Rain-avoiding cultivation greenhouse control method and system based on intelligent perception

Abstract

The present application relates to the technical field of agricultural equipment control, and particularly relates to a rain-avoiding cultivation greenhouse control method and system based on intelligent sensing. A real-time growth state model graph is imported into a dictionary search tree for search matching to obtain growth water requirement range data of pepper seedlings in a current growth stage in a target greenhouse. Real-time water data of soil in the target greenhouse is collected at a plurality of preset time nodes, and a soil water suitability deviation coefficient of the pepper seedlings in the target greenhouse is obtained by combining the collected real-time water data with the growth water requirement range data and analyzing by a Bezier curve algorithm. The water condition of the soil in the target greenhouse is analyzed according to the soil water suitability deviation coefficient, and the target greenhouse is controlled according to the analysis result. The target greenhouse can be intelligently controlled according to the soil water condition, and the pepper seedlings can grow in suitable soil water conditions, so that the growth quality and yield of the pepper seedlings are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of agricultural equipment control, in particular to a rain-avoiding cultivation greenhouse control method and system based on intelligent sensing. BACKGROUND

[0002] In recent years, with the continuous development of agricultural technology, intelligent greenhouse has been widely used in pepper cultivation, effectively improving the yield and quality of peppers and reducing production costs. However, the control method of traditional rain-avoiding cultivation greenhouse mainly relies on simple sensor data, which has the following shortcomings: first, it cannot realize real-time sensing of the growth state of pepper seedlings, and it is difficult to accurately grasp the water demand of pepper seedlings, resulting in unreasonable irrigation strategy, which easily causes high or low soil moisture, affecting the growth and development of pepper seedlings; second, it lacks accurate judgment of the growth stage of pepper seedlings, and cannot formulate corresponding control strategies according to the differentiated needs of different growth stages, resulting in slow growth or disease of pepper seedlings; third, it lacks intelligent decision mechanism, and it is difficult to realize fine management of greenhouse environment. At the same time, although some researches in the prior art try to use image recognition technology to identify the growth state of pepper seedlings, most of them lack accurate judgment of the growth stage of pepper seedlings, and it is difficult to combine with soil moisture management, lack of accurate grasp of the growth needs of pepper seedlings, and it is difficult to realize precise irrigation control. Therefore, there is an urgent need for an intelligent control method that can combine pepper seedling growth state, growth stage and soil moisture and other factors to realize fine management of rain-avoiding cultivation greenhouse for peppers, improve pepper yield and quality, and reduce production costs. SUMMARY

[0003] The present application overcomes the shortcomings of the prior art and provides a rain-avoiding cultivation greenhouse control method and system based on intelligent sensing.

[0004] To achieve the above-mentioned purpose, the technical scheme adopted by the present application is as follows:

[0005] The present application discloses a rain-avoiding cultivation greenhouse control method based on intelligent sensing, comprising the following steps:

[0006] Obtaining the real-time growth state image of pepper seedlings in the target greenhouse, and constructing a real-time growth state model image of pepper seedlings in the target greenhouse according to the real-time growth state image;

[0007] Obtaining the growth characteristic image and growth water requirement range data corresponding to different growth stages of pepper seedlings through a big data network, and constructing a dictionary search tree according to the growth characteristic image and growth water requirement range data corresponding to different growth stages of pepper seedlings;

[0008] Importing the real-time growth state model image into the dictionary search tree for search matching, and obtaining the growth water requirement range data of pepper seedlings in the current growth stage in the target greenhouse;

[0009] collecting real-time moisture data of the soil in the target greenhouse at several preset time nodes, and obtaining a soil moisture suitability deviation coefficient of the pepper seedlings in the target greenhouse by combining the collected real-time moisture data with the growth moisture requirement range data and using a Bezier curve algorithm;

[0010] analyzing the moisture condition of the soil in the target greenhouse according to the soil moisture suitability deviation coefficient, and performing a control treatment on the target greenhouse according to the analysis result.

[0011] Preferably, a real-time growth state model graph of the pepper seedlings in the target greenhouse is constructed according to the real-time growth state image, specifically as follows:

[0012] A Canny edge detection algorithm is introduced, and feature extraction is performed on the real-time growth state image based on the Canny edge detection algorithm to obtain contour feature information of each part of the pepper seedlings;

[0013] The real-time growth state image is converted from an RGB color space to an HSV color space, and color feature information of each part of the pepper seedlings is extracted in the HSV space;

[0014] A gray level co-occurrence matrix extraction algorithm is introduced, and the gray level co-occurrence frequency of pixel pairs in each preset direction in the real-time growth state image is extracted based on the gray level co-occurrence matrix extraction algorithm, and the texture feature information of each part of the pepper seedlings is determined according to the obtained gray level co-occurrence frequency;

[0015] The real-time growth state model graph of the pepper seedlings in the target greenhouse is constructed according to the contour feature information, the color feature information and the texture feature information of each part of the pepper seedlings and in combination with three-dimensional software.

[0016] Preferably, the growth characteristic image corresponding to the pepper seedlings at different growth stages and the growth moisture requirement range data are obtained through a big data network, and a dictionary search tree is constructed according to the growth characteristic image corresponding to the pepper seedlings at different growth stages and the growth moisture requirement range data, specifically as follows:

[0017] The growth characteristic image corresponding to the pepper seedlings at different growth stages and the growth moisture requirement range data are obtained through a big data network, and a growth characteristic model graph corresponding to the pepper seedlings at different growth stages is constructed according to the growth characteristic image;

[0018] A dictionary tree is constructed, and several dictionary branches are cut out from the dictionary tree according to the pepper at different growth stages;

[0019] The growth moisture requirement range data corresponding to the pepper seedlings at different growth stages are obtained, and the growth moisture requirement range data corresponding to the pepper seedlings at different growth stages are converted into specific string data;

[0020] mapping each string data on the root node of the corresponding dictionary fork branch, completing the coding operation of each dictionary fork branch;

[0021] The growth characteristic model graph corresponding to the pepper seedlings at different growth stages is stored on the leaf node of the corresponding dictionary fork branch to obtain a dictionary search tree.

