suggestions for the indicators with a relatively large projection angle, such as adjusting the direction of the fertilization strategy to better meet the soil nutrient requirements; the other is to provide correction suggestions for the optimization amplitude for the indicators with a relatively low projection value, such as increasing the application rate of soil conditioners or enhancing the irrigation intensity to improve the effect. These feedback information clarify the deficiencies of the current strategy and put forward specific directions for optimization and adjustment, laying a foundation for generating new optimization strategies.

[0051] Finally, the first feedback information is combined with the conditional probability matrix built in the strategy generator, and through retraining and adjusting the weights, a new second optimization strategy is generated. This process includes: first, applying the first feedback information to correct the parameters in the conditional probability matrix, so that the generator can more accurately reflect the latest optimization objectives; second, under the guidance of the adjusted conditional probability matrix, re-generating the single-factor optimization strategies for each quality main control factor; finally, combining each single-factor strategy into the second optimization strategy and ensuring its coordination and applicability within the global scope. The new optimization strategy can better balance the relationship between the actual needs and the ideal state of the target cultivated land, and can provide an efficient solution for realizing the final quality optimization.

[0052] Through the above steps, the generation of feedback optimization not only realizes the precise adjustment of the first optimization strategy, but also further improves the scientificity and practicality of the optimization strategy through the combination of dynamic feedback and the conditional probability matrix. This iterative optimization mechanism ensures that the output quality optimization strategy can fully adapt to the actual conditions of the target cultivated land, providing strong support for resource management and cultivated land improvement.

[0053] Furthermore, after determining the optimization objective, step P31 of the embodiment of the present application further includes:

[0054] P31-1a: Guided by the optimization objective, initialize the weights of the first matrix to determine the first distribution weight, where the first distribution weight is positively correlated with the relevance of the optimization objective; P31-2a: Guided by the optimization objective, initialize the weights of the second matrix to determine the second distribution weight, where the second distribution weight is negatively correlated with the relevance of the optimization objective.

[0055] In a possible embodiment of the present application, after determining the optimization objective, taking the optimization objective as the guide, the weight of the first matrix (the main control factor matrix of cultivated land quality) in the quality relationship matrix is initialized, and the first distribution weight is calculated and generated. Specifically, the setting of the first distribution weight is positively correlated with the relevance of the optimization objective, that is, the higher the contribution degree of a certain main control factor to achieving the optimization objective, the greater its weight value. For example, if the goal is to increase the organic matter content of cultivated land, then the main control factors directly related to organic matter in the first matrix (such as soil organic matter level, soil aeration, etc.) will be given higher weights, while the weights of other factors will be relatively reduced.

[0056] The technical core of this process lies in the positive correlation evaluation. By analyzing the historical optimization effect data of the optimization objective and each main control factor, a correlation model is constructed, and the weights of each factor are allocated according to the model results. Through this weight initialization step, the optimization direction of the first matrix becomes clearer, providing a scientific basis for the subsequent generation of optimization strategies.

[0057] Next, taking the optimization objective as the guide, the weight of the second matrix (the quality decline driving mechanism matrix) in the quality relationship matrix is initialized, and the second distribution weight is calculated and generated. Different from the first matrix, the second distribution weight is negatively correlated with the relevance of the optimization objective, that is, the greater the negative impact of a certain driving mechanism on the optimization objective, the lower its weight value. For example, if the optimization objective is to increase the content of soil trace elements, and some driving mechanisms (such as unreasonable fertilization methods or element loss caused by irrigation) may lead to the inferior optimization of the objective, the weights of these mechanisms will be correspondingly reduced, thereby reducing their influence on the strategy generation.

[0058] The key to the weight initialization lies in the negative correlation control. By analyzing the historical negative effect data of the driving mechanism on the target optimization effect, the reverse adjustment algorithm is used to dynamically reduce its weight value, ensuring that the negative guiding effect of the second matrix on the optimization strategy is effectively controlled, and at the same time avoiding optimization deviations caused by excessive weights.

[0059] Through the weight initialization of the above steps, the weight distributions of the first matrix and the second matrix are optimized, forming a dynamic weight configuration system guided by the optimization objective. This configuration method enhances the response ability of the strategy generator to the optimization objective, enabling the subsequent generated optimization strategies to not only give full play to the positive role of the main control factors but also effectively avoid the negative impact of the quality decline driving mechanism, providing technical support for efficient and accurate cultivated land quality optimization.

