An environmental dynamic control method and system based on the internet of things

Abstract

The application discloses an environment dynamic control method and system based on Internet of Things, relates to the technical field of agricultural Internet of Things, and discloses an environment dynamic control method and system based on Internet of Things, which realizes accurate regulation and control by acquiring environment information, identifying a growth stage, calculating a deviation, generating and optimizing a control instruction, can realize multi-factor collaborative accurate dynamic regulation and control of a mulberry growth environment, effectively avoids control instruction conflicts and resource waste, and improves the stability and regulation and control efficiency of environment control.

Description

Technical Field

[0001] This application relates to the field of agricultural Internet of Things (IoT) technology, and in particular to an IoT-based method and system for dynamic environmental control. Background Technology

[0002] With the widespread application of IoT technology in agriculture, sensor-based environmental automation control has become an important development direction for modern agricultural production. Existing agricultural environmental control systems typically employ preset thresholds or simple rules for independent single-factor control, such as automatically activating fans to cool the air when the temperature exceeds a set value or starting humidifiers when humidity is insufficient. However, in practical applications, especially in agricultural production scenarios like mulberry orchards where precise environmental control is required, these methods face technical bottlenecks: complex interactions and coupling relationships exist between different environmental control devices. For example, activating fans to cool the air reduces humidity, while activating humidifiers may affect temperature changes. This strong coupling of multiple variables makes it difficult for simple threshold control methods to simultaneously optimize multiple environmental parameters, easily leading to control command conflicts, system oscillations, and resource waste. Furthermore, existing systems lack the ability to dynamically identify the growth stages of mulberry trees, failing to determine the growth status in real time based on key information such as bud morphology, leaf expansion, and leaf color, resulting in a disconnect between environmental control objectives and actual growth needs. Meanwhile, the static model of equipment impact relationships failed to consider the priority weights of environmental factors and the synergistic effects of equipment, resulting in a lack of prediction of the offsetting effect and energy consumption exceedance during the control command generation process. This further exacerbated the instability of the regulation process and failed to meet the dynamic, synergistic, and precise regulation needs of mulberry trees for environmental factors throughout their entire life cycle.

[0003] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main purpose of this application is to provide an environmental dynamic control method and system based on the Internet of Things, which aims to improve the stability and regulation efficiency of environmental control.

[0005] To achieve the above objectives, this application proposes an environmental dynamic control method based on the Internet of Things, the method comprising: The system acquires current environmental information collected by sensors and preprocesses the current environmental information to obtain standard environmental information; the current environmental information includes temperature data, humidity data, light intensity data, soil moisture data, and image data. Based on the image data, the current growth stage of the mulberry tree is identified, and the corresponding target environmental parameters are obtained from a preset database according to the current growth stage. Calculate the environmental deviation between the standard environmental information and the target environmental parameters; the environmental deviation includes the deviation value and direction of each environmental factor; Based on the environmental deviation and combined with the preset equipment influence matrix, a preliminary control instruction set is generated; the preliminary control instruction set includes control parameters for at least two devices. Based on the preset device influence matrix, the preliminary control instruction set is subjected to collaborative conflict detection to generate conflict detection results. Based on the conflict detection results, the preliminary control instruction set is adjusted to obtain an optimized control instruction set. The optimized control instruction set is sent to the execution device to control the execution device to perform environmental adjustment operations; After the execution device performs the environmental adjustment operation, it reacquires the updated environmental information collected by the sensor, and updates the preset device influence matrix based on the comparison result between the updated environmental information and the target environmental parameters.

[0006] In one embodiment, the step of identifying the current growth stage of the mulberry tree based on the image data and obtaining the corresponding target environmental parameters from a preset database according to the current growth stage includes: Key features of mulberry trees are extracted from the image data, including bud morphology, leaf spread, and leaf color. The key features of the mulberry tree are matched with a preset growth stage feature library, and the current growth stage of the mulberry tree is determined based on the matching results. Based on the current growth stage, basic environmental parameters are obtained from a preset stage-environment parameter mapping table; Based on the historical environmental regulation effect, the basic environmental parameters are dynamically adjusted to generate the target environmental parameters.

[0007] In one embodiment, the step of generating a preliminary control instruction set based on the environmental deviation and a preset equipment influence matrix includes: Based on the current growth stage, obtain the corresponding environmental factor priority weights; Calculate the weighted environmental deviation based on the environmental deviation and the priority weights of the environmental factors; Based on the preset equipment influence matrix, candidate equipment capable of adjusting the environmental factors corresponding to the weighted environmental deviation is identified; Based on the weighted environmental deviation and the influence coefficient of each device in the candidate devices, the theoretical control strength of each candidate device is calculated; The theoretical control strength is converted into control parameters that can be executed by the device, forming the preliminary control instruction set.

[0008] In one embodiment, the step of performing cooperative conflict detection on the preliminary control instruction set based on the preset device influence matrix and generating conflict detection results includes: Based on the preset device influence matrix, a device collaborative influence relationship network is constructed. Based on the aforementioned equipment collaborative influence relationship network, the mutual influence between the control parameters of each equipment in the preliminary control instruction set is analyzed. Based on the results of the interaction analysis, identify equipment combinations that may produce offsetting effects; Based on a pre-trained energy consumption assessment model, identify combinations of devices whose energy consumption exceeds a preset threshold; The collision detection result is generated by combining the device combinations that may produce a counteracting effect with the device combinations whose energy consumption exceeds a preset threshold.

[0009] In one embodiment, the step of adjusting the preliminary control instruction set based on the conflict detection results to obtain an optimized control instruction set includes: Based on the conflict detection results, the control parameters of the device that caused the conflict are determined; Based on preset device substitution relationships, at least two alternative device schemes are generated for the conflicting device control parameters; Based on a pre-trained digital twin environment model, a pre-execution simulation is performed on each of the alternative device schemes to generate simulation execution results; Based on the simulation results, evaluate the overall performance score of each alternative equipment solution; Based on the comprehensive performance score, the alternative equipment scheme with the highest score is selected, and the corresponding control parameters in the preliminary control instruction set are replaced to generate the optimized control instruction set.

[0010] In one embodiment, the step of performing pre-execution simulations on each of the alternative device schemes based on a pre-trained digital twin environment model and generating simulation execution results includes: The current environmental state and alternative equipment options are input into the pre-trained digital twin environment model; Based on the preset environmental factor coupling relationship and device interaction influence, the alternative device scheme is simulated and executed in the pre-trained digital twin environment model; Simulate the environmental state change process at multiple time steps to predict the final environmental state; Calculate the comprehensive deviation between the predicted final environmental state and the target environmental parameters.

[0011] In one embodiment, the step of evaluating the overall performance score of each alternative device scheme based on the simulation execution results includes: Based on the comprehensive deviation, the environmental regulation effect score is calculated; Based on the pre-trained energy consumption assessment model, the energy consumption score of the alternative equipment scheme is calculated; Based on a pre-trained equipment life prediction model, calculate the equipment wear score; The comprehensive performance score is calculated based on the environmental regulation effect score, the energy consumption score, and the equipment wear score, according to preset weights.

[0012] In one embodiment, after the execution device performs an environmental adjustment operation, the step of reacquiring updated environmental information collected by the sensors and updating the preset device influence matrix based on the comparison result of the updated environmental information and the target environmental parameters includes: Based on the updated environmental information and the environmental information before the environmental adjustment operation, the actual value of the environmental change is calculated; Based on the preset equipment influence matrix and the optimized control instruction set, the theoretical environmental changes are calculated. Compare the actual values ​​of the environmental changes with the theoretical environmental changes; Based on the comparison results, analyze the difference between the actual influence coefficient and the theoretical influence coefficient of the equipment; Based on the aforementioned differences, the device influence coefficients in the preset device influence matrix are adjusted according to an adaptive learning algorithm.

