Flower greenhouse parameter optimization method and system based on deep learning

Abstract

The present application relates to the field of greenhouse environment intelligent control, and discloses a method for optimizing parameters of a flower greenhouse based on deep learning, the method comprising: obtaining a first historical parameter set and a current parameter set of the flower greenhouse; determining a first control parameter set in a first subsequent time period starting from the current moment according to the first historical parameter set and the current parameter set through a time series control model; determining a first revised control parameter set in a first subsequent time period starting from the current moment according to an expert knowledge base model, according to the first historical parameter set, the current parameter set and the first control parameter set, and controlling the environment in the flower greenhouse according to the first revised control parameter set; wherein the first control parameter set and the first revised control parameter set are control parameter sets in time series. The present application improves the effect of greenhouse environment control by combining an expert knowledge base with deep learning.

Description

Technical Field

[0001] The present application relates to the technical field of greenhouse environment intelligent control, and more specifically, to a method and system for optimizing flower greenhouse parameters based on deep learning. Background Art

[0002] Greenhouses can provide a suitable growth environment for green plants and flowers, avoid the adverse effects of changes in the external natural environment and natural disasters on the growth of green plants and flowers, and reduce the dependence of green plants and flowers on the external environment. Greenhouses are the most important environmental conditions for the cultivation of green plants and flowers, and the important parameters of greenhouses are temperature, humidity and light intensity. Different types of green plants and flowers have different requirements for temperature and humidity. In order to ensure the good appearance of the green plants and flowers that are finally grown, it is crucial to ensure that the green plants and flowers are not restricted by greenhouse conditions and to ensure a suitable and good growth environment. In recent years, with the rapid development of information technology, Internet of Things technology, sensor technology, network communication and mobile Internet technology have gradually been applied to greenhouses. Smart greenhouses have become an important part of agricultural modernization. Sensors can be used to continuously monitor greenhouse temperature, relative humidity and light, and irrigation and fertilization can be controlled based on the data. Factors such as temperature and humidity in the greenhouse can be remotely and automatically controlled to reduce labor costs.

[0003] Patent CN116910490B (application number: 202311153863.8) provides a method for providing environmental regulation of agricultural greenhouses, which relates to the field of artificial intelligence technology. The method includes: obtaining the crop growth stage in the target agricultural greenhouse; at the end of the current time step, inputting the time period corresponding to the next time step, the crop growth stage and the environmental change information in the target agricultural greenhouse into the trained target reinforcement learning model, obtaining the equipment regulation information of the next time step output by the target reinforcement learning model, and controlling the environmental equipment based on the equipment regulation information in the next time step; wherein the target reinforcement learning model is trained based on multiple groups of randomly generated sample data and corresponding target reward values. The method in patent CN116910490B can realize intelligent automatic regulation of the environment in the agricultural greenhouse, but the control of the greenhouse environment by the reinforcement learning model in patent CN116910490B may be too focused on the short-term rewards of reinforcement learning, while ignoring the long-term environmental regulation strategy during greenhouse planting, which may be detrimental to the long-term growth of plants and flowers. Summary of the invention

[0004] The purpose of this application is to provide a method and system for optimizing flower greenhouse parameters based on deep learning, which solves the technical problem of controlling the greenhouse environment through a reinforcement learning model and ignoring the long-term environmental adjustment strategy during greenhouse planting, and achieves the technical effect of improving the effect of greenhouse environmental control by combining an expert knowledge base with deep learning.

[0005] An embodiment of the present application provides a method for optimizing flower greenhouse parameters based on deep learning, the method comprising: obtaining a first historical parameter set and a current parameter set of the flower greenhouse; wherein the first historical parameter set includes the temperature, humidity, light intensity, soil moisture, and soil pH value in the flower greenhouse within the first historical time period starting from the current moment in the historical data, and the current parameter set includes the temperature, humidity, light intensity, soil moisture, and soil pH value in the flower greenhouse at the current moment; through a timing control model, according to the first historical parameter set and the current parameter set, determining a first control parameter set within a first subsequent time period starting from the current moment; according to an expert knowledge base model, according to the first historical parameter set, the current parameter set and the first control parameter set, determining a first revised control parameter set within the first subsequent time period starting from the current moment, and controlling the environment in the flower greenhouse according to the first revised control parameter set; wherein the first control parameter set and the first revised control parameter set are control parameter sets in timing.

