Crop culture medium production management method and system based on planting and breeding circulation

Abstract

The invention relates to the technical field of data processing, and discloses a crop culture medium production management method and system based on planting and breeding circulation, which constructs a whole-process intelligent management system from raw material proportioning, conveying scheduling to production dynamic regulation and control through multi-source data fusion, multi-objective optimization and deep reinforcement learning. Based on matrix demands and nutritional demands in demand prediction, a dynamic and static combined optimization decision is realized through multi-objective optimization and reinforcement learning. Therefore, the initial production strategy is planned through multi-objective optimization, scientific configuration and intelligent management of multi-source matrix production raw materials are achieved, then the initial production strategy is dynamically optimized through reinforcement learning, the method can adapt to the influence of different actual factors on the production strategy, the problems of raw material heterogeneity processing and supply uncertainty are solved, and the production efficiency is improved. Cost and matrix adaptability are balanced, a crop cultivation matrix production management scheme aiming at the organic vinegar residues and the silkworm excrement is provided, and intelligent agricultural planting and breeding circulation development is promoted.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and system for the production management of crop cultivation substrates based on crop-livestock cycles. Background Technology

[0002] With the increasing demand for sustainable agricultural development, the crop-livestock cycle model has attracted much attention due to its ability to efficiently utilize agricultural waste. Organic vinegar residue (acetic acid fermentation residue) and silkworm excrement (silkworm feces) are rich in nutrients such as nitrogen, phosphorus, potassium, and organic matter, making them high-quality raw materials for crop cultivation substrates.

[0003] However, in actual production, the nutrient ratio of raw materials varies greatly depending on their source, and the substrate requirements of crops change dynamically over time. Traditional substrate production management relies on experience-based adjustments and lacks dynamic optimization capabilities, resulting in low resource utilization efficiency and high production costs. Summary of the Invention

[0004] This invention provides a method and system for the production management of crop cultivation substrate based on crop-livestock cycle, aiming to solve at least one of the above-mentioned technical problems.

[0005] To achieve the above objectives, the present invention provides a method for the production and management of crop cultivation substrates based on crop-livestock cycles, the method comprising the following steps: S1: Obtain batch supply information of matrix raw materials and generate standardized nutritional data of multi-source raw materials; S2: Upon receiving the crop planting plan for the target crop cultivation area, extract the crop planting planning information from the crop planting plan, analyze the substrate requirements and cultivation nutrient requirements for each planting period based on time series analysis, and determine the predicted cultivation requirements. S3: Based on the standardized nutrient data and the predicted cultivation requirements, a multi-objective optimization algorithm is used to solve the initial production strategy of the crop cultivation substrate; S4: Using demand satisfaction and nutritional deviation as the state space, and production volume adjustment and ingredient ratio adjustment as the action space, a reinforcement learning model based on dynamic deviation penalty is established. The optimal adjustment strategy is iterated based on the reward value. The adjustment instructions of the optimal adjustment strategy are used to optimize the initial production strategy and generate a real-time production strategy for crop cultivation substrate. S5: Implement production management and control of crop cultivation substrate according to the real-time production strategy.

[0006] Optionally, the steps of obtaining batch supply information of matrix raw materials and generating standardized nutritional data for multi-source raw materials specifically include: S11: Query batch supply information for different matrix raw material sources; wherein, the matrix raw material sources include several vinegar residue sources and several silkworm excrement sources, and the batch supply information includes the supplier's test report for each batch of matrix raw material source; S12: Extract the nutritional parameters of the raw materials from the supplier's test reports for each batch of matrix raw materials, and generate a list containing the nutritional content of several batches of raw materials. Standardized nutritional data; where i represents the type of the i-th raw material source, i=1 is vinegar residue, i=2 is silkworm excrement; j represents the batch of raw material; k represents the content of the k-th nutrient.

[0007] Optionally, upon receiving the crop planting plan for the target crop cultivation area, the crop planting planning information in the crop planting plan is extracted, and the substrate requirements and cultivation nutrient requirements for each planting period are analyzed based on time series analysis to determine the cultivation forecasting requirements. This step specifically includes: S21: Upon receiving crop planting planning information for the target crop cultivation area, the crop planting planning information is used as a basis; wherein, the crop planting planning information includes the planting area and planting growth period plan for each crop type; S22: Based on the planting area and the planting production period of each crop type at different planting times, analyze the substrate requirements and cultivation nutrient requirements for each planting time period to determine the cultivation forecast requirements.

[0008] Optionally, based on the planting area and production stage of each crop type at different planting periods, the substrate requirements and nutrient requirements for each planting period are analyzed to determine the cultivation forecasting steps, specifically including: S221: Based on the planting area and production period of each crop type at different planting times, and according to the nutrient content requirements and soil supply of the crop type per unit planting area and at different planting production periods, analyze the substrate requirements and cultivation nutrient requirements for each planting period. The expression for the required matrix quantity is as follows: ; In the formula, This represents the substrate requirement for each planting period t. This represents the planting area of ​​crop type m during planting period t. This represents the nutrient content requirement per unit planting area for crop type m during planting period t. The expression for the cultivation nutrient requirements is specifically as follows: ; In the formula, This represents the cultivation nutrient requirements for nutrient index k at each planting period t. This represents the nutrient requirement k per unit planting area for crop type m during planting period t. This represents the basic supply of soil to nutrient index k per unit planting area for crop type m during planting period t. S222: Determine the predicted cultivation requirements of the target crop cultivation area based on the substrate requirements and cultivation nutrient requirements of the target crop cultivation area at each planting period.