[0013] In one embodiment, the method further includes: The history of environmental control at different growth stages and the corresponding mulberry tree growth responses were collected to analyze the sensitivity of environmental factors at each growth stage. Based on the sensitivity to the environmental factors, the weights of the target environmental parameters for each growth stage are dynamically adjusted. Based on the adjusted target environment parameter weights, update the priority weights in the preset stage-environment parameter mapping table; When the same growth stage is identified again, the corresponding environmental factor priority weight is obtained from the updated preset stage-environment parameter mapping table using the updated priority weight.

[0014] Furthermore, to achieve the above objectives, this application also proposes an IoT-based environmental dynamic control system, which includes: a memory, a processor, and an IoT-based environmental dynamic control program stored in the memory and executable on the processor. The IoT-based environmental dynamic control program is configured to implement the steps of the IoT-based environmental dynamic control method.

[0015] This application proposes an IoT-based dynamic environmental control method and system. By acquiring environmental information, identifying growth stages, calculating deviations, and generating and optimizing control commands, it achieves precise regulation and control. This enables multi-factor collaborative precise dynamic regulation of the mulberry tree's growth environment, effectively avoiding control command conflicts and resource waste, and improving the stability and efficiency of environmental control. Attached Figure Description

[0016] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating an embodiment of the IoT-based dynamic environmental control method of this application. Figure 2 This is a schematic diagram of a structural embodiment of an IoT-based environmental dynamic control system provided in this application.

[0019] Explanation of icon numbers: 10. Memory; 20. Processor.

[0020] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] The technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of this application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0022] It should be understood that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, the terms "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0023] In existing technologies, agricultural environmental control systems typically employ preset thresholds or rules for independent control of single factors when regulating the environment. However, different environmental control devices interact and are coupled, exhibiting strong multivariate coupling. This makes threshold-based control methods difficult to simultaneously optimize multiple environmental parameters, easily leading to control command conflicts, system oscillations, and resource waste. Consequently, they fail to meet the dynamic, coordinated, and precise regulation needs of mulberry trees at different growth stages.

[0024] Based on this, embodiments of this application provide an environmental dynamic control method based on the Internet of Things, referring to... Figure 1 The IoT-based dynamic environmental control method includes steps S100 to S700, wherein: Step S100: Obtain the current environmental information collected by the sensor, and preprocess the current environmental information to obtain standard environmental information; the current environmental information includes temperature data, humidity data, light data, soil moisture data and image data; Step S200: Identify the current growth stage of the mulberry tree based on the image data, and obtain the corresponding target environmental parameters from the preset database according to the current growth stage; Step S300: Calculate the environmental deviation between the standard environmental information and the target environmental parameters; the environmental deviation includes the deviation value and deviation direction of each environmental factor; Step S400: Based on the environmental deviation and combined with the preset equipment influence matrix, a preliminary control instruction set is generated; the preliminary control instruction set includes control parameters for at least two devices. Step S500: Based on the preset device influence matrix, perform collaborative conflict detection on the preliminary control instruction set, generate conflict detection results, and adjust the preliminary control instruction set based on the conflict detection results to obtain an optimized control instruction set; Step S600: Send the optimized control instruction set to the execution device to control the execution device to perform environmental adjustment operations; Step S700: After the execution device performs the environmental adjustment operation, the updated environmental information collected by the sensor is reacquired, and the preset device influence matrix is ​​updated based on the comparison result between the updated environmental information and the target environmental parameters.

[0025] In this embodiment, current environmental information refers to environmental data collected in real time by various sensors deployed in the agricultural environment, such as temperature data from temperature sensors, humidity data from humidity sensors, light data from light sensors, soil moisture data from soil moisture sensors, and image data from cameras. This data reflects the real-time state of the environment. Standard environmental information refers to data obtained after performing preprocessing operations such as standardized formatting, noise reduction, and calibration on the raw current environmental information. The purpose is to eliminate sensor errors and data redundancy, ensuring the accuracy and consistency of subsequent processing.

[0026] In this embodiment, the current growth stage of the mulberry tree refers to a specific developmental stage in its life cycle, such as the budding stage, leaf unfolding stage, vigorous growth stage, and maturity stage. Different growth stages have different requirements for environmental factors. Target environmental parameters refer to the set of ideal environmental conditions set according to the optimal growth requirements of the mulberry tree at its current growth stage. These parameters are the targets of environmental regulation, such as the optimal temperature range, humidity range, light intensity, and soil moisture content required for a specific growth stage. Environmental deviation refers to the difference between standard environmental information and target environmental parameters. It includes the specific deviation value for each environmental factor (e.g., the difference between the actual temperature and the target temperature) and the direction of the deviation (e.g., higher or lower than the target value).

[0027] In this embodiment, the device influence matrix refers to a pre-defined data structure used to describe the degree and direction of influence of each environmental control device on different environmental factors. For example, the influence coefficient of a humidifier on humidity, the influence coefficient of a fan on temperature and humidity, etc. This matrix reflects the coupling relationship between devices. The preliminary control instruction set refers to a set of control instructions initially calculated based on environmental deviations and the device influence matrix. This instruction set contains control parameters for at least two executing devices, such as the on / off state, power level, or operating time of a device. Cooperative conflict detection refers to analyzing the mutual influence between the control parameters of each device in the preliminary control instruction set to identify conflict situations that may lead to negative effects (such as offsetting, over-adjustment, excessive energy consumption).

[0028] In this embodiment, the conflict detection result refers to the set of all conflict situations identified by the collaborative conflict detection process, such as which device combinations might produce a canceling effect, or which device combinations exceed a preset threshold in energy consumption. The optimized control command set refers to the final control command set obtained after adjusting and optimizing the initial control command set based on the conflict detection results. This command set aims to eliminate conflicts and achieve synergy and efficiency in environmental regulation. The executing device refers to the physical equipment that actually performs the environmental regulation operation, such as fans, humidifiers, heaters, supplemental lighting, irrigation systems, etc. Updated environmental information refers to the environmental data re-collected by the sensors after the executing device completes the environmental regulation operation. This information is used to evaluate the regulation effect and feed back to the system for learning and optimization.

[0029] In this embodiment, the IoT-based environmental dynamic control method first acquires current environmental information collected by sensors and preprocesses this information to obtain standard environmental information. The current environmental information can be collected in real time by various sensors deployed in the environment, such as temperature sensors, humidity sensors, light sensors, soil moisture sensors, and image sensors. For example, it can be obtained through regular manual inspections, manually recording readings of various environmental parameters, and uploading image data manually. Preprocessing this raw data can include simple format conversion, such as unifying all data into text format, or performing simple averaging calculations to reduce instantaneous fluctuations, thereby obtaining standard environmental information.

[0030] In this embodiment, the current growth stage of the mulberry tree is identified based on the image data, and the corresponding target environmental parameters are obtained from a preset database according to the current growth stage. The current growth stage of the mulberry tree can be determined by manually observing its morphological characteristics, such as empirical indicators like leaf size and branch length. Once the growth stage is determined, such as the "leaf unfolding stage," the system can search for the corresponding fixed environmental parameter values ​​from a preset database, such as preset temperature and humidity ranges, as the target environmental parameters.

[0031] In this embodiment, the environmental deviation between the standard environmental information and the target environmental parameter is calculated. The environmental deviation includes the deviation value and direction of each environmental factor. For example, the temperature deviation value is obtained by subtracting the actual temperature in the standard environmental information from the target temperature in the target environmental parameter, and the direction of deviation is determined by the sign. The same method is also applicable to other environmental factors such as humidity, light intensity, and soil moisture.

