Greenhouse control instruction decision method and related device

Abstract

This application provides a method and related equipment for greenhouse control command decision-making, belonging to the field of greenhouse automatic control technology. The method includes: performing environmental deviation analysis based on various environmental indicator data within the greenhouse to determine environmental deviation results; the environmental deviation results include the deviation degree of each environmental indicator data; detecting control conflicts based on the environmental deviation results, and, in the presence of control conflicts, identifying the crop growth stage based on greenhouse crop images to obtain the current crop growth stage; querying indicator weights based on the crop growth stage to obtain the control weights of each conflicting indicator; determining the priority indicator score of the conflicting indicator based on the control weight and deviation degree of the conflicting indicator; and making a priority adjustment decision for each conflicting indicator based on the priority indicator score to determine the greenhouse control command. This application can improve the efficiency and effectiveness of greenhouse environmental control.

Description

Technical Field

[0001] This application relates to the field of greenhouse automatic control technology, and in particular to a greenhouse control command decision-making method and related equipment. Background Technology

[0002] Current automated control systems for greenhouses mostly rely on threshold judgments of single environmental parameters (such as soil moisture and air temperature) to trigger corresponding control devices. However, this method ignores the inherent coupling relationship between environmental factors, which can easily lead to conflicting effects from different control commands and make it impossible to efficiently adjust the greenhouse environment to a suitable one for growth. Summary of the Invention

[0003] The main objective of this application is to propose a greenhouse control command decision-making method and related equipment, which aims to improve the efficiency and effectiveness of greenhouse environmental control.

[0004] To achieve the above objectives, one aspect of this application proposes a greenhouse control command decision-making method, comprising the following steps: An environmental deviation analysis was conducted based on the environmental indicator data within the greenhouse to determine the environmental deviation results; the environmental deviation results include the degree of deviation of each environmental indicator data. Based on the environmental deviation results, control conflict detection is performed, and in the case of control conflict, crop growth stage is identified based on greenhouse crop images to obtain the current crop growth stage. Based on the crop growth stage, the indicator weights are queried to obtain the control weights of each conflicting indicator. Based on the control weight and deviation of the conflict indicators, the priority indicator score of the conflict indicators is determined; Based on the priority index scores, priority adjustment decisions are made for each conflict index to determine the greenhouse control instructions.

[0005] In some embodiments, the step of performing environmental deviation analysis based on various environmental indicator data within the greenhouse to determine the environmental deviation results includes the following steps: Calculate the difference between each environmental indicator data and the corresponding standard value and normalize it to obtain the deviation of the environmental indicator data; The environmental deviation results are generated based on the deviation of various environmental indicator data.

[0006] In some embodiments, the control conflict detection based on the environmental deviation results includes the following steps: The test determines whether at least two environmental indicator data points in the environmental deviation results have a deviation greater than a deviation threshold. If at least two environmental indicator data deviate from the deviation threshold, a control conflict is determined, and the environmental indicators that deviate from the deviation threshold are identified as conflict indicators. If no two environmental indicator data deviate from the deviation threshold, it is determined that there is no control conflict, and the environmental indicator that deviates from the deviation threshold is determined as the target indicator.

[0007] In some embodiments, the greenhouse control command decision-making method further includes the following steps: In the absence of control conflicts, greenhouse control instructions are determined based on the target indicators.

[0008] In some embodiments, the step of identifying the crop growth stage based on greenhouse crop images to obtain the current crop growth stage includes the following steps: Obtain a trained image classification model based on a convolutional neural network; The greenhouse crop image is input into the image classification model for growth stage classification and identification to obtain the current crop growth stage.

[0009] In some embodiments, determining the greenhouse control instruction by prioritizing and adjusting each conflicting indicator based on the priority indicator score includes the following steps: Based on the conflicting indicator with the highest priority index score and the corresponding environmental indicator data, the environmental indicator adjustment requirements are determined. Based on the aforementioned indicators, control action decisions are made to adjust the requirements, resulting in greenhouse control commands.

