Greenhouse environment control method and system based on AI algorithm

Abstract

The invention provides a greenhouse environment control method and system based on an AI algorithm, and the method comprises the following steps: collecting environment data in a greenhouse through environment collection equipment, and carrying out the preprocessing of the environment data, and generating primary data; transmitting the primary data set to a cloud computing platform, randomly splitting the primary data set into a plurality of contrast data sets through the cloud computing platform, and operating a crop growth model on the cloud computing platform in combination with weather forecast and the plurality of contrast groups so as to respectively obtain plant growth prediction data; inputting the plant growth prediction data into an adjustment model for analysis so as to output a plurality of corresponding pre-adjustment parameters; and performing overall calculation on the plurality of pre-adjustment parameters to obtain a target adjustment parameter, and adjusting the regulation and control equipment in the greenhouse according to the target adjustment parameter. According to the invention, the environment in the greenhouse can be automatically controlled, and the growth efficiency of plants in the greenhouse is improved.

Description

Technical Field

[0001] This invention belongs to the field of big data technology and relates to an AI control method for greenhouse environment, particularly to a greenhouse environment control method and system based on AI algorithms. Background Technology

[0002] Traditional greenhouse ventilation primarily relies on manually opening and closing side / top windows, using thermal or wind pressure for natural air exchange. Especially in high-density planting scenarios, traditional methods struggle to balance the dynamic demands of temperature, humidity, and CO2 concentration, often leading to localized high temperature and humidity or CO2 deficiency. With the large-scale development of facility agriculture, traditional methods relying on manual experience to regulate the greenhouse environment are no longer sufficient and also negatively impact plant growth efficiency. While big data models are a crucial component of current intelligent control, existing technologies lack information on how to effectively utilize them for greenhouse environmental control. Summary of the Invention

[0003] In view of the shortcomings of the prior art described above, the purpose of this invention is to provide a greenhouse environment control method and system based on AI algorithms to solve the problem that the prior art cannot accurately adjust the environment inside the greenhouse, thus affecting plant growth.

[0004] To achieve the above and other related objectives, this invention provides a greenhouse environment control method based on an AI algorithm, comprising the following steps:

[0005] Environmental data inside the greenhouse is collected using environmental acquisition equipment, and the environmental data is preprocessed to generate primary data.

[0006] The primary data set is transmitted to a cloud computing platform, where it is randomly split into multiple control data sets.

[0007] By combining weather forecasts and multiple control groups, a crop growth model was run on the cloud computing platform to obtain plant growth prediction data.

[0008] The plant growth prediction data is input into the adjustment model for analysis to output multiple corresponding pre-adjustment parameters;

[0009] The target adjustment parameter is obtained by comprehensively calculating multiple pre-adjustment parameters, and the control equipment in the greenhouse is adjusted according to the target adjustment parameter.

[0010] In one embodiment of the present invention, the environmental data includes at least temperature and humidity data, plant physiological parameters, and light intensity. The step of collecting environmental data within the greenhouse using an environmental acquisition device, and generating primary data after preprocessing the environmental data, includes:

[0011] Within a preset time, temperature and humidity data in the greenhouse are collected by temperature and humidity sensors, plant physiological parameters in the greenhouse are collected by infrared cameras and multispectral imagers, and light intensity in the greenhouse is obtained by light sensors.

[0012] The temperature and humidity data, the plant physiological parameters, and the light intensity were standardized to obtain first standard data, second standard data, and third standard data, respectively.

[0013] Clustering is performed on the first standard data, the second standard data, and the third standard data to obtain the corresponding primary data groups.

[0014] In one embodiment of the present invention, the step of clustering the first standard data, the second standard data, and the third standard data to obtain corresponding primary data groups includes:

[0015] The system acquires historical data on temperature and humidity, plant physiological parameters, and light intensity within the greenhouse, and calculates the noise coefficient corresponding to the environmental data within the greenhouse based on the corresponding historical data.

[0016] Noise calculations are performed on the first standard data, the second standard data, and the third standard data based on the noise figures;

[0017] Based on the noise calculation results, noise data is removed from the first standard data, the second standard data, and the third standard data to obtain the corresponding primary data set.

[0018] In one embodiment of the present invention, the step of performing noise calculation on the first standard data, the second standard data, and the third standard data based on the noise figure includes:

[0019] The first standard data, the second standard data, and the third standard data are selected sequentially as the calculation data group;

[0020] The calculated data set is sorted, and the data located in the middle position is selected as the cluster point data;

[0021] Calculate the first distance between the cluster point data and the remaining data in the calculated data group, and calculate the first average distance of multiple first distances;

[0022] The corresponding noise distance is calculated based on the first average distance and the noise figure.

[0023] The step of removing noise data from the first standard data, the second standard data, and the third standard data according to the noise calculation results to obtain the corresponding primary data set includes:

[0024] After removing the data corresponding to the first distance being greater than the noise distance, the remaining data in the calculated data group is used as the primary data group.

[0025] In one embodiment of the present invention, the step of randomly splitting the primary data set into multiple control data sets through the cloud computing platform includes:

[0026] The corresponding random number interval is determined based on the number of the primary data sets, and the maximum value of the random number interval is equal to the number of the primary data sets.

[0027] Multiple first random numbers are generated within the random number interval using a random number model, and the number of first random numbers is one more than the number of the control data group.

[0028] The adjacent first random numbers are combined sequentially to form a distribution interval. The random number model generates multiple second random numbers located within the random number interval in each distribution interval. The number of second random numbers in each distribution interval is equal to the number of data in the control data group.

