Plant growth environment regulation and control method and device, electronic equipment and storage medium

Abstract

The invention provides a plant growth environment regulation and control method and device, electronic equipment and a storage medium. The plant growth environment regulation and control method comprises the steps that environment information of a target plant growth environment is acquired through a multi-sensor network, and the environment information comprises indoor environment parameters in a first preset time period before the current moment and outdoor environment parameters at least at the current moment; obtaining the operation state of related equipment used for changing the environment information in the target plant growth environment; according to the environment information and the operation state, predicting predicted environment parameters in a second preset time period in the future; on the basis of the predicted environment parameters and the current growth stage of the target plant, predicted equipment operation information of the related equipment is determined, and the predicted equipment operation information comprises equipment control actions of at least one piece of related equipment; and controlling related equipment based on the predicted equipment operation information. According to the scheme, the plant growth environment can be more reasonably regulated and controlled.

Description

Technical Field

[0001] This invention relates to the field of intelligent planting technology, specifically to a method for regulating the plant growth environment, a device for regulating the plant growth environment, electronic equipment, storage media, and computer program products. Background Technology

[0002] In recent years, with the development of facility agriculture and smart agriculture, greenhouse environmental control systems have gradually transitioned from manual, experience-based regulation to automated and intelligent control. By providing a controllable growing environment, greenhouse environmental control systems effectively mitigate the adverse effects of weather changes on crop growth, significantly increasing crop yields.

[0003] Traditional greenhouse environmental control methods primarily rely on experience and basic automated equipment, such as threshold-based or rule-based control. This approach lacks flexibility and cannot handle the complex coupling relationships between different environmental factors. While model-based greenhouse environmental control exists, it depends heavily on model accuracy, and the model may even output invalid solutions, negatively impacting greenhouse environmental control.

[0004] Therefore, a more reasonable method is needed to control the greenhouse environment, so as to provide a good growth environment for the plants in the greenhouse. Summary of the Invention

[0005] The present invention was proposed in view of the above-mentioned problems.

[0006] According to a first aspect of the present invention, a method for regulating the plant growth environment is provided. The method includes: acquiring environmental information of the target plant's growth environment using a multi-sensor network, wherein the environmental information includes indoor environmental parameters for a first preset time period prior to the current moment and outdoor environmental parameters at least at the current moment; acquiring the operating status of relevant devices within the target plant's growth environment for modifying the environmental information; predicting predicted environmental parameters for a future second preset time period based on the environmental information and the operating status; determining predicted device operating information of the relevant devices based on the predicted environmental parameters and the current growth stage of the target plant, wherein the predicted device operating information includes device control actions of at least one relevant device; and controlling the relevant devices based on the predicted device operating information.

[0007] For example, the environmental information is multiple, and the step of predicting the predicted environmental parameters in the second preset time period based on the environmental information and the operating status includes: for each type of environmental information, calculating the mean of that type of environmental information in the first preset time period; standardizing the mean of all environmental information by Z-score to obtain the standardized result of each type of environmental information; and predicting the predicted environmental parameters based on the standardized result of each type of environmental information and the operating status.

[0008] For example, predicting the predicted environment parameters based on the standardization results and the operating state includes: unifying the standardization results of each type of environment information and the time steps corresponding to the operating state; determining a sliding window matrix based on the time features corresponding to the time steps, the standardization results after unifying the time steps, and the operating state; and inputting the sliding window matrix into the time series prediction model to output the predicted environment parameters.

[0009] For example, determining the predictive equipment operation information of the relevant equipment based on the predicted environmental parameters and the current growth stage of the target plant includes:

[0010] The target difference between the suitable environmental information of the target plant at its current growth stage and the predicted environmental parameters is determined. Based on the target difference, the current growth stage of the target plant, and basic rules, the operation information of the prediction equipment is determined, wherein the basic rules include: the reference difference between the suitable environmental information and the predicted environmental parameters at each growth stage of the target plant, and the equipment control actions corresponding to the reference difference.

[0011] For example, determining the predicted equipment operation information of the relevant equipment based on the predicted environmental parameters and the current growth stage of the target plant includes: determining a candidate equipment control scheme based on the predicted environmental parameters and the current growth stage of the target plant; determining whether the predicted environmental parameters meet the mandatory triggering conditions corresponding to the mandatory equipment control actions; for cases where the predicted environmental parameters meet any mandatory triggering conditions, adding a mandatory equipment control action corresponding to the met mandatory triggering conditions to the candidate equipment control scheme to obtain an updated candidate equipment control scheme; and determining the predicted equipment operation information based on the updated candidate equipment control scheme.

[0012] For example, determining the predicted equipment operation information of the relevant equipment based on the predicted environmental parameters and the current growth stage of the target plant includes: determining multiple candidate equipment control schemes based on the predicted environmental parameters and the current growth stage of the target plant; using an arbitration model to rank the determined candidate equipment control schemes to obtain ranked candidate equipment control schemes, wherein the arbitration model is trained based on a near-end policy optimization algorithm; and determining the predicted equipment operation information based on one of the ranked candidate equipment control schemes with the highest number of targets.

[0013] For example, the multi-sensor network includes at least one of the following: a temperature and humidity sensor, a carbon dioxide sensor, a photosynthetically active radiation sensor, a total radiation sensor, a soil sensor, and a weather station.

[0014] For example, the method further includes: performing an invalid data removal operation on the acquired indoor environmental parameters so that for each remaining indoor environmental parameter, the parameter value of that indoor environmental parameter is within its corresponding preset parameter range, and the distance between it and the mean of that indoor environmental parameter is less than or equal to three standard deviations.

[0015] For example, the operating state includes at least one of the following: switch state, rotational speed, opening degree, running time, and energy consumption.

[0016] For example, the method further includes: performing an invalid data removal operation on the acquired operating status so that the remaining rotation speed and opening degree of each related device are within their respective preset ranges.

[0017] According to a second aspect of the present invention, a device for regulating the plant growth environment is also provided, comprising:

[0018] The acquisition module is used to acquire environmental information of the target plant's growth environment using a multi-sensor network. The environmental information includes indoor environmental parameters during a first preset time period before the current moment and outdoor environmental parameters at least at the current moment.