[0009] Optionally, based on the standardized nutrient data and the predicted cultivation requirements, a multi-objective optimization algorithm is used to solve the initial production strategy steps for crop cultivation substrates, specifically including: S31: Extract the nutrient content of several batches of raw materials from the standardized nutrient data. and the substrate requirement in the predicted cultivation needs Nutritional requirements for cultivation ; S32: The decision variable is the amount of raw material of the i-th source type used in the j-th batch of raw materials during planting period t. Based on the set of constraints determined by the total substrate demand and nutrient demand, and the set of optimization objective functions determined by minimizing procurement costs and maximizing nutrient matching, a multi-objective optimization algorithm is used to solve the initial production strategy of crop cultivation substrate.

[0010] Optionally, the expression for the set of constraints determining the total substrate demand and nutrient demand, and the set of optimization objective functions determined by minimizing procurement costs and maximizing nutrient matching, are as follows: Constraint set: ; ; In the formula, , Indicates the coefficient for the nutritional balance range; Optimize the objective function set: ; ; In the formula, This represents the transportation cost per unit quantity of raw material from the j-th batch, for the i-th source type. This represents the purchase cost per unit quantity of raw material from the j-th batch, for the ith raw material source type.

[0011] Optionally, a multi-objective optimization algorithm is used to solve the initial production strategy steps for crop cultivation substrates, specifically including: S321: The optimization objective function that minimizes procurement costs. As the primary objective function, the optimization objective function is to maximize the nutrient matching degree. As a secondary objective function; S322: Set a threshold for the secondary objective function, and convert the secondary objective function into a constraint condition; wherein the expression of the converted constraint condition is as follows: ; In the formula, This indicates the set nutritional matching threshold. S323: Summarize the transformed constraints with the original constraint set determined by the total matrix requirement and nutrient requirement, and then optimize based on the summarized constraint set and the optimization objective function of minimizing procurement cost as the main objective function. Construct a single-objective optimization model with multiple constraints; S324: Solve the optimization model using a heuristic optimization algorithm to obtain the raw material usage for each batch of each raw material source type at each planting period. The optimal plan is used as the initial production strategy for crop cultivation substrate.

[0012] Optionally, using demand satisfaction and nutritional deviation as the state space, and production quantity adjustment and ingredient ratio adjustment as the action space, a reinforcement learning model based on dynamic deviation penalty is established, specifically including: S41: Construct a reinforcement learning environment with demand satisfaction and nutritional deviation as the state space, production quantity adjustment and ingredient ratio adjustment as the action space, and a reward function based on a weighted negative penalty term; The expressions for the state space and action space are as follows: ; ; ; ; In the formula, Representing the state space, This indicates that the substrate does not meet the requirements. Indicates nutritional imbalance. Represents the action space, This indicates an adjustment in production volume. This indicates an adjustment in the ingredient ratio; Specifically, the expression based on the weighted negative penalty term as the reward function is as follows: ; ; In the formula, This represents the reward value during planting period t. , , Indicates the weight of the penalty item. This represents the total procurement and transportation costs during the planting period t; S42: Construct a state space As input, with action space probability distribution The output Actor network and the state space and action space As input, with state-action value This is the output Critic network, and the Actor-Critic network is initialized. S43: Associate the state space, action space, and reward function in the reinforcement learning environment with the Actor-Critic network, and generate a reinforcement learning model by using the Critic network loss function constructed based on temporal difference error and the Actor network advantage function determined based on the network policy gradient.

[0013] Optionally, the step of iteratively adjusting the optimal strategy based on the reward value, optimizing the initial production strategy using the adjustment instructions of the optimal adjustment strategy, and generating a real-time production strategy for crop cultivation substrate specifically includes: S44: Based on the initial production strategy, use the raw material usage for each batch of each raw material source type for each planting period. Determine the initial substrate production quantity and initial ingredient ratio; The expressions for the initial matrix production amount and the initial ingredient ratio are as follows: ; ; In the formula, This indicates the initial substrate production quantity. Indicates the initial ingredient ratio; S45: During each iteration of the planting period, collect the real-time state of the reinforcement learning environment. Real-time status Inputting the Actor network, the Softmax function outputs an action probability distribution, and the current adjustment action is obtained by sampling. ; S46: Adjust the matrix production volume and ingredient ratio according to the adjustment action, and calculate the adjusted raw material consumption based on the adjusted matrix production volume and ingredient ratio; ; ; ; In the formula, This indicates the adjusted raw material usage for each batch under each raw material source type at each planting stage. This indicates the corrected matrix production volume. This indicates the revised ingredient ratio; S47: After executing the correction action, collect the reward value for the planting period t. and the status of the next planting period The parameters of the Critic network are updated using the temporal difference error, and the parameters of the Actor network are updated using the policy gradient. The above iterative process is repeated until the policy converges, and the optimal adjustment policy is output. S48: Output the optimal adjustment strategy as a real-time production strategy for the crop cultivation substrate after optimizing the initial production strategy.