[0032] Furthermore, based on this environmental deviation and a preset device influence matrix, a preliminary control instruction set is generated. This preliminary control instruction set includes control parameters for at least two devices. The device influence matrix can be a simple lookup table recording the impact of each environmental control device on different environmental factors. For example, if the temperature is higher than the target value, the system can directly select to turn on the fan according to preset rules; if the humidity is lower than the target value, the humidifier will be turned on. The preliminary control instruction set can be set to a preset control intensity, such as the fan operating at 50% power and the humidifier running for 30 minutes.

[0033] Based on this, a collaborative conflict detection is performed on the preliminary control command set using the preset device influence matrix, generating a conflict detection result. This result is then used to adjust the preliminary control command set, resulting in an optimized control command set. Collaborative conflict detection can be based on preset simple conflict rules. For example, if the preliminary command set contains both "turn on the fan" and "turn on the humidifier," a conflict is considered to exist. The conflict detection result can be a simple list indicating which device combinations conflict. When a conflict is detected, a preset priority rule can be used for adjustment. For example, if the fan and humidifier conflict, and the current humidity deviation is more severe, the humidifier command is executed first, and the fan command is canceled, thus obtaining an optimized control command set.

[0034] In this embodiment, the optimized control command set is sent to the execution device to control the execution device to perform environmental adjustment operations. The optimized control command set can be sent to the corresponding execution device, such as a fan, humidifier, heater, supplemental lighting, or irrigation system, via wired or wireless communication. After receiving the command, the execution device performs the corresponding operation to adjust the environment. Finally, after the execution device performs the environmental adjustment operation, it re-acquires the updated environmental information collected by the sensors. Based on the comparison result between the updated environmental information and the target environmental parameters, the preset device influence matrix is ​​updated. After the adjustment operation is completed, the system can read the sensor data again to obtain the new environmental state as updated environmental information. The update of the device influence matrix can be based on a simple feedback mechanism. For example, if humidification is performed but the humidity change is not significant, the influence coefficient of the humidifier on humidity in the device influence matrix can be manually adjusted to make its value larger to reflect the actual effect.

[0035] In this embodiment, by dynamically acquiring environmental information and identifying the growth stages of mulberry trees, and combining this with the generation and optimization of control commands using an equipment influence matrix, the problem of command conflicts and resource waste caused by the mutual influence between devices in traditional single-factor control is solved. This method achieves coordinated and precise regulation of the mulberry tree growth environment, avoids system oscillations, and thus meets the dynamic needs of mulberry trees for environmental factors at different growth stages.

[0036] In one feasible implementation, the step of identifying the current growth stage of a mulberry tree based on the image data and obtaining corresponding target environmental parameters from a preset database according to the current growth stage includes: extracting key features of the mulberry tree from the image data, the key features of the mulberry tree including bud morphology features, leaf spread features, and leaf color features; matching the key features of the mulberry tree with a preset growth stage feature library, and determining the current growth stage of the mulberry tree based on the matching result; obtaining basic environmental parameters from a preset stage-environmental parameter mapping table based on the current growth stage; and dynamically adjusting the basic environmental parameters based on historical environmental adjustment effects to generate the target environmental parameters.

[0037] In this embodiment, key features of mulberry trees are extracted from the image data. These key features include bud morphology, leaf spread, and leaf color. This step aims to identify and quantify visual information closely related to the growth status of mulberry trees from the image data collected by sensors using image processing and analysis techniques. Bud morphology features can include parameters such as bud size, shape, and fullness, reflecting the budding and growth potential of the mulberry tree. Leaf spread features can quantify leaf area, spread angle, and leaf shape index, indicating the photosynthetic capacity and growth vitality of the leaves. Leaf color features can be assessed by analyzing the leaf color space (such as RGB, HSV) data to evaluate chlorophyll content and nutritional status. The extraction of these features can utilize computer vision algorithms, for example, by training a large number of labeled images using a deep learning model (such as a convolutional neural network), enabling it to automatically and accurately identify and extract these key features.

[0038] In this embodiment, the key features of the mulberry tree are matched with a pre-established growth stage feature library, and the current growth stage of the mulberry tree is determined based on the matching results. After extracting the key features of the mulberry tree, they need to be compared with the pre-established growth stage feature library to determine the specific growth stage of the mulberry tree. The pre-established growth stage feature library stores the numerical range or pattern of typical bud morphology, leaf expansion, leaf color, and other features of mulberry trees at different growth stages (e.g., budding stage, leaf expansion stage, vigorous growth stage, maturity stage, etc.). The matching process can use pattern recognition algorithms, such as support vector machines (SVM), decision trees, or neural network classifiers. The extracted feature vectors are input into these models, and the models will output the growth stage that best matches the current features, thereby achieving accurate identification of the mulberry tree's growth stage.

[0039] Based on this, and according to the current growth stage, basic environmental parameters are obtained from a preset stage-environment parameter mapping table. Once the current growth stage of the mulberry tree is determined, the system will query and retrieve the corresponding basic environmental parameters from the preset stage-environment parameter mapping table according to that growth stage. This mapping table is a structured database that records in detail the ideal environmental conditions required by the mulberry tree at each specific growth stage (such as budding, leaf expansion, etc.), including but not limited to suitable temperature range, humidity range, light intensity, and soil moisture content. These basic parameters are derived from the biological characteristics of the mulberry tree and agronomic experience, providing preliminary guidance for subsequent environmental regulation.

[0040] Furthermore, based on historical environmental regulation effects, the basic environmental parameters are dynamically adjusted to generate the target environmental parameters. To make environmental control more precise and adaptive, this step, based on the acquired basic environmental parameters, further utilizes historical environmental regulation effect data for dynamic correction. Historical environmental regulation effect data includes the actual growth response of the mulberry tree (e.g., growth rate, leaf health index, yield data, etc.) and the actual changes in environmental parameters after each environmental regulation operation (e.g., heating, humidification, supplemental lighting, irrigation). The system can use adaptive learning algorithms or reinforcement learning models to analyze this historical data and evaluate the impact of different combinations of environmental parameters on mulberry tree growth. For example, if historical data shows that mulberry tree growth is poor at a certain base temperature, the system will fine-tune that base temperature based on learned experience to better suit the current environment and the actual needs of the mulberry tree, thereby generating more optimized and adaptive target environmental parameters.

[0041] In this embodiment, the above-described technical solution precisely extracts bud morphology, leaf spread, and leaf color features of mulberry trees from image data and matches them with a pre-defined growth stage feature library. This enables a more accurate and detailed identification of the current growth stage of the mulberry tree, effectively avoiding errors that may arise from coarse identification. Furthermore, this method not only obtains the basic environmental parameters for this growth stage but also dynamically adjusts these parameters based on historical environmental regulation effects, thereby generating target environmental parameters that better meet the actual growth needs and environmental adaptability of the mulberry tree. This dynamic adjustment mechanism makes environmental control no longer static and unchanging but adaptively optimized according to the actual response of the mulberry tree, improving the accuracy and effectiveness of environmental regulation and promoting healthy growth and increased yield of the mulberry tree.

[0042] In one feasible implementation, the step of generating a preliminary control instruction set based on the environmental deviation and a preset equipment influence matrix includes: obtaining the corresponding environmental factor priority weights based on the current growth stage; calculating a weighted environmental deviation based on the environmental deviation and the environmental factor priority weights; searching for candidate devices that can adjust the environmental factors corresponding to the weighted environmental deviation according to the preset equipment influence matrix; calculating the theoretical control strength of each candidate device based on the weighted environmental deviation and the influence coefficients of each device among the candidate devices; and converting the theoretical control strength into control parameters that the device can execute to form the preliminary control instruction set.