[0022] Preferably, the real-time growth state model graph is imported into the dictionary search tree for search matching to obtain the growth water requirement range data of the pepper seedlings in the target greenhouse at the current growth stage, specifically:

[0023] The real-time growth state model graph of the pepper seedlings in the target greenhouse is obtained, and the growth characteristic model graph on each dictionary fork branch in the dictionary search tree is obtained;

[0024] The real-time growth state model graph and the growth characteristic model graph on each dictionary fork branch are subjected to similarity analysis to obtain the similarity between the real-time growth state model graph and the growth characteristic model graph on each dictionary fork branch;

[0025] The similarity between the real-time growth state model graph and the growth characteristic model graph on each dictionary fork branch is subjected to size sorting processing, and the maximum similarity is sorted out;

[0026] The growth characteristic model graph corresponding to the maximum similarity is marked, the string data of the dictionary fork branch of the marked growth characteristic model graph is obtained, and the obtained string data is interpreted to obtain the growth water requirement range data of the pepper seedlings in the target greenhouse at the current growth stage.

[0027] Preferably, the real-time water data of the soil in the target greenhouse is collected at a plurality of preset time nodes, and the soil water suitability deviation coefficient of the pepper seedlings in the target greenhouse is analyzed according to the collected real-time water data and the growth water requirement range data combined with the Bezier curve algorithm, specifically:

[0028] The real-time water data of the soil in the target greenhouse is collected at a plurality of preset time nodes, the Bezier curve algorithm is introduced, and the real-time water data collected at each preset time node is taken as a discrete point;

[0029] According to the sequence of each collection time node, the discrete points are connected to construct a water dynamic Bezier curve of the soil in the target greenhouse;

[0030] The upper constraint boundary and the lower constraint boundary are determined according to the growth water requirement range data of the pepper seedlings in the target greenhouse at the current growth stage, and a constraint region is divided in the water dynamic Bezier curve according to the upper constraint boundary and the lower constraint boundary;

[0031] calculating a total curve length of the moisture dynamic Bezier curve outside the constraint region, and calculating a total curve length of the moisture dynamic Bezier curve inside the constraint region;

[0032] performing ratio processing on the total curve length of the moisture dynamic Bezier curve outside the constraint region and the total curve length of the moisture dynamic Bezier curve inside the constraint region to obtain a soil moisture suitability deviation coefficient of the pepper seedlings in the target greenhouse.

[0033] Preferably, the soil moisture condition in the target greenhouse is analyzed according to the soil moisture suitability deviation coefficient, and the target greenhouse is controlled according to the analysis result, specifically:

[0034] comparing the soil moisture suitability deviation coefficient of the pepper seedlings in the target greenhouse with a preset coefficient threshold value;

[0035] If the soil moisture suitability deviation coefficient of the pepper seedlings in the target greenhouse is not greater than the preset coefficient threshold value, it indicates that the soil moisture condition in the target greenhouse meets the growth demand of the pepper seedlings in the current growth stage, and the target greenhouse is not controlled.

[0036] Preferably, the soil moisture condition in the target greenhouse is analyzed according to the soil moisture suitability deviation coefficient, and the target greenhouse is controlled according to the analysis result, specifically:

[0037] If the soil moisture suitability deviation coefficient of the pepper seedlings in the target greenhouse is greater than the preset coefficient threshold value, it indicates that the soil moisture condition in the target greenhouse does not meet the growth demand of the pepper seedlings in the current growth stage, and an average value of real-time moisture data collected at a plurality of preset time nodes is calculated to obtain a moisture data average value.

[0038] The moisture data average value is compared with a preset threshold value, if the moisture data average value is greater than the preset threshold value, the soil in the target greenhouse is determined to be in a drought condition; otherwise, the soil in the target greenhouse is determined to be in an over-wet condition.

[0039] Preferably, the soil moisture condition in the target greenhouse is analyzed according to the soil moisture suitability deviation coefficient, and the target greenhouse is controlled according to the analysis result, and the method further comprises the following steps:

[0040] If the soil in the target greenhouse is in an over-wet condition, real-time rainfall in a preset range of the target greenhouse is obtained, if the real-time rainfall in the preset range of the target greenhouse is greater than a preset rainfall, the roof of the target greenhouse is controlled to be closed to realize a rain blocking function.

[0041] If the real-time rainfall in the preset range area of the target greenhouse is not greater than the preset rainfall, the real-time light intensity in the preset range area of the target greenhouse is acquired; if the real-time light intensity in the preset range area of the target greenhouse is greater than the preset intensity value, the roof of the target greenhouse is controlled to be opened, and the natural sunlight irradiation dehumidification function is realized.

[0042] Preferably, the water condition of the soil in the target greenhouse is analyzed according to the soil water suitability deviation coefficient, and the target greenhouse is controlled according to the analysis result, and the method further comprises the following steps:

[0043] If the soil in the target greenhouse is in a drought condition, the real-time rainfall in the preset range area of the target greenhouse is acquired, and if the real-time rainfall in the preset range area of the target greenhouse is greater than the preset rainfall, the roof of the target greenhouse is controlled to be opened, and the natural rainwater irrigation function is realized.

[0044] If the real-time rainfall in the preset range area of the target greenhouse is not greater than the preset rainfall, the real-time light intensity in the preset range area of the target greenhouse is acquired; if the real-time light intensity in the preset range area of the target greenhouse is greater than the preset intensity value, the roof of the target greenhouse is controlled to be closed, and the moisture retention function of the target greenhouse is strengthened.

[0045] The application further discloses a rain-avoiding cultivation greenhouse control system based on intelligent sensing, which comprises a memory and a processor, and the memory stores a rain-avoiding cultivation greenhouse control method program.

[0046] The application solves the technical defects in the background art, and has the following beneficial effects: the rain-avoiding greenhouse control method for pepper cultivation based on intelligent sensing realizes accurate monitoring and judgment of the growth state of pepper seedlings and the water condition of soil by integrating image analysis, big data processing, algorithm calculation and environmental factor consideration. The water demand of the current growth stage of the pepper seedlings can be accurately acquired, the suitable degree of soil water is quantified, and the greenhouse environment is intelligently regulated according to the analysis result, so that the pepper seedlings grow in suitable soil water conditions, thereby improving the growth quality and yield of the pepper seedlings, reducing the blindness of artificial intervention, and improving the efficiency and scientific nature of greenhouse cultivation management. BRIEF DESCRIPTION OF DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the application, and those skilled in the art can obtain other drawings of other embodiments according to these drawings without any creative effort.