[0029] After placing the data sequence number in the primary data set and the data corresponding to the second random number into the distribution interval, multiple control data sets are formed.

[0030] In one embodiment of the present invention, the step of combining weather forecasts and multiple control groups to run a crop growth model on the cloud computing platform to obtain plant growth prediction data includes:

[0031] Acquire meteorological data from the weather forecast and the plant growth rate in the greenhouse. The meteorological data includes the expected precipitation, expected temperature, and expected solar irradiance.

[0032] The expected precipitation and the expected temperature are combined with the data from multiple control data groups corresponding to the temperature and humidity data to form a first parameter matrix; the plant growth rate is combined with the data from multiple control data groups corresponding to the plant growth parameters to form a second parameter matrix; and the expected solar irradiance is combined with the data from multiple control data groups corresponding to the light intensity to form a third parameter matrix.

[0033] The first parameter matrix, the second parameter matrix, and the third parameter matrix are combined into a matrix group in sequence, and the eigenvectors and eigenvalues ​​of the first parameter matrix, the second parameter matrix, and the third parameter matrix in each matrix group are calculated respectively.

[0034] The eigenvectors and eigenvalues ​​of the first parameter matrix, the second parameter matrix, and the third parameter matrix within each matrix group are combined to form an input sequence;

[0035] The input sequence is fed into the crop growth model to generate the corresponding plant growth prediction data.

[0036] In one embodiment of the present invention, the step of inputting the plant growth prediction data into a regulation model for analysis to output multiple corresponding pre-regulation parameters includes:

[0037] The plant growth prediction data is directly input into the regulation model, and then the full set of pre-regulation parameters are output.

[0038] After setting different regulation variable parameters within the regulation model to preset ranges, the plant growth prediction data are input into the regulation model accordingly, and the regulation model outputs corresponding local pre-regulation parameters. The regulation variable parameters include temperature and humidity regulation, light regulation, and plant nutrient parameter regulation.

[0039] In one embodiment of the present invention, the pre-adjustment parameters include a total pre-adjustment parameter and multiple local pre-adjustment parameters. The step of comprehensively calculating the multiple pre-adjustment parameters to obtain a target adjustment parameter, and adjusting the control equipment in the greenhouse according to the target adjustment parameter, includes:

[0040] Obtain historical growth data and historical adjustment data of the plants in the greenhouse, and calculate the individual growth coefficient and individual value coefficient of the plants in the greenhouse based on the historical adjustment data and the historical growth data;

[0041] The comprehensive cost-effectiveness parameter of each of the pre-adjustment parameters is calculated based on the individual growth coefficient and the individual value coefficient.

[0042] The adjustment parameter corresponding to the maximum comprehensive cost-effectiveness parameter is selected as the target adjustment parameter. The control equipment in the greenhouse is adjusted according to the target adjustment parameter to regulate the plant growth environment in the greenhouse. The control equipment includes temperature and humidity equipment, plant nutrient equipment, and light equipment.

[0043] In one embodiment of the present invention, the step of calculating the individual growth coefficient and individual value coefficient of the plants in the greenhouse based on the historical adjustment data and the historical growth data includes:

[0044] Obtain individual growth regulation data from the historical regulation data, and obtain individual plant growth data corresponding to the individual regulation data from the historical growth data.

[0045] The individual growth coefficient of the plants in the greenhouse is calculated based on the individual adjustment data and the individual plant growth data.

[0046] Obtain the power consumption information of each of the control devices in the greenhouse, and determine the corresponding single growth value coefficient based on the power consumption information;

[0047] The step of calculating the comprehensive cost-effectiveness parameter for each of the pre-adjustment parameters based on the individual growth coefficient and the individual value coefficient includes:

[0048] Based on the historical growth data and historical regulation data of the plants in the greenhouse, the analytic hierarchy process (AHP) is used to obtain the individual weight values ​​corresponding to the parameters regulated by each of the regulation devices.

[0049] The plant growth value corresponding to each pre-adjustment parameter is calculated based on the single growth coefficient, the pre-adjustment parameter, and the single weight value; the value consumption value corresponding to each pre-adjustment parameter is calculated based on the single value coefficient, the pre-adjustment parameter, and the single weight value.

[0050] The ratio of the plant growth value to the value consumption value for each of the pre-adjustment parameters is calculated as the comprehensive cost-effectiveness parameter.

[0051] This invention also provides a greenhouse environment control system based on AI algorithms, comprising the following steps:

[0052] The data acquisition module is used to collect environmental data inside the greenhouse through environmental acquisition equipment, and to generate primary data after preprocessing the environmental data;

[0053] The computing module is used to transmit the primary data set to a cloud computing platform, and then randomly split the primary data set into multiple control data sets through the cloud computing platform.

[0054] The prediction module is used to combine weather forecasts and multiple control groups to run a crop growth model on the cloud computing platform to obtain plant growth prediction data respectively.

[0055] The analysis module is used to input the plant growth prediction data into the adjustment model for analysis and output multiple corresponding pre-adjustment parameters;

[0056] The adjustment module is used to perform overall calculations on multiple pre-adjustment parameters to obtain target adjustment parameters, and to adjust the control equipment in the greenhouse according to the target adjustment parameters.