[0006] In a possible implementation, the method also includes: determining a first evaluation value according to an expert knowledge base model, according to a first historical parameter set, a current parameter set and a first corrected control parameter set; when the first evaluation value does not meet the first preset condition, determining a second corrected control parameter set within a first subsequent time period starting from the current moment according to the expert knowledge base model, according to a second historical parameter set, the current parameter set and the first corrected control parameter set; when the first evaluation value meets the first preset condition, controlling the parameters of the greenhouse according to the first corrected control parameter set; wherein the second historical time period includes the temperature, humidity, light intensity, soil moisture, and soil pH value in the flower greenhouse within the second historical time period starting from the current moment, the second historical time period is greater than the first historical time period, and the second corrected control parameter set is a time-series control parameter set.

[0007] In another possible implementation, when the first evaluation value meets the preset conditions, the parameters of the greenhouse are controlled according to the first corrected control parameter set, and the method further includes: when the first subsequent time period is greater than the preset time length, obtaining the first subsequent parameter set of the first corrected control parameter set after the second subsequent time period, and determining the second evaluation value according to the local climate change parameter set, the current parameter set and the first subsequent parameter set through the expert knowledge base model; wherein the first subsequent parameter set includes the temperature, humidity, light intensity, soil moisture, and soil pH value in the flower greenhouse after the second subsequent time period, and the second subsequent time period is 1 / 5 to 1 / 2 of the first subsequent time period, The first subsequent parameter set is a control parameter set in time series, and the local climate change parameter set is a local climate change parameter set in time series; when the second evaluation value does not meet the second preset condition, according to the expert knowledge base model, according to the local climate change parameter set, the current parameter set and the first subsequent parameter set, the third revised control parameter set after the second subsequent time period is determined, and the environment in the flower greenhouse is controlled according to the third revised control parameter set; when the second evaluation value meets the second preset condition, the parameters of the greenhouse continue to be controlled according to the first revised control parameter set after the second subsequent time period; wherein, the third revised control parameter set is a control parameter set in time series.

[0008] In another possible implementation, according to the expert knowledge base model, according to the local climate change parameter set, the current parameter set and the first subsequent parameter set, a third corrected control parameter set after the second subsequent time period is determined, including: obtaining the time series impact rate parameter set of the external environment of the flower greenhouse on the internal environment of the greenhouse during the second subsequent time period; determining the third corrected control parameter set after the second subsequent time period according to the time series impact rate parameter set, the local climate change parameter set, the current parameter set and the first subsequent parameter set.

[0009] In another possible implementation, the length of the first historical time period is 3 to 5 days, and the length of the second historical time period is 7 to 10 days.

[0010] In another possible implementation, the timing control model is trained by empirical data collected during the greenhouse flower cultivation process; the expert knowledge base model is a neural network model trained by flower cultivation experts' flower cultivation expertise, flower cultivation experience and flower cultivation rules.

[0011] The embodiment of the present application also provides a flower greenhouse parameter optimization system based on deep learning, including a unit for executing any of the above methods.

[0012] An embodiment of the present application also provides a flower greenhouse parameter optimization system based on deep learning, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the method described above when executing the computer program.

[0013] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described above is implemented.

[0014] An embodiment of the present application also provides a computer program product, including a computer program, which implements the steps of the method described above when executed by a processor.