[0019] The collection module is used to acquire the operating status of relevant devices in the target plant's growth environment that are used to change the environmental information;

[0020] The prediction module is used to predict environmental parameters for a future second preset time period based on the environmental information and the operating status.

[0021] The determination module is used to determine the predicted equipment operation information of the relevant equipment based on the predicted environmental parameters and the current growth stage of the target plant, wherein the predicted equipment operation information includes the equipment control actions of at least one relevant equipment;

[0022] The equipment control module is used to control the relevant equipment based on the predicted equipment operation information.

[0023] According to a third aspect of the present invention, an electronic device is also provided, comprising: a processor and a memory, wherein the memory stores computer program instructions, which, when executed by the processor, are used to perform the above-described method for regulating the plant growth environment.

[0024] According to a fourth aspect of the present invention, a storage medium is also provided, on which program instructions are stored, which, when executed, are used to perform the above-described method for regulating the plant growth environment.

[0025] According to a fifth aspect of the present invention, a computer program product is also provided, comprising computer program instructions, which, when executed, are used to perform the above-described method for regulating the plant growth environment.

[0026] In the above technical solution, a multi-sensor network is used to acquire environmental information about the target plant's growth environment. This environmental information includes indoor environmental parameters for a first preset time period prior to the current moment and outdoor environmental parameters at least at the current moment. Then, the operating status of relevant devices within the target plant's growth environment used to modify this environmental information is acquired. Next, based on predicted environmental parameters and the target plant's current growth stage, predicted device operating information is determined. This predicted device operating information includes control actions for at least one relevant device. Finally, based on this predicted device operating information, the relevant devices are controlled. Combining the indoor and outdoor environments acquired by the multi-sensor network with the operating status of relevant devices allows for more accurate prediction of future environmental parameters. Furthermore, combining this with the plant's current growth stage allows for the prediction of more reasonable device operating information for the future. Controlling the relevant devices based on this predicted operating information ensures that the plant's growth environment more closely matches the needs of its current growth stage, thus enabling more rational regulation of the plant's growth environment.

[0027] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0028] The above and other objects, features, and advantages of the present invention will become more apparent from the more detailed description of the embodiments of the invention in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same parts or steps.

[0029] Figure 1 A schematic flowchart of a method for regulating the plant growth environment according to an embodiment of the present invention is shown;

[0030] Figure 2 A schematic flowchart illustrating the prediction of environmental parameters for a second preset time period in the future, according to an embodiment of the present invention, is shown.

[0031] Figure 3 A schematic flowchart illustrating the prediction of environmental parameters based on the standardized results and operating status of each type of environmental information, according to an embodiment of the present invention, is shown.

[0032] Figure 4 A schematic flowchart illustrating the determination of predictive device operating information according to an embodiment of the present invention is shown;

[0033] Figure 5 A schematic flowchart illustrating the determination of predictive device operating information is shown according to yet another embodiment of the present invention;

[0034] Figure 6 A schematic flowchart illustrating the determination of predictive device operating information is shown according to yet another embodiment of the present invention;

[0035] Figure 7 A schematic block diagram of a device for regulating the plant growth environment according to an embodiment of the present invention is shown;

[0036] Figure 8 A schematic block diagram of an electronic device according to an embodiment of the present invention is shown. Detailed Implementation

[0037] To make the objectives, technical solutions, and advantages of the present invention more apparent, exemplary embodiments according to the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are merely a part of the embodiments of the present invention, and not all of the embodiments of the present invention. It should be understood that the present invention is not limited to the exemplary embodiments described herein. Based on the embodiments of the present invention described herein, all other embodiments obtained by those skilled in the art without inventive effort should fall within the protection scope of the present invention.

[0038] To at least partially address the aforementioned problems, a method for regulating the plant growth environment is proposed. This method utilizes a multi-sensor network to acquire environmental information about the target plant's growth environment. This information includes indoor environmental parameters for a first preset time period prior to the current moment and outdoor environmental parameters at least at the current moment. Then, it acquires the operational status of relevant devices within the target plant's growth environment used to modify this environmental information. Next, based on predicted environmental parameters and the target plant's current growth stage, it determines predicted device operation information, including control actions for at least one relevant device. Finally, based on this predicted device operation information, it controls the relevant devices. By combining the indoor and outdoor environmental parameters acquired through the multi-sensor network with the device operation status, future predicted environmental parameters can be predicted more accurately. Furthermore, by combining this with the plant's current growth stage, more reasonable predicted device operation information for the future can be predicted. Controlling the relevant devices based on this predicted operation information allows the plant growth environment to more closely match the needs of the plant's current growth stage, thus enabling more rational regulation of the plant growth environment.

[0039] Figure 1 A schematic flowchart illustrating a method for regulating the plant growth environment according to an embodiment of the present invention is shown. Figure 1 As shown, the method for regulating the plant growth environment may include steps S110 to S150.

[0040] In step S110, environmental information of the target plant's growth environment is acquired using a multi-sensor network. The environmental information includes indoor environmental parameters during a first preset time period prior to the current moment and outdoor environmental parameters at least at the current moment.

[0041] A multi-sensor network can include multiple sensors or detection nodes. Multiple sensors can be used to collect similar types of environmental information; for example, multiple carbon dioxide sensors can be placed at different locations in the target plant's growth environment to each collect a set of carbon dioxide data as part of the environmental information. Multiple sensors can also be used to collect different types of environmental information; for example, a multi-sensor network can include temperature and humidity sensors and carbon dioxide concentration sensors to collect temperature, humidity, and carbon dioxide concentration data respectively. Detection nodes can be single sensors or clusters of sensors; for example, a detection node can be a weather station to detect outdoor environmental information such as temperature, humidity, light intensity, carbon dioxide concentration, and weather conditions.

[0042] For example, a multi-sensor network includes at least one of the following: a temperature and humidity sensor, a carbon dioxide sensor, a photosynthetically active radiation sensor, a total radiation sensor, a soil sensor, and a weather station.