[0010] To achieve the above objectives, another aspect of this application proposes a greenhouse control command decision system, comprising: The deviation perception module is used to perform environmental deviation analysis based on various environmental indicator data in the greenhouse and determine the environmental deviation results; the environmental deviation results include the deviation degree of various environmental indicator data. The conflict detection and growth recognition module is used to detect control conflicts based on the environmental deviation results, and, in the presence of control conflicts, to identify the crop growth stage based on the greenhouse crop image to obtain the current crop growth stage. The weight query module is used to query the indicator weights based on the crop growth stage to obtain the control weights of each conflicting indicator. The priority calculation module is used to determine the priority score of the conflict index based on the control weight and deviation of the conflict index. The priority adjustment decision module is used to make priority adjustment decisions on each of the conflicting indicators based on the priority indicator scores, and to determine the greenhouse control instructions.

[0011] To achieve the above objectives, another aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method.

[0012] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0013] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0014] The embodiments of this application include at least the following beneficial effects: This application provides a greenhouse control command decision-making method, system, electronic device, storage medium, and program product. This solution first performs environmental deviation analysis based on various environmental indicator data within the greenhouse to determine the environmental deviation results. The environmental deviation results include the deviation degree of each environmental indicator data. Then, control conflict detection is performed based on the environmental deviation results. If a control conflict exists, the crop growth stage is identified based on the greenhouse crop image to obtain the current crop growth stage. Next, the indicator weights are queried based on the crop growth stage to obtain the control weights of each conflicting indicator that matches the growth stage. The priority indicator scores of the conflicting indicators are determined based on the control weights and deviation degrees. Then, based on the priority indicator scores, priority adjustment decisions are made for each conflicting indicator to determine the priority greenhouse control command to be executed, thereby avoiding control conflicts. Furthermore, the decision-making of this greenhouse control command considers the crop growth stage and the deviation degree of different conflicting indicators for selection and decision-making, which can meet the environmental needs of the crop at the current stage and improve the efficiency and effectiveness of greenhouse environmental control. Attached Figure Description

[0015] Figure 1 This is a flowchart of the greenhouse control command decision-making method provided in the embodiments of this application; Figure 2 yes Figure 1 The flowchart of step S101 in the text; Figure 3 yes Figure 1 The flowchart for controlling collision detection in step S102; Figure 4 This is a flowchart of a greenhouse control command decision-making method provided in another embodiment of this application; Figure 5 yes Figure 1 The flowchart for crop growth stage identification in step S102; Figure 6 yes Figure 1The flowchart of step S105 in the process; Figure 7 This is a schematic diagram of the system architecture provided in the embodiments of this application; Figure 8 This is a schematic diagram of the greenhouse control command decision system provided in the embodiments of this application; Figure 9 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0016] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0017] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0018] Current automated control systems for greenhouses largely rely on threshold judgments of single environmental parameters (such as soil moisture and air temperature) to trigger corresponding control devices. However, this method ignores the inherent coupling relationships between environmental factors, easily leading to conflicting effects from different control commands. For example, based on current environmental parameters indicating a high-temperature and low-humidity environment, the system might activate fans to lower the temperature to address the high temperature, while simultaneously shutting down fans and activating misting to increase humidity to address the low humidity. These conflicting commands fail to efficiently adjust the greenhouse environment to a suitable state for growth.

[0019] In view of this, this application provides a greenhouse control command decision-making method and related equipment. This scheme detects control conflicts based on environmental deviation results, and when control conflicts exist, identifies the crop growth stage based on the greenhouse crop image to obtain the current crop growth stage. Then, it queries the index weights based on the crop growth stage to obtain the control weights of each conflict index that matches the growth stage. Based on the control weights and deviations of the conflict indexes, it determines the priority index scores of the conflict indexes. Then, based on the priority index scores, it makes a priority adjustment decision for each conflict index to determine the priority greenhouse control command to be executed, thereby avoiding control conflicts. Moreover, the decision-making of this greenhouse control command takes into account the crop growth stage and the deviation of different conflict indexes for selection and decision, which can meet the environmental needs of the crop at the current stage and improve the efficiency and effectiveness of greenhouse environmental control.

[0020] The greenhouse control command decision-making method provided in this application relates to the field of greenhouse automatic control technology. The greenhouse control command decision-making method provided in this application can be applied to a terminal, a server, or software running on a terminal or server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or vehicle terminal, but is not limited to these. The server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network. The software can be an application implementing the greenhouse control command decision-making method, but is not limited to the above forms.

[0021] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0022] Figure 1 This is an optional flowchart of the greenhouse control command decision-making method provided in the embodiments of this application. Figure 1 The method may include, but is not limited to, steps S101 to S105.