[0043] In this embodiment, when obtaining the corresponding environmental factor priority weights, the environmental factor priority weights refer to the quantitative indicators of the degree of influence of different environmental factors (such as temperature data, humidity data, light data, soil moisture data, etc.) on the growth health and yield of mulberry trees at a specific growth stage. The higher the weight value, the more critical the environmental factor is at that growth stage, and the more priority or greater the adjustment is required. The system can pre-store the mapping relationship between different growth stages (e.g., budding stage, leaf unfolding stage, vigorous growth stage, cocooning stage, etc.) and the priority weights of each environmental factor in the database. When the system identifies the current growth stage of the mulberry tree based on image data, it can query and obtain the corresponding environmental factor priority weights from the database. These weights can be determined and updated periodically based on agricultural expert experience, historical data analysis, or machine learning model training. For example, during the budding stage of mulberry trees, temperature data and humidity data may have higher priority weights; while during the vigorous growth stage, light data and soil moisture data may be more critical.

[0044] In this embodiment, when calculating the weighted environmental deviation, the weighted environmental deviation is the result of weighting the original environmental deviation (including the deviation values ​​and directions of each environmental factor) by introducing environmental factor priority weights. The purpose is to highlight the deviations of environmental factors that have a greater impact on the mulberry tree at the current growth stage, giving them a more significant role in the generation of subsequent control commands. For each environmental factor, its weighted environmental deviation can be calculated by multiplying its original deviation value by the corresponding environmental factor priority weight. For example, if the temperature deviation is +2℃ and the temperature priority weight is 0.8, then the weighted deviation for temperature is +1.6. If the humidity deviation is -10% and the humidity priority weight is 0.5, then the weighted deviation for humidity is -5%. Thus, in the overall environmental deviation, the deviations of high-priority environmental factors are amplified, while the deviations of low-priority environmental factors are relatively reduced, thereby more accurately reflecting the environmental problems that most need adjustment at present.

[0045] In this embodiment, when searching for candidate devices capable of adjusting environmental factors corresponding to weighted environmental deviations, candidate devices refer to execution devices that can adjust environmental factors with weighted environmental deviations. A preset device influence matrix records the type (e.g., increase, decrease) and degree (influence coefficient) of each execution device's influence on different environmental factors. The system iterates through environmental factors with large weighted environmental deviations. For each environmental factor requiring adjustment, the system queries the preset device influence matrix to find all devices capable of effectively regulating that environmental factor. For example, if the weighted temperature deviation indicates a low temperature, the system searches the device influence matrix for devices that can increase the temperature (e.g., heaters, supplemental lighting) as candidate devices. If the weighted humidity deviation indicates excessive humidity, the system searches for devices that can decrease humidity (e.g., ventilation equipment, dehumidifiers) as candidate devices.

[0046] In this embodiment, when calculating the theoretical control strength of each candidate device, the theoretical control strength refers to the theoretical adjustment level that each candidate device needs to achieve in order to eliminate or reduce the weighted environmental deviation. This requires comprehensive consideration of the magnitude of the weighted deviation of the environmental factor and the device's efficiency in influencing that environmental factor. For each candidate device, its theoretical control strength can be calculated based on its influence coefficient on the target environmental factor and the weighted deviation of that environmental factor. For example, if the heater's influence coefficient on temperature is 0.1°C per unit power increase, and the weighted temperature deviation requires an increase of 1.6°C, then the heater's theoretical control strength is 1.6 / 0.1 = 16 units of power. This calculation process aims to determine how much energy each device needs to output or at what level of operation under ideal conditions to effectively correct the environmental deviation.

[0047] In this embodiment, when converting theoretical control strength into executable control parameters to form a preliminary control instruction set, the executable control parameters are specific operational instructions that the device can directly recognize and execute, such as on / off status, power level, wind speed, and duration. The preliminary control instruction set is a collection of these control parameters for all selected candidate devices. Theoretical control strength is usually a continuous, idealized value, while actual devices often only accept discrete control parameters within a specific range. Therefore, it is necessary to map the theoretical control strength to the actual operating range of the device. For example, a heater with a theoretical control strength of 16 units of power may need to be converted into specific instructions such as "turn on heating mode, set power level to medium-high" or "continuous heating for 15 minutes." This conversion process needs to consider the physical characteristics of the device, safety limitations, and preset control strategies. Finally, all converted device control parameters are aggregated into a preliminary control instruction set for subsequent cooperative conflict detection and optimization.

[0048] In this embodiment, through the above technical solution, this application can dynamically adjust the importance of different environmental factors according to the current growth stage of the mulberry tree. When calculating the weighted environmental deviation, priority is given to the environmental factors that have the greatest impact on the current growth stage, thereby making the subsequent control command generation process more targeted. By calculating the theoretical control strength of each candidate device based on the weighted environmental deviation and the device influence matrix, and converting it into control parameters that the device can execute, it can be ensured that the generated preliminary control command set can more accurately respond to the key environmental needs of the mulberry tree at a specific growth stage, avoiding over-adjustment of unimportant environmental factors, improving the efficiency and accuracy of environmental control, thereby optimizing resource utilization and providing more suitable environmental conditions for the healthy growth of the mulberry tree.

[0049] In one feasible implementation, the step of performing cooperative conflict detection on the preliminary control instruction set based on the preset device influence matrix and generating conflict detection results includes: constructing a device cooperative influence relationship network based on the preset device influence matrix; analyzing the mutual influence between the control parameters of each device in the preliminary control instruction set based on the device cooperative influence relationship network; identifying device combinations that may produce offsetting effects based on the mutual influence analysis results; identifying device combinations whose energy consumption exceeds a preset threshold based on a pre-trained energy consumption assessment model; and merging the device combinations that may produce offsetting effects and the device combinations whose energy consumption exceeds the preset threshold to generate the conflict detection results.

[0050] In this embodiment, a network of synergistic influence relationships between devices is constructed based on the preset device influence matrix. This network can be constructed using a graph theory model, where nodes represent environmental control devices or key environmental factors, and edges represent the influence relationships between devices and between devices and environmental factors. These influence relationships can be positive, negative, or neutral, and can be accompanied by quantified influence strength. For example, a heating device has a positive influence on temperature, while a humidifier has a positive influence on humidity, but simultaneously turning on both heating and humidifiers may produce complex synergistic effects on humidity control. The preset device influence matrix provides initial quantified data for these influence relationships; for example, the elements in the matrix can represent the influence coefficient of device A on environmental factor X, and the potential interference of device A on the operating state of device B during operation.

[0051] Based on this, and using the aforementioned network of device synergistic effects, the mutual influences between the control parameters of each device in the preliminary control instruction set are analyzed. This analysis involves simulating or calculating all the device instructions to be executed in the preliminary control instruction set to assess their potential superposition, cancellation, or enhancement effects on target environmental factors and their respective operating states under simultaneous action. For example, if the preliminary control instruction set includes turning on the fan and turning on the humidifier, it is necessary to analyze whether the operation of the fan will accelerate the diffusion of moisture generated by the humidifier, thereby affecting the local humidity regulation effect.

[0052] Furthermore, based on the results of the interaction analysis, equipment combinations that may produce offsetting effects are identified. If the analysis finds that there are two or more equipment commands in the initial control command set that have opposite regulatory effects on the same environmental factor, and their effects cancel each other out to some extent, these equipment combinations are marked as combinations that may produce offsetting effects. For example, when the command set contains both equipment operations for "increasing temperature" and "decreasing temperature," or equipment operations for "increasing humidity" and "decreasing humidity," the system will identify these potential conflicts.