[0048] Figure 1 The whole method flow chart of the pepper cultivation rain-avoiding greenhouse control method is shown in the figure;

[0049] Figure 2 The partial method flow chart of the pepper cultivation rain-avoiding greenhouse control method is shown in the figure;

[0050] Figure 3 The system block diagram of the pepper cultivation rain-avoiding greenhouse control system is shown in the figure. DETAILED DESCRIPTION

[0051] In order to enable the above-mentioned objects, features and advantages of the present application to be more clearly understood, the following further describes the present application with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0052] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application. However, the present application can be practiced in other manners different from those described herein, and therefore, the scope of protection of the present application is not limited by the specific embodiments disclosed below.

[0053] The present application discloses a rain-avoiding cultivation greenhouse control method based on intelligent sensing, as shown in the figure, comprising the following steps: Figure 1

[0054] S102: Obtain the real-time growth state image of the pepper seedlings in the target greenhouse, and construct a real-time growth state model graph of the pepper seedlings in the target greenhouse according to the real-time growth state image;

[0055] S104: Obtain the growth characteristic image and growth water requirement range data corresponding to the pepper seedlings at different growth stages through a big data network, and construct a dictionary search tree according to the growth characteristic image and growth water requirement range data corresponding to the pepper seedlings at different growth stages;

[0056] S106: Import the real-time growth state model graph into the dictionary search tree for search matching, and obtain the growth water requirement range data of the pepper seedlings in the target greenhouse at the current growth stage;

[0057] S108: Collect the real-time water data of the soil in the target greenhouse at a plurality of preset time nodes, and analyze the soil water suitability deviation coefficient of the pepper seedlings in the target greenhouse by combining the collected real-time water data with the growth water requirement range data and using a Bezier curve algorithm;

[0058] S110: Analyze the water condition of the soil in the target greenhouse according to the soil water suitability deviation coefficient, and perform control processing on the target greenhouse according to the analysis result. ​

[0059] The intelligent perception-based rain-avoiding greenhouse control method for pepper cultivation realizes accurate monitoring and judgment of the growth state of pepper seedlings and the soil moisture condition by integrating image analysis, big data processing, algorithm calculation, and environmental factor consideration. It can accurately obtain the current water demand of the pepper seedlings at the growth stage, quantify the suitable degree of soil moisture, and intelligently regulate the greenhouse environment according to the analysis results to ensure that the pepper seedlings grow in suitable soil moisture conditions, thereby improving the growth quality and yield of the pepper seedlings, while reducing the blindness of manual intervention and improving the efficiency and scientificity of greenhouse cultivation management.

[0060] Preferably, a real-time growth state model graph of the pepper seedlings in the target greenhouse is constructed according to the real-time growth state image, specifically:

[0061] The Canny edge detection algorithm is introduced, and feature extraction is performed on the real-time growth state image based on the Canny edge detection algorithm to obtain contour feature information of each part of the pepper seedlings;

[0062] The real-time growth state image is converted from the RGB color space to the HSV color space, and color feature information of each part of the pepper seedlings is extracted in the HSV space;

[0063] The gray level co-occurrence matrix extraction algorithm is introduced, and the gray level co-occurrence frequency of pixel pairs in each preset direction in the real-time growth state image is extracted based on the gray level co-occurrence matrix extraction algorithm, and the texture feature information of each part of the pepper seedlings is determined according to the obtained gray level co-occurrence frequency;

[0064] The real-time growth state model graph of the pepper seedlings in the target greenhouse is constructed according to the contour feature information, color feature information, and texture feature information of each part of the pepper seedlings and combined with three-dimensional software.

[0065] It should be noted that the Canny edge detection algorithm is a classic edge detection algorithm. When processing the real-time growth state image of the pepper seedlings, it can accurately identify the edges of each part of the pepper seedlings, thereby obtaining contour feature information. For example, it can clearly distinguish the edge shapes of the stems, leaves, fruits, and other parts of the pepper seedlings, which helps to determine the overall morphological structure of the pepper seedlings and provides a basic shape framework for subsequent model construction.

[0066] It is meaningful to convert the image from the RGB color space to the HSV color space. The RGB color space is sensitive to light changes, while the HSV color space is more consistent with human perception of color. Extracting color feature information of each part of the pepper seedlings in the HSV space can more accurately describe the color state of the pepper seedlings. For example, the color of the leaves of the pepper seedlings at different growth stages may change from light green to dark green, and the color of the fruits may change from green to red. Through color feature extraction in the HSV space, these changes can be well captured.

[0067] The gray level co-occurrence matrix extraction algorithm is used to extract the gray level co-occurrence frequency of pixel pairs in each preset direction in the real-time growth state image. Through this frequency, the texture feature information of each part of the pepper seedling can be determined. The leaves, stems and other parts of the pepper seedling have different textures, for example, the leaf surface may have fine vein texture, and the stem may have certain roughness texture. These texture features help to further distinguish different parts of the pepper seedling and can reflect the health status and growth state of the pepper seedling.

[0068] According to the contour feature information, color feature information and texture feature information of each part of the pepper seedling obtained in the foregoing, a real-time growth state model graph of the pepper seedling in the target greenhouse is constructed by combining a three-dimensional software. The three-dimensional software can integrate these feature information to construct a realistic three-dimensional model that can reflect the actual growth state of the pepper seedling. This model can display the shape, color and texture features of the pepper seedling from multiple angles.

[0069] Through the above series of operations, a model graph that comprehensively and accurately reflects the real-time growth state of the pepper seedling in the target greenhouse can be constructed. This model graph integrates the contour, color and texture features of the pepper seedling and describes the growth state of the pepper seedling in multiple dimensions. It can provide intuitive and accurate basis for subsequent judgment of the growth stage, health status of the pepper seedling and the difference from the standard growth state, which helps to accurately formulate greenhouse control strategies for the growth needs of the pepper seedling, thereby improving the growth quality and yield of the pepper seedling.

[0070] Preferably, the growth characteristic image corresponding to the pepper seedling in different growth stages and the growth water requirement range data are obtained through a big data network, and a dictionary search tree is constructed according to the growth characteristic image corresponding to the pepper seedling in different growth stages and the growth water requirement range data, as shown in Figure 2 , specifically as follows:

[0071] S202: Obtain the growth characteristic image corresponding to the pepper seedling in different growth stages and the growth water requirement range data through a big data network, and construct a growth characteristic model graph corresponding to the pepper seedling in different growth stages according to the growth characteristic image;

[0072] S204: Construct a dictionary tree, and cut out a plurality of dictionary fork branches in the dictionary tree according to the pepper in different growth stages;

[0073] S206: Obtain the growth water requirement range data corresponding to the pepper seedling in different growth stages, and convert the growth water requirement range data corresponding to the pepper seedling in different growth stages into specific string data;

[0074] S208: Map each string data on the root node of the corresponding dictionary fork branch, complete the coding operation of each dictionary fork branch;

[0075] S210: Store the growth characteristic model graph corresponding to the pepper seedlings at different growth stages on the leaf node of the corresponding dictionary fork branch, and obtain the dictionary search tree.