[0015] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0016] The embodiment of the present application provides a method for optimizing parameters of a flower greenhouse based on deep learning, and the method includes: obtaining a first historical parameter set and a current parameter set of the flower greenhouse; determining a first control parameter set in a first subsequent time period starting from the current moment according to the first historical parameter set and the current parameter set through a timing control model; determining a first revised control parameter set in a first subsequent time period starting from the current moment according to an expert knowledge base model, according to the first historical parameter set, the current parameter set and the first control parameter set, and controlling the environment in the flower greenhouse according to the first revised control parameter set. The embodiment of the present application can correct the first control parameter set generated by the timing control model through the expert knowledge base model, and then can use the long-term environmental adjustment strategy during greenhouse planting to adjust the control parameters when the flower greenhouse is used, which is conducive to the control of the long-term growth state of plants and flowers. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0018] Figure 1 A flow chart of a method for optimizing flower greenhouse parameters based on deep learning provided in an embodiment of the present application;

[0019] Figure 2 A schematic diagram of the workflow of a method for optimizing flower greenhouse parameters based on deep learning provided in an embodiment of the present application;

[0020] Figure 3A flow chart of another method for optimizing flower greenhouse parameters based on deep learning provided in an embodiment of the present application;

[0021] Figure 4 A schematic diagram of the workflow of another method for optimizing flower greenhouse parameters based on deep learning provided in an embodiment of the present application;

[0022] Figure 5 A schematic diagram of the workflow of another method for optimizing flower greenhouse parameters based on deep learning provided in an embodiment of the present application;

[0023] Figure 6 A schematic diagram of the workflow of another method for optimizing flower greenhouse parameters based on deep learning provided in an embodiment of the present application;

[0024] Figure 7 A logical schematic diagram of a flower greenhouse parameter optimization system based on deep learning provided in an embodiment of the present application;

[0025] Figure 8 A physical schematic diagram of a flower greenhouse parameter optimization system based on deep learning provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0027] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0028] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0029] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0030] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0031] The greenhouse environment control method in the prior art can realize intelligent and automatic adjustment of the environment in the agricultural greenhouse. For example, the greenhouse environment can be controlled through a reinforcement learning model. However, when controlling the environmental parameters in the greenhouse through reinforcement learning, it may be too focused on the short-term rewards of reinforcement learning and ignore the long-term environmental adjustment strategy during greenhouse cultivation, which may be detrimental to the long-term growth of plants and flowers.

[0032] Based on the above reasons, the embodiment of the present application provides a method for optimizing parameters of a flower greenhouse based on deep learning, and the method includes: obtaining a first historical parameter set and a current parameter set of the flower greenhouse; determining a first control parameter set in a first subsequent time period starting from the current moment according to the first historical parameter set and the current parameter set through a timing control model; determining a first revised control parameter set in a first subsequent time period starting from the current moment according to an expert knowledge base model, according to the first historical parameter set, the current parameter set and the first control parameter set, and controlling the environment in the flower greenhouse according to the first revised control parameter set. The embodiment of the present application can correct the first control parameter set generated by the timing control model through the expert knowledge base model, and then can use the long-term environmental adjustment strategy during greenhouse planting to adjust the control parameters when the flower greenhouse is used, which is conducive to the control of the long-term growth state of plants and flowers.

[0033] In some scenarios, a flower greenhouse parameter optimization method based on deep learning in an embodiment of the present application can be applied to the environmental control of greenhouses for various flowers, which can improve the effect of planting various flowers in greenhouses and is beneficial to the long-term planting effect of flowers.

[0034] The following is a detailed description of a flower greenhouse parameter optimization method based on deep learning provided in an embodiment of the present application with reference to specific examples.

[0035] Figure 1 A flow chart of a method for optimizing flower greenhouse parameters based on deep learning provided in an embodiment of the present application is shown in FIG. Figure 1As shown, the method includes S110 to S130, and S110 to S130 are described in detail below.

[0036] S110, obtaining a first historical parameter set and a current parameter set of the flower greenhouse, wherein the first historical parameter set includes the temperature, humidity, light intensity, soil moisture, and soil pH value in the flower greenhouse in the first historical time period starting from the current moment in the historical data, and the current parameter set includes the temperature, humidity, light intensity, soil moisture, and soil pH value in the flower greenhouse at the current moment.