[0053] In this embodiment, a pre-trained energy consumption assessment model is used to identify equipment combinations whose energy consumption exceeds a preset threshold. This pre-trained energy consumption assessment model is a predictive model trained using historical operating data, equipment specifications, and environmental conditions. It can predict the total energy consumption of the equipment combination during execution based on the control parameters of each device in the initial control instruction set. If the predicted total energy consumption exceeds the preset energy consumption threshold, the equipment combination is identified as an energy-consuming combination. For example, if multiple high-power heating or lighting devices are started simultaneously, their total energy consumption may far exceed the economic considerations of daily operation. Finally, the equipment combinations that may have a canceling effect and the equipment combinations whose energy consumption exceeds the preset threshold are combined to generate the conflict detection result. This step summarizes the two types of conflict situations to form a comprehensive conflict report or data structure, providing a clear basis for subsequent adjustments to the initial control instruction set.

[0054] In this embodiment, through the above technical solution, this application introduces a cooperative conflict detection mechanism after generating the preliminary control instruction set. This mechanism first constructs a network of device cooperative influence relationships, enabling in-depth analysis of the complex interactions between the control parameters of each device in the preliminary control instruction set. This effectively identifies device combinations that may cancel each other out, avoiding ineffective regulation and resource waste caused by instruction conflicts. Simultaneously, combined with a pre-trained energy consumption assessment model, the system can predict and identify device combinations whose energy consumption may exceed a preset threshold, thus avoiding excessive operating costs due to blindly executing instructions. This comprehensive conflict detection mechanism ensures that the subsequently generated optimized control instruction set not only effectively achieves environmental regulation goals but also is more efficient and economical in terms of resource utilization and energy consumption, improving the intelligence, stability, and sustainability of the entire environmental dynamic control system.

[0055] In one feasible implementation, the step of adjusting the preliminary control instruction set based on the conflict detection results to obtain an optimized control instruction set includes: determining the control parameters of the conflicting equipment based on the conflict detection results; generating at least two alternative equipment schemes for the conflicting equipment control parameters based on preset equipment substitution relationships; performing pre-execution simulations on each of the alternative equipment schemes based on a pre-trained digital twin environment model to generate simulation execution results; evaluating the comprehensive performance score of each alternative equipment scheme based on the simulation execution results; and selecting the alternative equipment scheme with the highest comprehensive performance score to replace the corresponding control parameters in the preliminary control instruction set, thereby generating the optimized control instruction set.

[0056] In this embodiment, after obtaining the conflict detection results, the system first determines the equipment control parameters that caused the conflict based on the conflict detection results. This step aims to accurately locate the specific equipment control parameters from the conflict detection results. These parameters are the direct cause of the conflict and are the targets for subsequent adjustments and optimizations. For example, if the conflict detection results indicate that the simultaneous operation of the heater and the fan will produce a canceling effect, this step will determine the heating power parameter of the heater and the ventilation volume parameter of the fan as the equipment control parameters that caused the conflict.

[0057] In this embodiment, based on preset device substitution relationships, at least two alternative device schemes are generated for the conflicting device control parameters. The preset device substitution relationships can be stored in a database or rule base, indicating which other devices or control strategies can achieve similar functions or the same environmental regulation goals when a device or its control parameters malfunction. For example, when a conflict is determined in the control parameters of a heater, the system can search based on the substitution relationships and find that, in addition to the heater, the same temperature increase effect can be achieved by adding insulation measures, adjusting the heat pump's operating mode, or utilizing solar collectors. For each alternative scheme, a complete set of device control parameters needs to be generated. For example, if a heat pump is selected as the alternative, parameters such as the heat pump's start-up time and operating power need to be generated.

[0058] In this embodiment, to evaluate the actual effects and potential impacts of different alternative solutions, this application further performs pre-execution simulations on each of the alternative device solutions based on a pre-trained digital twin environment model, generating simulation execution results. The pre-trained digital twin environment model is a high-fidelity virtual model capable of reflecting the complex coupling relationships between the physical characteristics of the real environment, device behavior, and environmental factors. It receives the current environmental state and the alternative device solution as input, and simulates the change of the environmental state over time after the device performs an operation, predicting the final environmental state, based on preset environmental factor coupling relationships and device interaction effects.

[0059] In this embodiment, after obtaining the simulation execution results, the comprehensive performance score of each alternative equipment scheme is evaluated based on these results. The comprehensive performance score can be evaluated based on multiple dimensions. For example, the environmental regulation effect score can be calculated based on the deviation between the predicted final environmental state and the target environmental parameters in the simulation execution results. Simultaneously, the energy consumption score of the scheme can be calculated using a pre-trained energy consumption assessment model, and the equipment wear score can be calculated using a pre-trained equipment lifespan prediction model. Finally, the comprehensive performance score is obtained by weighted summation of these sub-scores; the weights can be preset according to actual needs.

[0060] In this embodiment, based on the comprehensive performance score, the alternative equipment scheme with the highest score is selected, and the corresponding control parameters in the preliminary control instruction set are replaced to generate the optimized control instruction set. The system compares the comprehensive performance scores of all alternative equipment schemes and selects the scheme with the highest score. Then, the equipment control parameters included in the optimal alternative scheme replace the original control parameters in the preliminary control instruction set that caused the conflict.

[0061] In this embodiment, through the above-described technical solution, after identifying potential conflicts in the preliminary control instruction set, this application no longer simply abandons or roughly adjusts them, but systematically generates and evaluates multiple alternative solutions. Specifically, after determining the control parameters of the conflicting equipment, based on preset equipment substitution relationships, at least two alternative equipment solutions can be generated for these conflicting parameters, thus providing diverse options for resolving conflicts. Subsequently, a pre-trained digital twin environment model is used to perform pre-execution simulations on each alternative solution, enabling accurate prediction of its impact on the environmental state in a virtual environment, avoiding the risks and resource waste that may result from blindly trying in the actual environment. Based on the simulation execution results, a comprehensive performance scoring mechanism can be used to comprehensively evaluate the performance of each alternative solution in terms of environmental regulation effects, energy consumption, and equipment wear, allowing the system to weigh the advantages and disadvantages from multiple dimensions. Finally, the alternative equipment solution with the highest score is selected to replace the corresponding control parameters in the preliminary control instruction set, thereby generating an optimized control instruction set. This not only effectively solves the coordination conflict problem in the initial control instruction set, avoiding the cancellation effect between devices or unnecessary energy consumption, but also ensures that the generated control instruction set is optimal, enabling precise environmental regulation goals to be achieved with higher efficiency and lower cost, thus improving the intelligence level and robustness of environmental control.

[0062] In one feasible implementation, the step of pre-executing simulations for each alternative device scheme based on a pre-trained digital twin environment model and generating simulation execution results includes: inputting the current environmental state and the alternative device scheme into the pre-trained digital twin environment model; simulating the execution of the alternative device scheme in the pre-trained digital twin environment model based on preset environmental factor coupling relationships and device interaction effects; simulating environmental state change processes at multiple time steps to predict the final environmental state; and calculating the comprehensive deviation between the predicted final environmental state and the target environmental parameters.

[0063] In this embodiment, the current environmental state and alternative equipment scheme are input into the pre-trained digital twin environment model; based on the preset environmental factor coupling relationship and device interaction influence, the alternative equipment scheme is simulated and executed in the pre-trained digital twin environment model; the environmental state change process of multiple time steps is simulated to predict the final environmental state; and the comprehensive deviation between the predicted final environmental state and the target environmental parameters is calculated.