[0060] P40: Based on the quality optimization strategy, the cultivated land resources of the target cultivated land are managed.

[0061] Furthermore, step P40 of the embodiment of the present application further includes:

[0062] P41: Identify the quality optimization strategy, and divide it into M strategy phases, where each strategy phase is marked with a phase quality matrix; P42: Based on the M strategy phases, conduct quality optimization acceptance for the target cultivated land in stages, and determine the acceptance quality matrix; P43: Map the acceptance quality matrix and the phase quality matrix, and conduct feedback optimization management.

[0063] It should be understood that based on the generated quality optimization strategy, comprehensive resource management is carried out on the target cultivated land. By refining the optimization strategy into a phased plan, and conducting acceptance and feedback adjustment on the quality objectives of each phase, it is ensured that the optimization effect is gradually achieved, and efficient management of cultivated land resources is realized.

[0064] Before implementing the optimization strategy, first conduct in-depth analysis of the quality optimization strategy. According to its optimization objectives and implementation sequence, divide the strategy into M phases. Each phase takes an independent quality optimization objective as the core and generates a corresponding phase quality matrix, which clarifies the key indicators that the cultivated land needs to reach within the phase (such as soil organic matter content, trace element level, pH value range, etc.). Through this phased management method, complex global optimization tasks can be decomposed into several easy-to-execute subtasks, making resource allocation more precise and optimization implementation more orderly.

[0065] After each strategy phase is completed, conduct quality optimization acceptance to evaluate whether the actual optimization effect reaches the phase objective. Specifically, through real-time data collection and monitoring, generate an acceptance quality matrix, and conduct comparative analysis with the phase quality matrix. The acceptance quality matrix covers the current state indicators of the cultivated land, helping to identify the success points and deficiencies in the optimization implementation.

[0066] The advantage of phased acceptance is that it can dynamically monitor the optimization progress and avoid the risk of global failure. For example, during the acceptance of a certain phase, if some soil nutrient indicators do not meet the standards, subsequent measures can be adjusted in time. This phased evaluation mechanism effectively improves the flexibility of management and the accuracy of goal achievement.

[0067] Finally, map and analyze the acceptance quality matrix and the stage quality matrix to identify gaps and conduct feedback optimization management. Since the optimization process of cultivated land resources may be affected by external environments (such as climate change, natural soil restoration cycle, etc.), some goals may not be fully achieved, and real-time adjustment is required through feedback optimization management. Exemplarily, through gap analysis, identify the indicators in the acceptance quality matrix that do not meet the stage goals, and analyze the reasons for non-achievement. For example, the fertilization effect is weakened due to climate conditions. By adjusting the optimization plan, for the gap indicators, adjust the optimization strategy of the current stage, and extend the implementation time of this stage if necessary to ensure that the optimization effect meets the expected goals. Through feedback optimization, transmit the adjusted strategy to the next stage to provide a basis for correction for subsequent strategy implementation, forming a closed-loop management.

[0068] Through feedback optimization management, it is possible to dynamically respond to external uncertainties and ensure that the quality optimization effect of each stage meets the expectations. The phased management method provides refined support for resource optimization, while the feedback optimization mechanism enhances the adaptability of management and provides guarantee for the continuous improvement of cultivated land resources.

[0069] In summary, the embodiments of the present application have at least the following technical effects:

[0070] The present application constructs a quality relationship matrix of the main control factors of cultivated land quality and the decline driving mechanism, combines a strategy generator with an internal conditional probability matrix to dynamically generate optimization strategies, and based on real-time quality matrix information collection and grey relational projection analysis, realizes feedback optimization adjustment, and conducts phased management and acceptance of the target cultivated land according to the optimization strategy to ensure the efficient use of resources and the achievement of optimization goals.

[0071] It achieves the technical effects of realizing the accuracy and dynamic adaptability of cultivated land quality optimization through multi-source data analysis and feedback optimization mechanism.

[0072] Embodiment 2, based on the same inventive concept as the method for optimizing the quality of cultivated land resources under multi-source data analysis in the foregoing embodiment, as Figure 2 shown, the present application provides a device for optimizing the quality of cultivated land resources under multi-source data analysis. The device in the embodiments of the present application and the method embodiments are based on the same inventive concept. Among them, the device includes:

[0073] A quality relationship matrix mining module 11, which is used to obtain the attributes of the target cultivated land and mine the quality relationship matrix, where the quality relationship matrix includes a first matrix based on the main control factors of cultivated land quality and a second matrix based on the decline driving mechanism of cultivated land quality.