[0014] Furthermore, to achieve the above objectives, the present invention also provides a crop cultivation substrate production management system based on crop-livestock cycle, comprising: The acquisition module is used to acquire batch supply information of matrix raw materials and generate standardized nutritional data of multi-source raw materials; The receiving module is used to extract the crop planting planning information from the crop planting plan when it receives the crop planting plan for the target crop cultivation area, and to determine the cultivation forecast requirements based on the time series analysis of the substrate requirements and cultivation nutrient requirements for each planting period. The solution module is used to solve the initial production strategy of crop cultivation substrate based on the standardized nutrient data and the predicted cultivation requirements, using a multi-objective optimization algorithm. The optimization module is used to establish a reinforcement learning model based on dynamic deviation penalty, with demand satisfaction and nutritional deviation as the state space and production volume adjustment and ingredient ratio adjustment as the action space. It iterates the optimal adjustment strategy based on the reward value, optimizes the initial production strategy using the adjustment instructions of the optimal adjustment strategy, and generates a real-time production strategy for crop cultivation substrate. The execution module is used to perform production management and control of crop cultivation substrate according to the real-time production strategy.

[0015] The beneficial effects of this invention are as follows: It proposes a method and system for the production management of crop cultivation substrates based on crop-livestock cycles. Through multi-source data fusion, multi-objective optimization, and deep reinforcement learning, it constructs a full-process intelligent management system from raw material ratio and transportation scheduling to dynamic production control. Based on substrate and nutrient requirements in demand forecasting, it achieves dynamic and static optimization decision-making through multi-objective optimization and reinforcement learning. Therefore, this invention achieves the scientific allocation and intelligent management of multi-source substrate production raw materials by planning the initial production strategy through multi-objective optimization. Then, it uses reinforcement learning to dynamically optimize the initial production strategy, adapting to the impact of different actual factors on the production strategy. This solves the problems of handling raw material heterogeneity and supply uncertainty, optimizes and improves forecast accuracy and resource utilization efficiency, balances costs, improves substrate adaptability, and promotes the development of smart agricultural crop-livestock cycles. Attached Figure Description

[0016] Figure 1 This is a schematic flowchart of the crop cultivation substrate production management method based on crop-livestock cycle according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of the crop cultivation substrate production management system based on crop-livestock cycle according to an embodiment of the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0018] This invention provides a method for the production and management of crop cultivation substrates based on crop-livestock cycles, referring to... Figure 1 , Figure 1 This is a schematic diagram of the production management method for crop cultivation substrate based on crop-livestock cycle according to an embodiment of the present invention.

[0019] In this embodiment, a method for production management of crop cultivation substrate based on crop-livestock cycle is provided, the method comprising the following steps: S1: Obtain batch supply information of matrix raw materials and generate standardized nutritional data of multi-source raw materials; S2: Upon receiving the crop planting plan for the target crop cultivation area, extract the crop planting planning information from the crop planting plan, analyze the substrate requirements and cultivation nutrient requirements for each planting period based on time series analysis, and determine the predicted cultivation requirements. S3: Based on the standardized nutrient data and the predicted cultivation requirements, a multi-objective optimization algorithm is used to solve the initial production strategy of the crop cultivation substrate; S4: Using demand satisfaction and nutritional deviation as the state space, and production volume adjustment and ingredient ratio adjustment as the action space, a reinforcement learning model based on dynamic deviation penalty is established. The optimal adjustment strategy is iterated based on the reward value. The adjustment instructions of the optimal adjustment strategy are used to optimize the initial production strategy and generate a real-time production strategy for crop cultivation substrate. S5: Implement production management and control of crop cultivation substrate according to the real-time production strategy.

[0020] It should be noted that organic vinegar residue (acetic acid fermentation residue) and silkworm excrement (silkworm feces) are rich in nutrients such as nitrogen, phosphorus, potassium, and organic matter, making them high-quality raw materials for crop cultivation substrates. However, in actual production, the nutrient ratio of raw materials varies greatly depending on their source, and the substrate requirements of the crops change dynamically over time. Traditional substrate production management relies on experience-based adjustments and lacks dynamic optimization capabilities, resulting in low resource utilization efficiency and high production costs.

[0021] To address the aforementioned issues, this embodiment focuses on the precision production needs of agricultural waste (vinegar residue, silkworm excrement) resource utilization in a crop-livestock integrated farming scenario. It establishes a five-stage closed-loop process covering the entire supply chain for crop cultivation substrate production management: raw material data standardization, cultivation demand prediction, multi-objective optimization of initial strategies, reinforcement learning-based dynamic adjustment, and production control implementation. This upgrades production strategies from static planning to dynamic adaptation, providing a standardized technical framework for the efficient resource utilization of agricultural waste.

[0022] In a preferred embodiment, the steps of obtaining batch supply information of the matrix raw materials and generating standardized nutritional data for multi-source raw materials specifically include: S11: Query batch supply information for different matrix raw material sources; wherein, the matrix raw material sources include several vinegar residue sources and several silkworm excrement sources, and the batch supply information includes the supplier's test report for each batch of matrix raw material source; S12: Extract the nutritional parameters of the raw materials from the supplier's test reports for each batch of matrix raw materials, and generate a list containing the nutritional content of several batches of raw materials. Standardized nutritional data; where i represents the type of the i-th raw material source, i=1 is vinegar residue, i=2 is silkworm excrement; j represents the batch of raw material; k represents the content of the k-th nutrient.

