GIS data visual management method and system based on digital twinning

Abstract

The invention discloses a GIS data visual management method and system based on digital twinning, and relates to the field of visual management, the method is applied to an intelligent agricultural management platform, and the method comprises the steps: obtaining soil parameter data of a to-be-monitored planting area; acquiring a crop image of a to-be-monitored planting area, and performing image recognition on the crop image to obtain crop basic data; constructing a soil and crop association model by using the soil parameter data and the crop basic data; acquiring environment data of a to-be-monitored planting area, and constructing an environment model; carrying out model fusion on the environment model and the soil crop association model to obtain a microclimate environment model, and determining an association relationship among soil attributes, environment factors and crop states; determining a planning strategy of the to-be-monitored planting area through the association relationship; and visually displaying the planning strategy in a pre-constructed digital twinborn model of the planting area to be monitored. The problem of inaccurate manual monitoring can be effectively solved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of visualization management, and in particular, to a GIS data visualization management method and system based on digital twins. Background Art

[0002] Greenhouse cultivation is a method of agricultural production carried out in a closed or semi-closed environment. It mainly provides suitable growth conditions for crops by adjusting environmental factors such as light, temperature, and humidity. Regular monitoring of crop growth in greenhouses can help farmers understand changes in the greenhouse environment and take timely measures to adjust the environment to ensure the normal growth and development of crops. At the same time, it can reduce the use of pesticides and fertilizers, reduce costs, and improve economic benefits.

[0003] At present, the monitoring of crop growth conditions in greenhouses is mainly carried out through manual monitoring. The growth of crops is judged based on the experience of farmers, and whether the crops need fertilization or watering is judged based on experience. However, using manual experience for monitoring will result in insufficient reserves of artificial agricultural production knowledge, resulting in low accuracy in crop growth monitoring, causing misjudgment of crop growth, affecting the growth status of crops, and causing not only economic losses to farmers but also pollution to the environment.

[0004] There is currently no better solution to the above problems. Summary of the invention

[0005] The embodiments of the present application provide a GIS data visualization management method and system based on digital twins, which are used to solve the problem of inaccurate manual monitoring.

[0006] To achieve the above objectives, the embodiments of the present application adopt the following technical solutions:

[0007] In a first aspect, a GIS data visualization management method based on digital twin is provided, characterized by comprising:

[0008] Obtain soil parameter data of the planting area to be monitored in the greenhouse;

[0009] Acquire crop images of the planting area to be monitored, and perform image recognition on the crop images to obtain basic crop data;

[0010] Constructing a soil-crop association model based on the soil parameter data and the crop basic data;

[0011] Acquiring environmental data of the planting area to be monitored, and constructing an environmental model based on the environmental data;

[0012] The environmental model and the soil-crop association model are integrated to obtain a microclimate environmental model, and the association between soil properties, environmental factors and crop status is determined;

[0013] Determining the planning strategy of the planting area to be monitored through the association relationship;

[0014] The planning strategy is visualized in a pre-built digital twin model of the planting area to be monitored.

[0015] In another possible implementation manner of the first aspect, acquiring the crop image of the to-be-monitored planting area and performing image recognition on the crop image to obtain basic crop data includes:

[0016] Using a drone to take images of the crops in the to-be-monitored planting area to obtain crop images;

[0017] Performing image segmentation on the crop image to obtain a plurality of sub-images;

[0018] Performing image recognition on each of the sub-images to obtain at least one crop leaf feature;

[0019] Based on at least one of the crop leaf characteristics, basic crop data is determined.

[0020] In another possible implementation manner of the first aspect, performing image recognition on each of the sub-images to obtain at least one crop leaf feature includes:

[0021] For any one of the sub-images, image recognition is performed on the sub-image to determine the edge of the crop leaf, and image segmentation is performed on the sub-image based on the edge of the crop leaf to obtain a crop leaf area;

[0022] Extracting features from the crop leaf region to obtain at least one crop leaf feature, wherein the crop leaf feature includes a leaf edge feature, a leaf texture feature, and a leaf color feature;

[0023] Determining basic crop data according to at least one crop leaf feature includes:

[0024] For one of the crop leaf features, basic crop data is determined based on the leaf edge feature, the leaf texture feature and the leaf color feature. The basic crop data includes nutrient data required by the crop, crop disease and pest data and crop growth stage data.