[0023] S101, Based on the environmental indicator data in the greenhouse, conduct environmental deviation analysis to determine the environmental deviation results; the environmental deviation results include the degree of deviation of each environmental indicator data. S102, based on the environmental deviation results, control conflict detection is performed, and in the case of control conflict, crop growth stage is identified based on the greenhouse crop image to obtain the current crop growth stage; S103, query the index weights according to the crop growth stage to obtain the control weights of each conflicting index; S104. Based on the control weight and deviation of the conflict indicators, determine the priority indicator score of the conflict indicators. S105, based on the priority index scores, makes priority adjustment decisions on each conflicting index to determine the greenhouse control instructions.

[0024] Steps S101 to S105 of this embodiment involve analyzing environmental deviations based on various environmental indicator data within the greenhouse to determine environmental deviation results, including the deviation degree of each environmental indicator data. Then, control conflict detection is performed based on the environmental deviation results. If a control conflict exists, the crop growth stage is identified based on the greenhouse crop image to obtain the current crop growth stage. Next, indicator weights are queried based on the crop growth stage to obtain the control weights of each conflicting indicator that matches the growth stage. Priority indicator scores for the conflicting indicators are determined based on their control weights and deviation degrees. Finally, priority adjustment decisions are made for each conflicting indicator based on its priority indicator score to determine the priority greenhouse control command to be executed, thereby avoiding control conflicts. Furthermore, the decision-making process for this greenhouse control command considers the crop growth stage and the deviation degree of different conflicting indicators, which can meet the environmental needs of the crop at the current stage and improve the efficiency and effectiveness of greenhouse environmental control.

[0025] In step S101 of some embodiments, a sensor network deployed inside and outside the greenhouse can synchronously collect various environmental indicator data within the greenhouse, as well as crop data and meteorological data. The various environmental indicator data within the greenhouse can be collected using multi-sensor cameras, including but not limited to air temperature, air humidity, light intensity, carbon dioxide concentration, and soil fertility. Meteorological data can be collected using miniature weather stations, including but not limited to information on atmospheric wind speed, wind direction, and rainfall. Crop data can be collected using high-definition network cameras, specifically capturing images of the crop canopy within the greenhouse, which can then be used to identify the current growth stage of the crop. Environmental deviation analysis can be performed by analyzing the deviations of environmental indicator data such as air humidity, air temperature, and light intensity from preset crop environmental indicator standards.

[0026] In step S102 of some embodiments, control conflict detection is performed based on the environmental deviation results. Control conflict detection can be measured by detecting whether two or more environmental indicators need to be adjusted simultaneously. If two or more environmental indicators need to be adjusted simultaneously, a control conflict may occur. For example, adjusting one environmental indicator requires turning on the fan, while another may require turning off the fan, thus a control conflict occurs. Whether an environmental indicator needs adjustment can be determined by the deviation of the current environmental indicator data.

[0027] If a control conflict is identified, the crop growth stage is determined based on the acquired greenhouse crop images to obtain the current crop growth stage. In this embodiment, crop growth stage identification can employ image processing classification methods such as feature extraction combined with machine learning classifiers, image feature description combined with rule-based judgment, or neural network algorithms. Crop growth stages can include budding, flowering, and fruit enlargement stages.

[0028] In step S103 of some embodiments, different control weights are assigned to different factors such as temperature, humidity, and light intensity according to different growth stages of the crop. The weight mapping relationship can be represented as a weight matrix W, as detailed in Table 1: Table 1

[0029] For example, after determining the crop growth stage to be the flowering period through image analysis, the conflict indicators are air temperature and air humidity. The control weight of the queried air temperature indicator is 0.7, and the control weight of the air humidity indicator is 0.9.

[0030] In step S104 of some embodiments, the priority score of the conflict index is determined based on the control weight and deviation of the conflict index. The dynamic priority score is a dimensionless value used to quantify the urgency of each control objective (i.e., the adjustment requirement corresponding to the conflict index). It is calculated based on the control weight and real-time deviation of environmental factors queried during the crop growth stage. This score is the direct basis for subsequent conflict arbitration.

[0031] Specifically, the priority indicator score P can be calculated using the following formula: P=W*D, where W represents the control weight and D represents the deviation.