[0023] In this embodiment, addressing the heterogeneity of nutritional data for raw materials such as vinegar residue and silkworm excrement due to differences in origin (different vinegar factories, silkworm breeding bases) and batch fluctuations, this invention collects supply information from multiple sources and batches, extracts standardized nutritional parameters, and generates a unified-format raw material nutrition database. This provides a reliable data foundation for subsequent ingredient optimization. Thus, by obtaining supplier test reports for each batch from different matrix raw material sources, this invention transforms scattered report data into a structured, computable, standardized nutritional dataset. This ensures the comparability of raw material data from different sources and batches, enabling quantifiable comparison of the nutritional characteristics of raw materials from multiple sources. It provides a unified data benchmark for precise ingredient formulation based on nutritional requirements, avoiding formulation deviations caused by data heterogeneity.

[0024] In a preferred embodiment, upon receiving the crop planting plan for the target crop cultivation area, the crop planting planning information in the crop planting plan is extracted, and the substrate requirements and cultivation nutrient requirements for each planting period are analyzed based on time series analysis to determine the cultivation forecast requirements. This step specifically includes: S21: Upon receiving crop planting planning information for the target crop cultivation area, the crop planting planning information is used as a basis; wherein, the crop planting planning information includes the planting area and planting growth period plan for each crop type; S22: Based on the planting area and the planting production period of each crop type at different planting times, analyze the substrate requirements and cultivation nutrient requirements for each planting time period to determine the cultivation forecast requirements.

[0025] In this embodiment, the crop planting plan for the target area is first received (which can be an electronic document or data entered into the system). Two key types of information are extracted: a list of crop types (e.g., tomatoes, cucumbers, lettuce, etc.) and a single-crop planting plan (including the total planting area for each crop, the allocation of planting area by time period, the division of growth stages (e.g., seedling stage, vegetative growth stage, reproductive growth stage), and the expected harvest period), ensuring that the information covers spatial, temporal, and biological characteristics. Following this, based on crop growth patterns, there are significant differences in substrate requirements (amount) and nutrient supply requirements (NPK, etc.) at different growth stages (e.g., seedlings require less substrate but have sufficient nitrogen, while fruiting stages require more and are rich in phosphorus and potassium). Combining the actual planting area and growth stage of each crop at each planting stage, a time-crop-demand correlation model fitted with historical production data is used to calculate the total substrate requirement and cultivation requirements for different nutrient indicators at each stage. Finally, a time-based cultivation forecast demand list is compiled.

[0026] Therefore, this invention extracts core information such as crop type, planting area, and growth period division from the planting planning documents of the target crop cultivation area. Then, it combines the substrate consumption characteristics and nutrient demand patterns of crops at different growth stages, and quantifies the substrate demand and nutrient supplementation requirements through time-segmented analysis. This transforms the abstract planting plan into specific production targets, thereby turning vague planting tasks into precise production indicators, clarifying the minimum usage and nutrient standards for substrate production at each time period, providing clear targets for subsequent production strategy formulation, and avoiding raw material stockpiling or insufficient supply due to unclear demand.

[0027] Based on this, according to the planting area and production stage of each crop type at different planting periods, the substrate requirements and cultivation nutrient requirements for each planting period are analyzed to determine the cultivation demand prediction steps, specifically including: S221: Based on the planting area and production period of each crop type at different planting times, and according to the nutrient content requirements and soil supply of the crop type per unit planting area and at different planting production periods, analyze the substrate requirements and cultivation nutrient requirements for each planting period. The expression for the required matrix quantity is as follows: ; In the formula, This represents the substrate requirement for each planting period t. This represents the planting area of ​​crop type m during planting period t. This represents the nutrient content requirement per unit planting area for crop type m during planting period t. The expression for the cultivation nutrient requirements is specifically as follows: ; In the formula, This represents the cultivation nutrient requirements for nutrient index k at each planting period t. This represents the nutrient requirement k per unit planting area for crop type m during planting period t. This represents the basic supply of soil to nutrient index k per unit planting area for crop type m at planting time t. S222: Determine the predicted cultivation requirements of the target crop cultivation area based on the substrate requirements and cultivation nutrient requirements of the target crop cultivation area at each planting period.

[0028] In this embodiment, based on crop planting area, unit demand during the growth period, and soil basic supply capacity, the substrate demand and nutrient supplementation requirements for each planting period are accurately calculated using quantitative formulas, achieving quantification and calculable expression of cultivation forecast demand. It should be noted that, considering soil basic supply capacity, when determining cultivation nutrient requirements, the demand and supply gap for a single nutrient for a single crop are first calculated (if supply ≥ demand, the gap is 0, and no substrate supplementation is needed). Then, the gaps for all crops are summed to obtain the nutrient supplementation requirement for period t, ensuring the accuracy and operability of the demand indicators and providing clear data for subsequent production strategy optimization.

[0029] In a preferred embodiment, based on the standardized nutrient data and the predicted cultivation requirements, a multi-objective optimization algorithm is used to solve the initial production strategy steps for crop cultivation substrates, specifically including: S31: Extract the nutrient content of several batches of raw materials from the standardized nutrient data. and the substrate requirement in the predicted cultivation needs Nutritional requirements for cultivation ; S32: The decision variable is the amount of raw material of the i-th source type used in the j-th batch of raw materials during planting period t. Based on the set of constraints determined by the total substrate demand and nutrient demand, and the set of optimization objective functions determined by minimizing procurement costs and maximizing nutrient matching, a multi-objective optimization algorithm is used to solve the initial production strategy of crop cultivation substrate.

