A vegetable greenhouse environment management method, system, storage medium and program product

Abstract

A vegetable greenhouse environmental management method, system, storage medium and program product. In the method, historical environmental parameters of the vegetable greenhouse, vegetable growth data and the current growth status of the vegetables in the vegetable greenhouse are obtained; a multi-stable growth model is established based on the historical environmental parameters and the vegetable growth data, the multi-stable growth model including a plurality of stable growth points; the growth state is located in the multi-stable growth model, and the dominant stable growth point closest to the growth state is determined; an attractor potential field is established, the dominant stable growth point is set as the attractor center, and the potential energy gradient from the growth state to the attractor center is calculated; a progressive control path of the vegetable greenhouse environmental parameters is constructed based on the potential energy gradient, and a staged environmental control instruction is generated; the staged environmental control instruction is sent to an environmental control device, so that the environmental control device performs environmental adjustment according to the progressive control path based on the staged environmental control instruction, thereby improving the timeliness and accuracy of agricultural operations and environmental adjustment.

Description

Technical Field

[0001] This application belongs to the field of agricultural Internet services, and in particular relates to a vegetable greenhouse environment management method, system, storage medium and program product. Background Art

[0002] With the development of modern agricultural technology, greenhouse vegetable production has become an important way to ensure vegetable supply and improve vegetable quality. However, traditional greenhouse management relies primarily on manual experience and lacks real-time monitoring and scientific regulation of vegetable growth and the greenhouse environment, making it difficult to further improve vegetable yield and quality.

[0003] In order to solve the above problems, relevant technologies can obtain vegetable images and environmental information of facility greenhouses through inspection robots, and then obtain the growth physiological information of vegetables based on the vegetable images. The growth physiological information and environmental information are input into the health scoring model to score the current growth status of the vegetables and the facility greenhouse environment. Based on the scoring results, agricultural operations are performed on the vegetables and the facility greenhouse environment is adjusted.

[0004] However, this health scoring model only considers the static characteristics of vegetable growth and the instantaneous state of the greenhouse environment, ignoring the dynamic change trends during vegetable growth and the cumulative effects of environmental factors. This may lead to deviations between the scoring results and the actual growth status of vegetables and long-term environmental impacts, thereby reducing the timeliness and accuracy of agricultural operations and environmental adjustments. Summary of the Invention

[0005] The present application provides a vegetable greenhouse environmental management method, system, storage medium and program product for improving the timeliness and accuracy of agricultural operations and environmental adjustments.

[0006] In a first aspect, the present application provides a vegetable greenhouse environmental management method, which obtains historical environmental parameters of the vegetable greenhouse, vegetable growth data, and the current growth status of vegetables in the vegetable greenhouse. The historical environmental parameters include temperature, humidity, light intensity, and carbon dioxide concentration. The vegetable growth data includes plant height, leaf area, stem diameter, and yield.

[0007] A multi-stable growth model is established based on historical environmental parameters and vegetable growth data. The multi-stable growth model includes several stable growth points, each of which corresponds to a set of environmental parameter combinations.

[0008] Locate the growth state in a multi-stable growth model and determine the dominant stable growth point closest to the growth state;

[0009] Establish an attractor potential field, set the dominant stable growth point as the attractor center, and calculate the potential energy gradient from the growth state to the attractor center;

[0010] Based on the potential energy gradient, a gradual control path for the environmental parameters of the vegetable greenhouse is constructed, and phased environmental control instructions are generated;

[0011] The phased environmental control instructions are sent to the environmental control device, so that the environmental control device adjusts the environment according to the phased environmental control instructions along a progressive control path.

[0012] By adopting the above technical solution, a growth model that can reflect the multi-stable characteristics of vegetable growth is established. The multi-stable growth model includes several stable growth points, each of which corresponds to a set of optimal environmental parameter combinations. By locating the current growth state in the multi-stable growth model, determining the dominant stable growth point closest to the current growth state, establishing an attractor potential field centered on the dominant stable growth point, and calculating the potential energy gradient required to reach the dominant stable growth point from the current growth state, a gradual control path from the current growth state to the dominant stable growth point can be obtained. Based on the gradual control path, a phased environmental control instruction is generated and sent to the environmental control device, so that the environmental control device can perform phased adjustments to the vegetable greenhouse environment according to the gradual control path, guiding the vegetable growth state to move closer to the optimal environmental parameter combination corresponding to the dominant stable growth point, thereby improving the timeliness and accuracy of agricultural operations and environmental adjustments.

[0013] In conjunction with some embodiments of the first aspect, in some embodiments, establishing a multi-stable growth model based on historical environmental parameters and growth data specifically includes:

[0014] The historical environmental parameters and vegetable growth data were segmented into time series to obtain the key stages of vegetable growth;

[0015] Constructing a phase space, and generating environmental parameter trajectories and vegetable growth trajectories in the phase space that correspond one-to-one with historical environmental parameters and vegetable growth data;

[0016] The stable growth point is determined based on the environmental parameter trajectory and the vegetable growth trajectory. The stable growth point is the convergence point where the Lyapunov index is negative. The convergence point is the intersection of the environmental parameter trajectory and the vegetable growth trajectory.

[0017] Determine the attraction domain range and attraction strength of each stable growth point;

[0018] Calculate the comprehensive advantage coefficient of each stable growth point;

[0019] The stable growth point, attraction domain range, attraction intensity and comprehensive advantage coefficient are integrated to obtain a multi-stable growth model.

[0020] By employing the above technical solution, historical environmental parameter and vegetable growth data are segmented into time series to identify key stages of vegetable growth. Environmental parameter trajectories and vegetable growth trajectories are generated in phase space, and the intersection of the two trajectories is defined as a stable growth point. Stable growth points are identified based on the Lyapunov exponent. Only points around which the trajectory converges are considered stable growth points, enhancing the scientific nature and reliability of the stable growth points. After determining the stable growth points, the attraction domain, attraction strength, and comprehensive advantage coefficient of each stable growth point are calculated and integrated into a multi-stable growth model. This allows the model to more comprehensively and accurately reflect the multi-stable characteristics and dynamic changes of vegetable growth.

[0021] In conjunction with some embodiments of the first aspect, in some embodiments, establishing an attractor potential field specifically includes:

[0022] A local potential field function is constructed with each stable growth point as the potential field center. The potential field intensity in the local potential field function decays exponentially with the distance from the potential field center, and the decay coefficient is determined by the stability of the stable growth point.

[0023] Set the weight coefficient according to the advantage coefficient of each stable growth point;

[0024] All local potential fields are weightedly superimposed according to the weight coefficient to obtain the attractor potential field.