[0032] In step S105 of some embodiments, the priority adjustment decision may be to select the conflicting indicator with the highest priority index score to determine the adjustment requirement, thereby determining the greenhouse control instruction; alternatively, a model knowledge base may be used to conduct a benefit analysis and comparison of the adjustment requirements corresponding to each conflicting indicator based on the crop growth stage. If the adjustment requirement of the conflicting indicator with the lower priority index score does indeed affect the adjustment effect of the adjustment requirement of the conflicting indicator with the higher priority index score, then the conflicting indicator with the higher priority index score is selected to determine the greenhouse control instruction; otherwise, multiple conflicting indicators whose adjustment effects do not affect each other can be combined to determine the greenhouse adjustment instruction. The greenhouse adjustment instruction in this application embodiment is a collaborative control instruction that considers the crop growth stage and the conflict of indicator adjustments.

[0033] For example, when high temperature D(T) and low humidity D(H) conflict, since the humidity weight W(H) = 0.9 is higher than the temperature weight W(H) = 0.7 during the flowering period, and high temperature exacerbates the harm of low humidity, the humidity control P(H) will be significantly higher than P(T). The system will abandon ventilation cooling and prioritize misting humidification, because while humidifying, water mist evaporation can also have a partial cooling effect, which meets the core needs of the flowering period. The model is used to verify whether multiple indicators can be improved simultaneously with a single command, such as "mist humidification" in the example above, which also partially solves the "high temperature" problem. The generated collaborative control command is as follows: { Priority: High Action: Activate the fog system Duration: t seconds Expected results: Humidity increases to >75%, temperature decreases to <32℃ }

[0034] The coordinated control command is sent to the IoT smart control cabinet to drive the actuator. The environmental changes after execution are captured again by the sensors, forming a closed-loop feedback, which can be used to optimize the relevant model algorithm parameters (such as the model algorithm parameters used for action decision) and weight matrix involved in the above process.

[0035] This application embodiment uses image recognition technology to determine the crop growth stage and uses this as a key variable to dynamically adjust the decision weights of different environmental control objectives, thereby resolving conflicts between multiple control objectives, achieving collaborative optimization, solving the problem of resource consumption in greenhouse environmental control, and achieving simultaneous improvement in crop yield and resource utilization efficiency.

[0036] In some embodiments, please refer to Figure 2 Step S101 may include, but is not limited to, the following steps: S201, Calculate the difference between each environmental indicator data and the corresponding standard value and normalize it to obtain the deviation of the environmental indicator data; S202, based on the deviation of various environmental indicator data, forms the environmental deviation results.

[0037] In this embodiment, the original environmental indicator data, which may have different dimensions, are converted into a unified and comparable deviation value by calculating the difference from the standard value and normalizing it, and finally forming a comprehensive environmental deviation result, thereby achieving accurate conflict detection in the future.

[0038] In some embodiments, please refer to Figure 3 The control conflict detection based on the environmental deviation results in step S102 may include, but is not limited to, the following steps: S301, Check whether there are at least two environmental indicator data in the environmental deviation results that have a deviation greater than the deviation threshold; S302, If at least two environmental indicator data have a deviation greater than the deviation threshold, then a control conflict is determined, and the environmental indicators with a deviation greater than the deviation threshold are identified as conflict indicators. S303 If there are no at least two environmental indicator data whose deviation is greater than the deviation threshold, then it is determined that there is no control conflict, and the environmental indicator whose deviation is greater than the deviation threshold is determined as the target indicator.

[0039] In this embodiment, a uniform deviation threshold can be set, or different deviation thresholds can be set for each environmental indicator based on the different deviation requirements of different environmental indicators. The deviation threshold can be a fixed value, or it can be adaptively updated based on environmental feedback after the greenhouse control action interacts with the greenhouse, thereby improving the accuracy of detecting indicators that need adjustment. This embodiment performs conflict detection by the number of deviations in environmental indicator data. This method has a simple algorithm and can improve conflict detection efficiency. At the same time, based on the environmental indicator data that exceeds the deviation threshold, the indicators that need adjustment are initially determined, which facilitates subsequent targeted control command decisions and improves the effect of greenhouse environmental adjustment.