[0043] Temperature and humidity sensors can be any type of sensor used to detect temperature and / or humidity. Carbon dioxide sensors can be any type of sensor used to detect carbon dioxide concentration. Photosynthetically active radiation (PAR) sensors can be used to detect the portion of solar radiation energy that can be absorbed and utilized by the photosynthetic system of green plants. Total radiation sensors can be used to detect solar radiation energy. Environmental parameters detected by PAR and / or total radiation sensors and soil sensors can be used to extrapolate light information. They can also be used to detect soil-related information, such as temperature and humidity. For example, temperature and humidity sensors, carbon dioxide sensors, PAR sensors, total radiation sensors, and soil sensors can be used to detect indoor environmental parameters. Weather stations are used to detect outdoor meteorological information, such as temperature, humidity, and weather conditions. These sensors or detection nodes allow for the flexible acquisition of environmental information tailored to specific needs.

[0044] The target plant's growth environment can include both the indoor and outdoor environments of the target greenhouse used to grow the target plant. Sensors installed within the target greenhouse can continuously collect and save corresponding indoor environmental parameters. The first preset time period can be a pre-set fixed duration or can be manually adjusted.

[0045] When environmental information is needed, the indoor environmental parameters for the first preset time period can be read, and the outdoor environmental parameters at least for the current moment can be determined based on the outdoor environmental parameters collected by sensors or detection nodes set outside the target greenhouse. In this way, complete environmental information about the target plant's growth environment can be obtained.

[0046] For example, invalid data can be removed from the acquired indoor environmental parameters so that for each remaining indoor environmental parameter, the parameter value of that indoor environmental parameter is within its corresponding preset parameter range, and the distance between it and the mean of that indoor environmental parameter is less than or equal to three standard deviations.

[0047] Validity checks can be performed separately for each type of indoor environmental parameter, removing outliers that exceed their preset range or deviate from the overall trend by more than three standard deviations. For example, the preset range for indoor temperature can be 0℃ to 50℃. Temperatures outside this range may be due to sensor malfunction or distortion caused by transient interference, and therefore can be considered outliers and removed. Similarly, if the difference between the detected indoor temperature at a certain moment and the mean indoor temperature is less than or equal to three standard deviations, it can be considered an outlier and removed. Similar procedures apply to other types of indoor environmental parameters, and will not be detailed here.

[0048] This avoids the impact of mean distortion caused by sensor failure or transient interference on subsequent processing.

[0049] In step S120, the operating status of relevant equipment used to change environmental information within the target plant's growth environment is obtained.

[0050] After determining the type of environmental information, the operating status of the relevant equipment used to change this type of environmental information can be read. For example, relevant equipment may include side fans, circulating fans, evaporative cooling pads, roof windows, internal insulation, external insulation, and awnings. The operating status of relevant equipment can be detected directly or determined from the currently executed equipment operating information. Taking a fan as an example, the fan's operating status may include its opening degree; other relevant equipment are similar and will not be detailed here.

[0051] For example, the operating status of the relevant equipment can be the operating status at the current moment.

[0052] For example, the operating status includes at least one of the following: on / off status, rotational speed, opening degree, running time, and energy consumption.

[0053] For example, the switch state can be binarized, such as on = 1, off = 0.

[0054] For example, the engine speed and / or opening degree can be normalized. For instance, if the engine speed range is 0-2000 rpm, the normalized engine speed at 1000 rpm could be 0.5. Similarly, if the opening degree range is 0-100%, the normalized opening degree at 30% could be 0.3.

[0055] For example, the runtime can be log-normalized to mitigate the impact of long-tailed distributions.

[0056] For example, energy consumption can be uniformly converted into standard energy consumption units (such as kWh) and normalized for easy comparison with other operating parameters.

[0057] One or more of these data can be collected according to actual needs. Because these data all affect environmental parameters, they can provide corresponding auxiliary information for predicting environmental parameters more accurately. In particular, when the operating status includes on / off status, speed, opening degree, running time, and energy consumption, it can more comprehensively reflect the operating status of the relevant equipment.

[0058] For example, invalid data can be removed from the acquired operating status so that the remaining speed and opening of each relevant device are within their respective preset ranges.

[0059] The preset ranges for both rotational speed and opening degree can be pre-set. For example, negative rotational speeds or speeds exceeding the rated speed limit can be rejected. Similarly, opening degrees exceeding 100% can be rejected. This allows for the understanding of the impact of abnormal values ​​in rotational speed and opening degree on subsequent processing.

[0060] For example, when the operating status includes on / off status, speed, opening degree, running time, and energy consumption, operating status data lacking any one of these items can be removed. This data is incomplete and therefore not conducive to subsequent processing, so it can be removed.

[0061] In step S130, based on environmental information and operating status, predictive environmental parameters are generated for the second preset time period in the future.

[0062] It can directly predict environmental parameters for a second preset time period based on environmental information and operational status. Alternatively, it can convert environmental information and operational status into a calculation-friendly format, and then predict environmental parameters for a second preset time period based on the converted environmental information and operational status.

[0063] For example, for each time point within the second preset time period, starting from the first time point within the second preset time period, the predicted environmental parameter value at that time point can be determined by using a smoothing method combined with the average of environmental information from multiple previous time points. Similarly, the predicted environmental parameter for each time point within future second preset time periods can be determined.

[0064] For example, an autoregressive model can be built based on environmental information, and then the predicted environmental parameters for a second preset time period can be determined based on the autoregressive model.

[0065] For example, a corresponding prediction model can be used to combine environmental information and operational status to predict environmental parameters for a future second preset time period. The type and structure of this prediction model are not limited here. For instance, environmental parameters and the operational status of related equipment within a target time period can be pre-acquired as training data. Then, the environmental parameters and operational status of related equipment before a target time within the target time period are used as a data pair input to the prediction model to output the predicted environmental parameters. Then, based on the difference between the predicted result and the environmental parameters after the target time, a loss value is determined, and the parameters of the prediction model are adjusted using the loss value to train the prediction model. After multiple training iterations, a prediction model with satisfactory performance can be obtained for predicting environmental parameters for a future second preset time period.

[0066] In addition to the methods described in the above embodiments, other methods can be used to combine environmental information and operating status to predict environmental parameters in the second preset time period in the future, such as decomposition method, dynamic model based on state space, etc., which will not be described in detail here.

[0067] In step S140, based on the predicted environmental parameters and the current growth stage of the target plant, the predicted equipment operation information of the relevant equipment is determined, wherein the predicted equipment operation information includes the equipment control actions of at least one relevant equipment.