[0025] By employing this technical solution, a local potential field function is constructed with each stable growth point as the potential field center. The potential field strength in this local potential field function decays exponentially with distance from the potential field center, with the decay coefficient determined by the stability of the stable growth point. This exponential decay of potential field strength with distance reduces the impact on points farther from the stable point, making environmental control more precise within the local space. This achieves smooth and continuous environmental control, minimizing the impact of sudden changes in environmental parameters on vegetable growth.

[0026] In conjunction with some embodiments of the first aspect, in some embodiments, after establishing the multi-stable growth model based on historical environmental parameters and vegetable growth data, the method further includes:

[0027] Based on historical environmental parameters and vegetable growth data, the entropy value of the environmental parameter set and the entropy value of the vegetable growth state set at each growth stage are calculated;

[0028] Calculate the mutual information between the entropy value of the environmental parameter set and the entropy value of the vegetable growth state set to obtain the correlation strength between the environmental parameters and the vegetable growth state within the growth stage;

[0029] The weight coefficients of environmental parameter regulation in each growth stage were determined based on the correlation strength, and the weight coefficients were introduced into the multi-stable growth model.

[0030] By adopting the above technical solution, mutual information is a metric that can measure the correlation between two random variables. It reduces the uncertainty of the random variables themselves and more accurately reflects the degree of correlation between them. Determining the weight coefficients for environmental parameter regulation at each growth stage based on the strength of the correlation and introducing the weight coefficients into the multistable growth model allows the model to adapt to the dynamic changes in the importance of environmental parameters in different growth stages. When regulating environmental parameters, higher weights are assigned to key parameters to highlight their influence, while non-key parameters are correspondingly reduced to avoid over-regulation, thereby achieving stage-by-stage differentiation of environmental regulation and further improving the accuracy and effectiveness of environmental regulation.

[0031] In conjunction with some embodiments of the first aspect, in some embodiments, calculating the entropy value of the environmental parameter set and the entropy value of the vegetable growth state set at each growth stage specifically includes:

[0032] Calculate the probability distribution function of the environmental parameter set and the vegetable growth state set;

[0033] Substitute the probability distribution function into the preset entropy formula to calculate the entropy value of the environmental parameter set and the vegetable growth state set in each growth stage.

[0034] By employing the above technical solution, the probability distribution functions of the environmental parameter set and the vegetable growth state set are calculated. Substituting the probability distribution functions into a preset entropy formula allows for a quantitative assessment of the uncertainty of these parameters and vegetable growth states within each growth stage. A larger entropy value indicates a higher degree of disorder within the set, a more dispersed distribution of elements, and a higher degree of uncertainty. Conversely, a smaller entropy value indicates a higher degree of order within the set, a more concentrated distribution of elements, and a lower degree of uncertainty. Entropy analysis can reveal the changing characteristics of environmental parameters and vegetable growth states within different growth stages and identify the stage with the highest uncertainty, which is crucial for targeted environmental parameter regulation. Comparing the entropy values ​​of the environmental parameter set with those of the vegetable growth state set reveals the difference in uncertainty between the two and, therefore, infers the impact of environmental parameter changes on the stability of vegetable growth states.

[0035] In conjunction with some embodiments of the first aspect, in some embodiments, after determining the weight coefficients for regulating the environmental parameters of each growth stage based on the correlation strength, the method further includes:

[0036] Taking environmental factors as control variables and vegetable growth state parameters as state variables, a state feedback equation for environmental parameter regulation is established;

[0037] The optimal controller is designed based on the weight coefficient to minimize the deviation of vegetable growth status while satisfying the environmental parameter constraints in each growth stage.

[0038] Solve the state feedback equation to obtain the optimal control value of each environmental parameter;

[0039] Generate a multi-stage environmental control strategy based on the optimal control quantity.

[0040] By adopting the above technical solution and introducing state feedback, it is possible to obtain real-time information on changes in vegetable growth state parameters and establish a direct mathematical relationship between this information and the control values ​​of environmental parameters. This allows environmental control to be dynamically adjusted based on the immediate feedback of vegetable growth status, thereby improving the adaptability and effectiveness of environmental control. Based on the state feedback equation, an optimal controller is designed in combination with the weight coefficients of environmental parameter control at each growth stage. By solving the state feedback equation, the optimal control values ​​for each environmental parameter can be obtained, thereby generating a multi-stage environmental control strategy. By constructing a closed-loop optimization of environmental parameters and vegetable growth status through state feedback, the relationship between the two is dynamically balanced to seek the optimal effect of environmental control, which is more in line with the objective laws of vegetable growth and has a positive effect on improving vegetable yield and quality.

[0041] In conjunction with some embodiments of the first aspect, in some embodiments, solving the state feedback equation to obtain the optimal control value of each environmental parameter specifically includes:

[0042] Convert the state feedback equation into the objective function of a convex optimization problem;

[0043] According to the variation range of environmental parameters in each growth stage, the boundary constraints of decision variables are set;

[0044] Introducing boundary constraints into the objective function, we obtain the Lagrangian function;

[0045] Derivative the Lagrangian function and transform it into an unconstrained optimization problem;

[0046] The gradient descent algorithm is used to search for the optimal solution of the unconstrained optimization problem and obtain the optimal control value of each environmental parameter.

[0047] By adopting the above technical solution, the state feedback equation is transformed into the objective function of a convex optimization problem. Boundary constraints on the decision variables are set based on the range of variation of the environmental parameters within each growth stage. The boundary constraints are then introduced into the objective function to obtain a Lagrangian function. By differentiating the Lagrangian function, the original constrained optimization problem can be transformed into an equivalent unconstrained optimization problem. Based on the unconstrained optimization problem, a gradient descent algorithm is used to perform an iterative search to find the optimal solution to the objective function, namely the optimal control variable of the environmental parameter. Converting the complex state feedback equation problem into a convex and unconstrained optimization problem allows the use of existing mature algorithms such as the Lagrange multiplier method and gradient descent method, improving solution efficiency and accuracy while reducing computational complexity. The introduction of boundary constraints ensures that the optimal control variable of the environmental parameter always lies within a reasonable range of variation at each growth stage, avoiding over- or under-control of the environmental parameter and improving the feasibility and safety of the environmental control scheme.

[0048] In the second aspect, an embodiment of the present application provides a vegetable greenhouse environmental management system, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and one or more processors call the computer instructions to enable the system to execute the method described in the first aspect and any possible implementation method of the first aspect.

[0049] In a third aspect, an embodiment of the present application provides a computer-readable storage medium comprising instructions, which, when executed on a system, enables the system to execute the method described in the first aspect and any possible implementation of the first aspect.

[0050] In a fourth aspect, an embodiment of the present application provides a computer program product, characterized in that when the computer program product is run on a system, the system executes the method described in any possible implementation manner in the first aspect.