[0040] For example, a real-time sensor data vector S=(T,H,SM,L,EC) is acquired, where each factor in the vector represents air temperature, air humidity, soil moisture, light intensity, and fertility data, respectively. The deviation D of each factor is calculated using the following formula: D = |S - Si| / S_range; Where Si is the standard value of environmental indicator i, S is the collected data of environmental indicator i, and S_range is the range of values ​​for environmental indicator i. The factors are made dimensionless so that all deviations can be compared and calculated on the same dimension.

[0041] If two or more factors have a deviation threshold D greater than the deviation threshold, a control conflict is determined to have occurred.

[0042] In some embodiments, please refer to Figure 4 The greenhouse control command decision-making method in this application embodiment may also include, but is not limited to, the following steps: S401, in the absence of control conflicts, determine the greenhouse control instructions based on the target indicators.

[0043] In this embodiment, assuming no control conflicts, all environmental indicators may deviate within the deviation threshold, while one indicator may deviate beyond it. In this case, the system identifies the indicator exceeding the threshold as the target indicator and directly determines the greenhouse control command based on it. For example, the target indicator might be air temperature. Environmental data analysis shows the current temperature is higher than the standard air temperature; therefore, the target indicator requires cooling. Based on this cooling requirement, the greenhouse control command can be determined using methods such as action mapping or model decision-making, thereby achieving greenhouse cooling. In this embodiment, if any environmental indicator data shows excessive deviation, a suitable greenhouse control command is output to achieve real-time adjustment of the greenhouse environment, thereby improving crop growth. In some embodiments, please refer to Figure 5 Step S102, which involves identifying the crop growth stage based on the greenhouse crop image to determine the current crop growth stage, may include, but is not limited to, the following steps: S501, Obtain the trained image classification model based on convolutional neural network; S502, input the greenhouse crop image into the image classification model to classify and identify the growth stage, and obtain the current crop growth stage.

[0044] In this embodiment, neural network models such as VGG, ResNet, and MobileNet are trained on a large-scale crop image dataset, enabling the trained image classification model to extract image features and identify crop growth stages. In practical applications, greenhouse crop images are input into the trained image classification model for forward propagation. The model extracts image features layer by layer, and finally outputs a probability distribution through fully connected layers and a Softmax function, representing the likelihood that the greenhouse crop image belongs to each growth stage category (such as budding, flowering, and fruit enlargement stages). The category with the highest probability is then selected as the final classification result. This CNN-based image classification system can achieve 24 / 7 uninterrupted automatic identification, thereby enabling continuous coordinated adjustment of the greenhouse environment.

[0045] In some embodiments, please refer to Figure 6 Step S105 may include, but is not limited to, the following steps: S601, Based on the conflicting indicator with the highest priority indicator score and the corresponding environmental indicator data, determine the environmental indicator adjustment requirements; S602 makes control action decisions based on indicator adjustment needs and obtains greenhouse control instructions.

[0046] In this embodiment, taking air temperature and air humidity as conflicting indicators, the priority score for air temperature is 0.525, and the priority score for air humidity is 1.575. Air humidity has a higher priority score, and based on the magnitude of the air humidity data, the current greenhouse environment is determined to be low-humidity. Accordingly, the environmental indicator adjustment requirement is to increase air humidity. The system performs instruction mapping based on the humidity increase requirement (which can be achieved through knowledge base regulation mapping or a decision model) to determine the greenhouse control instructions. These instructions may include, but are not limited to, instruction priority, execution action, execution time, and expected effect. The execution time can be comprehensively determined based on the deviation of various environmental indicators and meteorological data. For example, if meteorological data indicates that rain is likely in the future, the humidification time can be shortened to prevent the greenhouse environment from becoming excessively humid due to the combined effects of greenhouse humidification and atmospheric humidity. This embodiment selects the conflicting indicator with the highest priority score to calculate the environmental indicator adjustment requirement, thus avoiding control conflicts. By combining the current environmental indicator data with the calculated environmental indicator adjustment requirement, the greenhouse environment can efficiently achieve the desired environment.

[0047] According to some embodiments of this application, please refer to Figure 7 The system architecture diagram shown illustrates the greenhouse environment adjustment process in this application embodiment, using a tomato greenhouse in early summer afternoon when the crop is in the flowering stage as an example: First, data was collected by various sensors in the sensing layer, including: soil moisture 45%; air temperature 35.5℃; air humidity 30%; high light intensity; images of greenhouse crops; and a weather station report: instantaneous wind speed increased, but no rainfall.