[0030] Furthermore, the expressions for the set of constraints determining the total substrate demand and nutrient demand, and the set of optimization objective functions determined by minimizing procurement costs and maximizing nutrient matching, are as follows: Constraint set: ; ; In the formula, , Indicates the coefficient for the nutritional balance range; Optimize the objective function set: ; ; In the formula, This represents the transportation cost per unit quantity of raw material from the j-th batch, for the i-th source type. This represents the purchase cost per unit quantity of raw material from the j-th batch, for the ith raw material source type.

[0031] In this embodiment, key parameters are first extracted from the standardized nutrient dataset. The substrate requirement for time period t and the nutrient supplementation requirement for time period t are extracted from the cultivation forecast demand. Simultaneously, raw material procurement and transportation cost data (from supplier quotations) are supplemented to form a complete input dataset for the optimization model. Outlier detection (e.g., values ​​exceeding the normal range for similar raw materials are removed) ensures data reliability. After this, the following steps are taken: The decision variable is the amount of raw material (vinegar residue / silkworm excrement) of batch j of type i used during planting period t. Based on actual production needs, core constraints such as total substrate amount constraint (ensuring the amount meets the standard) and nutrient balance constraint (ensuring nutrient suitability) are constructed. By setting dual objectives: minimizing the total cost of procurement and transportation (controlling economic efficiency) and maximizing the nutrient matching degree (controlling product quality), a multi-objective optimization algorithm is used to solve the model and generate the globally optimal initial production plan. Under the premise of meeting the substrate usage and nutrient requirements, the procurement and transportation costs are precisely controlled.

[0032] Therefore, this invention, based on standardized raw material nutrient data and quantitative cultivation forecasting requirements, uses the amount of raw materials used in each batch at each time period as the core decision variable, constructs a mathematical model that integrates constraints and optimization objectives, and solves it through a multi-objective optimization algorithm to obtain an initial production strategy that balances cost and nutritional suitability.

[0033] Based on this, a multi-objective optimization algorithm is used to solve the initial production strategy steps for crop cultivation substrates, specifically including: S321: The optimization objective function that minimizes procurement costs. As the primary objective function, the optimization objective function is to maximize the nutrient matching degree. As a secondary objective function; S322: Set a threshold for the secondary objective function, and convert the secondary objective function into a constraint condition; wherein the expression of the converted constraint condition is specifically as follows: ; In the formula, This indicates the set nutritional matching threshold. S323: Summarize the transformed constraints with the original constraint set determined by the total matrix requirement and nutrient requirement, and then optimize based on the summarized constraint set and the optimization objective function of minimizing procurement cost as the main objective function. Construct a single-objective optimization model with multiple constraints; S324: Solve the optimization model using a heuristic optimization algorithm to obtain the raw material usage for each batch of each raw material source type at each planting period. The optimal plan is used as the initial production strategy for crop cultivation substrate.

[0034] In this embodiment, the primary objective is to minimize procurement costs, while the secondary objective is to maximize nutrient matching, taking into account the actual needs of agricultural production. The optimization priorities are clearly defined. To avoid the dispersion of solution sets in multi-objective optimization, a minimum acceptable threshold for the secondary objective is set (determined based on crop growth experiments, typically 0.85-0.9, i.e., nutrient matching ≥ 85%-90%). The original objective function is transformed into constraints to ensure that the nutrient suitability of the solution is not lower than the minimum requirement. The transformed nutrient matching constraint is then combined with the original total substrate constraint and nutrient balance constraint to form a complete set of constraints. A single-objective, multi-constraint mathematical model is constructed and solved using the primary objective as the optimization goal.

[0035] Therefore, this invention simplifies the complexity of multi-objective optimization by dividing primary and secondary objectives, converting secondary objectives into constraints, and solving single-objective models. Combined with heuristic algorithms (such as genetic algorithms) for efficient solution, it obtains an initial production strategy that meets production priorities, realizing the engineering-based and efficient solution of multi-objective optimization problems, and minimizing production costs while ensuring the minimum nutritional matching degree.

[0036] In a preferred embodiment, using demand satisfaction and nutritional deviation as the state space, and production volume adjustment and ingredient ratio adjustment as the action space, the steps for establishing a reinforcement learning model based on dynamic deviation penalty specifically include: S41: Construct a reinforcement learning environment with demand satisfaction and nutritional deviation as the state space, production quantity adjustment and ingredient ratio adjustment as the action space, and a reward function based on a weighted negative penalty term; The expressions for the state space and action space are as follows: ; ; ; ; In the formula, Representing the state space, This indicates that the substrate does not meet the requirements. Indicates nutritional imbalance. Represents the action space. This indicates an adjustment in production volume. This indicates an adjustment in the ingredient ratio; Specifically, the expression based on the weighted negative penalty term as the reward function is as follows: ; ; In the formula, This represents the reward value during planting period t. , , Indicates the weight of the penalty item. This represents the total procurement and transportation costs during the planting period t; S42: Construct a state space As input, with action space probability distribution The output Actor network and the state space and action space As input, with state-action value This is the output Critic network, and the Actor-Critic network is initialized. S43: Associate the state space, action space, and reward function in the reinforcement learning environment with the Actor-Critic network, and generate a reinforcement learning model by using the Critic network loss function constructed based on temporal difference error and the Actor network advantage function determined based on the network policy gradient.

[0037] It should be noted that this invention employs an Actor-Critic dual-network architecture, responsible for action generation and value evaluation respectively. The Actor network consists of: a state space... As input, with action space probability distribution The output is a network structure containing an input layer, hidden layers, and a Softmax output layer; the Critic network is a network structure with a state space... and action space As input, with state-action value The output is a network structure containing an input layer, hidden layers, and a Softmax output layer.