[0068] The predicted environmental parameters reflect the potential changes in the target plant's growth environment during the second time period. The required suitable environmental information varies depending on the target plant's different growth stages.

[0069] The suitable environmental information required for different growth stages of the target plant can be determined in advance. For example, the adjustment amount required to adjust the operating status of relevant equipment can be determined based on the difference between the predicted environmental parameters and the suitable environmental information for the current growth stage of the target plant. Based on the operating status of the relevant equipment and the required adjustment amount, the corresponding equipment control actions can be determined to obtain predicted equipment operation information containing the equipment control actions of the relevant equipment.

[0070] For example, a corresponding prediction model can be used to predict environmental parameters and the current growth stage of the target plant to predict the operational information of related equipment. Training data on environmental parameters and the growth stage of the target plant can be pre-acquired, and then the environmental parameters and growth stage are input as a data pair into the prediction model to output the predicted results of equipment control actions. Then, based on the difference between this prediction result and pre-determined standard equipment operational information for the environmental parameters and growth stage, a loss value is determined, and the parameters of the prediction model are adjusted using the loss value to train the prediction model. After multiple training iterations, a prediction model that meets the requirements can be obtained to determine the predicted equipment operational information.

[0071] For example, a candidate scheme prediction model can be used to combine predicted environmental parameters and the current growth stage of the target plant to predict multiple candidate schemes for the control actions of the relevant equipment, and then one of these candidate schemes can be selected as the predicted equipment operation information of the relevant equipment.

[0072] For example, the equipment control actions of the relevant equipment can include the operating status of the relevant equipment and the corresponding time points. For instance, in predicting equipment operating information, the relevant equipment could be a fan, and the equipment control action of the fan could be "the speed is 80% within 1 minute after the current moment, and the speed is 30% after 1 minute after the current moment." Here, the value of "speed" is the operating status of the fan, and "within 1 minute after the current moment" and "after 1 minute after the current moment" are the corresponding time points.

[0073] In step S150, the relevant equipment is controlled based on the predicted equipment operation information.

[0074] After obtaining the predicted equipment operation information, the corresponding equipment can be controlled to perform the corresponding equipment control actions based on the equipment control actions in the predicted equipment operation information, until the predicted equipment operation information is completed or the predicted equipment operation information is updated.

[0075] In the above technical solution, a multi-sensor network is used to acquire environmental information about the target plant's growth environment. This environmental information includes indoor environmental parameters for a first preset time period prior to the current moment and outdoor environmental parameters at least at the current moment. Then, the operating status of relevant devices within the target plant's growth environment used to modify this environmental information is acquired. Next, based on predicted environmental parameters and the target plant's current growth stage, predicted device operating information is determined. This predicted device operating information includes control actions for at least one relevant device. Finally, based on this predicted device operating information, the relevant devices are controlled. Combining the indoor and outdoor environments acquired by the multi-sensor network with the operating status of relevant devices allows for more accurate prediction of future environmental parameters. Furthermore, combining this with the plant's current growth stage allows for the prediction of more reasonable device operating information for the future. Controlling the relevant devices based on this predicted operating information ensures that the plant's growth environment more closely matches the needs of its current growth stage, thus enabling more rational regulation of the plant's growth environment.

[0076] For example, the above environmental information is multifaceted. Figure 2 A schematic flowchart illustrating the prediction of environmental parameters for a second preset time period according to an embodiment of the present invention is shown. Figure 2 As shown, step S130 may include steps S210 to S230.

[0077] In step S210, for each type of environmental information, the mean value of that type of environmental information within a first preset time period is calculated.

[0078] For each type of indoor environmental parameter, the corresponding mean value can be calculated based on the indoor environmental parameter of that type collected at each time point within the first preset time period.

[0079] For each type of outdoor environmental parameter, the average value can also be calculated from the outdoor environmental parameters of that type collected at each time point within the first preset time period.

[0080] The calculated mean can be an arithmetic mean, a robust mean, a weighted mean, etc.

[0081] For example, the same type of environmental information can be collected by multiple sensors or detection nodes. Therefore, the average value of this type of environmental information can be calculated by combining the environmental information collected by multiple sensors or detection nodes. For instance, if 80 temperature sensors are used to collect indoor temperature, the average indoor temperature can be calculated based on the indoor temperature collected by each of these 80 temperature sensors in the first time period.

[0082] In step S220, the mean of all environmental information is standardized by Z-score to obtain the standardized result for each type of environmental information.

[0083] For each type of environmental information, the difference between the value at each time point and the corresponding mean can be calculated, and the standard deviation of the environmental information can be determined based on the difference. Then, the standardization result of the environmental information can be determined based on the ratio between each difference and the standard deviation.

[0084] For example, the standardization result for each type of environmental information can be determined according to the following formula 1:

[0085] X i ′ =(x i -η) / σ Formula 1

[0086] Among them, X i ′ Let x represent the standardized result of this environmental information at the i-th time point. i Let η represent the value of this type of environmental information at the i-th time point, η represent the mean of this type of environmental information, and σ represent the standard deviation of this type of environmental information.

[0087] In step S230, environmental parameters are predicted based on the standardized results and operating status of each type of environmental information.

[0088] For example, an autoregressive model can be built based on the standardized results of each type of environmental information, and then the predicted environmental parameters can be determined based on the autoregressive model.

[0089] For example, the standardized results and operational status of each type of environmental information can be input into the corresponding prediction model to output predicted environmental parameters. For instance, the standardized results of environmental parameters and the operational status of related equipment within a target time period can be pre-acquired as training data. Then, the standardized results of environmental parameters within the target time period and the operational status of related equipment before the target time are input into the prediction model as a pair of data to output predicted environmental parameters. Then, based on the difference between the predicted results and the environmental parameters after the target time, a loss value is determined, and the parameters of the prediction model are adjusted using the loss value to train the prediction model. After multiple training iterations, a prediction model with satisfactory performance can be obtained to predict the predicted environmental parameters.

[0090] In addition to the methods described in the above embodiments, other methods can be used to combine the standardized results and operating status of each type of environmental information to predict the predicted environmental parameters in the second preset time period in the future, such as smoothing method, decomposition method, dynamic model based on state space, etc., which will not be described in detail here.