[0064] In this embodiment, the pre-trained digital twin environment model is a trained virtual model that accurately reflects the dynamic behavior and response of the physical environment (e.g., a greenhouse or a specific planting area). This model is constructed by integrating historical environmental data, equipment operation data, and information from mulberry tree growth physiological models. It can simulate the changing patterns of environmental factors such as temperature, humidity, light intensity, and soil moisture under different control commands, and consider the complex coupling relationships between these factors. The current environmental state refers to the set of environmental parameters collected in real time by sensors and preprocessed, such as current temperature, humidity, and light intensity data. This serves as the starting condition for the simulation, providing the digital twin model with a realistic initial environmental snapshot. The alternative equipment schemes are alternative schemes generated by the system, containing different equipment control parameters, for conflicting parts in the initial control command set. For example, for a certain conflict, there may be scheme A (turn on the fan, turn off the heater) and scheme B (turn on the fan, reduce the heater power).

[0065] In this embodiment, the pre-established environmental factor coupling relationships and device interaction effects refer to rules or models pre-established in the digital twin model that describe the interactions between environmental factors and the mutual influence between the operations of different devices. For example, an increase in temperature may lead to a decrease in relative humidity, while turning on ventilation equipment may not only affect temperature and humidity but also change the CO2 concentration distribution. Device interaction effects may include the indirect impact of the operation of one device on the efficiency or effectiveness of another device. These relationships and effects can be based on physical laws, empirical rules, or learned from a large amount of historical data through machine learning. Simulating the execution of the alternative device scheme in the pre-trained digital twin environment model means taking the current environmental state as the initial input and the control parameters of a certain alternative device scheme as the driving input of the model. The digital twin model calculates and predicts the evolution of the environmental state under the action of these control parameters based on the environmental factor coupling relationships and device interaction effects established internally.

[0066] In this embodiment, simulating environmental state changes over multiple time steps to predict the final environmental state means that the digital twin model does not only predict a single time step, but also simulates the dynamic changes of the environmental state at multiple consecutive time points through iterative calculations. For example, the environmental state is updated every one minute or five minutes until a preset simulation duration is reached or the environmental state tends to stabilize. In this way, the delayed response of the environment to control commands, the dynamic adjustment process, and the final stable state can be captured, thus obtaining a more accurate prediction of the final environmental state. Calculating the comprehensive deviation between the predicted final environmental state and the target environmental parameters means comparing the simulated final environmental state with the preset target environmental parameters. The comprehensive deviation can be a weighted average, which quantifies the difference between the prediction result and the expected target, such as temperature deviation, humidity deviation, etc., and assigns different weights according to their importance, ultimately obtaining a single comprehensive evaluation value.

[0067] In this embodiment, by pre-training a digital twin environment model, the current environmental state and alternative equipment schemes can be input into the model. Based on preset environmental factor coupling relationships and device interaction effects, the alternative equipment schemes are simulated and executed in a virtual environment. This simulation not only considers the direct impact of device operation but also reveals the complex linkages between environmental factors and the indirect effects between devices. By simulating the environmental state change process over multiple time steps, the final environmental state can be accurately predicted. Finally, by calculating the comprehensive deviation between the predicted final environmental state and the target environmental parameters, a precise and reliable basis is provided for subsequent comprehensive performance evaluation, thereby effectively avoiding the risk of trial and error in the actual environment and improving the optimization efficiency of the control strategy and the accuracy of environmental regulation.

[0068] In one feasible implementation, the step of evaluating the comprehensive performance score of each alternative equipment scheme based on the simulation execution results includes: calculating the environmental regulation effect score based on the comprehensive deviation; calculating the energy consumption score of the alternative equipment scheme based on the pre-trained energy consumption assessment model; calculating the equipment wear score based on the pre-trained equipment life prediction model; and calculating the comprehensive performance score according to preset weights based on the environmental regulation effect score, the energy consumption score, and the equipment wear score.

[0069] In this embodiment, after obtaining the comprehensive deviation between the final environmental state of the pre-execution simulation and the target environmental parameters, this comprehensive deviation needs to be quantified into an environmental regulation effectiveness score. This score aims to reflect the effectiveness of the alternative equipment solution in environmental regulation; generally, the smaller the comprehensive deviation, the higher the environmental regulation effectiveness score. For example, an inverse proportional function, a step function, or a scoring model based on fuzzy logic can be used for calculation. Alternatively, different weights can be assigned according to the importance of different environmental factors, and a weighted deviation can be calculated before scoring.

[0070] In this embodiment, to comprehensively evaluate the merits of alternative equipment solutions, it is also necessary to calculate the energy consumption score of the alternative equipment solutions based on a pre-trained energy consumption assessment model. The pre-trained energy consumption assessment model can be a machine learning model, such as a regression model. Its inputs can include the type of equipment, operating parameters (such as power, operating time, adjustment intensity, etc.), and the current environmental state, with the output being the expected energy consumption value. The energy consumption score is usually inversely proportional to the energy consumption value; that is, the higher the energy consumption, the lower the score, reflecting the importance of energy saving. This model is trained using historical operating data and energy consumption parameters provided by the equipment manufacturer to ensure the accuracy of the assessment.

[0071] In this embodiment, to consider the long-term reliability and maintenance costs of the equipment, it is also necessary to calculate the equipment wear score based on a pre-trained equipment life prediction model. The pre-trained equipment life prediction model can predict the degree of wear of the equipment after implementing a specific alternative equipment solution, based on factors such as historical failure data, equipment operating time, operating intensity, and environmental conditions (such as the impact of temperature and humidity on equipment wear). The wear score is usually inversely proportional to the predicted wear degree; that is, the higher the wear degree, the lower the score, to encourage the selection of solutions that cause less wear to the equipment.

[0072] In this embodiment, the environmental regulation effect score, energy consumption score, and equipment wear score obtained above are weighted according to preset weights to obtain the comprehensive performance score. These preset weights can be flexibly adjusted according to the needs of actual application scenarios. For example, in scenarios with extremely high requirements for environmental regulation effect, the weight of the environmental regulation effect score can be set higher; while in scenarios sensitive to operating costs, the weight of the energy consumption score can be higher. In this way, the comprehensive performance score can comprehensively reflect the overall performance of the alternative equipment solution in terms of environmental regulation, economy, and equipment maintenance.

[0073] In this embodiment, through the above-described technical solution, when selecting alternative equipment solutions, this application no longer relies solely on the single indicator of environmental regulation effect, but introduces energy consumption score and equipment wear score. The environmental regulation effect score quantifies the degree of improvement of environmental parameters by the solution; the energy consumption score evaluates the economic efficiency of the solution from the perspective of operating costs; and the equipment wear score considers the potential impact of the solution on equipment lifespan. By comprehensively calculating these three scores according to preset weights, a comprehensive performance score that fully reflects the merits of the solution can be obtained. This multi-dimensional and comprehensive evaluation method enables the system to select alternative equipment solutions that not only effectively regulate the environment but also have better performance in terms of energy consumption and equipment maintenance. This avoids the problem of excessively high operating costs or premature equipment wear caused by unilaterally pursuing environmental effects, thereby improving the long-term operational efficiency and sustainability of the environmental dynamic control system.

[0074] In one feasible implementation, after the execution device performs an environmental adjustment operation, the updated environmental information collected by the sensors is reacquired, and the preset device influence matrix is ​​updated based on the comparison result of the updated environmental information and the target environmental parameters. The steps include: calculating the actual value of environmental change based on the updated environmental information and the environmental information before the environmental adjustment operation; calculating the theoretical environmental change based on the preset device influence matrix and the optimized control instruction set; comparing the actual value of environmental change with the theoretical environmental change; analyzing the difference between the actual and theoretical influence coefficients of the device based on the comparison result; and adjusting the device influence coefficients in the preset device influence matrix according to the difference using an adaptive learning algorithm.