[0037] like Figure 1 As shown, the first historical parameter set of the flower greenhouse can be obtained first. The first historical parameter set includes the temperature, humidity, light intensity, soil moisture, and soil pH value in the flower greenhouse during the first historical time period traced back from the current moment in the historical data. The first historical parameter set represents the historical environmental parameters in the flower greenhouse, and then the subsequent environmental parameters in the flower greenhouse can be controlled according to the historical environmental data of the environment in the flower greenhouse, thereby ensuring the control effect of the environment in the greenhouse.

[0038] like Figure 1 As shown, the current parameter set of the flower greenhouse can also be obtained. The current parameter set includes the temperature, humidity, light intensity, soil moisture, and soil pH value in the flower greenhouse at the current moment. The current parameter set represents the current environmental parameters in the flower greenhouse, and then the subsequent environmental parameters in the flower greenhouse can be controlled according to the current environmental data of the environment in the flower greenhouse, thereby ensuring the control effect of the environment in the greenhouse.

[0039] S120. Determine, through a timing control model, a first control parameter set in a first subsequent time period starting from the current moment according to the first historical parameter set and the current parameter set.

[0040] like Figure 1 As shown, a first control parameter set in a first subsequent time period starting from the current moment can be determined through a timing control model according to a first historical parameter set and a current parameter set, and the first control parameter set is used to control the environment in the flower greenhouse.

[0041] For example, the time sequence control model can be trained according to the time sequence environmental control parameter set, and the environmental parameters in the flower greenhouse can be controlled according to the time sequence control model. The time sequence control model can be a reinforcement learning model.

[0042] S130. According to the expert knowledge base model, according to the first historical parameter set, the current parameter set and the first control parameter set, determine the first revised control parameter set in the first subsequent time period starting from the current moment, and control the environment in the flower greenhouse according to the first revised control parameter set.

[0043] like Figure 1 As shown, in order to avoid ignoring the long-term environmental regulation strategy during greenhouse planting when controlling the environment in the flower greenhouse through the timing control model, and to improve the long-term control effect on the growth of plants and flowers, the control process can be corrected through an expert knowledge base model with expert knowledge.

[0044] Figure 2 A workflow diagram of a method for optimizing flower greenhouse parameters based on deep learning provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, according to the expert knowledge base model, based on the first historical parameter set, the current parameter set and the first control parameter set, a first corrected control parameter set in the first subsequent time period starting from the current moment can be determined. The first corrected control parameter set represents the control parameters after the parameters in the flower planting greenhouse are corrected according to expert knowledge, thereby improving the long-term control effect on the growth of plants and flowers.

[0045] During operation, after obtaining the first modified control parameter set, the environment in the flower greenhouse can be controlled according to the first modified control parameter set.

[0046] During operation, the first control parameter set and the first revised control parameter set are time-series control parameter sets, through which the environment in the greenhouse can be continuously adjusted in time, thereby improving the control effect of the environmental parameters in the greenhouse.

[0047] The beneficial effect brought about by the above-mentioned implementation method is that the first control parameter set generated by the timing control model is corrected through the expert knowledge base model, and then the greenhouse environment can be controlled in combination with the long-term environmental adjustment strategy during greenhouse planting, which is beneficial to the long-term growth state control of plants and flowers.

[0048] In some implementations, Figure 3 A flow chart of another method for optimizing flower greenhouse parameters based on deep learning provided in an embodiment of the present application is shown in FIG. Figure 3 As shown, the above method further includes S210 to S220, and S210 to S220 are described in detail below.

[0049] S210. Determine a first evaluation value according to the expert knowledge base model, the first historical parameter set, the current parameter set and the first corrected control parameter set.

[0050] Figure 4 A schematic diagram of the workflow of another method for optimizing flower greenhouse parameters based on deep learning provided in an embodiment of the present application is shown in FIG. Figure 4As shown, in order to further verify the control effect of the environmental parameter control set in the flower greenhouse, a first evaluation value can be determined according to the expert knowledge base model, according to the first historical parameter set, the current parameter set and the first revised control parameter set. The first evaluation value represents the growth control effect of flowers when the environment in the flower greenhouse is controlled according to the first historical parameter set, the current parameter set and the first revised control parameter set.