[0091] In the above technical solution, for each type of environmental information, the mean value of that environmental information within a first preset time period is calculated. Then, the mean values ​​of all environmental information are standardized using Z-scores to obtain the standardized result for each type of environmental information. Subsequently, based on the standardized result of each type of environmental information and the operating status, the predicted environmental parameters are calculated. By determining the standardized result of each type of environmental information, a unified dimension can be achieved for each type of environmental information. This makes it easier to accurately combine the impact of each type of environmental information on the predicted environmental parameters when making predictions, thus leading to more reasonable predicted environmental parameters.

[0092] Figure 3 A schematic flowchart illustrating the prediction of environmental parameters based on the standardized results and operational status of each type of environmental information, according to an embodiment of the present invention, is shown. Figure 3 As shown, step S230 may include steps S310 to S330.

[0093] In step S310, the standardized results of each type of environmental information and the corresponding time steps of the operating status are unified.

[0094] Each type of environmental information has its own standardized result and operational status, corresponding to a timestamp or collection time point. When the time steps are different, it is not conducive to efficiently combining the standardized results and operational status of environmental information to accurately predict environmental parameters.

[0095] For example, the interval between data collection points for indoor environmental parameters within a first preset time period is 1 minute, while the interval between data collection points for outdoor environmental parameters within the same time period is 5 minutes. In this case, the time steps corresponding to the standardized results of each type of environmental information are different. For the standardized results of each type of environmental information, interpolation or moving average can be used to adjust the time steps based on the differences in time steps, thus aligning the time steps corresponding to the standardized results of each type of environmental information. For example, for outdoor environmental parameters, based on the standardized results of outdoor environmental parameters collected at 5-minute intervals, at least the standardized results of indoor environmental parameters with time steps synchronized with those of indoor environmental parameters can be calculated. The reverse is also true.

[0096] The same principle applies to the operating status of related equipment. For example, the operating status of related equipment can be the operating status at the current moment, so the corresponding time step is the current moment. The time step corresponding to the standardized result of each type of environmental information can be directly added to the time step corresponding to the operating status of related equipment to align the standardized result of each type of environmental information with the time step corresponding to the operating status.

[0097] In step S320, the sliding window matrix is ​​determined based on the time characteristics corresponding to the time step, the standardized results after unifying the time step, and the running status.

[0098] The time features corresponding to a time step can include time features such as minutes, hours, and months, which can be used to reflect circadian rhythms and seasonal characteristics.

[0099] Environmental mean sequences, external meteorological sequences, equipment operating status vectors, and time features can be concatenated along the same time dimension to form a sliding window matrix. For example, the rows of the sliding window matrix can represent time steps, and the columns can represent input dimensions (standardized results of indoor environmental parameters + standardized results of outdoor environmental parameters + operating status of relevant equipment + time features). The dimension value of the input dimensions can be determined by summing the number of types of indoor environmental parameters, the number of types of outdoor environmental parameters, the number of relevant equipment, and the number of time features.

[0100] In step S330, the sliding window matrix is ​​input into the time series prediction model to output the predicted environment parameters.

[0101] Temporal prediction models can combine time steps and input dimensions in a sliding window matrix for analysis to predict reasonable prediction environment parameters. Temporal prediction models can be of any type and structure, such as long short-term memory network temporal prediction models.

[0102] For example, a reference sliding window matrix can be pre-obtained based on standardized environmental parameters within the target time period prior to the target time, and environmental parameters within the target time period after the target time. The reference sliding window matrix is ​​then input into the prediction model to output predicted environmental parameters. A loss value is then determined based on the difference between this prediction and the environmental parameters after the target time, and the parameters of the prediction model are adjusted using this loss value to train the model. After multiple training iterations, a prediction model with satisfactory performance can be obtained as a time-series prediction model to predict environmental parameters.

[0103] In the above technical solution, the standardized results and operating states of each type of environmental information are unified, and their corresponding time steps are standardized. Then, based on the time characteristics corresponding to each time step, the standardized results after unifying the time steps, and the operating states, a sliding window matrix is ​​determined. This sliding window matrix is ​​then input into the time series prediction model to output predicted environmental parameters. This allows the time series prediction model to combine environmental information and operating states from the same time series to predict more reasonable environmental parameters.

[0104] Figure 4 A schematic flowchart illustrating the determination of predictive device operating information is shown according to an embodiment of the present invention. Figure 4 As shown, step S140 may include steps S410 to S420.

[0105] In step S410, the target difference between the suitable environmental information and the predicted environmental parameters of the target plant at the current growth stage is determined.

[0106] This target difference indicates the deviation that would result from adjusting the growth environment of the target plant based on the current equipment operating status. The larger the target difference, the less suitable the future growth environment will be for the growth of the target plant.

[0107] The target variance can include the deviation between each type of suitable environmental information and the predicted environmental parameter of the same type. This deviation can be the average of the overall deviations, or it can be a deviation related to time information within a second preset time period, such as a 30% deviation between the predicted temperature and the suitable temperature 5 minutes after the current moment.

[0108] In step S420, based on the target differences, the current growth stage of the target plant, and the basic rules, the predictive equipment operation information is determined. The basic rules include: the reference differences between the suitable environmental information and the predicted environmental parameters at each growth stage of the target plant, and the equipment control actions corresponding to the reference differences.

[0109] The data in the basic rules can be predetermined. In the basic rules, the device control action corresponding to the reference difference can include the device control action of at least one related device, and the same reference difference can correspond to at least one combination of device control actions.

[0110] For example, based on the current growth stage of the target plant, a reference difference that matches the target difference under the current growth stage of the target plant can be matched in the basic rules, and the corresponding equipment control action can be determined as the equipment control action in the predicted equipment operation information to obtain the predicted equipment operation information.

[0111] For example, based on the current growth stage of the target plant, reference differences that match the target difference under the current growth stage can be matched in the basic rules, and the corresponding combinations of equipment control actions can be determined as equipment control actions in the candidate schemes. This yields at least one candidate scheme, from which one can then be selected as the predicted equipment operation information.