[0075] In this embodiment, based on the updated environmental information and the environmental information before the environmental adjustment operation, the actual value of the environmental change is calculated. This step aims to objectively quantify the real response of the environment after the execution of the equipment action. For example, for temperature data, the temperature difference before and after adjustment can be directly calculated; for humidity or light data, a similar method can be used to obtain the actual change within the adjustment period. Based on the preset equipment influence matrix and the optimized control instruction set, the theoretical environmental change is calculated. The preset equipment influence matrix describes the degree and direction of influence of each executing device on different environmental factors, while the optimized control instruction set contains the specific control parameters of each device. By performing mathematical operations (e.g., matrix multiplication) between the optimized control instruction set and the preset equipment influence matrix, the theoretical change that environmental factors should produce under a given control instruction can be predicted. This step aims to establish a benchmark for expected environmental changes based on the current model prediction.

[0076] In this embodiment, the actual values ​​of environmental changes are compared with the theoretical environmental changes. This comparison aims to quantify the difference between model predictions and actual observations. Comparison methods may include calculating absolute error, relative error, or employing more complex statistical indicators to comprehensively assess the accuracy of the predictions. Based on the comparison results, the difference between the actual and theoretical influence coefficients of the equipment is analyzed. When there is a deviation between the actual environmental changes and the theoretical predictions, it indicates that one or more equipment influence coefficients in the preset equipment influence matrix may no longer be accurate. This analysis aims to identify the main equipment or equipment combinations causing the deviation, for example, by using sensitivity analysis or error attribution algorithms to determine which equipment's theoretical influence coefficients do not match their actual performance.

[0077] In this embodiment, finally, based on the differences, the device influence coefficients in the preset device influence matrix are adjusted according to an adaptive learning algorithm. The adaptive learning algorithm can take various forms, such as gradient descent, Kalman filtering, reinforcement learning, or least squares. These algorithms can iteratively correct the coefficients in the device influence matrix based on the actual observed errors, making it more accurately reflect the actual effect of the device. For example, if the theoretical heating effect of a heating device is lower than the actual heating effect, its corresponding temperature influence coefficient will be increased.

[0078] In this embodiment, through the above technical solution, this application can achieve continuous optimization and adaptive updating of the preset equipment influence matrix. This ensures that the system's ability to predict environmental changes remains highly accurate, thereby enabling the subsequently generated optimized control instruction set to more accurately and effectively guide the execution equipment to adjust to the environment. This adaptive learning mechanism improves the robustness and accuracy of the environmental control system, enabling it to better adapt to equipment aging, dynamic environmental changes, and unforeseen inter-equipment synergistic effects, ultimately achieving refined and intelligent management of the mulberry tree growth environment, effectively improving resource utilization efficiency and the growth quality of mulberry trees.

[0079] In one feasible implementation, the method further includes: collecting the environmental control history of different growth stages and their corresponding mulberry tree growth responses to analyze the sensitivity of environmental factors at each growth stage; dynamically adjusting the target environmental parameter weights for each growth stage based on the environmental factor sensitivity; updating the priority weights in the preset stage-environmental parameter mapping table based on the adjusted target environmental parameter weights; and when the same growth stage is identified again, obtaining the corresponding environmental factor priority weights from the updated preset stage-environmental parameter mapping table using the updated priority weights.

[0080] In this embodiment, the historical environmental control data and corresponding mulberry tree growth responses at different growth stages are collected to analyze the sensitivity of environmental factors at each growth stage. The aim is to quantify the specific response of mulberry trees to various environmental factors such as temperature, humidity, light, and soil moisture at different growth stages through long-term data accumulation and analysis. For example, the system can continuously record growth response data such as growth rate, leaf photosynthetic efficiency, and biomass accumulation of mulberry trees under specific combinations of temperature, humidity, light, and soil moisture. By performing statistical analysis on this historical data or using machine learning algorithms (such as regression analysis and decision tree models), it is possible to identify which environmental factors have the greatest impact on the growth of mulberry trees at a specific growth stage, thereby determining the sensitivity of mulberry trees to each environmental factor at that stage. For example, during the budding period, mulberry trees exhibit extremely high sensitivity to changes in temperature and humidity, while during the fruit enlargement period, light intensity and soil moisture become the dominant influencing factors.

[0081] In this embodiment, dynamically adjusting the weights of target environmental parameters at each growth stage based on the sensitivity of environmental factors means assigning different levels of importance or priority to these environmental factors based on the sensitivity of mulberry trees to various environmental factors at different growth stages obtained from the above analysis. For example, if the analysis results indicate that temperature and humidity are the most critical factors affecting the survival and healthy growth of mulberry trees during the seedling stage, then the system will increase the weights of these two environmental factors in the target environmental parameters during the seedling stage. This adjustment can be based on expert experience rules or optimized through adaptive learning algorithms (such as reinforcement learning) to ensure that, given limited resources, the environmental factors with the greatest impact on mulberry tree growth are prioritized.

[0082] In this embodiment, updating the priority weights in the preset stage-environment parameter mapping table based on the adjusted target environmental parameter weights means persistently storing the dynamically adjusted and optimized environmental parameter weight values ​​in the system's knowledge base. The preset stage-environment parameter mapping table can be a structured database or lookup table, containing the ideal environmental parameter ranges corresponding to each growth stage of the mulberry tree and the priority weights of various environmental factors. Through the update operation, the system ensures that its internal knowledge base always reflects the latest and verified mulberry tree growth requirements and the importance of environmental factors, providing an accurate basis for subsequent control decisions.

[0083] In this embodiment, when the same growth stage is identified again, the corresponding environmental factor priority weights are obtained from the updated preset stage-environment parameter mapping table using updated priority weights. This means that during system operation, once the image data identifies that the mulberry tree has entered a specific growth stage, the system will no longer use fixed or initially set priority weights, but will instead query and extract the latest priority weights stored in the updated stage-environment parameter mapping table for that growth stage. These updated priority weights will be directly applied to subsequent environmental deviation calculations and the generation of preliminary control instruction sets. For example, when calculating weighted environmental deviations, this ensures that the control strategy can accurately focus on the environmental factors that have the greatest impact on the mulberry tree at the current growth stage.

[0084] In this embodiment, through the above-described technical solution, the system can accurately identify the differences in the sensitivity of mulberry trees to different environmental factors at each growth stage by collecting and analyzing the environmental control history and mulberry tree growth responses at different growth stages. Based on this sensitivity analysis, the system can dynamically adjust the target environmental parameter weights of each environmental factor and update them to a preset stage-environmental parameter mapping table. When the mulberry tree re-enters the same growth stage, the system will use these optimized priority weights to guide environmental control, thereby ensuring that the control strategy can more accurately respond to the key needs of the mulberry tree at a specific growth stage. This avoids over-adjustment of non-critical factors and under-adjustment of critical factors, making environmental regulation operations more targeted and efficient, improving the precision of environmental control, promoting the healthy growth of mulberry trees, and optimizing resource utilization efficiency.

[0085] In the embodiments of this application, the IoT-based environmental dynamic control method achieves precise regulation by acquiring environmental information, identifying growth stages, calculating deviations, and generating and optimizing control commands. It can realize multi-factor collaborative precise dynamic regulation of the mulberry tree growth environment, effectively avoid control command conflicts and resource waste, and improve the stability and regulation efficiency of environmental control.