[0051] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0052] 1. The present application provides a method for managing the environment of a vegetable greenhouse, and establishes a growth model that can reflect the multi-stable characteristics of the vegetable growth process. The multi-stable growth model includes several stable growth points, and each stable growth point corresponds to a set of optimal environmental parameter combinations. By locating the current growth state in the multi-stable growth model, determining the dominant stable growth point closest to the current growth state, establishing an attractor potential field centered on the dominant stable growth point, and calculating the potential energy gradient required to reach the dominant stable growth point from the current growth state, a progressive control path from the current growth state to the dominant stable growth point can be obtained. Based on the progressive control path, a phased environmental control instruction is generated, and the instruction is sent to the environmental control device, so that the environmental control device can perform phased adjustments to the vegetable greenhouse environment according to the progressive control path, guiding the vegetable growth state to move closer to the optimal environmental parameter combination corresponding to the dominant stable growth point, thereby improving the timeliness and accuracy of agricultural operations and environmental adjustments.

[0053] 2. The present application provides a method for managing the environment of a vegetable greenhouse. Mutual information is an indicator that can measure the correlation between two random variables. It reduces the uncertainty influence of the random variables themselves and more accurately reflects the degree of correlation between them. Based on the correlation strength, the weight coefficients for regulating the environmental parameters at each growth stage are determined, and the weight coefficients are introduced into the multi-stable growth model. This allows the model to adapt to the dynamic changes in the importance of environmental parameters in different growth stages. When regulating the environmental parameters, higher weights are given to key parameters to highlight their influence, while the weights of non-key parameters are reduced accordingly to avoid excessive regulation, thereby achieving stage-by-stage differentiation of environmental regulation and further improving the accuracy and effectiveness of environmental regulation.

[0054] 3. The present application provides a method for managing the environment of a vegetable greenhouse, which converts the state feedback equation into the objective function of a convex optimization problem, sets the boundary constraints of the decision variables according to the range of variation of the environmental parameters in each growth stage, and then introduces the boundary constraints into the objective function to obtain the Lagrangian function. By deriving the Lagrangian function, the original constrained optimization problem can be converted into an equivalent unconstrained optimization problem. On the basis of the unconstrained optimization problem, the gradient descent algorithm is used for iterative search to find the optimal solution of the objective function, that is, the optimal control amount of the environmental parameters. By converting the complex state feedback equation solution problem into a convex optimization and unconstrained optimization problem, existing mature algorithms such as the Lagrange multiplier method and the gradient descent method can be used to improve the solution efficiency and accuracy and reduce the computational complexity. The introduction of boundary constraints can ensure that the optimal control amount of the environmental parameters is always within the reasonable variation range of each growth stage, avoid over-control or under-control of the environmental parameters, and improve the feasibility and safety of the environmental control scheme. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is a flow chart of a vegetable greenhouse environment management method in an embodiment of the present application.

[0056] Figure 2 This is another flow chart of a vegetable greenhouse environment management method in an embodiment of the present application.

[0057] Figure 3 This is a schematic diagram of the physical device structure of a vegetable greenhouse environmental management system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0058] The terms used in the following examples of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification and appended claims of this application, the singular expressions "a," "an," "said," "above," "the," and "this" are intended to include plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in this application refers to any or all possible combinations comprising one or more of the listed items.

[0059] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to imply or suggest relative importance or implicitly indicate the number of the technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of this application, unless otherwise specified, "plurality" means two or more.

[0060] The following uses an embodiment and combines Figure 1 , a vegetable greenhouse environment management method in an embodiment of the present application is described:

[0061] See also Figure 1 , which is a flow chart of a vegetable greenhouse environment management method in an embodiment of the present application.

[0062] S101, obtaining historical environmental parameters of the vegetable greenhouse, vegetable growth data, and the current growth status of the vegetables in the vegetable greenhouse;

[0063] The system obtains the historical environmental parameters of the vegetable greenhouse, vegetable growth data and the growth status of vegetables in the vegetable greenhouse at the current moment. The historical environmental parameters include temperature, humidity, light intensity and carbon dioxide concentration. The vegetable growth data includes plant height, leaf area, stem diameter and yield.

[0064] In this step, the system first needs to obtain various historical data of the vegetable greenhouse and the current vegetable growth status data. Among them, historical environmental parameters include key environmental factors that can affect vegetable growth, such as temperature, humidity, light intensity and carbon dioxide concentration. These parameters can be obtained by deploying various sensors in the greenhouse and continuously collecting them to form a complete historical environmental parameter data set. Vegetable growth data includes various indicators related to vegetable growth and development, such as plant height, leaf area, stem diameter and yield. These data can be obtained through manual measurement or image recognition and other technical means. In addition, the system also needs to obtain the real-time growth status of vegetables in the vegetable greenhouse at the current moment as an important basis for subsequent environmental regulation.

[0065] During the acquisition process, the system can perform necessary preprocessing on the raw data, such as denoising, smoothing, and interpolation, to improve data quality. Furthermore, the system can aggregate and compile statistics based on the data at regular intervals, generating data metrics at different time scales, such as daily, weekly, and monthly averages, to facilitate subsequent analysis. Furthermore, given the potential time lag between environmental parameters and vegetable growth status, the system can also obtain environmental parameter data from a recent period of time, alongside the current vegetable growth status, to comprehensively assess the impact of environmental conditions on vegetable growth.

[0066] S102, establishing a multi-stable growth model based on historical environmental parameters and vegetable growth data;

[0067] A multi-stable growth model is established based on historical environmental parameters and vegetable growth data. The multi-stable growth model includes several stable growth points, each of which corresponds to a set of environmental parameter combinations. Specifically: A multi-stable growth model is established based on historical environmental parameters and growth data, specifically including:

[0068] The historical environmental parameters and vegetable growth data were segmented into time series to obtain the key stages of vegetable growth;

[0069] Constructing a phase space, and generating environmental parameter trajectories and vegetable growth trajectories in the phase space that correspond one-to-one with historical environmental parameters and vegetable growth data;

[0070] The stable growth point is determined based on the environmental parameter trajectory and the vegetable growth trajectory. The stable growth point is the convergence point where the Lyapunov index is negative. The convergence point is the intersection of the environmental parameter trajectory and the vegetable growth trajectory.

[0071] Determine the attraction domain range and attraction strength of each stable growth point;

[0072] Calculate the comprehensive advantage coefficient of each stable growth point;

[0073] The stable growth point, attraction domain range, attraction intensity and comprehensive advantage coefficient are integrated to obtain a multi-stable growth model.

[0074] The core of this step is to use the acquired historical data to construct a multi-stable growth model that can reflect the growth patterns of vegetables. The so-called multi-stable state refers to the fact that under different combinations of environmental parameters, vegetable growth may exhibit several relatively stable states, each of which corresponds to a specific set of environmental conditions and growth indicators. These stable states are called stable growth points and represent the ideal equilibrium state during vegetable growth. The establishment of a multi-stable growth model can help the system fully understand the dynamic characteristics of the vegetable growth process and grasp the corresponding relationship between environmental conditions and growth states during the growth process.