[0051] Exemplarily, the first evaluation value may be a scalar value output by the expert knowledge base model based on the first historical parameter set, the current parameter set and the first corrected control parameter set. Based on the first evaluation value, the environmental control effect of the first corrected control parameter set can be evaluated.

[0052] S220: When the first evaluation value does not meet the first preset condition, determine a second corrected control parameter set within a first subsequent time period starting from the current moment according to the expert knowledge base model, the second historical parameter set, the current parameter set and the first corrected control parameter set. When the first evaluation value meets the first preset condition, control the parameters of the greenhouse according to the first corrected control parameter set.

[0053] During use, when the first evaluation value does not meet the first preset condition, it means that the environmental control effect based on the first corrected control parameter set is not good at this time, and it is impossible to control the greenhouse environment in combination with the long-term environmental adjustment strategy during greenhouse planting, and it is impossible to effectively control the long-term growth state of plants and flowers.

[0054] Figure 5 A schematic diagram of the workflow of another method for optimizing flower greenhouse parameters based on deep learning provided in an embodiment of the present application is shown in FIG. Figure 5 As shown, in order to improve the control effect of the long-term environmental adjustment strategy for flower planting, the second corrected control parameter set in the first subsequent time period starting from the current moment can be determined according to the expert knowledge base model, the second historical parameter set, the current parameter set and the first corrected control parameter set. The second corrected control parameter set is also the control parameter after correcting the parameters in the flower planting greenhouse according to expert knowledge, thereby improving the long-term control effect on the growth of plants and flowers.

[0055] When in use, the second historical time period includes the temperature, humidity, light intensity, soil moisture, and soil pH value in the flower greenhouse within the second historical time period starting from the current moment. The second historical time period is longer than the first historical time period. Compared with the first historical time period, the parameters in the flower greenhouse within the second historical time period with a longer time span can be used to control the greenhouse environment, thereby further improving the long-term control effect on the growth of plants and flowers.

[0056] When used, the second modified control parameter set is a time-sequential control parameter set.

[0057] Exemplarily, the first preset condition may be that the first evaluation value is less than a preset first evaluation value.

[0058] During use, when the first evaluation value meets the first preset condition, the parameters of the greenhouse can be controlled according to the first modified control parameter set.

[0059] The beneficial effect brought about by the above-mentioned implementation method is that it can evaluate the effect of controlling the greenhouse environment by the parameters in the flower greenhouse according to the first historical parameter set, and can evaluate the effect of controlling the environment in the flower greenhouse, thereby ensuring the reliability of long-term control of the parameters in the flower greenhouse.

[0060] The beneficial effect brought about by the above-mentioned implementation method is that when the effect of controlling the greenhouse environment by using the parameters in the flower greenhouse according to the first historical parameter set is not good, the greenhouse environment can be controlled by using the parameters in the flower greenhouse in the second historical time period with a longer time span, thereby further improving the long-term control effect on the growth of plants and flowers.

[0061] In some implementations, in the above S220, when the first evaluation value meets the preset conditions, the parameters of the greenhouse are controlled according to the first modified control parameter set, and also include S221 to S222. S221 to S222 are described in detail below.

[0062] S221. When the first subsequent time period is greater than the preset time length, obtain the first subsequent parameter set of the first modified control parameter set after the second subsequent time period, and determine the second evaluation value according to the local climate change parameter set, the current parameter set and the first subsequent parameter set through the expert knowledge base model. The first subsequent parameter set includes the temperature, humidity, light intensity, soil moisture and soil pH value in the flower greenhouse after the second subsequent time period, the second subsequent time period is 1 / 5 to 1 / 2 of the first subsequent time period, the first subsequent parameter set is a control parameter set in time series, and the local climate change parameter set is a local climate change parameter set in time series.

[0063] When the environment during flower planting is controlled for a long time, when the first subsequent time period is greater than the preset time length, the control effect of the greenhouse environment in the first subsequent time period can be verified, and the first subsequent parameter set of the first revised control parameter set after the second subsequent time period can be obtained, and the greenhouse environment control effect of the first subsequent parameter set can be verified, and the first subsequent parameter set is a subset of the first revised control parameter set after the second subsequent time period.