[0057] As described above, the greenhouse environment control method and system based on AI algorithms of the present invention have the following beneficial effects:

[0058] Compared with existing technologies, this invention dynamically monitors environmental data within the greenhouse and uses a big data model to comprehensively calculate the environmental data to determine the appropriate adjustment parameters for plant growth. Based on these parameters, the invention automatically controls the control equipment within the greenhouse, thereby achieving automated adjustment of the greenhouse environment without relying on manual intervention and effectively improving the growth efficiency of plants in the greenhouse. Attached Figure Description

[0059] Figure 1 The flowchart shown is a process for the greenhouse environment control method based on AI algorithm of the present invention.

[0060] Figure 2 The diagram shown is a structural block diagram of the greenhouse environment control system based on AI algorithms of the present invention. Detailed Implementation

[0061] The following specific embodiments illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, unless otherwise specified, the following embodiments and features described therein can be combined with each other.

[0062] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. The illustrations only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0063] The present invention relates to a greenhouse environment control method and system based on AI algorithms. This invention dynamically monitors the environmental data inside the greenhouse and uses a big data model to comprehensively calculate the environmental data to determine the adjustment parameters suitable for plant growth inside the greenhouse. Based on the adjustment parameters, the control equipment inside the greenhouse is automatically controlled, thereby realizing the automatic adjustment of the environmental data inside the greenhouse without relying on manual intervention, which effectively improves the growth efficiency of plants inside the greenhouse.

[0064] like Figure 1 As shown, in one embodiment, the present invention provides a greenhouse environment control method based on an AI algorithm, referring to... Figure 1 This includes the following steps:

[0065] S101. Collect environmental data inside the greenhouse using environmental acquisition equipment, and generate primary data after preprocessing the environmental data.

[0066] In this embodiment, in order to effectively regulate the environment inside the greenhouse in response to the plant growth, environmental data inside the greenhouse is first collected by an environmental acquisition device. After preprocessing the environmental data, primary data is generated. On the one hand, this ensures that real-time data inside the greenhouse is collected. On the other hand, by preprocessing the collected environmental data, abnormal data can be removed in a timely manner, so as to avoid local abnormal data from affecting the overall monitoring situation and thus avoid affecting subsequent environmental control.

[0067] In some embodiments, the environmental data includes at least temperature and humidity data, plant physiological parameters, and light intensity. The process of collecting environmental data within the greenhouse using an environmental acquisition device, and then preprocessing the environmental data to generate primary data, includes:

[0068] Within a preset time, temperature and humidity data in the greenhouse are collected by temperature and humidity sensors, plant physiological parameters in the greenhouse are collected by infrared cameras and multispectral imagers, and light intensity in the greenhouse is obtained by light sensors.

[0069] The temperature and humidity data, the plant physiological parameters, and the light intensity were standardized to obtain first standard data, second standard data, and third standard data, respectively.

[0070] Clustering is performed on the first standard data, the second standard data, and the third standard data to obtain the corresponding primary data groups.

[0071] In this embodiment, when monitoring the environment inside the greenhouse, the temperature and humidity data inside the greenhouse are first collected by a temperature and humidity sensor within a preset time period. Then, the physiological parameters of the plants inside the greenhouse are collected by an infrared camera and a multispectral imager, and the light intensity inside the greenhouse is obtained by a light sensor, so as to facilitate subsequent data processing.

[0072] The preset time is the time before the greenhouse environment is adjusted, such as data from 1 to 24 hours before the adjustment, so as to ensure the accuracy of the data.

[0073] After collecting relevant environmental data, the temperature and humidity data, plant physiological parameters and light intensity data were first standardized to obtain the first standard data, the second standard data and the third standard data.

[0074] It should be noted that the standardization process here is mainly for the purpose of unifying the format to facilitate subsequent normalization calculations. Since the content of the standardized and unified format is existing technology, this solution does not impose any special restrictions on it, and will not be elaborated here.

[0075] After obtaining the first standard data, the second standard data, and the third standard data, clustering is performed on the first standard data, the second standard data, and the third standard data respectively to obtain the corresponding primary data groups.

[0076] In some other embodiments, the step of clustering the first standard data, the second standard data, and the third standard data to obtain corresponding primary data groups includes:

[0077] The system acquires historical data on temperature and humidity, plant physiological parameters, and light intensity within the greenhouse, and calculates the noise coefficient corresponding to the environmental data within the greenhouse based on the corresponding historical data.

[0078] Noise calculations are performed on the first standard data, the second standard data, and the third standard data based on the noise figures;

[0079] Based on the noise calculation results, noise data is removed from the first standard data, the second standard data, and the third standard data to obtain the corresponding primary data set.

[0080] Specifically, in order to perform clustering, the recent temperature and humidity data, plant physiological parameters, and historical light intensity data of the greenhouse are first obtained. This allows the noise coefficient in the greenhouse environmental data to be calculated based on the historical data. Then, noise calculations are performed on the first, second, and third standard data based on the noise coefficients to identify the noise data present. After removing the noise data from the first, second, and third standard data according to the noise calculation results, the corresponding primary data groups can be obtained. This completes the preprocessing of the environmental data and ensures the accuracy of subsequent environmental control results.

[0081] It should be noted that the noise figure here refers to the abnormal data in the environmental data from the past period, such as data that is too large or too small, or data that does not conform to common sense. The calculated noise figure is the proportion of abnormal data. The process of calculating the noise figure based on the environmental data from the past period in the greenhouse adopts the existing noise figure calculation process. This solution does not involve any improvement to the noise figure calculation process, and will not be elaborated here.