[0112] For example, target differences, the current growth stage of the target plant, and basic rules can be input into the corresponding prediction model so that the prediction model can directly predict the corresponding equipment operation information. For instance, sample differences, the growth stage of the target plant, and basic rules can be used as training data to input into the prediction model to output prediction results. Here, sample differences are the difference between the sample environmental information and the suitable environmental information for the target plant's growth stage. A loss value is calculated based on the difference between the prediction result and pre-determined standard equipment operation information for the input data. Then, the parameters of the prediction model are adjusted based on this loss value to train the prediction model. After training the prediction model multiple times, a prediction model for predicting equipment operation information can be obtained.

[0113] For example, target differences, the current growth stage of the target plant, and basic rules can be input into the corresponding prediction model to directly predict the corresponding candidate schemes for equipment control actions. Further, equipment operation information can be determined from the candidate schemes. For instance, sample differences, the growth stage of the target plant, and basic rules can be used as training data input into the prediction model to output prediction results. Here, sample differences are the difference between sample environmental information and suitable environmental information at the target plant's growth stage. A loss value is calculated based on the difference between the prediction results and a pre-determined standard equipment control action scheme for the input data. The parameters of the prediction model are then adjusted based on this loss value to train the model. After training the prediction model multiple times, candidate schemes for predicting equipment control actions can be obtained.

[0114] In the above technical solution, the target difference between the suitable environmental information and the predicted environmental parameters of the target plant at its current growth stage is determined. Then, based on this target difference, the target plant's current growth stage, and fundamental rules, the predictive equipment operation information is determined. The fundamental rules include: reference differences between the suitable environmental information and the predicted environmental parameters at each growth stage of the target plant, and the corresponding equipment control actions. In this way, by combining the difference between the suitable environmental information and the predicted environmental parameters of the target plant at its current growth stage, the target plant's current growth stage, and the predetermined fundamental rules, predictive equipment operation information that can adjust subsequent environmental information to be more suitable for the target plant's current growth stage can be determined.

[0115] Figure 5A schematic flowchart illustrating the determination of predictive device operating information is shown according to yet another embodiment of the present invention. Figure 5 As shown, step S140 may include steps S510 to S540.

[0116] In step S510, a candidate equipment control scheme is determined based on the predicted environmental parameters and the current growth stage of the target plant.

[0117] Candidate equipment control schemes can be determined using a corresponding prediction model based on predicted environmental parameters and the current growth stage of the target plant. For example, this prediction model could be a deep learning model trained based on sample environmental parameters and the corresponding growth stage of the target plant.

[0118] Alternatively, based on predicted environmental parameters, the current growth stage of the target plant, the above step S410, and the basic rules in the above embodiments, the device control actions in each candidate device control scheme can be determined to obtain at least one candidate device control scheme.

[0119] Candidate equipment control schemes can also be determined in other ways based on predicted environmental parameters and the current growth stage of the target plant, which will not be detailed here.

[0120] In step S520, it is determined whether the predicted environmental parameters meet the mandatory triggering conditions corresponding to the mandatory device control action to be executed.

[0121] Enforcement rules, including mandatory triggering conditions and corresponding mandatory equipment control actions, can be predetermined. For example, if the mandatory triggering condition is rainfall (weather), the corresponding mandatory equipment control action could include at least closing the sunroof. Mandatory triggering conditions can be matched to the enforcement rules based on predicted environmental parameters. For instance, mandatory triggering conditions that match the predicted environmental parameters can be matched to the enforcement rules based on semantics or by utilizing a model. If no mandatory triggering condition is matched, it means that the predicted environmental parameters do not meet the mandatory triggering conditions corresponding to the mandatory equipment control action. If a mandatory triggering condition is matched, it means that the predicted environmental parameters meet the mandatory triggering conditions corresponding to the mandatory equipment control action.

[0122] In step S530, for cases where the predicted environmental parameters meet any forced triggering conditions, a forced device control action corresponding to the met forced triggering conditions is added to the candidate device control scheme to obtain an updated candidate device control scheme.

[0123] The execution priority of a mandatory device control action can be the highest. If a candidate device control scheme contains a conflicting device control action, the mandatory action will be executed first. For example, if a candidate device control scheme contains a "partially open the skylight" action, and the predicted environmental parameter indicates "continuous rainfall," and this predicted environmental parameter meets the mandatory condition, and the mandatory device control action corresponding to the met trigger condition is "close the skylight," then a mandatory "close the skylight" action can be added to the candidate device control scheme. If this candidate device control scheme is subsequently used as predicted device information, then "close the skylight" will be executed first when controlling the skylight in subsequent operations, instead of "partially open the skylight."

[0124] For each candidate device control scheme, any device control action within that candidate device control scheme that targets the same related device as the enforced device control action can be considered a device control action that conflicts with the enforced device control action.

[0125] For example, a mandatory device control action can have a corresponding execution time, which can be determined based on the time period corresponding to the predicted environmental parameters that meet the triggering conditions. If the device control actions in the candidate device control schemes have corresponding execution times, the mandatory device control actions can be executed first based on the execution time. For example, if a candidate device control scheme contains a device control action of "opening part of the skylight within 15 minutes after the current moment," and if the predicted environmental parameter indicates "continuous rainfall within 10 minutes after the current moment," this predicted environmental parameter meets the mandatory condition. If the mandatory device control action corresponding to the met triggering condition is "closing the skylight," then the mandatory device control action of "closing the skylight within 10 minutes after the current moment" can be added to the candidate device control scheme. If this candidate device control scheme is subsequently used as predicted device information, then when controlling the skylight later, "closing the skylight" will be executed first within 10 minutes after the current moment, instead of "opening part of the skylight," and "opening part of the skylight" will be executed only between 10 and 15 minutes after the current moment.

[0126] In step S540, the predicted equipment operation information is determined based on the updated candidate equipment control scheme.

[0127] For example, one can be randomly selected from the updated candidate device control schemes as the predicted device operation information.

[0128] For example, each updated candidate device control scheme can be evaluated based on the expected results after execution, energy consumption, and smoothness of device start-up and shutdown, and finally the optimal one can be selected as the predicted device operation information.

[0129] For example, artificial intelligence models can be used to evaluate each updated candidate device control scheme, and the optimal one can be selected as the predicted device operation information based on the evaluation results.