[0025] In another possible implementation manner of the first aspect, the step of constructing a soil-crop association model based on the soil parameter data and the crop basic data includes:

[0026] Obtaining a training set corresponding to the soil parameter data, wherein the training set includes pH value and organic matter;

[0027] The training set is input into the initial model to train the initial model to obtain a trained initial model, and the trained initial model is used to characterize a soil-crop association model.

[0028] In another possible implementation manner of the first aspect, building an environment model based on the environment data includes:

[0029] Obtaining a training set corresponding to the environmental data, wherein the training set includes temperature, humidity and light intensity;

[0030] The training set is input into the initial model to train the initial model to obtain a trained initial model, and the trained initial model is used to characterize the environment model.

[0031] In another possible implementation of the first aspect, fusing the environmental model with the soil and crop association model to obtain a microclimate environmental model, and determining the association between soil properties, environmental factors and crop status, includes:

[0032] Determine a first change data set of soil properties and crop status at a future time node by using the soil and crop association model;

[0033] Determine a second change data set of environmental data at a future time node by using the environmental model;

[0034] Performing data fitting on the first change data set and the second change data set to obtain a correlation analysis function;

[0035] A microclimate environment model is constructed based on the correlation analysis function;

[0036] The soil property data, environmental data or crop status data at the target time node are input into the association analysis function to obtain the association relationship between the soil property data, environmental data and crop status data at a preset time node in the future.

[0037] In another possible implementation of the first aspect, constructing the microclimate environment model includes:

[0038] Obtain greenhouse space data and carbon dioxide concentration data

[0039] Correcting the correlation analysis function by using the space influencing factor and the air circulation influencing factor to obtain a corrected correlation analysis function;

[0040] An optimized microclimate environment model is obtained through the corrected correlation analysis function.

[0041] In another possible implementation manner of the first aspect, determining the planning strategy for the to-be-monitored planting area through the association relationship includes:

[0042] For one of the crop leaf features, determining a crop adjustment strategy for a target crop corresponding to the crop leaf feature according to the crop basic data;

[0043] Determine the sub-image where the target crop is located, and obtain positioning data in the planting area to be monitored corresponding to the sub-image;

[0044] Determining an adjustment area of ​​the planting area to be monitored according to the positioning data;

[0045] Acquiring soil property data of the adjustment area, and inputting the soil property data into the microclimate environment model to obtain environmental data and crop status data associated with the soil property data;

[0046] Determining suitable environmental data of the target crop according to the crop basic data of the target crop, and determining a first adjustment strategy of the environmental data associated with the soil attribute data according to the suitable environmental data;

[0047] Determining standard state data corresponding to the growth stage data of the target crop through a preset state database, and determining a second adjustment strategy for the crop state data associated with the soil attribute data based on the standard state data;

[0048] The first adjustment strategy, the second adjustment strategy and the crop adjustment strategy are integrated to obtain the planning strategy for the adjustment area of ​​the planting area to be monitored.

[0049] In a second aspect, the present application provides a machine-readable storage medium having instructions stored thereon, the instructions being used to enable a machine to execute the above-mentioned digital twin-based GIS data visualization management method.

[0050] In a third aspect, the present application provides a GIS data visualization management system based on digital twins, including:

[0051] a memory configured to store instructions; and

[0052] The processor is configured to call the instructions from the memory and to implement the above-mentioned digital twin-based GIS data visualization management method when executing the instructions.