[0038] In practical applications, the temporal difference error of the Critic network is used to measure the value prediction bias of the Critic network, and its expression is: , This is the discount factor. The Critic network constructs its loss function during updates. The loss is minimized using gradient descent. The Critic network updates based on the policy gradient method, aiming to maximize the expected reward. The expression for the policy gradient is: ,in, For the advantage function ( (The state value is calculated by the Critic network), and the parameters are updated along the gradient direction.

[0039] In this embodiment, a reinforcement learning model based on the Actor-Critic architecture is constructed to address real-time fluctuations (such as changes in demand and deviations in raw material nutrition) that the initial production strategy cannot handle. The model takes the state feedback (demand deviation and nutrition deviation) in the production process as input and achieves dynamic optimization of the strategy through action adjustments (production volume and ingredient ratio) and reward feedback (cost and deviation penalty).

[0040] Based on this, the process involves iterating the optimal adjustment strategy according to the reward value, optimizing the initial production strategy using the adjustment instructions of the optimal adjustment strategy, and generating a real-time production strategy for crop cultivation substrate. This process specifically includes: S44: Based on the initial production strategy, use the raw material usage for each batch of each raw material source type for each planting period. Determine the initial substrate production quantity and initial ingredient ratio; The expressions for the initial matrix production amount and the initial ingredient ratio are as follows: ; ; In the formula, This indicates the initial substrate production quantity. Indicates the initial ingredient ratio; S45: During each iteration of the planting period, collect the real-time state of the reinforcement learning environment. Real-time status Inputting the Actor network, the Softmax function outputs an action probability distribution, and the current adjustment action is obtained by sampling. ; S46: Adjust the matrix production volume and ingredient ratio according to the adjustment action, and calculate the adjusted raw material consumption based on the adjusted matrix production volume and ingredient ratio; ; ; ; In the formula, This indicates the adjusted raw material usage for each batch under each raw material source type at each planting stage. This indicates the corrected matrix production volume. This indicates the revised ingredient ratio; S47: After executing the correction action, collect the reward value for the planting period t. and the status of the next planting period The parameters of the Critic network are updated using the temporal difference error, and the parameters of the Actor network are updated using the policy gradient. The above iterative process is repeated until the policy converges, and the optimal adjustment policy is output. S48: Output the optimal adjustment strategy as a real-time production strategy for the crop cultivation substrate after optimizing the initial production strategy.

[0041] In this embodiment, the initial raw material usage for each time period is first extracted from the initial production strategy and converted into two core baseline parameters: initial matrix production and initial ingredient ratio. Then, by setting the number of iterations, real-time data is acquired through the production monitoring system in each iteration round to calculate the state vector. , the state vector The trained Actor network is input, and the softmax function is used to transform the network output into an action probability distribution. The current adjustment action is then sampled. Following this, based on the principle of total quantity × proportion, and using the initial parameters as a benchmark, the corrected parameters are calculated in conjunction with the adjustment work to ensure that the corrected usage meets both the total quantity requirement and adapts to the new ingredient ratio; after executing the correction action, the reward value for the current period is collected. Status in the next period Utilizing time-series difference error Update the Critic network parameters using policy gradients. Update Actor network parameters; reward value after 100 consecutive rounds. When the fluctuation range is ≤3%, the decision strategy converges and outputs the optimal adjustment strategy. Finally, based on the optimal adjustment strategy, specific adjustment instructions (production adjustment) are generated for each planting period t. This indicates an adjustment in the ingredient ratio. The dosage is adjusted to obtain the real-time raw material dosage.

[0042] Therefore, this invention uses an initial production strategy as a baseline and achieves closed-loop optimization of state perception, action decision-making, reward feedback, and parameter updates through multiple iterations of a reinforcement learning model. Once the strategy converges, a real-time production strategy is output, completing the dynamic correction of the initial plan. By optimizing the initial production strategy through multi-objective optimization, the scientific allocation and intelligent management of raw materials for multi-source substrate production are achieved. Furthermore, reinforcement learning is used to dynamically optimize the initial production strategy, adapting to the impact of different practical factors on the production strategy. This solves the problems of handling raw material heterogeneity and supply uncertainty, optimizing prediction accuracy and resource utilization efficiency, balancing costs, improving substrate adaptability, and promoting the development of smart agricultural planting and breeding cycles.

[0043] Reference Figure 2 , Figure 2 This is a schematic diagram of the structure of the crop cultivation substrate production management system based on crop-livestock cycle according to an embodiment of the present invention.

[0044] like Figure 2As shown in the embodiments of the present invention, the crop cultivation substrate production management system based on crop-livestock cycle includes: The acquisition module 10 is used to acquire batch supply information of matrix raw materials and generate standardized nutritional data of multi-source raw materials; The receiving module 20 is used to extract the crop planting planning information from the crop planting plan when it receives the crop planting plan for the target crop cultivation area, and to determine the cultivation forecast requirements based on the time series analysis of the substrate requirements and cultivation nutrient requirements for each planting period. The solution module 30 is used to solve the initial production strategy of crop cultivation substrate based on the standardized nutrient data and the cultivation prediction requirements, using a multi-objective optimization algorithm. The optimization module 40 is used to establish a reinforcement learning model based on dynamic deviation penalty with demand satisfaction and nutritional deviation as the state space and production volume adjustment and ingredient ratio adjustment as the action space. It iterates the optimal adjustment strategy based on the reward value, optimizes the initial production strategy using the adjustment instructions of the optimal adjustment strategy, and generates a real-time production strategy for crop cultivation substrate. The execution module 50 is used to perform production management and control of crop cultivation substrate according to the real-time production strategy.