[0082] In a further embodiment, the step of performing noise calculations on the first standard data, the second standard data, and the third standard data based on the noise figure includes:

[0083] The first standard data, the second standard data, and the third standard data are selected sequentially as the calculation data group;

[0084] The calculated data set is sorted, and the data located in the middle position is selected as the cluster point data;

[0085] Calculate the first distance between the cluster point data and the remaining data in the calculated data group, and calculate the first average distance of multiple first distances;

[0086] The corresponding noise distance is calculated based on the first average distance and the noise figure.

[0087] The step of removing noise data from the first standard data, the second standard data, and the third standard data according to the noise calculation results to obtain the corresponding primary data set includes:

[0088] After removing the data corresponding to the first distance being greater than the noise distance, the remaining data in the calculated data group is used as the primary data group.

[0089] Specifically, after considering the noise coefficients in the greenhouse in the past, in order to perform noise calculations on the first standard data, the second standard data, and the third standard data in sequence, the first standard data, the second standard data, and the third standard data are selected as the calculation data group in sequence for subsequent noise calculations. The following explanation uses the first standard data as an example.

[0090] First, a first standard data set is selected as the calculation data set. Then, the data within the calculation data set is sorted, and the data in the middle position within the calculation data set is selected as the cluster point data. Next, the first distance between the cluster point data and the remaining data in the calculation data set is calculated, and the first average distance between multiple first distances is calculated. Based on the first average distance and the noise coefficient, the noise distance corresponding to the current calculation data set is calculated. After calculating the noise distance, the data in the calculation data set whose first distance is greater than the noise distance is removed. The remaining data in the calculation data set are then combined to form the corresponding primary data set, thereby completing the data preprocessing process.

[0091] S102. The primary data set is transmitted to a cloud computing platform, and the primary data set is randomly split into multiple control data sets by the cloud computing platform.

[0092] After obtaining the preprocessed primary data set, in order to facilitate subsequent calculations, the primary data set is randomly split into multiple control data sets through a cloud computing platform to obtain more accurate environmental control results.

[0093] In some other embodiments, the step of randomly splitting the primary data set into multiple control data sets via the cloud computing platform includes:

[0094] The corresponding random number interval is determined based on the number of the primary data sets, and the maximum value of the random number interval is equal to the number of the primary data sets.

[0095] Multiple first random numbers are generated within the random number interval using a random number model, and the number of first random numbers is one more than the number of the control data group.

[0096] The adjacent first random numbers are combined sequentially to form a distribution interval. The random number model generates multiple second random numbers located within the random number interval in each distribution interval. The number of second random numbers in each distribution interval is equal to the number of data in the control data group.

[0097] After placing the data sequence number in the primary data set and the data corresponding to the second random number into the distribution interval, multiple control data sets are formed.

[0098] In this embodiment, to randomly split the data within the primary data set, a corresponding random number interval is first determined based on the number of primary data sets, ensuring that the subsequent random number model can generate random numbers that correspond one-to-one with the data sequence numbers in the primary data set. Then, the random number model generates multiple first random numbers located within the random number interval. Since the number of first random numbers is one more than the number of control data sets, it facilitates the subsequent formation of a distribution interval between adjacent first random numbers that corresponds to the control data set.

[0099] By forming distribution intervals between adjacent first random numbers, and using a random number model to generate second random numbers within each distribution interval, the number of second random numbers is unique, and the number of second random numbers within each distribution interval is equal to the number of data in the control data group. In this way, the primary data group can be randomly split into multiple control data groups to facilitate subsequent prediction calculations of environmental data.

[0100] S103. Combine weather forecasts and multiple control groups to run crop growth models on the cloud computing platform to obtain plant growth prediction data.

[0101] In some embodiments, the step of combining weather forecasts and multiple control groups to run a crop growth model on the cloud computing platform to obtain plant growth prediction data includes:

[0102] Acquire meteorological data from the weather forecast and the plant growth rate in the greenhouse. The meteorological data includes the expected precipitation, expected temperature, and expected solar irradiance.

[0103] The expected precipitation and the expected temperature are combined with the data from multiple control data groups corresponding to the temperature and humidity data to form a first parameter matrix; the plant growth rate is combined with the data from multiple control data groups corresponding to the plant growth parameters to form a second parameter matrix; and the expected solar irradiance is combined with the data from multiple control data groups corresponding to the light intensity to form a third parameter matrix.

[0104] The first parameter matrix, the second parameter matrix, and the third parameter matrix are combined into a matrix group in sequence, and the eigenvectors and eigenvalues ​​of the first parameter matrix, the second parameter matrix, and the third parameter matrix in each matrix group are calculated respectively.

[0105] The eigenvectors and eigenvalues ​​of the first parameter matrix, the second parameter matrix, and the third parameter matrix within each matrix group are combined to form an input sequence;

[0106] The input sequence is fed into the crop growth model to generate the corresponding plant growth prediction data.

[0107] In this embodiment, to predict plant growth in the greenhouse, the first step is to acquire meteorological data from weather forecasts for the predicted time period, as well as the plant growth rate within the greenhouse. The meteorological data is obtained through weather forecasts, while the plant growth rate is calculated by accessing historical plant growth data within the greenhouse; details will not be elaborated further here.

[0108] Multiple first parameter matrices are formed by combining the predicted precipitation and predicted air temperature with data from multiple control data groups corresponding to the temperature and humidity values. Similarly, a second parameter matrix is ​​formed by combining the plant growth rate with data from multiple control data groups corresponding to the plant growth parameters. A third parameter matrix is ​​formed by combining the predicted solar irradiance with data from multiple control data groups corresponding to the light intensity. This results in multiple first parameter matrices, multiple second parameter matrices, and multiple third parameter matrices. These matrices are then sequentially combined into matrix groups, and the eigenvectors and eigenvalues ​​of each matrix group are calculated. The eigenvalues ​​and eigenvectors of each matrix group are then combined to form an input sequence. This input sequence is then input into a crop growth model, which generates corresponding plant growth prediction data, resulting in multiple sets of plant growth prediction data.