[0053] Through the above technical solution, by performing image recognition on the crop images in the planting area of ​​the greenhouse, the basic data of the crops can be obtained, which can help farmers understand the changes in the internal environment of the greenhouse, take measures to adjust the environment in time, and effectively solve the problem of inaccurate manual monitoring. Obtaining the soil parameter data of the planting area to be monitored in the greenhouse, and constructing a soil-crop association model with the soil parameter data and the basic crop data can clearly show the relationship between the soil parameter data and the basic crop data. By constructing an environmental model with the environmental data of the monitored planting area, it is helpful to more accurately evaluate the relationship between the environmental data and the basic crop data. By integrating the environmental model and the soil-crop association model to obtain a microclimate environment model, the correlation between soil properties, environmental factors and crops can be better determined, which helps to better predict the future crop growth status. According to the correlation, the planting planning strategy is determined, and the planning strategy is displayed in the digital twin model of the planting area to be monitored. By simulating the planting planning strategy, the waste of resources in the agricultural production process is reduced, and the optimal growth state of crops is guaranteed, thereby improving agricultural production efficiency.

[0054] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 A flowchart of a GIS data visualization management method based on digital twins provided in an embodiment of the present application;

[0056] Figure 2 A schematic diagram of a process for determining basic crop data provided in an embodiment of the present application. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0058] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back...), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0059] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0060] Figure 1 The following schematically shows a flow chart of a GIS data visualization management method based on digital twins according to an embodiment of the present application. Figure 1 As shown, an embodiment of the present application provides a GIS data visualization management method based on digital twins, which may include the following steps.

[0061] S110, obtaining soil parameter data of the planting area to be monitored in the greenhouse;

[0062] S120, obtaining crop images of the planting area to be monitored, and performing image recognition on the crop images to obtain basic crop data;

[0063] S130, constructing a soil-crop association model based on soil parameter data and crop basic data;

[0064] S140, obtaining environmental data of the planting area to be monitored, and building an environmental model based on the environmental data;

[0065] S150, integrating the environmental model with the soil-crop association model to obtain a microclimate environmental model, and determining the association between soil properties, environmental factors and crop status;

[0066] S160, determining a planning strategy for the planting area to be monitored through the association relationship;

[0067] S170. Visualize the planning strategy in a pre-built digital twin model of the planting area to be monitored.

[0068] First, obtain the soil parameter data of the planting area to be monitored in the greenhouse. The greenhouse is a closed or semi-closed agricultural facility for cultivating plants, which can be transparent and heat-insulated to meet the needs of plant growth. In the present embodiment, the greenhouse is a closed space composed of a plastic film and a skeleton, and the planting area to be monitored is the planting area in the greenhouse, and the planting area can be determined according to actual conditions. In the present embodiment, the soil parameter data includes pH parameter data (i.e., pH value) and organic matter parameter data (i.e., organic matter) in the soil. pH parameter data refers to the pH parameter data in the soil, and organic matter parameter data refers to the various animal and plant residues and microorganisms contained in the soil and the amount of organic matter decomposed and synthesized by them. Acquiring organic matter in the soil is through a spectral sensor, and the soil in the monitored planting area is analyzed by near-infrared spectroscopy through the spectral sensor to obtain organic matter parameter data in the soil. The spectral sensor can analyze organic matter in the soil through near-infrared spectroscopy, and identify and quantify organic compounds in the soil.

[0069] By acquiring the crop image of the planting area to be monitored and performing image recognition on the crop image, the basic crop data is obtained. Image recognition technology is an important field of artificial intelligence, which refers to the technology of using computers to process, analyze and understand images to identify targets and objects of various different patterns. In this embodiment, the planting area to be monitored can be photographed by an unmanned aerial vehicle to obtain a crop image, and the crop image can be segmented to obtain multiple sub-images, and the crop leaf features in the sub-images can be identified. In this embodiment, the crop leaf features include leaf edge features, leaf texture features, and leaf color features. By identifying the leaf edge features, the nutrient data required by the crop can be determined, the crop disease and insect pest data can be determined by identifying the leaf texture features, and the crop growth stage data can be determined by identifying the leaf color features of the crop. The nutrient data required by the crop, the crop disease and insect pest data, and the crop growth stage data are summarized to obtain the basic crop data.