[0074] The policy generator construction module 12 is used to construct a policy generator based on the quality relationship matrix. The policy generator has a built-in conditional probability matrix for policy generation constraints, and the policy generator is a cyclic structure.

[0075] The optimized policy generation module 13 is used to collect information on the target cultivated land, determine the real-time quality matrix, transmit it to the policy generator, generate an optimized policy under the constraint of the conditional probability matrix, and perform feedback optimization based on grey relational projection analysis to determine the quality optimization policy.

[0076] The cultivated land resource management module 14 is used to manage the cultivated land resources of the target cultivated land based on the quality optimization policy.

[0077] Furthermore, the quality relationship matrix mining module 11 is also used to perform the following steps:

[0078] Obtain the attributes of the target cultivated land, perform agricultural big data retrieval with the region of the target cultivated land as the constraint, and call the cultivated land monitoring data of the same attributes; traverse the cultivated land monitoring data to mine the matrix element range of the quality relationship matrix; based on the matrix element range, perform quality optimization constraints on the target cultivated land, including natural optimization that meets the matrix element range and non-natural condition optimization that does not meet the matrix element range.

[0079] Furthermore, the policy generator construction module 12 is also used to perform the following steps:

[0080] Traverse the quality main control factors, call the cultivated land resource optimization samples for factor-by-factor decomposition to determine N groups of optimization samples, where the N groups of optimization samples correspond one-to-one to the quality main control factors; traverse the N groups of optimization samples to perform within-group co-reference fitting to determine the baseline adjustment plan, where co-reference fitting refers to fitting the optimization samples of the same method; incorporate the baseline adjustment plan into the policy generator and perform supervised training on the policy generator based on the cultivated land resource optimization samples.

[0081] Furthermore, the optimized policy generation module 13 is also used to perform the following steps:

[0082] Obtain the real-time quality matrix and the ideal quality matrix of the target cultivated land, measure the matrix difference, and determine the optimization target; input the optimization target into the policy generator, and based on the conditional probability matrix, determine multiple single-factor policies and combine them to determine the first optimization policy; use the first optimization policy as a benchmark to perform generation feedback optimization until the preset number of iterations is met, and output the quality optimization policy.

[0083] Further, the optimization strategy generation module 13 is further configured to perform the following steps:

[0084] Simulate the first optimization strategy and perform grey relational projection analysis to determine a quality coefficient, where the quality coefficient includes a projection angle and a projection value. The projection angle is the direction difference from the ideal quality matrix, and the projection value is the goodness or badness degree from the ideal quality matrix; generate first feedback information based on the quality coefficient; generate and combine to determine a second optimization strategy based on the first feedback information and the conditional probability matrix.

[0085] Further, the optimization strategy generation module 13 is further configured to perform the following steps:

[0086] Taking the optimization objective as a guide, perform weight initialization on the first matrix to determine a first distribution weight, where the first distribution weight is positively correlated with the correlation degree of the optimization objective; taking the optimization objective as a guide, perform weight initialization on the second matrix to determine a second distribution weight, where the second distribution weight is negatively correlated with the correlation degree of the optimization objective.

[0087] Further, the cultivated land resource management module 14 is further configured to perform the following steps:

[0088] Identify the quality optimization strategy, divide it into M strategy stages, where each strategy stage is marked with a stage quality matrix; based on the M strategy stages, conduct quality optimization acceptance of the target cultivated land in stages to determine an acceptance quality matrix; map the acceptance quality matrix and the stage quality matrix for feedback optimization management.

[0089] It should be noted that the above sequence of embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above description of specific embodiments of this specification is made. Additionally, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0090] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included within the protection scope of the present application.

[0091] This specification and the drawings are only exemplary descriptions of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. A method for optimizing cultivated land resource quality under multi-source data analysis, characterized in that: The method comprises: Acquire the target cultivated land attributes and mine the quality relationship matrix, wherein the quality relationship matrix includes a first matrix based on the main control factors of cultivated land quality and a second matrix based on the driving mechanism of cultivated land quality decline; Based on the quality relationship matrix, a strategy generator is constructed, wherein the strategy generator has a built-in conditional probability matrix, the probability matrix is ​​used to perform strategy generation constraints, and the strategy generator is a loop structure; Collect information on the target cultivated land, determine the real-time quality matrix, transmit it to the strategy generator, generate the optimization strategy under the constraint of the conditional probability matrix, and determine the quality optimization strategy through feedback optimization based on grey relational projection analysis; Based on the quality optimization strategy, farmland resource management is performed on the target farmland.