[0064] When in use, the second evaluation value can be determined through the expert knowledge base model according to the local climate change parameter set, the current parameter set and the first subsequent parameter set. The local climate change parameter set characterizes the local climate change characteristics. When the first subsequent time period is greater than the preset duration, the greenhouse environment control effect of the first subsequent parameter set can be verified through the climate change characteristics.

[0065] When in use, the environmental control effect of long-term control of the environment when planting flowers can be verified by using the local climate change parameter set, the current parameter set and the first subsequent parameter set through the expert knowledge base model.

[0066] Exemplarily, the preset duration may be 8 days, 10 days or 12 days.

[0067] Exemplarily, the expert knowledge base model may be a parameter control model for long-term control of the environment within the greenhouse obtained by training with a local climate change parameter set, a current parameter set, and a first subsequent parameter set.

[0068] When working, the first subsequent parameter set includes the temperature, humidity, light intensity, soil moisture, and soil pH value in the flower greenhouse after the second subsequent time period. The second subsequent time period is 1 / 5 to 1 / 2 of the first subsequent time period, and the second subsequent time period is a subset of the first subsequent time period.

[0069] During operation, the first subsequent parameter set is a control parameter set in time sequence, and the greenhouse environmental parameters can be controlled in time sequence through the first subsequent parameter set.

[0070] When in use, the local climate change parameter set may be a local climate change parameter set in a time series obtained through meteorological data.

[0071] S222: When the second evaluation value does not meet the second preset condition, determine the third revised control parameter set after the second subsequent time period according to the expert knowledge base model, the local climate change parameter set, the current parameter set and the first subsequent parameter set, and control the environment in the flower greenhouse according to the third revised control parameter set. When the second evaluation value meets the second preset condition, continue to control the parameters of the greenhouse according to the first revised control parameter set after the second subsequent time period. The third revised control parameter set is a control parameter set in time sequence.

[0072] At work, Figure 6 A schematic diagram of the workflow of another method for optimizing flower greenhouse parameters based on deep learning provided in an embodiment of the present application is shown in FIG. Figure 6As shown, when the second evaluation value does not meet the second preset condition, it means that the control effect of the greenhouse environment in the first subsequent time is not good. According to the expert knowledge base model, according to the local climate change parameter set, the current parameter set and the first subsequent parameter set, a third revised control parameter set after the second subsequent time period can be determined. The third revised control parameter set is a control parameter set that corrects the first subsequent parameter set, and then the environment in the flower greenhouse can be controlled according to the third revised control parameter set.

[0073] Exemplarily, the second evaluation value may be a scalar value, and the second preset condition may be that the second evaluation value is less than a preset second evaluation value.

[0074] During operation, when the second evaluation value meets the second preset condition, it means that the control effect of the greenhouse environment in the first subsequent time is as expected, and the parameters of the greenhouse can continue to be controlled according to the first corrected control parameter set after the second subsequent time period.

[0075] When in use, the third modified control parameter set is a time-series control parameter set, and the greenhouse environment can be controlled in time sequence through the third modified control parameter set.

[0076] The beneficial effect brought about by the above-mentioned implementation method is that when the first subsequent time period is long, the environmental control effect of long-term control of the environment during flower planting is verified by using the local climate change parameter set, the current parameter set and the first subsequent parameter set through the expert knowledge base model.

[0077] The beneficial effect brought about by the above implementation method is that when the first subsequent time period is long, the control effect of the greenhouse environment can be verified in combination with the local climate change characteristics, thereby improving the accuracy of the verification of the control effect of the greenhouse environment.

[0078] The beneficial effect brought about by the above implementation method is that when the control effect after the second subsequent time period is not good, the control of the greenhouse environment after the second subsequent time period can be corrected in combination with the local climate change characteristics to improve the control effect of the greenhouse environment.