[0109] It should be noted that the crop growth model described is a neural network model trained using growth data of plants in a greenhouse. Other machine learning algorithms can also be used. This solution does not involve any improvement to the crop growth model itself; existing crop growth models can be used, which will not be elaborated upon here.

[0110] S104. Input the plant growth prediction data into the adjustment model for analysis to output multiple corresponding pre-adjustment parameters.

[0111] In some embodiments, the step of inputting the plant growth prediction data into a regulation model for analysis to output multiple corresponding pre-regulation parameters includes:

[0112] The plant growth prediction data is directly input into the regulation model, and then the full set of pre-regulation parameters are output.

[0113] After setting different regulation variable parameters within the regulation model to preset ranges, the plant growth prediction data are input into the regulation model accordingly. The regulation model then outputs corresponding local pre-regulation parameters. The regulation variable parameters include temperature and humidity regulation, light regulation, and plant nutrient parameter regulation. The local pre-regulation parameters include regulation variable parameters within the preset range and the remaining regulation variable parameters output by the regulation model.

[0114] The preset ranges for each adjustment variable parameter are not exactly the same. The specific preset range is either a preset value or an empirical value. This scheme does not impose any special restrictions on this.

[0115] In this embodiment, after obtaining the plant growth prediction data in the greenhouse, in order to further accurately adjust the environmental control within the greenhouse, the plant growth prediction data is first directly input into the adjustment model, and then the full pre-adjustment parameters are output. Next, the adjustment variable parameters within the adjustment model are set within a preset range, and then the plant growth prediction data is input into the adjustment model again, so that the adjustment model outputs corresponding local pre-adjustment parameters. The adjustment variable parameters of the adjustment model include temperature and humidity adjustment, light adjustment, and plant nutrient parameter adjustment. Thus, the full pre-adjustment parameters and multiple local pre-adjustment parameters are obtained through the above method, so that the adjustment of the greenhouse environment can be further optimized based on the full pre-adjustment parameters and multiple local pre-adjustment parameters.

[0116] For example, after setting the temperature and humidity parameters in the adjustment model within a preset range X, and inputting plant growth prediction data into the adjustment model, the adjustment model outputs the plant nutrient parameters and light regulation parameters that need to be adjusted. Combining the temperature and humidity parameters within the preset range X, the plant nutrient parameters, and the light regulation parameters output by the adjustment model together can form the current local pre-adjustment parameters, which will not be elaborated further here.

[0117] It should be noted that the regulation model is a neural network model trained using historical environmental regulation data from previous periods in the greenhouse. Other machine learning algorithms can also be used. This solution does not involve any improvement to the regulation model itself. Existing trained regulation models can be used, which will not be elaborated here.

[0118] S105. The target adjustment parameter is obtained by comprehensively calculating the multiple pre-adjustment parameters, and the control equipment in the greenhouse is adjusted according to the target adjustment parameter.

[0119] In some embodiments, the pre-adjustment parameters include a total pre-adjustment parameter and multiple local pre-adjustment parameters. The step of comprehensively calculating the target adjustment parameter from the multiple pre-adjustment parameters and adjusting the control equipment within the greenhouse according to the target adjustment parameter includes:

[0120] Obtain historical growth data and historical adjustment data of the plants in the greenhouse, and calculate the individual growth coefficient and individual value coefficient of the plants in the greenhouse based on the historical adjustment data and the historical growth data;

[0121] The comprehensive cost-effectiveness parameter of each of the pre-adjustment parameters is calculated based on the individual growth coefficient and the individual value coefficient.

[0122] The adjustment parameter corresponding to the maximum comprehensive cost-effectiveness parameter is selected as the target adjustment parameter. The control equipment in the greenhouse is adjusted according to the target adjustment parameter to regulate the plant growth environment in the greenhouse. The control equipment includes temperature and humidity equipment, plant nutrient equipment, and light equipment.

[0123] In this embodiment, after obtaining multiple pre-adjustment parameters through the adjustment model, the pre-adjustment parameters include full pre-adjustment parameters and local pre-adjustment parameters. In order to further select the optimal parameters for the control equipment for the greenhouse environment, the historical growth data and historical adjustment data of the plants in the greenhouse are first obtained. The historical adjustment data is the adjustment data corresponding to the control equipment in the greenhouse. Then, the individual growth coefficient and individual value coefficient of the plants in the greenhouse are calculated based on the historical adjustment data and historical growth data, respectively.

[0124] Then, based on the single growth coefficient and the single value coefficient, the comprehensive cost-effectiveness parameters corresponding to the total pre-adjustment parameters and the local pre-adjustment parameters are calculated respectively, so as to select the pre-adjustment parameter corresponding to the maximum comprehensive cost-effectiveness parameter as the target adjustment parameter, and adjust the control equipment in the greenhouse according to the target adjustment parameter, thereby realizing the automated control of the plant growth environment in the greenhouse.

[0125] In some other embodiments, calculating the individual growth coefficient and individual value coefficient of the plants in the greenhouse based on the historical adjustment data and the historical growth data includes:

[0126] Obtain individual growth regulation data from the historical regulation data, and obtain individual plant growth data corresponding to the individual regulation data from the historical growth data.