[0076] It should be noted that first, the growth characteristic image and growth water requirement range data of pepper seedlings at different growth stages are obtained through a big data network. The growth characteristic model graph is constructed using the growth characteristic image, which helps to represent the appearance characteristics of pepper seedlings at different growth stages in a structured model form. For example, the height of the plant, the number and shape of the leaves, the shape of the flowers and fruits, etc. are different at different stages such as seedling stage, flowering stage, fruiting stage, etc. The growth characteristic model graph can accurately capture these differences. Building a dictionary tree is a data structure organization method. By cutting out several dictionary fork branches in the dictionary tree, a framework structure is provided for storing related information of pepper seedlings at different stages. This structure is similar to a classification directory, which can store information of pepper seedlings at different growth stages for classification, facilitating quick search and matching. The growth water requirement range data is converted into specific string data, which is to adapt to the data storage and retrieval method of the dictionary tree. Then these string data are mapped on the root node of the corresponding dictionary fork branch for coding operation. This operation makes each dictionary fork branch have an identifier related to the growth water requirement range, which facilitates quick positioning to the information related to the specific water requirement during search. Finally, the growth characteristic model graph corresponding to the pepper seedlings at different growth stages is stored in the leaf node of the corresponding dictionary fork branch, thereby completing the construction of the dictionary search tree. In this way, the dictionary search tree integrates the growth characteristic model graph and the growth water requirement range data of pepper seedlings at different growth stages, forming a complete and convenient query data structure.

[0077] By constructing such a dictionary search tree, the growth characteristic model graph and the growth water requirement range data of pepper seedlings at different growth stages can be efficiently stored and managed. In practical applications, when the information of pepper seedlings at a certain growth stage is needed, the corresponding dictionary fork branch can be quickly and accurately located to obtain the growth characteristic model graph and the growth water requirement range data of the pepper seedlings. This helps to accurately determine the current growth stage of the pepper seedlings, and then develop reasonable greenhouse control strategies such as irrigation based on the growth water requirement range data, improve the growth quality and yield of the pepper seedlings, and realize intelligent pepper cultivation management.

[0078] Preferably, the real-time growth state model graph is imported into the dictionary search tree for search matching to obtain the growth water requirement range data of the pepper seedlings at the current growth stage in the target greenhouse, specifically:

[0079] obtain a real-time growth state model graph of the pepper seedlings in the target greenhouse, and obtain growth characteristic model graphs on each dictionary fork branch in the dictionary search tree;

[0080] perform similarity analysis on the real-time growth state model graph and the growth characteristic model graphs on each dictionary fork branch, to obtain similarity between the real-time growth state model graph and the growth characteristic model graphs on each dictionary fork branch;

[0081] perform size ordering processing on the similarity between the real-time growth state model graph and the growth characteristic model graphs on each dictionary fork branch, to sort out the maximum similarity;

[0082] mark the growth characteristic model graph corresponding to the maximum similarity, obtain string data of the dictionary fork of the marked growth characteristic model graph, and interpret the obtained string data to obtain growth water requirement range data of the pepper seedlings in the target greenhouse at the current growth stage.

[0083] It should be noted that the real-time growth state model graph of the pepper seedlings in the target greenhouse is obtained, which contains contour, color, texture and other characteristic information of the pepper seedlings, and is a comprehensive presentation of the actual growth state of the pepper seedlings in the current greenhouse. Meanwhile, the growth characteristic model graphs on each dictionary fork branch in the dictionary search tree are obtained, which are constructed in advance according to pepper seedlings at different growth stages and represent the characteristics of pepper seedlings at each typical growth stage. Similarity analysis is performed on the real-time growth state model graph and the growth characteristic model graphs on each dictionary fork branch. This process involves a variety of algorithms to quantify the similarity between the two. For example, the similarity of two model graphs in shape structure (contour feature), color distribution (color feature) and texture feature is compared. By calculating the difference or matching degree of these features, the similarity between the real-time growth state model graph and the growth characteristic model graphs on each dictionary fork branch is obtained. The obtained similarity is processed by size ordering, and the maximum similarity is found. The growth characteristic model graph on the dictionary fork corresponding to the maximum similarity is closest to the actual growth state of the pepper seedlings in the current greenhouse. This sorting operation can filter out the model that best matches the current pepper seedling state from the many predefined growth stage models. The growth characteristic model graph corresponding to the maximum similarity is marked, and then the string data of the dictionary fork where the growth characteristic model graph is located is obtained. This string data is converted from the growth water requirement range data, and by interpreting it, the growth water requirement range data of the pepper seedlings in the target greenhouse at the current growth stage can be obtained. This data is a key basis for subsequent soil moisture management and other greenhouse control operations.

[0084] By importing the real-time growth state model graph into the dictionary search tree for search matching operation, the current growth stage of the pepper seedlings in the target greenhouse can be accurately determined, and then the growth water requirement range data corresponding to the growth stage is obtained. This process realizes the accurate mapping from the actual growth state of the pepper seedlings to its growth demand, providing a basis for the accurate irrigation and scientific management of the pepper seedlings in the greenhouse. It can avoid the unreasonable water supply caused by inaccurate judgment of the growth stage of the pepper seedlings, and is helpful to improve the growth quality of the pepper seedlings, reduce the occurrence of diseases and pests, and ultimately improve the yield and quality of the pepper.

[0085] Preferably, real-time water data of the soil in the target greenhouse is collected at several preset time nodes, and the soil water suitability deviation coefficient of the pepper seedlings in the target greenhouse is obtained by combining the collected real-time water data with the growth water requirement range data and analyzing by using a Bezier curve algorithm. Specifically,

[0086] The real-time water data of the soil in the target greenhouse is collected at several preset time nodes, the Bezier curve algorithm is introduced, and the real-time water data collected at each preset time node is taken as a discrete point;

[0087] According to the sequence of each collection time node, the discrete points are connected to construct a water dynamic Bezier curve of the soil in the target greenhouse;

[0088] The upper and lower constraint boundaries are determined according to the growth water requirement range data of the pepper seedlings in the target greenhouse at the current growth stage, and a constraint region is divided in the water dynamic Bezier curve according to the upper and lower constraint boundaries;

[0089] The total curve length of the water dynamic Bezier curve outside the constraint region is calculated, and the total curve length of the water dynamic Bezier curve inside the constraint region is calculated;

[0090] The total curve length of the water dynamic Bezier curve outside the constraint region is compared with the total curve length of the water dynamic Bezier curve inside the constraint region to obtain the soil water suitability deviation coefficient of the pepper seedlings in the target greenhouse.