[0075] During the modeling process, the system first segments historical environmental parameters and vegetable growth data into time series to identify key stages of vegetable growth. The system then generates environmental parameter trajectories and vegetable growth trajectories in a high-dimensional phase space that correspond one-to-one with the historical data, describing the evolution of environmental conditions and growth status over time. By analyzing the environmental parameter trajectories and vegetable growth trajectories, the system can identify and extract stable growth points. These stable points have negative Lyapunov exponents, indicating that under the corresponding environmental conditions, vegetable growth can remain stable over the long term. After identifying stable growth points, the system further determines the attraction domain and strength of each stable point, assessing the ease with which vegetable growth can remain stable when environmental conditions near the stable point are disturbed. Furthermore, the system can calculate the comprehensive advantage coefficient for each stable growth point, measuring the advantages and disadvantages of different stable points.

[0076] Finally, the system integrates factors such as stable growth points, attraction domain range, attraction intensity, and comprehensive advantage coefficient to form a complete multi-stable growth model. This model can comprehensively characterize the multi-stable characteristics of vegetable growth, revealing the inherent laws of vegetable growth under different environmental conditions, and providing a theoretical basis and decision-making basis for intelligent environmental control.

[0077] S103, locating the growth state in the multi-stable growth model, and determining the dominant stable growth point closest to the growth state;

[0078] After establishing the multistable growth model, this step requires locating the current vegetable growth state within the model and searching for the stable growth point closest to the current state. Because the multistable growth model describes the topological structure of the state space during vegetable growth and includes several dispersed stable growth points, the system can map the current vegetable growth state to a specific location in the state space. The system then evaluates the proximity between the current growth state and each stable point, identifying the closest stable point or points by calculating the distance or similarity metric between two points in the state space.

[0079] After determining the nearest stable point, the system needs to further determine whether it is a dominant stable point. A dominant stable point is the one with the highest overall advantage coefficient among all stable points, representing the ideal target state for vegetable growth under current environmental conditions. By comparing the overall advantage coefficients of different stable points, the system can select the dominant stable point from the nearest stable points as a reference target for subsequent environmental control.

[0080] It's important to note that because vegetable growth states are dynamic, the system needs to continuously track and update the position of the current state within the multistable growth model based on real-time data, adjusting the selection of the dominant stable growth point accordingly. Furthermore, given the continuous nature of vegetable growth, the transition between the current state and the dominant stable point typically requires a gradual process. Therefore, after determining the dominant stable point, the system also needs to plan a gradual trajectory from the current state to the dominant stable point and formulate phased environmental control strategies accordingly.

[0081] S104, establishing an attractor potential field, setting the dominant stable growth point as the attractor center, and calculating the potential energy gradient from the growth state to the attractor center;

[0082] The system establishes an attractor potential field, sets the dominant stable growth point as the attractor center, and calculates the potential energy gradient from the growth state to the attractor center. The steps for establishing the attractor potential field are as follows: A local potential field function is constructed with each stable growth point as the potential field center. The potential field strength in the local potential field function decays exponentially with the distance from the potential field center, and the decay coefficient is determined by the stability of the stable growth point;

[0083] Set the weight coefficient according to the advantage coefficient of each stable growth point;

[0084] All local potential fields are weightedly superimposed according to the weight coefficient to obtain the attractor potential field.

[0085] After identifying the dominant stable growth point, this step requires constructing an attractor potential field in the state space, with the dominant stable point as the attractor center. The so-called attractor potential field is a dynamic model that describes the evolutionary trend of the system state. It defines the potential energy level at each point in space and gives the direction and speed of movement of the state point under the influence of the potential energy gradient. By introducing the attractor potential field, the system can quantitatively describe the interaction and evolutionary relationship between the current vegetable growth state and the dominant stable point, and accordingly plan a specific path for environmental regulation.

[0086] When constructing an attractor potential field, the system first constructs a local potential field function with each stable growth point as the center of the potential field. Within a local potential field, the potential field strength decays exponentially with distance from the center, with the decay coefficient determined by the stability of the stable growth point. The more stable a stable point is, the smaller its decay coefficient is, meaning it has a wider range of attraction and a greater influence on surrounding state points. Next, the system assigns different weight coefficients based on the dominance coefficient of each stable growth point. Stable points with higher dominance coefficients receive larger weight coefficients, making them more dominant in the attractor potential field. Finally, the system performs a weighted superposition of all local potential fields according to the weight coefficients to form a complete attractor potential field.

[0087] After establishing the attractor potential field, the system needs to calculate the potential energy gradient from the current vegetable growth state to the attractor center (i.e., the dominant stable point). The potential energy gradient characterizes the direction and magnitude of the force acting on the state point in the potential field, and it determines the trend and rate of evolution of the state point. By solving the potential energy gradient, the system can derive the equation of motion for the current growth state in the attractor potential field and predict its future evolution trajectory. The potential energy gradient also provides important guidance for environmental control. By applying environmental control forces in the same direction as the potential energy gradient, the system can guide the vegetable growth state to evolve toward the ideal region where the dominant stable point is located, thereby achieving the goal of intelligent environmental control.

[0088] Because the attractor potential field is defined in state space, the potential gradient is typically a high-dimensional vector. To facilitate its use in practical environmental control, the system can perform dimensionality reduction on the potential gradient, extracting components corresponding to various environmental parameters and forming a multi-parameter coordinated control strategy. Furthermore, the system can dynamically adjust the intensity of environmental control based on the magnitude of the potential gradient, reducing the intensity of control when the state point approaches the attractor center and increasing it appropriately when the state point deviates from the attractor center, thereby achieving more flexible and adaptive environmental control.

[0089] S105, constructing a gradual control path for the environmental parameters of the vegetable greenhouse based on the potential energy gradient, and generating phased environmental control instructions;

[0090] After calculating the potential energy gradient, this step requires constructing a progressive control path for the environmental parameters of the vegetable greenhouse based on the potential energy gradient and generating corresponding phased environmental control instructions. The so-called progressive control path refers to a continuous evolutionary trajectory from the current growth state to the dominant stable point in the state space. This trajectory represents the process by which the vegetable growth state gradually approaches the ideal growth state under the control of the external environment. Since vegetable growth is a gradual and dynamic process, environmental control also needs to be carried out in stages and steps. Therefore, constructing a progressive control path is crucial to achieving intelligent environmental control.