[0130] In the above technical solution, candidate equipment control schemes are determined based on predicted environmental parameters and the current growth stage of the target plant. Then, it is determined whether the predicted environmental parameters meet the mandatory triggering conditions corresponding to the enforced equipment control actions. For cases where the predicted environmental parameters meet any mandatory triggering condition, the candidate equipment control scheme is updated by adding the corresponding mandatory triggering action. Based on the updated candidate equipment control scheme, the predicted equipment operation information is determined. This allows for the correction of erroneous equipment control actions after obtaining the candidate equipment control scheme, resulting in a more reasonable updated candidate equipment control scheme. The updated candidate equipment control scheme allows for the determination of more reasonable predicted equipment operation information, which is beneficial for subsequent rational control of the relevant equipment.

[0131] Figure 6 A schematic flowchart illustrating the determination of predictive device operating information is shown according to yet another embodiment of the present invention. Figure 6 As shown, step S140 may include steps S610 to S630.

[0132] In step S610, based on the predicted environmental parameters and the current growth stage of the target plant, multiple candidate equipment control schemes are determined.

[0133] Step S610 can be referred to the description of steps S510 to S530 above and related embodiments, and will not be described in detail here.

[0134] In step S620, the determined candidate device control schemes are sorted using the arbitration model to obtain the sorted candidate device control schemes. The arbitration model is trained based on the near-end policy optimization algorithm.

[0135] The proximal policy optimization algorithm is a reinforcement learning training method. Compared to arbitration models obtained through traditional training methods, arbitration models trained using the proximal policy optimization algorithm can analyze the hidden advantages of candidate device control schemes to output a partially ordered list of candidate device control schemes. The candidate device control schemes ranked higher are considered superior by the arbitration model.

[0136] For example, the difference between the predicted environmental parameters and the aforementioned environmental information can be calculated to generate a reward signal for reinforcement training of the arbitration model.

[0137] In step S630, based on one of the candidate device control schemes with the highest number of targets, the predicted device operation information is determined.

[0138] For example, the top-ranked candidate device control scheme can be directly selected as the predicted device operation information.

[0139] The target number can be preset. Although the top-ranked candidate device control scheme is considered the best by the arbitration model, it may not necessarily best meet the user's needs. Therefore, the top-ranked candidate device control schemes can be evaluated from multiple dimensions to determine their respective evaluation results. Then, based on these evaluation results, the optimal candidate device control scheme is selected as the predicted device operation information. For example, the top-ranked candidate device control schemes can be evaluated based on expected results after execution, energy consumption, and device start-up and shutdown smoothness, and finally, the one with the best evaluation result is selected as the predicted device operation information.

[0140] In the above technical solution, multiple candidate device control schemes are determined based on predicted environmental parameters and the current growth stage of the target plant. Then, an arbitration model is used to rank these candidate control schemes, resulting in a ranked list. The arbitration model is trained using a proximal policy optimization algorithm. Subsequently, based on one of the top-ranked candidate control schemes, the predicted device operation information is determined. The arbitration model, trained using the proximal policy optimization algorithm, can analyze the hidden advantages of candidate device control schemes and rank them accordingly. The candidate control schemes ranked higher are considered superior, and the predicted device operation information determined based on this is more reasonable and suitable for regulating the growth environment of the target plant.

[0141] Figure 7 A schematic block diagram of a plant growth environment control device according to an embodiment of the present invention is shown. Figure 7 As shown, the plant growth environment regulation device includes a collection module 710, a gathering module 720, a prediction module 730, a determination module 740, and a control module 750.

[0142] The acquisition module 710 is used to acquire environmental information of the target plant's growth environment using a multi-sensor network. The environmental information includes indoor environmental parameters during a first preset time period before the current moment and outdoor environmental parameters at least at the current moment.

[0143] The collection module 720 is used to acquire the operating status of relevant equipment in the target plant's growth environment that is used to change environmental information.

[0144] The prediction module 730 is used to predict environmental parameters for a second preset time period in the future based on environmental information and operating status.

[0145] The determination module 740 is used to determine the predicted equipment operation information of relevant equipment based on the predicted environmental parameters and the current growth stage of the target plant, wherein the predicted equipment operation information includes the equipment control actions of at least one relevant device.

[0146] The control module 750 is used to control related equipment based on predicted equipment operating information.

[0147] According to another aspect of the present invention, an electronic device is also provided. Figure 8 A schematic block diagram of an electronic device according to an embodiment of the present invention is shown. Figure 8 As shown, the electronic device includes a processor and a memory, wherein the memory stores computer program instructions, which are executed by the processor to perform the plant growth environment regulation method described above.

[0148] Furthermore, according to another aspect of the present invention, a storage medium is provided, on which program instructions are stored. When the program instructions are executed by a computer or processor, the computer or processor performs corresponding steps of the plant growth environment regulation method described above in the embodiments of the present invention, and is used to implement corresponding modules in the plant growth environment regulation device described above in the embodiments of the present invention. The storage medium may, for example, include a storage component of a tablet computer, a hard disk of a personal computer, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a portable compact disc read-only memory (CD-ROM), a USB memory, or any combination of the above storage media. The computer-readable storage medium may be any combination of one or more computer-readable storage media.

[0149] According to another aspect of the present invention, a computer program product is also provided, including computer program instructions, which, when executed, are used to perform the above-described method for regulating the plant growth environment.

[0150] Those skilled in the art can understand the specific implementation and beneficial effects of the above-described plant growth environment regulation devices, electronic devices, storage media, and computer program products by reading the detailed description of the above-described plant growth environment regulation methods. For the sake of brevity, they will not be described in detail here.

[0151] Although exemplary embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above exemplary embodiments are merely illustrative and are not intended to limit the scope of the invention. Various changes and modifications can be made therein by those skilled in the art without departing from the scope and spirit of the invention. All such changes and modifications are intended to be included within the scope of the invention as claimed in the appended claims.

[0152] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0153] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed.

[0154] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0155] Similarly, it should be understood that, in order to streamline the invention and aid in understanding one or more of the various aspects of the invention, features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof in the description of exemplary embodiments of the invention. However, this approach should not be construed as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected in the corresponding claims, its inventive point lies in solving the corresponding technical problem with fewer features than all of those in a single disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of the invention.