[0045] Other embodiments or specific implementations of the crop cultivation substrate production management system based on crop-livestock cycle of the present invention can be referred to the above-mentioned method embodiments, and will not be repeated here.

[0046] It is understood that in the description of this specification, references to terms such as "one embodiment," "another embodiment," "other embodiments," or "first embodiment to Nth embodiment," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0047] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0048] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for production management of crop cultivation substrate based on crop-livestock cycle, characterized in that, The method includes the following steps: S1: Obtain batch supply information of matrix raw materials and generate standardized nutritional data of multi-source raw materials; S2: Upon receiving the crop planting plan for the target crop cultivation area, extract the crop planting planning information from the crop planting plan, analyze the substrate requirements and cultivation nutrient requirements for each planting period based on time series analysis, and determine the predicted cultivation requirements. S3: Based on the standardized nutrient data and the predicted cultivation requirements, a multi-objective optimization algorithm is used to solve the initial production strategy of the crop cultivation substrate; S4: Using demand satisfaction and nutritional deviation as the state space, and production volume adjustment and ingredient ratio adjustment as the action space, a reinforcement learning model based on dynamic deviation penalty is established. The optimal adjustment strategy is iterated based on the reward value. The adjustment instructions of the optimal adjustment strategy are used to optimize the initial production strategy and generate a real-time production strategy for crop cultivation substrate. S5: Implement production management and control of crop cultivation substrate according to the real-time production strategy.

2. The method for production management of crop cultivation substrate based on crop-livestock cycle as described in claim 1, characterized in that, The steps for obtaining batch supply information of matrix raw materials and generating standardized nutritional data for multi-source raw materials include: S11: Query batch supply information for different matrix raw material sources; wherein, the matrix raw material sources include several vinegar residue sources and several silkworm excrement sources, and the batch supply information includes the supplier's test report for each batch of matrix raw material source; S12: Extract the nutritional parameters of the raw materials from the supplier's test reports for each batch of matrix raw materials, and generate a list containing the nutritional content of several batches of raw materials. Standardized nutritional data; where i represents the type of the i-th raw material source, i=1 is vinegar residue, i=2 is silkworm excrement; j represents the batch of raw material; k represents the content of the k-th nutrient.

3. The method for production management of crop cultivation substrate based on crop-livestock cycle as described in claim 1, characterized in that, Upon receiving the crop planting plan for the target crop cultivation area, the crop planting planning information is extracted from the plan. Based on time series analysis, the substrate requirements and nutrient requirements for each planting period are determined to predict cultivation needs. This process includes: S21: Upon receiving crop planting planning information for the target crop cultivation area, the crop planting planning information is used as a basis; wherein, the crop planting planning information includes the planting area and planting growth period plan for each crop type; S22: Based on the planting area and the planting production period of each crop type at different planting times, analyze the substrate requirements and cultivation nutrient requirements for each planting time period to determine the cultivation forecast requirements.

4. The method for production management of crop cultivation substrate based on crop-livestock cycle as described in claim 3, characterized in that, Based on the planting area and production stage of each crop type at different planting periods, the substrate requirements and nutrient requirements for each planting period are analyzed to determine the steps for predicting cultivation needs, specifically including: S221: Based on the planting area and planting production period of each crop type at different planting times, and according to the nutrient content requirements and soil basic supply of the crop type per unit planting area and at different planting production periods, analyze the substrate requirements and cultivation nutrient requirements for each planting period. The expression for the required matrix quantity is as follows: ； In the formula, This represents the substrate requirement for each planting period t. This represents the planting area of ​​crop type m during planting period t. This represents the nutrient content requirement per unit planting area for crop type m during planting period t. The expression for the cultivation nutrient requirements is as follows: ； In the formula, This represents the cultivation nutrient requirements for nutrient index k at each planting period t. This represents the nutrient requirement k per unit planting area for crop type m during planting period t. This represents the basic supply of soil to nutrient index k per unit planting area for crop type m during planting period t. S222: Determine the predicted cultivation requirements of the target crop cultivation area based on the substrate requirements and cultivation nutrient requirements of the target crop cultivation area at each planting period.

5. The method for production management of crop cultivation substrate based on crop-livestock cycle as described in claim 1, characterized in that, Based on the standardized nutrient data and the predicted cultivation requirements, a multi-objective optimization algorithm is used to solve for the initial production strategy steps of the crop cultivation substrate, specifically including: S31: Extract the nutrient content of several batches of raw materials from the standardized nutrient data. and the substrate requirement in the predicted cultivation needs Nutritional requirements for cultivation ; S32: The decision variable is the amount of raw material of the i-th source type used in the j-th batch of raw materials during planting period t. Based on the set of constraints determined by the total substrate demand and nutrient demand, and the set of optimization objective functions determined by minimizing procurement costs and maximizing nutrient matching, a multi-objective optimization algorithm is used to solve the initial production strategy of crop cultivation substrate.