[0091] It should be noted that the real-time soil moisture data in the target greenhouse is collected at several preset time nodes, which ensures that the dynamic information of soil moisture at different times can be obtained. The Bezier curve algorithm is introduced, and the collected real-time moisture data is used as discrete points to prepare for constructing a curve that can reflect the trend of soil moisture change over time. According to the sequence of each collection time node, the discrete points are connected to construct the soil moisture dynamic Bezier curve in the target greenhouse. The Bezier curve has the characteristics of smoothness and flexibility, which can well fit these discrete moisture data points, thereby intuitively showing the change process of soil moisture over time, whether it is gradually increasing, decreasing or fluctuating.

[0092] According to the growth water requirement range data of the pepper seedlings in the target greenhouse at the current growth stage, the upper and lower constraint boundaries are determined. This growth water requirement range is obtained by judging the growth stage of the pepper seedlings before, and is the soil moisture range required for the healthy growth of the pepper seedlings. According to the two boundaries, a constraint region is divided in the soil moisture dynamic Bezier curve, which represents the soil moisture in the range suitable for the growth of the pepper seedlings. The total curve length of the soil moisture dynamic Bezier curve outside the constraint region and the total curve length inside the constraint region are calculated. The length of the curve outside the constraint region reflects the degree of deviation of the soil moisture from the suitable range, and the length inside the constraint region represents the duration or proportion of the soil moisture in the suitable range. The total curve length outside the constraint region is compared with the total curve length inside the constraint region to obtain the soil moisture suitability deviation coefficient of the pepper seedlings in the target greenhouse.

[0093] The soil moisture suitability deviation coefficient obtained by the above operation can quantitatively represent the degree of deviation of the soil moisture in the target greenhouse from the suitable range for the current growth stage of the pepper seedlings. This coefficient provides an intuitive and effective index for evaluating the soil moisture condition, which can be used to judge whether the soil moisture in the greenhouse needs to be regulated.

[0094] Preferably, the soil moisture condition in the target greenhouse is analyzed according to the soil moisture suitability deviation coefficient, and the target greenhouse is regulated according to the analysis result, specifically:

[0095] The soil moisture suitability deviation coefficient of the pepper seedlings in the target greenhouse is compared with a preset coefficient threshold.

[0096] If the soil moisture suitability deviation coefficient of the pepper seedlings in the target greenhouse is not greater than the preset coefficient threshold, it means that the soil moisture condition in the target greenhouse meets the growth demand of the pepper seedlings at the current growth stage, and the target greenhouse is not regulated.

[0097] It should be noted that a preset coefficient threshold is set, which is a measurement standard determined in advance according to the growth needs of pepper seedlings, past experience or experimental data. The calculated soil moisture suitability deviation coefficient is compared with the preset coefficient threshold. This comparison process is a key step to determine whether the soil moisture condition needs to be adjusted. If the soil moisture suitability deviation coefficient is not greater than the preset coefficient threshold, it means that the fluctuation or deviation of the soil moisture from the suitable range is within an acceptable range. In practical terms, the soil moisture in the target greenhouse basically meets the growth needs of pepper seedlings at the current growth stage. In this case, the target greenhouse is not controlled, which reflects a precise management strategy, avoids unnecessary intervention, reduces the waste of manpower and material resources, and also maintains a relatively stable growth environment in the greenhouse.

[0098] By comparing the soil moisture suitability deviation coefficient with the preset coefficient threshold, it can be accurately determined whether the soil moisture in the target greenhouse meets the needs of pepper seedlings at the current growth stage, so as to decide whether to control the greenhouse. This method realizes intelligent decision-making based on data, reduces unnecessary control operations, helps to maintain the stability of the soil moisture environment in the greenhouse, provides suitable conditions for the healthy growth of pepper seedlings, and improves the growth quality and final yield of pepper seedlings.

[0099] Preferably, the soil moisture condition in the target greenhouse is analyzed according to the soil moisture suitability deviation coefficient, and the target greenhouse is controlled according to the analysis result, specifically:

[0100] If the soil moisture suitability deviation coefficient of pepper seedlings in the target greenhouse is greater than the preset coefficient threshold, it means that the soil moisture condition in the target greenhouse does not meet the growth needs of pepper seedlings at the current growth stage, then the average value of the real-time moisture data collected at a plurality of preset time nodes is calculated to obtain the moisture data average value.

[0101] The moisture data average value is compared with the preset threshold value, if the moisture data average value is greater than the preset threshold value, the soil in the target greenhouse is determined as drought condition; otherwise, the soil in the target greenhouse is determined as over-wet condition.

[0102] Preferably, the soil moisture condition in the target greenhouse is analyzed according to the soil moisture suitability deviation coefficient, and the target greenhouse is controlled according to the analysis result, further comprising the following steps:

[0103] If the soil in the target greenhouse is in over-wet condition, the real-time rainfall in the preset range of the target greenhouse is obtained, if the real-time rainfall in the preset range of the target greenhouse is greater than the preset rainfall, the roof of the target greenhouse is controlled to be closed to realize the rain blocking function;

[0104] If the real-time rainfall in the preset range area of the target greenhouse is not greater than the preset rainfall, the real-time light intensity in the preset range area of the target greenhouse is acquired; if the real-time light intensity in the preset range area of the target greenhouse is greater than the preset intensity value, the roof of the target greenhouse is controlled to be opened, and the natural sunlight irradiation dehumidification function is realized.

[0105] Preferably, the water condition of the soil in the target greenhouse is analyzed according to the soil water suitability deviation coefficient, and the target greenhouse is controlled according to the analysis result, and the method further comprises the following steps:

[0106] If the soil in the target greenhouse is in a drought condition, the real-time rainfall in the preset range area of the target greenhouse is acquired, and if the real-time rainfall in the preset range area of the target greenhouse is greater than the preset rainfall, the roof of the target greenhouse is controlled to be opened, and the natural rainwater irrigation function is realized.