[0079] In some implementations, in the above S222, determining, according to the expert knowledge base model, the local climate change parameter set, the current parameter set, and the first subsequent parameter set, a third revised control parameter set after the second subsequent time period includes:

[0080] S222a, obtaining a time series impact rate parameter set of the external environment of the flower greenhouse on the internal environment of the greenhouse in the second subsequent time period.

[0081] When in use, when the greenhouse environment is controlled according to the local climate change parameter set, the time series impact rate parameter set of the external environment of the flower greenhouse on the internal environment of the greenhouse in the second subsequent time period can be obtained. The time series impact rate parameter set represents the degree of influence of the external environment of the greenhouse on the internal environment of the greenhouse in the time sequence.

[0082] Exemplarily, the timing impact rate parameter set may be pre-determined through experiments.

[0083] S222b, determining a third modified control parameter set after a second subsequent time period according to the time series impact rate parameter set, the local climate change parameter set, the current parameter set and the first subsequent parameter set.

[0084] When in use, the third corrected control parameter set after the second subsequent time period can be determined based on the time series impact rate parameter set, the local climate change parameter set, the current parameter set and the first subsequent parameter set. Then, the first subsequent parameter set can be adjusted in combination with the local climate change and the degree of impact of climate change on the environment inside the greenhouse to obtain the third corrected control parameter set after the second subsequent time period, thereby improving the control effect of the environment inside the greenhouse.

[0085] The beneficial effect brought about by the above implementation method is that the first subsequent parameter set can be adjusted in combination with the local climate change and the impact of climate change on the environment inside the greenhouse, thereby improving the control accuracy of the environment inside the greenhouse.

[0086] In some implementations, the first historical time period is 3 to 5 days long, and the second historical time period is 7 to 10 days long.

[0087] The beneficial effect brought about by the above implementation method is that the first historical time period and the second historical time period correspond to the greenhouse environment control parameters in different time spans respectively, and the greenhouse environment can be controlled in different time spans in combination with the long-term growth control strategy of flower plants.

[0088] In some implementations, the timing control model is trained by using empirical data collected during the flower greenhouse cultivation process. The empirical data collected during the flower greenhouse cultivation process can be used to train a timing control model for controlling the greenhouse environment in a short period of time.

[0089] In some implementations, flower cultivation expertise, flower cultivation experience, and flower cultivation rules corresponding to long-term strategies in flower cultivation can be converted into training data. The expert knowledge base model is a neural network model trained with the flower cultivation expertise, flower cultivation experience, and flower cultivation rules of flower cultivation experts. The expert knowledge base model can realize the control of long-term cultivation strategies for flower greenhouses.

[0090] The embodiment of the present application also provides a flower greenhouse parameter optimization system based on deep learning, including a unit for executing any of the above methods.

[0091] Figure 7 A logical structure diagram of a flower greenhouse parameter optimization system based on deep learning provided in one embodiment of the present application is shown in FIG. Figure 7 As shown, the system 1 of this embodiment includes a processing unit 11, a storage unit 12 and a transceiver unit 13. The processing unit 11 is used to process data, the storage unit 12 is used to store data, and the transceiver unit 13 is used to send and receive data. The processing unit 11, the storage unit 12 and the transceiver unit 13 cooperate with each other to implement the above method. The beneficial effects brought by the embodiment of the present application have been described in the above method and will not be repeated here.

[0092] An embodiment of the present application also provides a flower greenhouse parameter optimization system based on deep learning, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the method described above when executing the computer program.

[0093] Figure 8 A schematic diagram of the physical structure of a flower greenhouse parameter optimization system based on deep learning provided in one embodiment of the present application, such as Figure 8 As shown, the system 2 of this embodiment includes: at least one processor 20 ( Figure 8 Only one processor 20 is shown in the figure), a memory 21, and a computer program 22 stored in the memory 21 and executable on the at least one processor 20. When the processor 20 executes the computer program 22, the steps in any of the above-mentioned method embodiments are implemented. The beneficial effects brought about by the embodiments of the present application have been described in the above-mentioned methods and will not be repeated here.