[0091] When constructing a progressive control path, the system needs to fully utilize the information provided by the potential energy gradient. Because the potential energy gradient indicates the direction and magnitude of the force acting on the state point, the system can use it as the basic basis for environmental control. The system can coordinately control various environmental parameters along the direction of the potential energy gradient, allowing the state point to continuously move closer to the dominant stable point. At the same time, because the magnitude of the potential energy gradient reflects the distance between the state point and the dominant stable point, the system can also dynamically adjust the step size and intensity of environmental control based on the magnitude of the gradient. When the gradient is large, it means that there is still a large gap between the state point and the dominant stable point, so the system can adopt a larger range of environmental control; when the gradient is small, it means that the state point is close to the dominant stable point, so the system can reduce the control range and perform more precise adjustments.

[0092] Based on the progressive control path, the system also needs to generate corresponding phased environmental control instructions. These instructions clearly stipulate the specific set values ​​and adjustment strategies for each environmental parameter in different control stages to ensure that environmental conditions can accurately evolve along the progressive control path. When generating control instructions, the system can comprehensively consider factors such as the coupling relationship between environmental parameters, control costs, energy consumption, etc., and use multi-objective optimization methods to find the optimal control solution that can save energy and increase efficiency while meeting the control needs. In addition, since vegetable growth has a certain lag in responding to environmental conditions, the system also needs to consider the delayed characteristics of the control effect when formulating control instructions, and improve the control accuracy and stability through technologies such as predictive control.

[0093] It's important to note that the progressive control path and phased control instructions are not static; instead, they need to be dynamically adjusted based on real-time feedback from the vegetable's growth status. On the one hand, due to random fluctuations in environmental conditions and vegetable growth itself, the potential energy gradient and the location of the dominant stable point may also change. Therefore, the system needs to promptly update the progressive control path to adapt to the new environmental conditions. On the other hand, during the control process, due to factors such as modeling errors and control delays, the vegetable growth state may deviate from the expected trajectory. Therefore, the system also needs to introduce a feedback correction mechanism to adjust the control instructions in real time based on state deviations to ensure the robustness and effectiveness of the control process.

[0094] S106: Send the phased environmental control instruction to the environmental control device, so that the environmental control device adjusts the environment according to the phased environmental control instruction and the progressive control path.

[0095] After generating the phased environmental control instructions, this step requires sending the instructions to the various environmental control devices in the vegetable greenhouse. Based on the received instructions, the control devices adjust the greenhouse environment accordingly, allowing the environmental parameters to evolve according to the gradual control path. To achieve precise control, the system first needs to establish a reliable communication link with the environmental control devices to ensure that the instructions can be transmitted to each device in a timely and accurate manner. This can be achieved through wired or wireless communication networks, such as CAN bus, ZigBee, LoRa, etc. At the same time, to improve communication efficiency and reliability, the system can adopt various measures, such as data compression, error correction, multipath transmission, etc., to reduce delays and errors during the communication process.

[0096] Once the communication link is established, the system can send phased environmental control commands to the environmental control device in batches, according to predetermined time intervals or trigger conditions. Each command should include clear parameter setpoints, execution time, duration, and other information to enable precise control by the device. After the command is sent, the system also needs to monitor and manage the device's execution status. By receiving status data returned by the device, the system can understand the progress and effectiveness of the command execution and ensure the smooth progress of the control process. If any anomalies or deviations in device execution are detected, the system can intervene promptly to perform remote diagnosis or adjust the command to ensure the continuity and consistency of environmental regulation.

[0097] After receiving control instructions, environmental control devices must work together to adjust environmental parameters according to the instructions. This requires a high degree of collaboration and interoperability between devices, enabling them to autonomously divide responsibilities, coordinate, and cooperate according to a unified control strategy. For example, when adjusting temperature, ventilation, refrigeration, and heating equipment must work closely together, dynamically adjusting their operating status and output power based on temperature fluctuations to achieve the target temperature. When adjusting humidity, humidifiers and dehumidifiers must complement each other, alternating between turning on and off according to the changing humidity trend to maintain a constant humidity level. When adjusting light, the lighting control system must work in conjunction with the shading system to dynamically adjust the light intensity and photoperiod based on the light requirements of plant growth, creating a suitable light environment.

[0098] In the above embodiment, a growth model that can reflect the multi-stable characteristics of the vegetable growth process is established. The multi-stable growth model includes a number of stable growth points, each of which corresponds to a set of optimal environmental parameter combinations. By locating the current growth state in the multi-stable growth model, determining the dominant stable growth point closest to the current growth state, establishing an attractor potential field centered on the dominant stable growth point, and calculating the potential energy gradient required to reach the dominant stable growth point from the current growth state, a gradual control path from the current growth state to the dominant stable growth point can be obtained. Based on the gradual control path, a staged environmental control instruction is generated, and the instruction is sent to the environmental control device, so that the environmental control device can perform staged adjustments to the vegetable greenhouse environment according to the gradual control path, guiding the vegetable growth state to move closer to the optimal environmental parameter combination corresponding to the dominant stable growth point, thereby improving the timeliness and accuracy of agricultural operations and environmental adjustments.

[0099] The above embodiment realizes the gradual control of the vegetable greenhouse environment by establishing a multi-stable growth model and an attractor potential field. In order to further improve the accuracy and scientificity of environmental control and establish a closer relationship between environmental parameters and vegetable growth status, the following is combined with another embodiment and Figure 2 , another vegetable greenhouse environment management method in the embodiment of the present application is described:

[0100] See also Figure 2 , is another flow chart of a vegetable greenhouse environment management method in an embodiment of the present application.

[0101] S201, calculating the entropy value of the environmental parameter set and the entropy value of the vegetable growth state set at each growth stage based on historical environmental parameters and vegetable growth data;

[0102] Based on historical environmental parameters and vegetable growth data, the system calculates the entropy value of the environmental parameter set and the entropy value of the vegetable growth state set at each growth stage. Specifically: it calculates the probability distribution function of the environmental parameter set and the vegetable growth state set;

[0103] Substitute the probability distribution function into the preset entropy formula to calculate the entropy value of the environmental parameter set and the vegetable growth state set in each growth stage.

[0104] The system first retrieves historical greenhouse environmental parameter data and vegetable growth status data from the database. Environmental parameter data includes multiple dimensions such as temperature, humidity, light intensity, and carbon dioxide concentration, while vegetable growth status data includes indicators such as plant height, leaf area index, and fruit count. The system categorizes and organizes this historical data according to the different growth stages of the vegetables, forming several data subsets.

[0105] For each subset of environmental parameter data and growth status data at each growth stage, the system calculates their probability distribution functions. One feasible approach is to use kernel density estimation, which approximates the true probability distribution by smoothing the observed data. After obtaining the probability distribution function, the system substitutes it into a preset entropy formula to calculate the entropy value of the environmental parameter set and growth status set at that stage. The entropy formula used here can be Shannon entropy, Tsallis entropy, etc., all of which can quantitatively describe the degree of order in a system.