[0107] If the real-time rainfall in the preset range area of the target greenhouse is not greater than the preset rainfall, the real-time light intensity in the preset range area of the target greenhouse is acquired; if the real-time light intensity in the preset range area of the target greenhouse is greater than the preset intensity value, the roof of the target greenhouse is controlled to be closed, and the moisture retention function of the target greenhouse is strengthened.

[0108] It should be noted that when the soil water suitability deviation coefficient is greater than the preset coefficient threshold, it indicates that the soil water condition does not meet the current growth requirement of the pepper seedlings. At this time, the average value of the real-time water data collected at the preset time node is calculated, and the soil is determined to be in a drought or over-wet condition by comparing with the preset threshold. This step converts the abstract concept of the deviation coefficient into the judgment of the actual water condition of the soil (drought or over-wet), which provides a basis for subsequent precise control.

[0109] If the soil is in an over-wet condition, the real-time rainfall in the preset range area of the target greenhouse is acquired through the sensor. When the rainfall is greater than the preset rainfall, the roof is closed to prevent more water from entering the greenhouse and aggravating the over-wet condition. This is an active defense measure based on external rainfall conditions to avoid further increase of soil moisture. If the rainfall is not greater than the preset rainfall, the real-time light intensity is acquired. When the light intensity is greater than the preset intensity value, the roof is opened to utilize natural sunlight to irradiate and dehumidify. This is an effective method of using natural sunlight and air circulation to reduce soil humidity, and the humidity is adjusted by reasonably controlling the state of the greenhouse roof.

[0110] When the soil is in a drought condition, attention is also paid to the real-time rainfall. If the rainfall is greater than the preset rainfall, the roof is opened to allow natural rainfall to irrigate the soil, and natural precipitation is used to supplement soil moisture, which is an energy-saving and environmentally friendly irrigation method. When the rainfall is not greater than the preset rainfall, the real-time light intensity is checked. If the light intensity is greater than the preset intensity value, the roof is closed to enhance the moisture retention function and reduce soil moisture evaporation, so as to maintain the existing soil moisture content and prevent the drought condition from worsening.

[0111] It should be further noted that if the soil is in an over-wet condition, the ventilation system, drainage system, etc. in the greenhouse can also be controlled to be opened; if the soil is in a drought condition, the irrigation system, etc. can be controlled to be opened.

[0112] Through the above series of operations, the soil moisture condition is judged according to the soil moisture suitability deviation coefficient, and then the target greenhouse is precisely controlled according to different conditions (drought or over-wet) and external environmental factors (rainfall, light intensity). This control method realizes intelligent management of the soil moisture of the greenhouse, can effectively deal with the over-wet or drought condition of the soil, fully utilizes natural conditions (rainfall, sunlight) to adjust the soil moisture, reduces manual intervention while improving the stability of the growth environment of the pepper seedlings, thereby helping to improve the growth quality and yield of the pepper seedlings.

[0113] The pepper cultivation rain-avoiding greenhouse control method can further include the following steps:

[0114] Obtain the pest characteristic images corresponding to the various types of pests infected by the pepper seedlings through a big data network, perform feature conversion processing on the pest characteristic images, and obtain the wavelet coefficient matrix of the pepper seedlings infected by the various types of pests;

[0115] Construct a knowledge graph, import the wavelet coefficient matrix of the pepper seedlings infected by the various types of pests into the knowledge graph, and periodically update the knowledge graph;

[0116] Obtain the actual growth speed data of the pepper seedlings in each sub-region of the target greenhouse within a preset time period; compare the actual growth speed data of the pepper seedlings in each sub-region within the preset time period with the preset growth speed;

[0117] Obtain the sub-region corresponding to the actual growth speed data not greater than the preset growth speed, and mark it as a growth abnormal sub-region; obtain the growth image information of the pepper seedlings in the growth abnormal sub-region, perform matrix conversion processing on the growth image information, and obtain the wavelet coefficient matrix of the pepper seedlings in the growth abnormal sub-region;

[0118] Calculate the structural similarity index between the wavelet coefficient matrix of the pepper seedlings in the growth abnormal sub-region and the wavelet coefficient matrix of the pepper seedlings infected by the various types of pests, and obtain a plurality of structural similarity indexes;

[0119] If at least one of the structure similarity indexes is greater than the preset similarity index value, the growth abnormal sub-region is marked as a pest infection region, and the pest type of the pest infection region is matched in the knowledge graph according to the structure similarity index greater than the preset similarity index value.

[0120] It should be noted that the wavelet coefficient matrix can effectively represent the feature information in the pest feature image, which can capture the details and texture information of the image in different scales and directions. The knowledge graph is a semantic network that can organize the wavelet coefficient matrices of different types of pests in a structured manner, facilitating subsequent queries and matching. The knowledge graph is updated regularly to ensure that it contains the latest pest feature information to adapt to changing pest conditions.

[0121] When the actual growth rate of a sub-region is not greater than the preset growth rate, the sub-region is marked as a growth abnormal sub-region. This is based on the expected normal growth rate of pepper seedlings. If the growth rate is lower than expected, there may be factors affecting growth, such as pests, diseases, or other environmental problems. The structure similarity index can quantitatively represent the degree of structural similarity between two matrices. After obtaining several structure similarity indexes, they are compared with the preset similarity index value. If at least one structure similarity index is greater than the preset similarity index value, the growth abnormal sub-region is marked as a pest infection region, and the pest type is matched in the knowledge graph according to this greater than the preset similarity index value. This process compares the image features of the growth abnormal region with the similarity of known pest features to accurately determine the pest type. Through the analysis of the growth abnormal region pepper seedling image, the wavelet coefficient matrix and the structure similarity index are matched with the pest features in the knowledge graph to accurately determine whether it is a pest infection region and the type of infection, achieving intelligent monitoring and accurate judgment of pepper seedling pests, which helps to take targeted prevention and control measures in a timely manner, reduces the impact of pests on pepper seedling growth, and improves the yield and quality of peppers.

[0122] The pepper cultivation rain-avoiding greenhouse control method can further include the following steps:

[0123] According to the pest type of the pest infection region, the reproduction rate of the pest infection region under various environmental characteristic conditions is retrieved in the big data network;

[0124] The environmental characteristic conditions are used as condition nodes, and the corresponding reproduction rates are used as variable nodes. A network topology graph is generated according to the condition nodes and variable nodes, a graph embedding network model is constructed, the network topology graph is embedded in the graph embedding network model, and a pest reproduction rate prediction model is obtained.