[0156] Those skilled in the art will understand that, apart from the mutual exclusion of features, all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or apparatus so disclosed can be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0157] Furthermore, those skilled in the art will understand that although some embodiments described herein include certain features but not others included in other embodiments, combinations of features from different embodiments are intended to be within the scope of the invention and form different embodiments. For example, in the claims, any of the claimed embodiments can be used in any combination.

[0158] The various component embodiments of the present invention can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some modules in the plant growth environment control device according to embodiments of the present invention. The present invention can also be implemented as a device program (e.g., a computer program and computer program product) for performing part or all of the methods described herein. Such programs implementing the present invention can be stored on a computer-readable medium or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0159] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

[0160] The above description is merely a specific embodiment of the present invention or an explanation of that embodiment. The scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. The scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for regulating the plant growth environment, characterized in that, The method includes: The environmental information of the target plant's growth environment is acquired using a multi-sensor network, wherein the environmental information includes indoor environmental parameters during a first preset time period prior to the current moment and outdoor environmental parameters at least at the current moment; Acquire the operational status of relevant devices within the target plant's growth environment that are used to alter the environmental information; Based on the environmental information and the operating status, predict the predicted environmental parameters for the second preset time period in the future; Based on the predicted environmental parameters and the current growth stage of the target plant, the predicted equipment operation information of the relevant equipment is determined, wherein the predicted equipment operation information includes the equipment control actions of at least one relevant equipment; Based on the predicted equipment operating information, the relevant equipment is controlled.

2. The method according to claim 1, characterized in that, The environmental information is diverse, and the prediction of predicted environmental parameters for a future second preset time period based on the environmental information and the operating status includes: For each type of environmental information, calculate the mean value of that type of environmental information within the first preset time period; The mean of all environmental information is standardized using Z-scores to obtain the standardized result for each type of environmental information; Based on the standardization results and the operating status, the predicted environmental parameters are predicted.

3. The method according to claim 2, characterized in that, The step of predicting the prediction environment parameters based on the standardization results and the operating status includes: The standardized results of each type of environmental information and the corresponding time steps for each of the operating states are unified; The sliding window matrix is ​​determined based on the time characteristics corresponding to the time step, the standardized results after unifying the time step, and the running status. The sliding window matrix is ​​input into the time series prediction model to output the prediction environment parameters.

4. The method according to claim 1, characterized in that, The step of determining the predictive equipment operation information of the relevant equipment based on the predicted environmental parameters and the current growth stage of the target plant includes: Determine the target difference between the suitable environmental information of the target plant at its current growth stage and the predicted environmental parameters; Based on the target differences, the current growth stage of the target plant, and the basic rules, the operating information of the prediction device is determined. The basic rules include: the reference differences between the suitable environmental information and the predicted environmental parameters at each growth stage of the target plant, and the device control actions corresponding to the reference differences.

5. The method according to claim 1, characterized in that, The step of determining the predictive equipment operation information of the relevant equipment based on the predicted environmental parameters and the current growth stage of the target plant includes: Based on the predicted environmental parameters and the current growth stage of the target plant, a candidate equipment control scheme is determined; Determine whether the predicted environmental parameters meet the mandatory triggering conditions corresponding to the mandatory device control action; If the predicted environmental parameters meet any forced triggering conditions, add a forced device control action corresponding to the met forced triggering conditions to the candidate device control scheme to obtain an updated candidate device control scheme. Based on the updated candidate device control scheme, the predicted device operating information is determined.

6. The method according to claim 1, characterized in that, The step of determining the predictive equipment operation information of the relevant equipment based on the predicted environmental parameters and the current growth stage of the target plant includes: Based on the predicted environmental parameters and the current growth stage of the target plant, multiple candidate equipment control schemes are determined. The determined candidate device control schemes are ranked using an arbitration model to obtain the ranked candidate device control schemes. The arbitration model is trained based on a near-end policy optimization algorithm. The predicted device operation information is determined based on one of the candidate device control schemes with the highest number of target targets ranked.

7. The method according to claim 1, characterized in that, The multi-sensor network includes at least one of the following: temperature and humidity sensor, carbon dioxide sensor, photosynthetically active radiation sensor, total radiation sensor, soil sensor, and weather station.

8. The method according to claim 1, characterized in that, The method further includes: Invalid data is removed from the acquired indoor environmental parameters so that for each remaining indoor environmental parameter, the parameter value is within its corresponding preset parameter range and the distance between it and the mean of the indoor environmental parameter is less than or equal to three standard deviations.

9. The method according to claim 1, characterized in that, The operating status includes at least one of the following: on / off status, rotational speed, opening degree, running time, and energy consumption.

10. The method according to claim 9, characterized in that, The method further includes: Invalid data is removed from the acquired operating status to ensure that the remaining rotational speed and opening degree of each relevant device are within their respective preset ranges.

11. A device for regulating the plant growth environment, characterized in that, include: The acquisition module is used to acquire environmental information of the target plant's growth environment using a multi-sensor network. The environmental information includes indoor environmental parameters during a first preset time period before the current moment and outdoor environmental parameters at least at the current moment. The collection module is used to acquire the operating status of relevant devices in the target plant's growth environment that are used to change the environmental information; The prediction module is used to predict environmental parameters for a future second preset time period based on the environmental information and the operating status. The determination module is used to determine the predicted equipment operation information of the relevant equipment based on the predicted environmental parameters and the current growth stage of the target plant, wherein the predicted equipment operation information includes the equipment control actions of at least one relevant equipment; The equipment control module is used to control the relevant equipment based on the predicted equipment operation information.

12. An electronic device comprising a processor and a memory, characterized in that, The memory stores computer program instructions, which, when executed by the processor, are used to perform the plant growth environment regulation method as described in any one of claims 1 to 10.

13. A storage medium on which program instructions are stored, characterized in that, The program instructions, when executed, are used to perform the method for regulating the plant growth environment as described in any one of claims 1 to 10.

14. A computer program product comprising computer program instructions, characterized in that, The computer program instructions, when executed, are used to perform the method for regulating the plant growth environment as described in any one of claims 1 to 10.

Images