[0106] S202, calculating the mutual information between the entropy values ​​of the environmental parameter set and the entropy values ​​of the vegetable growth status set, and obtaining the correlation strength between the environmental parameters and the vegetable growth status within the growth stage;

[0107] Based on the calculated entropy of the environmental parameters and the growth state at each growth stage, the system further calculates the mutual information (Mutual Information) between the two sets. Mutual information is a key concept in information theory that measures the amount of information shared between two random variables. The formula for calculating mutual information is the difference between the joint entropy of the two variables and their individual entropies.

[0108] By calculating the mutual information between a set of environmental parameters and a set of growth states, the system can quantitatively assess the strength of the correlation between the two. A greater mutual information indicates a stronger dependency between changes in environmental parameters and changes in vegetable growth states—in other words, changing environmental parameters is more likely to cause changes in vegetable growth states. This correlation strength can serve as an important basis for manipulating environmental parameters to optimize plant growth.

[0109] In practical applications, the system can choose different methods for calculating mutual information, such as the histogram method, the nearest neighbor method, and the kernel density estimation method. For high-dimensional data, the system can also first perform independent component analysis (ICA) to map the data to a low-dimensional space, eliminate the correlation between different dimensions, and then calculate the mutual information to improve computational efficiency and accuracy. Considering that the estimation of mutual information for a finite sample may be biased, the system can introduce methods such as Jackknife resampling to correct the bias. In addition, the system can also calculate the difference between the mutual information of environmental parameters and growth status at different growth stages, revealing the dynamic changes in the relationship between the two during different periods, and providing targeted guidance for phased environmental regulation.

[0110] S203, determining weight coefficients for regulating environmental parameters at each growth stage based on the correlation strength, and introducing the weight coefficients into the multi-stable growth model;

[0111] The system determines the weighting coefficients for environmental control at different growth stages based on the strength of the correlation between environmental parameters and the vegetable's growth status. One feasible strategy is to normalize the mutual information value to obtain a weighting coefficient ranging from 0 to 1. The greater the mutual information, the larger the weighting coefficient, indicating a closer correlation between the environmental parameters and the plant's growth status at that growth stage, and therefore, a greater weight should be given to environmental control.

[0112] Introducing weight coefficients into the multistable growth model can make the model more closely aligned with the actual needs of vegetable growth. The multistable growth model is a type of kinetic model that describes the plant growth process, taking into account multiple factors that influence plant growth, such as temperature, humidity, and light. Building on the existing model, the system applies different control intensities to each environmental factor based on the weight coefficients of the environmental parameters. Factors with larger weights have greater control strength, while factors with smaller weights have relatively weaker control strength. This mutual information weight-based control method can adaptively balance multiple environmental factors according to the characteristics of the plant's growth stage, better meeting the dynamic needs of plant growth.

[0113] In terms of technical implementation, the system can incorporate weight coefficients into the model equations using a weighted average. Assuming the control term for the i-th environmental factor in the original model is fi(x), and the weight coefficient is wi, then the control term after the introduction of the weight can be expressed as wi·fi(x). The inclusion of the weight coefficient makes the model more flexible and changeable, and can automatically optimize the control strategy according to changes in environmental conditions. In addition, considering that the weight coefficient is estimated based on historical data, to improve the robustness of the system, the weight coefficient can be regularly updated online using newly collected environmental and growth data. At the same time, upper and lower limits are set for the weight coefficient to prevent excessively large or small weight values ​​from affecting system stability. By dynamically updating and reasonably limiting the weight coefficient, the multistable growth model can achieve precise control in complex and changing environments, providing a strong guarantee for high-quality and high-yield vegetables.

[0114] S204, establishing a state feedback equation for environmental parameter regulation using environmental factors as control variables and vegetable growth state parameters as state variables;

[0115] After clarifying the quantitative relationship between environmental factors and vegetable growth status at each growth stage, the system further established state feedback equations for regulating environmental parameters. State feedback control is a common closed-loop control method that monitors system state variables in real time and feeds deviation signals back to the controller, continuously adjusting the control variables to bring the system state closer to the desired value.

[0116] In greenhouse environmental control, the system uses environmental factors such as temperature, humidity, and light as control variables, adjusting actuators such as heating, ventilation, and lighting to alter these parameters. Furthermore, the system selects key indicators that reflect vegetable growth conditions as state variables, such as plant height, leaf area, and fruit count. Changes in these state variables reflect the plant's response to environmental conditions and serve as a crucial basis for optimizing control strategies.

[0117] Drawing on modern control theory, the system establishes a state feedback equation between environmental parameters and the vegetable growth state. This equation describes how the vegetable growth state will evolve under given environmental conditions and the potential impact of adjusting these parameters. Generally speaking, a state feedback equation can be expressed as a differential equation or a difference equation, meaning that the rate of change or amount of change in the state variable is functionally related to the current state variable and the control variable.

[0118] In practical applications, the system can derive specific state feedback equations based on crop growth models, such as the logistics model and the Richards model. Model parameters can be estimated by fitting historical data. For complex systems, factors such as time lag, nonlinearity, and random perturbations can be considered to establish a more refined state feedback model. The system can also establish multiple state feedback equations for different vegetable varieties and growth stages, improving the model's applicability and accuracy. Once the state feedback equations are obtained, various control algorithms, such as PID control, optimal control, adaptive control, and intelligent control, can be applied to dynamically adjust environmental parameters, continuously approaching the ideal growth state. The establishment of state feedback equations transforms complex environmental-plant interactions into computable and optimizable mathematical models, providing an important tool for quantitatively expressing and fine-tuning the vegetable growth process.

[0119] S205. Designing an optimal controller based on the weight coefficients to minimize the deviation of the vegetable growth state while satisfying the environmental parameter constraints in each growth stage;

[0120] Based on the state feedback equation, the system further designs an optimal controller to achieve dynamic optimization of environmental parameters. The goal of the optimal controller is to minimize the deviation of vegetable growth from the ideal value while satisfying the environmental parameter constraints at each growth stage, so that the plants are always in the optimal growth state.

[0121] The system incorporates the environmental parameter weights calculated previously into the design of the optimal controller. Specifically, a weighted quadratic performance function is constructed: the weighted sum of squared deviations in plant growth states. The larger the weight, the stronger the correlation between the environmental factor and the plant's response at the current growth stage, and the greater its weight in the performance function. The optimal control problem is then transformed into minimizing this performance function under the constraints of the environmental parameters—a typical quadratic programming problem.

[0122] When setting constraints, the system fully considers the adaptability of plants to environmental conditions. For example, temperatures must be neither too high nor too low, as this can cause thermal stress on crops; humidity must be neither too dry nor too humid, as this can lead to pests and diseases. These constraints are determined based on the characteristics of the vegetable variety and growth stage, and can be derived through expert experience or data analysis. Furthermore, the physical characteristics of the actuators, such as their adjustment range and response speed, are also considered within the constraints.