[0094] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0095] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0096] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0097] An embodiment of the present application provides a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0098] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0099] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0100] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example 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 performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0101] In the embodiments provided in the present 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 only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0102] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0103] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for optimizing flower greenhouse parameters based on deep learning, characterized in that: The method comprises: Obtain a first historical parameter set and a current parameter set of the flower greenhouse; wherein the first historical parameter set includes the temperature, humidity, light intensity, soil moisture, and soil pH value in the flower greenhouse in the first historical time period starting from the current moment in the historical data, and the current parameter set includes the temperature, humidity, light intensity, soil moisture, and soil pH value in the flower greenhouse at the current moment; Determine, by means of a timing control model, a first control parameter set in a first subsequent time period starting from the current moment according to the first historical parameter set and the current parameter set; According to the expert knowledge base model, according to the first historical parameter set, the current parameter set and the first control parameter set, a first revised control parameter set in a first subsequent time period starting from the current moment is determined, and the environment in the flower greenhouse is controlled according to the first revised control parameter set; wherein the first control parameter set and the first revised control parameter set are control parameter sets in time sequence; The method further comprises: Determining a first evaluation value based on the expert knowledge base model, based on the first historical parameter set, the current parameter set, and the first revised control parameter set; When the first evaluation value does not meet the first preset condition, the second corrected control parameter set within the first subsequent time period starting from the current moment is determined according to the expert knowledge base model, the second historical parameter set, the current parameter set and the first corrected control parameter set; when the first evaluation value meets the first preset condition, the parameters of the greenhouse are controlled according to the first corrected control parameter set; wherein the second historical time period includes the temperature, humidity, light intensity, soil moisture, soil pH value in the flower greenhouse within the second historical time period starting from the current moment, the second historical time period is greater than the first historical time period, and the second corrected control parameter set is a time series control parameter set.

2. The method according to claim 1, characterized in that When the first evaluation value meets the preset condition, the parameters of the greenhouse are controlled according to the first modified control parameter set, further comprising: When the first subsequent time period is greater than the preset time length, the first subsequent parameter set of the first corrected control parameter set after the second subsequent time period is obtained, and the second evaluation value is determined according to the local climate change parameter set, the current parameter set and the first subsequent parameter set through the expert knowledge base model; wherein the first subsequent parameter set includes the temperature, humidity, light intensity, soil moisture, and soil pH value in the flower greenhouse after the second subsequent time period, the second subsequent time period is 1 / 5 to 1 / 2 of the first subsequent time period, the first subsequent parameter set is a control parameter set in time series, and the local climate change parameter set is a local climate change parameter set in time series; When the second evaluation value does not meet the second preset condition, according to the expert knowledge base model, based on the local climate change parameter set, the current parameter set and the first subsequent parameter set, the third revised control parameter set after the second subsequent time period is determined, and the environment in the flower greenhouse is controlled according to the third revised control parameter set; when the second evaluation value meets the second preset condition, the parameters of the greenhouse continue to be controlled according to the first revised control parameter set after the second subsequent time period; wherein, the third revised control parameter set is a time sequence control parameter set.

3. The method according to claim 2, characterized in that According to the expert knowledge base model, a third revised control parameter set after the second subsequent time period is determined based on the local climate change parameter set, the current parameter set and the first subsequent parameter set, including: Obtaining a time series impact rate parameter set of the external environment of the flower greenhouse on the internal environment of the greenhouse in the second subsequent time period; A third revised control parameter set after a second subsequent time period is determined based on the time series impact rate parameter set, the local climate change parameter set, the current parameter set and the first subsequent parameter set.

4. The method according to claim 3, characterized in that The length of the first historical time period is 3 to 5 days, and the length of the second historical time period is 7 to 10 days.

5. The method according to claim 4, characterized in that The timing control model is trained by empirical data collected during the greenhouse cultivation process of flowers; the expert knowledge base model is a neural network model trained by flower cultivation experts' flower cultivation expertise, flower cultivation experience and flower cultivation rules.

6. A flower greenhouse parameter optimization system based on deep learning, characterized in that: The method comprises means for performing the method according to any one of claims 1 to 5.

7. A flower greenhouse parameter optimization system based on deep learning, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images