[0127] The individual growth coefficient of the plants in the greenhouse is calculated based on the individual adjustment data and the individual plant growth data.

[0128] The power consumption information of each of the control devices in the greenhouse is obtained, and the corresponding single growth value coefficient is determined based on the power consumption information.

[0129] In this embodiment, after obtaining the historical adjustment data and historical growth data of the current greenhouse, the individual growth adjustment data from the historical adjustment data is obtained. This individual growth adjustment data refers to the adjustment data when adjusting a single control device, while the individual plant growth data refers to the growth data of the plants in the greenhouse when the greenhouse environment is adjusted according to the individual growth adjustment data. Then, the single-phase growth coefficient of the plants in the greenhouse is calculated based on the individual adjustment data and the individual plant growth data; that is, the growth coefficient of the plants in the greenhouse when adjusting a single control device within the greenhouse environment. Finally, the individual growth value coefficient corresponding to each control device is determined based on the power consumption information of each control device.

[0130] For example, the single growth coefficient is the growth value of the plant per unit time when a unit change is made to a certain control device in the greenhouse. For example, when the temperature and humidity control device increases the temperature in the greenhouse by 1°C and the humidity by 1%, the growth rate of the plant in the greenhouse after each hour is as follows. The single value coefficient is the unit power consumption value when a single control device in the greenhouse is adjusted individually, such as the power consumption value when the temperature and humidity control device is adjusted individually.

[0131] The step of calculating the comprehensive cost-effectiveness parameter for each of the pre-adjustment parameters based on the individual growth coefficient and the individual value coefficient includes:

[0132] Based on the historical growth data and historical regulation data of the plants in the greenhouse, the analytic hierarchy process (AHP) is used to obtain the individual weight values ​​corresponding to the parameters regulated by each of the regulation devices.

[0133] The plant growth value corresponding to each pre-adjustment parameter is calculated based on the single growth coefficient, the pre-adjustment parameter, and the single weight value; the value consumption value corresponding to each pre-adjustment parameter is calculated based on the single value coefficient, the pre-adjustment parameter, and the single weight value.

[0134] The ratio of the plant growth value to the value consumption value for each of the pre-adjustment parameters is calculated as the comprehensive cost-effectiveness parameter.

[0135] In this embodiment, after calculating the individual growth coefficient and single-phase value coefficient of the plants in the greenhouse, the analytic hierarchy process (AHP) is first used to obtain the single-phase weight value corresponding to the parameter adjusted by each control device based on the current historical growth data and historical adjustment data of the greenhouse. Then, the plant growth value corresponding to each pre-adjustment parameter is calculated based on the individual growth coefficient and single-phase weight value. The value consumption value corresponding to each pre-adjustment parameter is calculated based on the individual value coefficient and single-phase weight value. The pre-adjustment parameters include total adjustment parameters and multiple local adjustment parameters. Finally, the ratio of the plant growth value to the value consumption value corresponding to each pre-adjustment parameter is calculated as a comprehensive cost-effectiveness parameter, thereby completing the comprehensive calculation of each pre-adjustment parameter to facilitate the selection of the optimal adjustment parameter.

[0136] It should be noted that the scope of protection of the greenhouse environment control method of the AI ​​algorithm described in this invention is not limited to the execution order of the steps listed in this embodiment. Any solution implemented by adding, subtracting, or replacing steps in the prior art based on the principles of this invention is included within the scope of protection of this invention.

[0137] This invention also provides a greenhouse environment control system based on AI algorithms, with reference to... Figure 2 This includes the following steps:

[0138] The data acquisition module 201 is used to acquire environmental data inside the greenhouse through environmental acquisition equipment, and generate primary data after preprocessing the environmental data;

[0139] The computing module 202 is used to transmit the primary data set to a cloud computing platform, and to randomly split the primary data set into multiple control data sets through the cloud computing platform;

[0140] The prediction module 203 is used to combine weather forecasts and multiple control groups to run a crop growth model on the cloud computing platform to obtain plant growth prediction data respectively.

[0141] Analysis module 204 is used to input the plant growth prediction data into the adjustment model for analysis and output multiple corresponding pre-adjustment parameters;

[0142] The adjustment module 205 is used to perform overall calculation on multiple pre-adjustment parameters to obtain target adjustment parameters, and adjust the control equipment in the greenhouse according to the target adjustment parameters.

[0143] It should be noted that the structure and principle of the greenhouse environment control system based on AI algorithms correspond one-to-one with the steps in the above-mentioned greenhouse environment control method based on AI algorithms, so they will not be repeated here.

[0144] It should be noted that the division of the various modules in the above system is merely a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, these modules can be implemented entirely in software through processing element calls; they can be fully implemented in hardware; or some modules can be implemented by processing element calls to software, while others are implemented in hardware. For example, module x can be a separate processing element, or it can be integrated into a chip within the system. Alternatively, it can be stored as program code in the system's memory, and its function can be called and executed by a processing element. The implementation of other modules is similar. Moreover, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element mentioned here can be an integrated circuit with signal processing capabilities. During implementation, each step of the above method or each of the above modules can be completed through integrated logic circuits in the hardware of the processor element or through software instructions.

[0145] For example, these modules can be one or more integrated circuits configured to implement the above methods, such as one or more Application Specific Integrated Circuits (ASICs), one or more Digital Signal Processors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs). As another example, when a module is implemented using processing element scheduler code, the processing element can be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. Furthermore, these modules can be integrated together as a System-On-a-Chip (SOC).