[0123] S206, solving the state feedback equation to obtain the optimal control value of each environmental parameter;

[0124] Solve the state feedback equation to obtain the optimal control value of each environmental parameter. Specifically: transform the state feedback equation into the objective function of the convex optimization problem;

[0125] According to the variation range of environmental parameters in each growth stage, the boundary constraints of decision variables are set;

[0126] Introducing boundary constraints into the objective function, we obtain the Lagrangian function;

[0127] Derivative the Lagrangian function and transform it into an unconstrained optimization problem;

[0128] The gradient descent algorithm is used to search for the optimal solution of the unconstrained optimization problem and obtain the optimal control value of each environmental parameter.

[0129] After designing the optimal controller, the system further solves the state feedback equation to obtain the optimal control value for each environmental parameter. This step is key to achieving dynamic optimization and adjustment of environmental parameters. Based on real-time information about the vegetable growth status, specific control instructions for each actuator are calculated to ensure that environmental conditions remain within the optimal range.

[0130] First, the system combines state feedback equations with an optimal controller to construct a complete closed-loop control system. The state feedback equations describe the dynamic relationship between environmental parameters and plant growth status, while the optimal controller determines the optimal strategy for adjusting environmental parameters based on performance indicator functions and constraints. Combining the two creates a state feedback optimal control system that automatically calculates the optimal control input based on the current state and desired goals.

[0131] To facilitate numerical solution, the system typically discretizes the state feedback equation into a differential equation. The discretization time step must be appropriately selected based on factors such as the time scale of environmental parameter changes and the response speed of the actuators. This ensures real-time control while avoiding system oscillations caused by overly frequent adjustments. After discretization, the state feedback optimal control problem can be further transformed into a convex optimization problem: minimizing a performance function at each time step while satisfying both the state equation and the constraints.

[0132] Convex optimization problems can be efficiently solved using a variety of numerical algorithms, such as the interior point method, the active set method, and the gradient projection method. These algorithms use an iterative search to continuously approach the optimal solution until certain convergence conditions are met. In practical applications, factors such as the numerical stability and robustness of the algorithm must also be considered. Regularization techniques, such as Tikhonov regularization, can be introduced when necessary to improve the reliability of the solution. Intermediate variables generated during the solution process, such as the predicted values ​​of state variables and the search directions of control variables, also provide useful information for monitoring and diagnosing the system's operating status.

[0133] The optimal control variables for environmental parameters obtained by solving the state feedback equations serve as direct instructions for intelligent management of vegetable greenhouses. The system converts the control variables obtained through optimization calculations into specific actuator control instructions, such as the opening degree of ventilation equipment and the power of fill lights, and issues them to the corresponding control units. These control instructions, through the action of the actuators, ultimately change the environmental conditions for vegetable growth, continuously approaching the optimal state. By organically combining the solution of state feedback equations with the generation of optimized control instructions, the system implements a complete closed-loop control process from environmental information collection, growth status assessment, to optimized adjustment of environmental conditions. This provides a comprehensive intelligent management solution for vegetable production, effectively improving yield and quality, and promoting the development of facility agriculture towards digitalization, networking, and intelligence.

[0134] S207. Generate a multi-stage environmental control strategy based on the optimal control quantity.

[0135] After determining the optimal control values ​​for environmental parameters at each growth stage, the system further generates a multi-stage environmental control strategy for the entire growth cycle. This strategy comprehensively considers the dynamic changes in environmental requirements during vegetable growth and optimizes the ratio of environmental conditions at different growth stages. It aims to create a consistently suitable growth environment for crops and achieve a synergistic improvement in yield and quality.

[0136] The process for generating a multi-stage environmental control strategy is as follows: First, based on knowledge of plant physiology and cultivation experience, the system divides the vegetable growth process into several key stages, such as seedling stage, bud stage, flowering stage, fruit expansion stage, and maturity stage. The stage divisions may vary for different vegetable varieties, and the system can flexibly adjust them based on data analysis and expert advice. Then, for each growth stage, the system extracts the environmental parameter control values ​​obtained from the previous optimization calculations to form a stage-by-stage environmental control plan. This plan clearly defines the optimal value range and dynamic adjustment strategy for each environmental factor within that stage to meet the growth needs of the plant at different developmental stages.

[0137] Based on the generated phased control plan, the system further optimizes the connection and coordination between each phase to form a continuous multi-stage environmental control strategy. Specifically, the system analyzes the changing trends of environmental conditions in adjacent phases and smoothly transitions control parameters to avoid the adverse effects of drastic environmental fluctuations during phase transitions on plant growth. At the same time, the system also needs to balance the priority and resource allocation of environmental control at different stages, taking into account factors such as energy consumption and cost while meeting the needs of plant growth, to optimize the overall benefits of environmental control.

[0138] Once a multi-stage environmental control strategy is generated, it becomes the action plan guiding the entire vegetable production process. Based on the strategy's requirements, the system implements corresponding environmental control measures at different growth stages, dynamically monitors vegetable growth, and evaluates the effectiveness of the control measures. If necessary, the established strategy can be revised online based on special circumstances encountered during the actual planting process, such as extreme weather, pests and diseases, to ensure that environmental control measures remain synchronized with plant growth. By formulating and implementing multi-stage environmental control strategies, the system can achieve a transition from qualitative management to quantitative decision-making, and from empirical judgment to data-driven management, truly realizing refined and intelligent management of the vegetable production process.

[0139] In the above embodiment, mutual information is a metric that can measure the correlation between two random variables. It reduces the uncertainty of the random variables themselves and more accurately reflects the degree of correlation between them. Determining the environmental parameter control weight coefficients for each growth stage based on the correlation strength and introducing the weight coefficients into the multistable growth model can make the model adapt to the dynamic changes in the importance of environmental parameters in different growth stages. When regulating environmental parameters, higher weights are assigned to key parameters to highlight their influence, while non-key parameters are correspondingly reduced to avoid over-regulation, thereby achieving stage-by-stage differentiation of environmental regulation and further improving the accuracy and effectiveness of environmental regulation.

[0140] The following describes the system in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , which is a schematic diagram of the physical device structure of a vegetable greenhouse environmental management system provided in an embodiment of the present application.

[0141] It should be noted that Figure 3 The structure of the system shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0142] like Figure 3 As shown, the system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes, such as the methods described in the above embodiments, based on programs stored in a read-only memory (ROM) 302 or programs loaded from a storage unit 308 into a random access memory (RAM) 303. RAM 303 also stores various programs and data required for system operation. CPU 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to bus 304.