[0048] Then, the decision-making level makes decisions on greenhouse control instructions, as follows: The system performs control conflict detection. The temperature deviation D(T) = |35.5-28| / 10 = 0.75; the humidity deviation D(H) = |30-65| / 20 = 1.75, both exceeding the deviation threshold of 0.3, thus confirming a control conflict. In this situation, the traditional decision-making process would simultaneously activate the fan (for cooling) and the misting system (for humidification), resulting in moisture removal, increased energy consumption, and poor effectiveness.

[0049] The crop growth stage recognition module is used to identify images of greenhouse crops and determine whether the crops are in the flowering stage.

[0050] Using the dynamic weight decision module, the control weights for air humidity (W(H) = 0.9) and air temperature (W(T) = 0.7) are obtained by querying the weight matrix based on the growth stage during the flowering period. Priority index scores are then calculated: air humidity priority index score P(H) = 0.9 * 1.75 = 1.575, and air temperature priority index score P(T) = 0.7 * 0.75 = 0.525.

[0051] Command Decision: The command decision process considers the priority of indicators, indicator scores, and the realization of the model knowledge base, i.e., P(H) is greater than P(T). According to the model knowledge base analysis, high temperature accompanied by low humidity during the flowering period is the main cause of pollen abortion, and the benefit of maintaining stable humidity is far greater than cooling. Therefore, the decision is not to start the fan to avoid further reduction in humidity, but to start the misting system.

[0052] The execution layer receives a coordinated control command after executing a decision, initiating misting for 5 seconds, with intermittent operation. Ten minutes later, the execution layer reports back on the greenhouse environment: humidity has risen to 68%, while the temperature has dropped to 33.2℃ due to moisture evaporation. The system determines that the humidification requirement has been met and stops misting. Although the temperature has not yet fully reached the target, it is now outside the danger zone, minimizing crop stress.

[0053] Please refer to Figure 8 This application also provides a greenhouse control command decision system, including: The deviation perception module is used to perform environmental deviation analysis based on various environmental indicator data in the greenhouse and determine the environmental deviation results; the environmental deviation results include the deviation degree of each environmental indicator data. The conflict detection and growth recognition module is used to detect control conflicts based on environmental deviation results, and in the presence of control conflicts, to identify the crop growth stage based on greenhouse crop images to obtain the current crop growth stage. The weight query module is used to query the weight of indicators based on the crop growth stage and obtain the control weight of each conflicting indicator. The priority calculation module is used to determine the priority score of conflicting indicators based on their control weights and deviations. The priority adjustment decision module is used to make priority adjustment decisions on each conflicting indicator based on the priority indicator score, and to determine the greenhouse control instructions.

[0054] It is understood that the methods described in the above method embodiments are applicable to this system embodiment. The specific functions implemented in this system embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0055] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method described above. This electronic device can be any smart terminal, including a tablet computer.

[0056] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0057] Please see Figure 9 , Figure 9 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 901 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 902 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 902 and is called and executed by the processor 901. The input / output interface 903 is used to implement information input and output; The communication interface 904 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 905 transmits information between various components of the device (e.g., processor 901, memory 902, input / output interface 903, and communication interface 904); The processor 901, memory 902, input / output interface 903, and communication interface 904 are connected to each other within the device via bus 905.

[0058] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0059] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0060] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0061] It is understood that the content of the above method embodiments is applicable to the embodiments of this program product. The specific functions implemented by the embodiments of this program product are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0062] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0063] The greenhouse control command decision-making method and related equipment provided in this application have at least one of the following beneficial effects: (1) In this embodiment, the visual recognition results of crop growth stages are used as the core input variables of the environmental control decision-making process, so that the control system changes from environment-driven to crop demand-driven. The system can understand the changes in the physiological needs of crops at different growth stages, thus laying the foundation for subsequent precise decision-making. This is the premise for achieving refined control.

[0064] (2) In this embodiment, a weight matrix is ​​used to define the basic weights of different control objectives at each growth stage. The normalized deviation of environmental factors is calculated in real time, and dynamic priority scores are calculated and compared to arbitrate control conflicts. This approach simulates the decision-making thinking of agricultural experts when facing complex situations, and can intelligently select the operation most beneficial to the crop at the current time. For example, when facing the conflict of high temperature and low humidity during the flowering period, humidity is prioritized, avoiding the waste of resources and the cancellation of effects caused by the simultaneous operation of traditional systems.