[0146] It should be noted that the greenhouse environment control system based on the AI ​​algorithm of the present invention can implement the greenhouse environment control method based on the AI ​​algorithm of the present invention. However, the implementation device of the greenhouse environment control method based on the AI ​​algorithm of the present invention includes, but is not limited to, the structure of the greenhouse environment control system based on the AI ​​algorithm listed in this embodiment. All structural modifications and substitutions of the prior art made according to the principle of the present invention are included within the protection scope of the present invention.

[0147] The storage medium of this invention stores a computer program, which, when executed by a processor, implements the greenhouse environment control method based on the AI ​​algorithm described below. The storage medium includes various media capable of storing program code, such as read-only memory (ROM), random access memory (RAM), magnetic disk, USB flash drive, memory card, or optical disk.

[0148] One or more storage media may be used in any combination. The storage medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, RAM, ROM, erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium that contains or stores a program that may be used by or in connection with an instruction execution system, apparatus, or device.

[0149] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including—but not limited to—electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0150] The program code contained on a computer-readable medium may be transmitted using any suitable medium, including—but not limited to—wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0151] Computer program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, Smalltalk, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0152] The present invention will now be described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, these computer program instructions create means for implementing the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams.

[0153] These computer program instructions may also be stored in a computer-readable medium, which causes a computer, other programmable data processing apparatus, or other device to operate in a particular manner, thereby producing an article of manufacture that includes instructions for implementing the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0154] Computer program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, such that the instructions that execute on the computer or other programmable apparatus provide a process for implementing the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0155] The terminal of this invention includes a processor and a memory.

[0156] The memory is used to store computer programs; preferably, the memory includes various media capable of storing program code, such as ROM, RAM, magnetic disk, USB flash drive, memory card or optical disk.

[0157] The processor is connected to the memory and is used to execute the computer program stored in the memory so that the terminal performs the following AI algorithm-based greenhouse environment control method.

[0158] Preferably, the processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0159] In summary, the greenhouse environment control method and system based on AI algorithms of this invention dynamically monitors environmental data within the greenhouse and utilizes a big data model to comprehensively calculate the environmental data, thereby determining the appropriate adjustment parameters for plant growth. Based on these parameters, the system automatically controls the greenhouse's control equipment, achieving automated adjustment of the greenhouse environment without relying on manual intervention, thus effectively improving plant growth efficiency. Therefore, this invention effectively overcomes the shortcomings of existing technologies and possesses high industrial application value.

[0160] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A greenhouse environment control method based on AI algorithms, characterized in that, Includes the following steps: Environmental data inside the greenhouse is collected using environmental acquisition equipment, and the environmental data is preprocessed to generate primary data. The primary data set is transmitted to a cloud computing platform, where it is randomly split into multiple control data sets. By combining weather forecasts and multiple control groups, a crop growth model was run on the cloud computing platform to obtain plant growth prediction data. The plant growth prediction data is input into the adjustment model for analysis to output multiple corresponding pre-adjustment parameters; The target adjustment parameter is obtained by comprehensively calculating multiple pre-adjustment parameters, and the control equipment in the greenhouse is adjusted according to the target adjustment parameter.

2. The greenhouse environment control method based on AI algorithm according to claim 1, characterized in that, The environmental data includes at least temperature and humidity data, plant physiological parameters, and light intensity. The environmental data collected from the greenhouse using environmental acquisition equipment is preprocessed to generate primary data, including: Within a preset time, temperature and humidity data in the greenhouse are collected by temperature and humidity sensors, plant physiological parameters in the greenhouse are collected by infrared cameras and multispectral imagers, and light intensity in the greenhouse is obtained by light sensors. The temperature and humidity data, the plant physiological parameters, and the light intensity were standardized to obtain first standard data, second standard data, and third standard data, respectively. Clustering is performed on the first standard data, the second standard data, and the third standard data to obtain the corresponding primary data groups.

3. The greenhouse environment control method based on AI algorithm according to claim 2, characterized in that, The clustering process performed on the first standard data, the second standard data, and the third standard data yields corresponding primary data groups, including: The system acquires historical data on temperature and humidity, plant physiological parameters, and light intensity within the greenhouse, and calculates the noise coefficient corresponding to the environmental data within the greenhouse based on the corresponding historical data. Noise calculations are performed on the first standard data, the second standard data, and the third standard data based on the noise figures; Based on the noise calculation results, noise data is removed from the first standard data, the second standard data, and the third standard data to obtain the corresponding primary data set.

4. The greenhouse environment control method based on AI algorithm according to claim 3, characterized in that, The step of performing noise calculations on the first standard data, the second standard data, and the third standard data based on the noise figure includes: The first standard data, the second standard data, and the third standard data are selected sequentially as the calculation data group; The calculated data set is sorted, and the data located in the middle position is selected as the cluster point data; Calculate the first distance between the cluster point data and the remaining data in the calculated data group, and calculate the first average distance of multiple first distances; The corresponding noise distance is calculated based on the first average distance and the noise figure. The step of removing noise data from the first standard data, the second standard data, and the third standard data according to the noise calculation results to obtain the corresponding primary data set includes: After removing the data corresponding to the first distance being greater than the noise distance, the remaining data in the calculated data group is used as the primary data group.