[0143] The following components are connected to the I / O interface 305: an input section 306 including a camera, infrared sensor, and the like; an output section 307 including a liquid crystal display (LCD) and speakers; a storage section 308 including a hard disk and the like; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. Removable media 311, such as a magnetic disk, optical disk, magneto-optical disk, or semiconductor memory, is installed in the drive 310 as needed, so that computer programs read from the media can be installed in the storage section 308 as needed.

[0144] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for executing the methods illustrated in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via the communication section 309 and / or installed from removable media 311. When executed by the central processing unit (CPU) 301, the computer program performs the various functions defined in the present invention.

[0145] It should be noted that the computer-readable medium described in the embodiments of the present invention may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present invention, a computer-readable signal medium may include a data signal transmitted in baseband or as part of a carrier wave, which carries a computer-readable computer program. Such a propagated data signal may take any of a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof.

[0146] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the boxes can also occur in an order different from that marked in the accompanying drawings. For example, two boxes shown in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.

[0147] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the system described in the above embodiments, or may exist independently and not incorporated into the system. The storage medium carries one or more computer programs, and when executed by a processor of a system, the system implements the methods provided in the above embodiments.

[0148] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0149] As used in the above embodiments, the term “when” may be interpreted to mean “if” or “after” or “in response to determining that” or “in response to detecting that”, depending on the context. Similarly, the phrases “upon determining that” or “if (stated condition or event) is detected” may be interpreted to mean “if determining that” or “in response to determining that” or “upon detecting (stated condition or event)” or “in response to detecting (stated condition or event)”, depending on the context.

[0150] In the above embodiments, all or part of the embodiments can be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, hard disk, tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive).

[0151] Those skilled in the art will appreciate that all or part of the process steps in the above-described method embodiments can be implemented by a computer program instructing the relevant hardware. The program can be stored in a computer-readable storage medium, and when executed, the program can include the process steps in the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A vegetable greenhouse environment management method, characterized in that: include: Obtaining historical environmental parameters of a vegetable greenhouse, vegetable growth data, and the current growth status of the vegetables in the vegetable greenhouse, wherein the historical environmental parameters include temperature, humidity, light intensity, and carbon dioxide concentration, and the vegetable growth data includes plant height, leaf area, stem diameter, and yield; A multi-stable growth model is established based on the historical environmental parameters and the vegetable growth data. The multi-stable growth model includes several stable growth points, each of which corresponds to a set of environmental parameter combinations, specifically including: Performing time series segmentation on the historical environmental parameters and the vegetable growth data to obtain key stages of vegetable growth; Constructing a phase space, and generating an environmental parameter trajectory and a vegetable growth trajectory in the phase space that correspond one-to-one to the historical environmental parameters and the vegetable growth data; Determining a stable growth point according to the environmental parameter trajectory and the vegetable growth trajectory, wherein the stable growth point is a convergence point where the Lyapunov exponent is negative, and the convergence point is an intersection of the environmental parameter trajectory and the vegetable growth trajectory; Determine the attraction domain range and attraction strength of each stable growth point; calculate the comprehensive advantage coefficient of each stable growth point; Integrating the stable growth point, the attraction domain range, the attraction strength and the comprehensive advantage coefficient to obtain a multi-stable growth model; Positioning the growth state in the multi-stable growth model and determining a dominant stable growth point closest to the growth state, wherein the dominant stable growth point is a stable growth point with the highest comprehensive advantage coefficient; Establishing an attractor potential field, setting the dominant stable growth point as the attractor center, and calculating the potential energy gradient from the growth state to the attractor center; Constructing a progressive control path for the environmental parameters of the vegetable greenhouse based on the potential energy gradient, and generating phased environmental control instructions; The phased environmental control instruction is sent to the environmental control device, so that the environmental control device performs environmental adjustment according to the phased environmental control instruction and the progressive control path.

2. The method according to claim 1, characterized in that The establishing of the attractor potential field specifically includes: Constructing a local potential field function with each of the stable growth points as the potential field center, wherein the potential field intensity in the local potential field function has an exponential decay relationship with the distance from the potential field center, and the decay coefficient is determined by the stability of the stable growth point; Setting a weight coefficient according to the advantage coefficient of each of the stable growth points; All the local potential fields are weightedly superimposed according to the weight coefficient to obtain the attractor potential field.

3. The method according to claim 1, characterized in that After establishing the multi-stable growth model according to the historical environmental parameters and the vegetable growth data, the method further includes: Calculating the entropy value of the environmental parameter set and the entropy value of the vegetable growth state set at each growth stage based on the historical environmental parameters and the vegetable growth data; Calculating the mutual information between the entropy value of the environmental parameter set and the entropy value of the vegetable growth state set to obtain the correlation strength between the environmental parameters and the vegetable growth state within the growth stage; The weight coefficients for regulating the environmental parameters of each growth stage are determined based on the correlation strength, and the weight coefficients are introduced into the multi-stable growth model.

4. The method according to claim 3, characterized in that The entropy value of the environmental parameter set and the entropy value of the vegetable growth state set of each growth stage is calculated, specifically including: Calculate the probability distribution function of the environmental parameter set and the vegetable growth state set; The probability distribution function is substituted into a preset entropy formula to calculate the entropy value of the environmental parameter set and the vegetable growth state set in each growth stage.

5. The method according to claim 3, characterized in that After determining the weight coefficients for regulating the environmental parameters of each growth stage based on the correlation strength, the method further includes: Taking environmental factors as control variables and vegetable growth state parameters as state variables, a state feedback equation for environmental parameter regulation is established; Designing an optimal controller in combination with the weight coefficients to minimize the deviation of the vegetable growth state under the condition of satisfying the environmental parameter constraints in each growth stage; Solving the state feedback equation to obtain the optimal control value of each environmental parameter; A multi-stage environmental control strategy is generated according to the optimal control quantity.

6. The method according to claim 5, characterized in that Solving the state feedback equation to obtain the optimal control value of each environmental parameter specifically includes: Converting the state feedback equation into an objective function of a convex optimization problem; Setting boundary constraints of decision variables according to the variation range of environmental parameters in each growth stage; Introducing the boundary constraint condition into the objective function to obtain a Lagrangian function; Derivative the Lagrangian function and transform it into an unconstrained optimization problem; A gradient descent algorithm is used to search for the optimal solution of the unconstrained optimization problem to obtain the optimal control value of each environmental parameter.

7. A vegetable greenhouse environmental management system, characterized in that: The system comprises: One or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to cause the system to execute the method according to any one of claims 1 to 6.

8. A computer-readable storage medium comprising instructions, characterized in that: When the instructions are executed on a system, the system is caused to perform the method according to any one of claims 1 to 6.

9. A computer program product, characterized in that When the computer program product is run on a system, the system is caused to perform the method according to any one of claims 1 to 6.

Images