[0086] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the IoT-based environmental dynamic control method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0087] This application also provides an environmental dynamic control system based on the Internet of Things, see reference. Figure 2 The IoT-based environmental dynamic control system includes: a memory 10, a processor 20, and an IoT-based environmental dynamic control program stored on the memory 10 and executable on the processor 20. The IoT-based environmental dynamic control program is configured to implement the steps of the IoT-based environmental dynamic control method.

[0088] The IoT-based environmental dynamic control system provided in this application, employing the IoT-based environmental dynamic control method described in the above embodiments, can improve the stability and regulation efficiency of environmental control. Compared with the prior art, the beneficial effects of the IoT-based environmental dynamic control system provided in this application are the same as those of the IoT-based environmental dynamic control method provided in the above embodiments, and other technical features in the IoT-based environmental dynamic control system are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0089] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0090] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. All equivalent structural transformations made under the technical concept of this application using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included within the scope of patent protection of this application.

Claims

1. An environmental dynamic control method based on the Internet of Things, characterized in that, The method includes: The system acquires current environmental information collected by sensors and preprocesses the current environmental information to obtain standard environmental information; the current environmental information includes temperature data, humidity data, light intensity data, soil moisture data, and image data. Based on the image data, the current growth stage of the mulberry tree is identified, and the corresponding target environmental parameters are obtained from a preset database according to the current growth stage. Calculate the environmental deviation between the standard environmental information and the target environmental parameters; the environmental deviation includes the deviation value and direction of each environmental factor; Based on the environmental deviation and combined with the preset equipment influence matrix, a preliminary control instruction set is generated; the preliminary control instruction set includes control parameters for at least two devices. Based on the preset device influence matrix, the preliminary control instruction set is subjected to collaborative conflict detection to generate conflict detection results. Based on the conflict detection results, the preliminary control instruction set is adjusted to obtain an optimized control instruction set. The optimized control instruction set is sent to the execution device to control the execution device to perform environmental adjustment operations; After the execution device performs the environmental adjustment operation, it reacquires the updated environmental information collected by the sensor, and updates the preset device influence matrix based on the comparison result between the updated environmental information and the target environmental parameters. The steps for performing collaborative conflict detection on the preliminary control instruction set based on the preset device influence matrix and generating conflict detection results include: Based on the preset device influence matrix, a device collaborative influence relationship network is constructed. Based on the aforementioned equipment collaborative influence relationship network, the mutual influence between the control parameters of each equipment in the preliminary control instruction set is analyzed. Based on the results of the interaction analysis, identify equipment combinations that may produce offsetting effects; Based on a pre-trained energy consumption assessment model, identify combinations of devices whose energy consumption exceeds a preset threshold; The collision detection result is generated by combining the device combinations that may produce a counteracting effect with the device combinations whose energy consumption exceeds a preset threshold. The steps for adjusting the preliminary control instruction set based on the conflict detection results to obtain the optimized control instruction set include: Based on the conflict detection results, the control parameters of the device that caused the conflict are determined; Based on preset device substitution relationships, at least two alternative device schemes are generated for the conflicting device control parameters; Based on a pre-trained digital twin environment model, a pre-execution simulation is performed on each of the alternative device schemes to generate simulation execution results; Based on the simulation results, evaluate the overall performance score of each alternative equipment solution; Based on the comprehensive performance score, the alternative equipment scheme with the highest score is selected, and the corresponding control parameters in the preliminary control instruction set are replaced to generate the optimized control instruction set.

2. The IoT-based dynamic environmental control method as described in claim 1, characterized in that, The steps of identifying the current growth stage of the mulberry tree based on the image data and obtaining the corresponding target environmental parameters from a preset database according to the current growth stage include: Key features of mulberry trees are extracted from the image data, including bud morphology, leaf spread, and leaf color. The key features of the mulberry tree are matched with a preset growth stage feature library, and the current growth stage of the mulberry tree is determined based on the matching results. Based on the current growth stage, basic environmental parameters are obtained from a preset stage-environment parameter mapping table; Based on the historical environmental regulation effect, the basic environmental parameters are dynamically adjusted to generate the target environmental parameters.

3. The IoT-based dynamic environmental control method as described in claim 1, characterized in that, Based on the aforementioned environmental deviation and in conjunction with a preset equipment influence matrix, the steps for generating a preliminary control instruction set include: Based on the current growth stage, obtain the corresponding environmental factor priority weights; Calculate the weighted environmental deviation based on the environmental deviation and the priority weights of the environmental factors; Based on the preset equipment influence matrix, candidate equipment capable of adjusting the environmental factors corresponding to the weighted environmental deviation is identified; Based on the weighted environmental deviation and the influence coefficient of each device in the candidate devices, the theoretical control strength of each candidate device is calculated; The theoretical control strength is converted into control parameters that can be executed by the device, forming the preliminary control instruction set.

4. The IoT-based dynamic environmental control method as described in claim 1, characterized in that, The steps for pre-executing simulations of each alternative device scheme based on a pre-trained digital twin environment model and generating simulation results include: The current environmental state and alternative equipment options are input into the pre-trained digital twin environment model; Based on the preset environmental factor coupling relationship and device interaction influence, the alternative device scheme is simulated and executed in the pre-trained digital twin environment model; Simulate the environmental state change process at multiple time steps to predict the final environmental state; Calculate the comprehensive deviation between the predicted final environmental state and the target environmental parameters.

5. The IoT-based dynamic environmental control method as described in claim 4, characterized in that, Based on the simulation results, the steps for evaluating the overall performance score of each alternative device scheme include: Based on the comprehensive deviation, the environmental regulation effect score is calculated; Based on the pre-trained energy consumption assessment model, the energy consumption score of the alternative equipment scheme is calculated; Based on a pre-trained equipment life prediction model, calculate the equipment wear score; The comprehensive performance score is calculated based on the environmental regulation effect score, the energy consumption score, and the equipment wear score, according to preset weights.

6. The IoT-based dynamic environmental control method as described in claim 1, characterized in that, After the execution device performs an environmental adjustment operation, the step of reacquiring updated environmental information collected by the sensors and updating the preset device influence matrix based on the comparison result of the updated environmental information and the target environmental parameters includes: Based on the updated environmental information and the environmental information before the environmental adjustment operation, the actual value of the environmental change is calculated; Based on the preset equipment influence matrix and the optimized control instruction set, the theoretical environmental changes are calculated. Compare the actual values ​​of the environmental changes with the theoretical environmental changes; Based on the comparison results, analyze the difference between the actual influence coefficient and the theoretical influence coefficient of the equipment; Based on the aforementioned differences, the device influence coefficients in the preset device influence matrix are adjusted according to an adaptive learning algorithm.

7. The IoT-based dynamic environmental control method as described in claim 1, characterized in that, The method further includes: The history of environmental control at different growth stages and the corresponding mulberry tree growth responses were collected to analyze the sensitivity of environmental factors at each growth stage. Based on the sensitivity to the environmental factors, the weights of the target environmental parameters for each growth stage are dynamically adjusted. Based on the adjusted target environment parameter weights, update the priority weights in the preset stage-environment parameter mapping table; When the same growth stage is identified again, the corresponding environmental factor priority weight is obtained from the updated preset stage-environment parameter mapping table using the updated priority weight.

8. An environmental dynamic control system based on the Internet of Things, characterized in that, The IoT-based environmental dynamic control system includes: a memory, a processor, and an IoT-based environmental dynamic control program stored in the memory and executable on the processor, wherein the IoT-based environmental dynamic control program is configured to implement the steps of the IoT-based environmental dynamic control method as described in any one of claims 1 to 7.

Images