2. The method for optimizing cultivated land resource quality under multi-source data analysis according to claim 1, characterized in that: Build a policy generator, including: Traversing the main quality control factors, calling the optimized samples of cultivated land resources to perform factor-by-factor decomposition, and determining N groups of optimized samples, wherein the N groups of optimized samples correspond one to one to the main quality control factors; Traversing the N groups of optimized samples, performing co-referential fitting within the group, and determining a baseline adjustment scheme, wherein co-referential fitting refers to fitting optimized samples of the same mode; The baseline adjustment scheme is built into the strategy generator, and supervised training is performed on the strategy generator based on the cultivated land resource optimization sample.

3. The method for optimizing cultivated land resource quality under multi-source data analysis according to claim 1, characterized in that: After mining the quality relationship matrix, it includes: Obtain the attributes of the target cultivated land, use the region of the target cultivated land as a constraint, perform agricultural big data retrieval, and call the cultivated land monitoring data with the same attributes; Traversing the cultivated land monitoring data, mining the matrix element range of the quality relationship matrix; Based on the matrix element range, the target cultivated land is subjected to quality optimization constraints, including natural optimization that satisfies the matrix element range and non-natural optimization that does not satisfy the matrix element range.

4. The method for optimizing cultivated land resource quality under multi-source data analysis according to claim 1, characterized in that: Generate optimization strategies under conditional probability matrix constraints and feedback optimization based on grey relational projection analysis, including: Obtain the real-time quality matrix and ideal quality matrix of the target cultivated land, measure the matrix difference, and determine the optimization target; Inputting the optimization target into the strategy generator, determining a plurality of single factor strategies based on a conditional probability matrix, and combining them to determine a first optimization strategy; Based on the first optimization strategy, feedback optimization is generated until a preset number of iterations is met, and the quality optimization strategy is output.

5. The method for optimizing cultivated land resource quality under multi-source data analysis according to claim 4, characterized in that: The generating feedback optimization comprises: Simulating the first optimization strategy and performing grey relational projection analysis to determine a quality coefficient, wherein the quality coefficient includes a projection angle and a projection value, the projection angle being a directional difference from an ideal quality matrix, and the projection value being a degree of superiority to an ideal quality matrix; Based on the quality coefficient, generating first feedback information; Based on the first feedback information and the conditional probability matrix, a second optimization strategy is generated and combined to determine.

6. The method for optimizing cultivated land resource quality under multi-source data analysis according to claim 4, characterized in that: After determining the optimization goals, including: Guided by the optimization goal, weight initialization is performed on the first matrix to determine a first distribution weight, wherein the first distribution weight is positively correlated with the correlation degree of the optimization goal; Guided by the optimization target, the second matrix is ​​weight initialized to determine a second distribution weight, wherein the second distribution weight is negatively correlated with the correlation of the optimization target.

7. The method for optimizing farmland resource quality under multi-source data analysis according to claim 1, characterized in that: The performing farmland resource management on the target farmland includes: Identify the quality optimization strategy and divide it into M strategy stages, wherein each strategy stage is marked with a stage quality matrix; Based on the M strategy stages, quality optimization acceptance of the target cultivated land is carried out in stages to determine an acceptance quality matrix; The acceptance quality matrix and the stage quality matrix are mapped to perform feedback optimization management.

8. A device for optimizing the quality of cultivated land resources under multi-source data analysis, characterized in that: The device comprises: A quality relationship matrix mining module, the quality relationship matrix mining module is used to obtain the target cultivated land attributes and mine the quality relationship matrix, wherein the quality relationship matrix includes a first matrix based on the main control factors of cultivated land quality and a second matrix based on the driving mechanism of cultivated land quality decline; A strategy generator construction module, wherein the strategy generator construction module is used to construct a strategy generator based on the quality relationship matrix, wherein the strategy generator has a built-in conditional probability matrix, the probability matrix is ​​used to perform strategy generation constraints, and the strategy generator is a loop structure; An optimization strategy generation module, the optimization strategy generation module is used to collect information on the target cultivated land, determine the real-time quality matrix, transmit it to the strategy generator, generate the optimization strategy under the constraints of the conditional probability matrix, and determine the quality optimization strategy based on feedback optimization of grey relational projection analysis; A farmland resource management module is used to perform farmland resource management on the target farmland based on the quality optimization strategy.

Images