5. The greenhouse environment control method based on AI algorithm according to claim 1, characterized in that, The step of randomly splitting the primary data set into multiple control data sets via the cloud computing platform includes: The corresponding random number interval is determined based on the number of the primary data sets, and the maximum value of the random number interval is equal to the number of the primary data sets. Multiple first random numbers are generated within the random number interval using a random number model, and the number of first random numbers is one more than the number of the control data group. The adjacent first random numbers are combined sequentially to form a distribution interval. The random number model generates multiple second random numbers located within the random number interval in each distribution interval. The number of second random numbers in each distribution interval is equal to the number of data in the control data group. After placing the data sequence number in the primary data set and the data corresponding to the second random number into the distribution interval, multiple control data sets are formed.

6. The greenhouse environment control method based on an AI large model according to claim 1, characterized in that, The crop growth model, which combines weather forecasts and multiple control groups, is run on the cloud computing platform to obtain plant growth prediction data, including: Acquire meteorological data from the weather forecast and the plant growth rate in the greenhouse. The meteorological data includes the expected precipitation, expected temperature, and expected solar irradiance. The expected precipitation and the expected temperature are combined with the data from multiple control data groups corresponding to the temperature and humidity data to form a first parameter matrix; the plant growth rate is combined with the data from multiple control data groups corresponding to the plant growth parameters to form a second parameter matrix; and the expected solar irradiance is combined with the data from multiple control data groups corresponding to the light intensity to form a third parameter matrix. The first parameter matrix, the second parameter matrix, and the third parameter matrix are combined into a matrix group in sequence, and the eigenvectors and eigenvalues ​​of the first parameter matrix, the second parameter matrix, and the third parameter matrix in each matrix group are calculated respectively. The eigenvectors and eigenvalues ​​of the first parameter matrix, the second parameter matrix, and the third parameter matrix within each matrix group are combined to form an input sequence; The input sequence is fed into the crop growth model to generate the corresponding plant growth prediction data.

7. The greenhouse environment control method based on an AI large model according to claim 1, characterized in that, The process involves inputting the plant growth prediction data into a regulation model for analysis to output multiple corresponding pre-regulation parameters, including: The plant growth prediction data is directly input into the regulation model, and then the full set of pre-regulation parameters are output. After setting different regulation variable parameters within the regulation model to preset ranges, the plant growth prediction data are input into the regulation model accordingly, and the regulation model outputs corresponding local pre-regulation parameters. The regulation variable parameters include temperature and humidity regulation, light regulation, and plant nutrient parameter regulation.

8. The greenhouse environment control method based on an AI large model according to claim 7, characterized in that, The pre-adjustment parameters include full pre-adjustment parameters and multiple local pre-adjustment parameters. The step of comprehensively calculating the target adjustment parameters from the multiple pre-adjustment parameters, and adjusting the control equipment within the greenhouse based on the target adjustment parameters, includes: Obtain historical growth data and historical adjustment data of the plants in the greenhouse, and calculate the individual growth coefficient and individual value coefficient of the plants in the greenhouse based on the historical adjustment data and the historical growth data; The comprehensive cost-effectiveness parameter of each of the pre-adjustment parameters is calculated based on the individual growth coefficient and the individual value coefficient. The adjustment parameter corresponding to the maximum comprehensive cost-effectiveness parameter is selected as the target adjustment parameter. The control equipment in the greenhouse is adjusted according to the target adjustment parameter to regulate the plant growth environment in the greenhouse. The control equipment includes temperature and humidity equipment, plant nutrient equipment, and light equipment.

9. The greenhouse environment control method based on an AI large model according to claim 8, characterized in that, The calculation of the individual growth coefficient and individual value coefficient of the plants in the greenhouse based on the historical adjustment data and the historical growth data includes: Obtain individual growth regulation data from the historical regulation data, and obtain individual plant growth data corresponding to the individual regulation data from the historical growth data. The individual growth coefficient of the plants in the greenhouse is calculated based on the individual adjustment data and the individual plant growth data. Obtain the power consumption information of each of the control devices in the greenhouse, and determine the corresponding single growth value coefficient based on the power consumption information; The step of calculating the comprehensive cost-effectiveness parameter for each of the pre-adjustment parameters based on the individual growth coefficient and the individual value coefficient includes: Based on the historical growth data and historical regulation data of the plants in the greenhouse, the analytic hierarchy process (AHP) is used to obtain the individual weight values ​​corresponding to the parameters regulated by each of the regulation devices. The plant growth value corresponding to each pre-adjustment parameter is calculated based on the single growth coefficient, the pre-adjustment parameter, and the single weight value; the value consumption value corresponding to each pre-adjustment parameter is calculated based on the single value coefficient, the pre-adjustment parameter, and the single weight value. The ratio of the plant growth value to the value consumption value for each of the pre-adjustment parameters is calculated as the comprehensive cost-effectiveness parameter.

10. A greenhouse environment control system based on AI algorithms, characterized in that, Includes the following steps: The data acquisition module is used to collect environmental data inside the greenhouse through environmental acquisition equipment, and to generate primary data after preprocessing the environmental data; The computing module is used to transmit the primary data set to a cloud computing platform, and then randomly split the primary data set into multiple control data sets through the cloud computing platform. The prediction module is used to combine weather forecasts and multiple control groups to run a crop growth model on the cloud computing platform to obtain plant growth prediction data respectively. The analysis module is used to input the plant growth prediction data into the adjustment model for analysis and output multiple corresponding pre-adjustment parameters; The adjustment module is used to perform overall calculations on multiple pre-adjustment parameters to obtain target adjustment parameters, and to adjust the control equipment in the greenhouse according to the target adjustment parameters.

Images