[0070] A soil-crop association model is constructed based on soil parameter data and basic crop data. In this embodiment, the soil parameter data includes pH value and organic matter in the soil, and the basic crop data includes nutrient data required by the crop, crop disease and pest data, and crop growth stage data. The soil-crop association model is constructed using soil parameter data and basic crop data. Specifically, a training set corresponding to the soil parameter data is obtained, wherein the training set includes pH data and organic matter data in the soil, and the training set corresponding to the soil parameter data is input into the initial model to train the initial model. In this embodiment, the initial model can be a pre-constructed neural network model, which is trained using a training set consisting of pH data and organic matter data. The trained neural network model is the soil-crop association model.

[0071] Acquire environmental data of the planting area to be monitored. In this embodiment, the environmental data include temperature data, humidity data and light intensity data of the planting area to be monitored, and build an environmental model based on the environmental data. Specifically, acquire a training set corresponding to the environmental data, wherein the training set includes temperature data, humidity data and light intensity data. Input the training set corresponding to the environmental data into the initial model to train the initial model. In this embodiment, the initial model may be a pre-constructed neural network model, which is trained by a training set consisting of pH data and organic matter data. The trained neural network model is a soil-crop association model.

[0072] The environmental model and the soil-crop association model are integrated to obtain a microclimate environmental model. Microclimate refers to a microclimate environment formed by spatial differences in climate factors such as temperature, humidity, wind speed and sunshine in a specific area. In this embodiment, the microclimate environmental model is a microclimate environmental model of the planting area to be monitored in the greenhouse. The environmental model and the soil-crop association model are integrated to obtain a microclimate environmental model. Specifically, the first change data set of soil properties and crop status at future time nodes is determined through the soil-crop association model. In this embodiment, the first change data set is a collection of soil property and crop status change data at future time nodes. The second change data set of environmental data at future time nodes is determined through the environmental model. In this embodiment, the second change data set is a data set of environmental data changes at future time nodes.

[0073] The first change data set and the second change data set are fitted to obtain a correlation analysis function. The data set of soil properties and crop status at future time nodes and the data set of environmental data at future time nodes are fitted to obtain a correlation analysis function through a preset data fitting software (such as MATLAB mathematical modeling software), and a microclimate environmental model is constructed through the correlation analysis function. After obtaining the microclimate environmental model, the correlation relationship between soil properties, environmental factors and crop status is determined, that is, the linkage relationship between soil properties, environmental factors and crop status is determined. For example, when the temperature, humidity and light intensity in the environment change, the pH value and organic matter values ​​in the soil also change accordingly, which will affect the change in the growth state of the crop.

[0074] After determining the linkage between soil properties, environmental factors and crop status, firstly, the crop leaf images are identified through image recognition technology to determine the crop leaf characteristics, and the basic crop data is obtained based on the crop leaf characteristics. Based on the crop basic data, the crop adjustment strategy corresponding to the crop leaf characteristics is determined.

[0075] In this embodiment, the crop adjustment strategy is a strategy for adjusting the growth of crops according to the basic data of crops. For example, the growth elements missing from the crops are determined through the basic data of crops, and the missing growth elements of the crops are adjusted. Secondly, by determining the sub-image where the target crop is located, and obtaining the positioning data in the planting area to be monitored corresponding to the sub-image. Through the positioning data, the adjustment area of ​​the planting area to be monitored is determined. In this embodiment, the adjustment area can be set by a preset range. The soil attribute data of the adjustment area is obtained, and the soil attribute data is input into the microclimate environment model to obtain environmental data and crop status data associated with the soil attribute data. That is to say, the soil attribute data of the adjustment area is input into the microclimate environment model to obtain environmental data and crop status data associated with the soil attribute data. According to the basic crop data of the target crop, the suitable environmental data of the target crop is determined, and according to the suitable environmental data, the first adjustment strategy of the environmental data associated with the soil attribute data is determined. In this embodiment, the first adjustment strategy refers to a strategy for adjusting the soil attribute data and environmental data according to the suitable environmental data of the target crop. The standard state data corresponding to the growth stage data of the target crop is determined through the preset state database, and the second adjustment strategy of the crop state data associated with the soil attribute data is determined based on the standard state data. In this embodiment, the second adjustment strategy refers to a strategy for adjusting the crop state data associated with the soil attribute data through the preset database. The first adjustment strategy, the second adjustment strategy and the crop adjustment strategy are integrated to obtain a planning strategy for the adjustment area of ​​the planting area to be monitored, that is, the first adjustment strategy, the second adjustment strategy and the crop adjustment strategy are combined to determine the planning strategy for the planting area.