[0065] (3) Based on the arbitration results, the system generates collaborative control instructions that can simultaneously optimize multiple environmental indicators, and realizes the linkage execution of multiple devices through the Internet of Things intelligent control cabinet, thereby achieving the synergistic effect of greenhouse planting and greatly improving resource utilization efficiency. For example, in the actual application of tomato planting, this solution significantly improves the fruit setting rate and yield while saving water resources and electricity.

[0066] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0067] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0068] The system embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0069] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0070] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or modules is not necessarily limited to those steps or modules explicitly listed, but may include other steps or modules not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0071] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0072] In the embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0073] The modules described above as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0074] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0075] If the integrated module is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0076] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A greenhouse control command decision-making method, characterized in that, Includes the following steps: Environmental deviation analysis is conducted based on various environmental indicator data within the greenhouse to determine the environmental deviation results; the environmental deviation results include the degree of deviation of each environmental indicator data. Based on the environmental deviation results, control conflict detection is performed, and in the case of control conflict, crop growth stage is identified based on greenhouse crop images to obtain the current crop growth stage. Based on the crop growth stage, the indicator weights are queried to obtain the control weights of each conflicting indicator. Based on the control weight and deviation of the conflict indicators, the priority indicator score of the conflict indicators is determined; Based on the priority index scores, priority adjustment decisions are made for each conflict index to determine the greenhouse control instructions.

2. The greenhouse control command decision-making method according to claim 1, characterized in that, The environmental deviation analysis based on various environmental indicator data within the greenhouse, and the determination of the environmental deviation results, includes the following steps: Calculate the difference between each environmental indicator data and the corresponding standard value and normalize it to obtain the deviation of the environmental indicator data; The environmental deviation results are generated based on the deviation of various environmental indicator data.

3. The greenhouse control command decision-making method according to claim 1, characterized in that, The control conflict detection based on the environmental deviation results includes the following steps: The test determines whether at least two environmental indicator data points in the environmental deviation results have a deviation greater than a deviation threshold. If at least two environmental indicator data deviate from the deviation threshold, a control conflict is determined, and the environmental indicators that deviate from the deviation threshold are identified as conflict indicators. If no two environmental indicator data deviate from the deviation threshold, it is determined that there is no control conflict, and the environmental indicator that deviates from the deviation threshold is determined as the target indicator.

4. The greenhouse control command decision-making method according to claim 3, characterized in that, The greenhouse control command decision-making method also includes the following steps: In the absence of control conflicts, greenhouse control instructions are determined based on the target indicators.

5. The greenhouse control command decision-making method according to claim 1, characterized in that, The process of identifying the crop growth stage based on greenhouse crop images to determine the current crop growth stage includes the following steps: Obtain a trained image classification model based on a convolutional neural network; The greenhouse crop image is input into the image classification model for growth stage classification and identification to obtain the current crop growth stage.

6. The greenhouse control command decision-making method according to claim 1, characterized in that, The step of prioritizing and adjusting each conflicting indicator based on the priority indicator score to determine the greenhouse control instruction includes the following steps: Based on the conflicting indicator with the highest priority index score and the corresponding environmental indicator data, the environmental indicator adjustment requirements are determined. Based on the aforementioned indicators, control action decisions are made to adjust the requirements, resulting in greenhouse control instructions.

7. A greenhouse control command decision system, characterized in that, include: The deviation perception module is used to perform environmental deviation analysis based on various environmental indicator data in the greenhouse and determine the environmental deviation results; the environmental deviation results include the deviation degree of each environmental indicator data. The conflict detection and growth recognition module is used to detect control conflicts based on the environmental deviation results, and, in the presence of control conflicts, to identify the crop growth stage based on the greenhouse crop image to obtain the current crop growth stage. The weight query module is used to query the indicator weights based on the crop growth stage to obtain the control weights of each conflicting indicator. The priority calculation module is used to determine the priority score of the conflict index based on the control weight and deviation of the conflict index. The priority adjustment decision module is used to make priority adjustment decisions on each of the conflicting indicators based on the priority indicator scores, and to determine the greenhouse control instructions.

8. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.

Images