[0125] acquiring real-time environmental characteristic conditions of the pest infection area at a plurality of time nodes, introducing the real-time environmental characteristic conditions obtained at each time node into the pest reproduction rate prediction model to obtain a predicted reproduction rate of the pest in the pest infection area at each time node;

[0126] performing weighted average processing on the predicted reproduction rate of the pest in the pest infection area at each time node to obtain a predicted reproduction rate of the pest in the pest infection area within a preset time period;

[0127] if the predicted reproduction rate of the pest in the pest infection area within the preset time period is greater than a preset rate value, searching for, according to a pest type of the pest infection area, a reproduction inhibition environmental condition that has reproduction inhibition on the pest in the pest infection area in a big data network;

[0128] controlling a corresponding environmental regulation system in a target greenhouse according to the reproduction inhibition environmental condition, so that the environment in the pest infection area reaches the reproduction inhibition environmental condition.

[0129] It should be noted that firstly, the reproduction rate under different environmental characteristic conditions is retrieved in the big data network according to the pest type of the pest infection area. The environmental characteristic conditions here cover various factors that may affect pest reproduction, such as temperature, humidity, and light. The environmental characteristic conditions are taken as conditional nodes, and the corresponding reproduction rate is taken as a variable node to construct a network topology graph, and then a graph embedding network model is generated to obtain a pest reproduction rate prediction model. This model construction method can effectively capture the complex relationship between environmental factors and pest reproduction rate, and by embedding the network topology graph into the graph embedding network model, the model can accurately predict the pest reproduction rate according to the input environmental characteristic conditions. The real-time environmental characteristic conditions of the pest infection area at multiple time nodes are obtained and input into the pest reproduction rate prediction model to obtain the predicted reproduction rate of the pest at each time node. Since the environmental conditions at different times may be different, the prediction is performed at each time node. Then, the predicted reproduction rates are weighted and averaged to obtain the predicted reproduction rate in the preset time period. The weighted average considers the importance or representativeness of different time nodes, making the prediction result more reflect the pest reproduction trend in the entire preset time period. If the predicted reproduction rate of the pest in the preset time period is greater than the preset rate value, it indicates that the pest has a rapid reproduction trend, and measures need to be taken to suppress it. At this time, the reproduction inhibition environmental conditions that have reproduction inhibition effect on the pest are retrieved in the big data network according to the pest type. For example, the reproduction of some pests will be inhibited under low temperature, low humidity, or specific light conditions. Finally, the environmental control system of the target greenhouse is controlled according to the retrieved reproduction inhibition environmental conditions, so that the environment of the pest infection area reaches the reproduction inhibition environmental conditions, thereby effectively controlling the reproduction of the pest and reducing the harm of the pest to the pepper cultivation. According to the prediction result, when the pest reproduction rate may be too high, the reproduction inhibition environmental conditions are obtained and implemented in time to inhibit the reproduction of the pest by regulating the environment of the greenhouse. Prospective management of pest reproduction in pepper cultivation is realized, which helps to reduce the damage of pests to pepper seedlings, improve the yield and quality of peppers, reduce the use of chemical pesticides, and realize more environmentally friendly and efficient pepper cultivation management.

[0130] The application further discloses an intelligent-sensing-based rain-avoiding cultivation greenhouse control system. Figure 3 As shown in the figure, the rain-avoiding cultivation greenhouse control system comprises a memory 10 and a processor 20, and the memory 10 stores a rain-avoiding cultivation greenhouse control method program. When the rain-avoiding cultivation greenhouse control method program is executed by the processor 20, the steps of any one of the rain-avoiding cultivation greenhouse control methods are realized.

[0131] The above is only a specific embodiment of the application, but the protection scope of the application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the application, which should be covered within the protection scope of the application.

Claims

1. A smart-sensing-based rain-avoiding cultivation greenhouse control method, characterized in that, The method comprises the following steps: acquire the real-time growth state image of the pepper seedlings in the target greenhouse, and construct a real-time growth state model graph of the pepper seedlings in the target greenhouse according to the real-time growth state image; acquire the growth characteristic image and the growth water requirement range data corresponding to the pepper seedlings at different growth stages through a big data network, and construct a dictionary search tree according to the growth characteristic image and the growth water requirement range data corresponding to the pepper seedlings at different growth stages; introduce the real-time growth state model graph into the dictionary search tree for search matching, and acquire the growth water requirement range data of the pepper seedlings in the target greenhouse at the current growth stage; collect the real-time water data of the soil in the target greenhouse at a plurality of preset time nodes, and analyze the soil water suitability deviation coefficient of the pepper seedlings in the target greenhouse by combining the real-time water data collected and the growth water requirement range data with a Bezier curve algorithm; analyze the water condition of the soil in the target greenhouse according to the soil water suitability deviation coefficient, and perform control processing on the target greenhouse according to the analysis result; wherein the real-time growth state model graph of the pepper seedlings in the target greenhouse is constructed according to the real-time growth state image, specifically as follows: introduce a Canny edge detection algorithm, perform feature extraction on the real-time growth state image based on the Canny edge detection algorithm, and acquire the contour feature information of each part of the pepper seedlings; convert the real-time growth state image from an RGB color space to an HSV color space, extract the color feature information of each part of the pepper seedlings in the HSV space, and introduce a gray level co-occurrence matrix extraction algorithm, extract the gray level co-occurrence frequency of pixel pairs in each preset direction in the real-time growth state image based on the gray level co-occurrence matrix extraction algorithm, and determine the texture feature information of each part of the pepper seedlings according to the gray level co-occurrence frequency; construct the real-time growth state model graph of the pepper seedlings in the target greenhouse according to the contour feature information, the color feature information and the texture feature information of each part of the pepper seedlings and in combination with a three-dimensional software; wherein the growth characteristic image and the growth water requirement range data corresponding to the pepper seedlings at different growth stages are acquired through a big data network, and the dictionary search tree is constructed according to the growth characteristic image and the growth water requirement range data corresponding to the pepper seedlings at different growth stages, specifically as follows: acquire the growth characteristic image and the growth water requirement range data corresponding to the pepper seedlings at different growth stages through a big data network, and construct a growth characteristic model graph corresponding to the pepper seedlings at different growth stages according to the growth characteristic image; construct a dictionary tree, and cut a plurality of dictionary fork branches in the dictionary tree according to the pepper at different growth stages; acquire the growth water requirement range data corresponding to the pepper seedlings at different growth stages, and convert the growth water requirement range data corresponding to the pepper seedlings at different growth stages into specific string data; map each string data on the root node of the corresponding dictionary fork branch, and complete the coding operation on each dictionary fork branch; store the growth characteristic model graph corresponding to the pepper seedlings at different growth stages on the leaf node of the corresponding dictionary fork branch, and obtain the dictionary search tree. ​ The real-time growth state model graph is imported into a dictionary search tree for search matching to obtain growth water requirement range data of the pepper seedlings in the current growth stage in the target greenhouse, specifically as follows: A real-time growth state model graph of the pepper seedlings in the target greenhouse is obtained, and growth characteristic model graphs on each dictionary fork branch in the dictionary search tree are obtained; Similarity analysis is performed on the real-time growth state model graph and the growth characteristic model graphs on each dictionary fork branch to obtain similarity between the real-time growth state model graph and the growth characteristic model graphs on each dictionary fork branch; The similarity between the real-time growth state model graph and the growth characteristic model graphs on each dictionary fork branch is sorted in size to sort out the maximum similarity; The growth characteristic model graph corresponding to the maximum similarity is marked, string data of the dictionary fork of the marked growth characteristic model graph is obtained, and the obtained string data is interpreted to obtain growth water requirement range data of the pepper seedlings in the current growth stage in the target greenhouse.