6. The method for production management of crop cultivation substrate based on crop-livestock cycle as described in claim 5, characterized in that, The expressions for the set of constraints determining the total substrate demand and nutrient demand, and the set of optimization objective functions determined by minimizing procurement costs and maximizing nutrient matching, are as follows: Constraint set: ； ； In the formula, , Indicates the coefficient for the nutritional balance range; Optimize the objective function set: ； ； In the formula, This represents the transportation cost per unit quantity of raw material from the j-th batch, for the i-th source type. This represents the purchase cost per unit quantity of raw material from the j-th batch, for the ith raw material source type.

7. The method for production management of crop cultivation substrate based on crop-livestock cycle as described in claim 6, characterized in that, A multi-objective optimization algorithm is used to solve the initial production strategy steps for crop cultivation substrates, specifically including: S321: The optimization objective function that minimizes procurement costs. As the primary objective function, the optimization objective function is to maximize the nutrient matching degree. As a secondary objective function; S322: Set a threshold for the secondary objective function, and convert the secondary objective function into a constraint condition; wherein the expression of the converted constraint condition is as follows: ； In the formula, This indicates the set nutritional matching threshold. S323: Summarize the transformed constraints with the original constraint set determined by the total matrix requirement and nutrient requirement, and then optimize based on the summarized constraint set and the optimization objective function of minimizing procurement cost as the main objective function. Construct a single-objective optimization model with multiple constraints; S324: Solve the optimization model using a heuristic optimization algorithm to obtain the raw material usage for each batch of each raw material source type at each planting period. The optimal plan is used as the initial production strategy for crop cultivation substrate.

8. The method for production management of crop cultivation substrate based on crop-livestock cycle as described in claim 1, characterized in that, Using demand satisfaction and nutritional deviation as the state space, and production quantity adjustment and ingredient ratio adjustment as the action space, the steps for establishing a reinforcement learning model based on dynamic deviation penalty include: S41: Construct a reinforcement learning environment with demand satisfaction and nutritional deviation as the state space, production quantity adjustment and ingredient ratio adjustment as the action space, and a reward function based on a weighted negative penalty term; The expressions for the state space and action space are as follows: ； ； ； ； In the formula, Representing the state space, This indicates that the substrate does not meet the requirements. Indicates nutritional imbalance. Represents the action space, This indicates an adjustment in production volume. This indicates an adjustment in the ingredient ratio; Specifically, the expression based on the weighted negative penalty term as the reward function is as follows: ； ； In the formula, This represents the reward value during planting period t. , , Indicates the weight of the penalty item. This represents the total procurement and transportation costs during the planting period t; S42: Construct a state space As input, with action space probability distribution The output Actor network and the state space and action space As input, with state-action value This is the output Critic network, and the Actor-Critic network is initialized. S43: Associate the state space, action space, and reward function in the reinforcement learning environment with the Actor-Critic network, and generate a reinforcement learning model by using the Critic network loss function constructed based on temporal difference error and the Actor network advantage function determined based on the network policy gradient.

9. The method for production management of crop cultivation substrate based on crop-livestock cycle as described in claim 8, characterized in that, The steps of iteratively adjusting the optimal strategy based on reward values, optimizing the initial production strategy using the adjustment instructions of the optimal adjustment strategy, and generating a real-time production strategy for crop cultivation substrate specifically include: S44: Based on the initial production strategy, use the raw material usage for each batch of each raw material source type for each planting period. Determine the initial substrate production quantity and initial ingredient ratio; The expressions for the initial matrix production amount and the initial ingredient ratio are as follows: ； ； In the formula, This indicates the initial substrate production quantity. Indicates the initial ingredient ratio; S45: During each iteration of the planting period, collect the real-time state of the reinforcement learning environment. Real-time status Inputting the Actor network, the Softmax function outputs an action probability distribution, and the current adjustment action is obtained by sampling. ; S46: Adjust the matrix production volume and ingredient ratio according to the adjustment action, and calculate the adjusted raw material consumption based on the adjusted matrix production volume and ingredient ratio; ； ； ； In the formula, This indicates the adjusted raw material usage for each batch under each raw material source type at each planting stage. This indicates the corrected matrix production volume. This indicates the revised ingredient ratio; S47: After executing the correction action, collect the reward value for the planting period t. and the status of the next planting period The parameters of the Critic network are updated using the temporal difference error, and the parameters of the Actor network are updated using the policy gradient. The above iterative process is repeated until the policy converges, and the optimal adjustment policy is output. S48: Output the optimal adjustment strategy as a real-time production strategy for the crop cultivation substrate after optimizing the initial production strategy.

10. A crop cultivation substrate production management system based on crop-livestock cycle, characterized in that, The system includes: The acquisition module is used to acquire batch supply information of matrix raw materials and generate standardized nutritional data of multi-source raw materials; The receiving module is used to extract the crop planting planning information from the crop planting plan when it receives the crop planting plan for the target crop cultivation area, and to determine the cultivation forecast requirements based on the time series analysis of the substrate requirements and cultivation nutrient requirements for each planting period. The solution module is used to solve the initial production strategy of crop cultivation substrate based on the standardized nutrient data and the predicted cultivation requirements, using a multi-objective optimization algorithm. The optimization module is used to establish a reinforcement learning model based on dynamic deviation penalty, with demand satisfaction and nutritional deviation as the state space and production volume adjustment and ingredient ratio adjustment as the action space. It iterates the optimal adjustment strategy based on the reward value, optimizes the initial production strategy using the adjustment instructions of the optimal adjustment strategy, and generates a real-time production strategy for crop cultivation substrate. The execution module is used to perform production management and control of crop cultivation substrate according to the real-time production strategy.

Images