2. The smart sensing-based rain-avoiding cultivation greenhouse control method according to claim 1, characterized in that, Real-time water data of soil in the target greenhouse is collected at a plurality of preset time nodes, and a soil water suitability deviation coefficient of the pepper seedlings in the target greenhouse is obtained by combining the collected real-time water data with the growth water requirement range data and analyzing by using a Bezier curve algorithm, specifically as follows: Real-time water data of soil in the target greenhouse is collected at a plurality of preset time nodes, a Bezier curve algorithm is introduced, and the real-time water data collected at each preset time node is taken as a discrete point; The discrete points are sequentially connected according to each collection time node to construct a water dynamic Bezier curve of the soil in the target greenhouse; The upper and lower constraint boundaries are determined according to the growth water requirement range data of the pepper seedlings in the current growth stage in the target greenhouse, and a constraint region is divided in the water dynamic Bezier curve according to the upper and lower constraint boundaries; The total curve length of the water dynamic Bezier curve outside the constraint region and the total curve length of the water dynamic Bezier curve inside the constraint region are calculated; The total curve length of the water dynamic Bezier curve outside the constraint region and the total curve length of the water dynamic Bezier curve inside the constraint region are compared to obtain a soil water suitability deviation coefficient of the pepper seedlings in the target greenhouse. 3.The smart sensing-based rain-avoiding cultivation greenhouse control method according to claim 2, wherein, The soil water suitability deviation coefficient is used to analyze the water condition of the soil in the target greenhouse, and the target greenhouse is controlled according to the analysis result, specifically as follows: The soil water suitability deviation coefficient of the pepper seedlings in the target greenhouse is compared with a preset coefficient threshold value; If the soil water suitability deviation coefficient of the pepper seedlings in the target greenhouse is not greater than the preset coefficient threshold value, it indicates that the water condition of the soil in the target greenhouse meets the growth demand of the pepper seedlings in the current growth stage, and the target greenhouse is not controlled.

4. The smart sensing-based rain-avoiding cultivation greenhouse control method according to claim 2, characterized in that, The soil water suitability deviation coefficient is used to analyze the water condition of the soil in the target greenhouse, and the target greenhouse is controlled according to the analysis result, specifically as follows: If the soil moisture suitability deviation coefficient of the pepper seedlings in the target greenhouse is greater than the preset coefficient threshold, it indicates that the soil moisture in the target greenhouse does not meet the growth requirements of the pepper seedlings at the current growth stage. Then, the average value of the real-time moisture data collected at a plurality of preset time nodes is calculated to obtain a moisture data average value. The moisture data average value is compared with a preset threshold. If the moisture data average value is greater than the preset threshold, the soil in the target greenhouse is determined to be in a drought condition. Otherwise, the soil in the target greenhouse is determined to be in an over-wet condition.

5. The smart sensing based rain shelter cultivation greenhouse control method according to claim 4, wherein, According to the soil moisture suitability deviation coefficient, the soil moisture in the target greenhouse is analyzed, and the target greenhouse is controlled and processed according to the analysis result. The method further includes the following steps: If the soil in the target greenhouse is in an over-wet condition, the real-time rainfall in a preset range of the target greenhouse is obtained. If the real-time rainfall in the preset range of the target greenhouse is greater than a preset rainfall, the roof of the target greenhouse is controlled to be closed to realize a rain-shielding function. If the real-time rainfall in the preset range of the target greenhouse is not greater than the preset rainfall, the real-time light intensity in the preset range of the target greenhouse is obtained. If the real-time light intensity in the preset range of the target greenhouse is greater than a preset intensity value, the roof of the target greenhouse is controlled to be opened to realize a natural sunlight irradiation dehumidification function.

6. The smart sensing based rain shelter cultivation greenhouse control method according to claim 4, wherein, According to the soil moisture suitability deviation coefficient, the soil moisture in the target greenhouse is analyzed, and the target greenhouse is controlled and processed according to the analysis result. The method further includes the following steps: If the soil in the target greenhouse is in a drought condition, the real-time rainfall in a preset range of the target greenhouse is obtained. If the real-time rainfall in the preset range of the target greenhouse is greater than a preset rainfall, the roof of the target greenhouse is controlled to be opened to realize a natural rainwater irrigation function. If the real-time rainfall in the preset range of the target greenhouse is not greater than the preset rainfall, the real-time light intensity in the preset range of the target greenhouse is obtained. If the real-time light intensity in the preset range of the target greenhouse is greater than a preset intensity value, the roof of the target greenhouse is controlled to be closed to strengthen the moisture retention function of the target greenhouse.

7. A rain-avoiding cultivation greenhouse control system based on intelligent sensing, characterized in that, The rain-avoiding cultivation greenhouse control system includes a memory and a processor. The memory stores a rain-avoiding cultivation greenhouse control method program. When the rain-avoiding cultivation greenhouse control method program is executed by the processor, the steps of the rain-avoiding cultivation greenhouse control method according to any one of claims 1 to 6 are realized.

Images