[0076] After determining the planning strategy for the planting area, the planning strategy is visualized in the pre-built digital twin model of the planting area to be monitored. The digital twin model refers to a virtual model of a physical entity, process or system created through digital modeling technology on an information platform. Displaying the planning strategy in the pre-built digital twin model of the planting area to be monitored can clearly simulate the operating status of the planning strategy in the actual environment.

[0077] Visual management of agriculture through digital twin technology and GIS data is the main way to eliminate poverty in rural areas and realize agricultural modernization. Building a visualization platform can effectively conduct regional dynamic monitoring of the crop growth environment and crop growth, improve the comprehensive diagnosis ability of crop growth and disasters, and provide more convenient application services for agricultural production management, helping to overcome the disadvantages of traditional agriculture.

[0078] Through the above technical scheme, by performing image recognition on the crop images in the planting area of ​​the greenhouse, the basic data of the crops can be obtained, which can help farmers understand the changes in the internal environment of the greenhouse, take measures to adjust the environment in time, and avoid the problem of inaccurate manual monitoring. Obtaining the soil parameter data of the planting area to be monitored in the greenhouse, and constructing a soil-crop association model with the soil parameter data and the basic crop data can clearly show the relationship between the soil parameter data and the basic crop data. By constructing an environmental model with the environmental data of the monitored planting area, it is helpful to more accurately evaluate the relationship between the environmental data and the basic crop data. By integrating the environmental model and the soil-crop association model to obtain a microclimate environment model, the correlation between soil properties, environmental factors and crops can be better determined, which helps to better predict the future crop growth status. According to the correlation, the planting planning strategy is determined, and the planning strategy is displayed in the digital twin model of the planting area to be monitored. By simulating the planting planning strategy, the waste of resources in the agricultural production process is reduced, and the optimal growth state of crops is guaranteed, thereby improving agricultural production efficiency.

[0079] In one implementation of this embodiment, a crop image of a planting area to be monitored is obtained, and image recognition is performed on the crop image to obtain basic crop data, including:

[0080] S210, photographing images of crops in the monitored planting area by using a drone to obtain crop images;

[0081] S220, performing image segmentation on the crop image to obtain a plurality of sub-images;

[0082] S230, performing image recognition on each sub-image to obtain at least one crop leaf feature;

[0083] S240: Determine basic crop data according to at least one crop leaf feature.

[0084] Acquire crop images of the planting area to be monitored, perform image recognition on the crop images, and obtain basic crop data. First, use a drone to take images of the crops in the planting area to be monitored to obtain crop images. That is, use a drone in a greenhouse to take photos of the planting area to be monitored in the greenhouse to obtain crop images of the planting area.

[0085] Secondly, after obtaining the crop image of the planting area, the crop image is segmented to obtain multiple sub-images, and the image is segmented and features are extracted from the sub-images using image recognition. Image recognition technology refers to the technology of using computers to process, analyze and understand images to identify various different patterns of targets and objects. In this embodiment, the sub-image refers to the image obtained after the crop image is processed by image recognition and segmentation.

[0086] In this embodiment, image recognition can be used to identify each sub-image, and at least one crop leaf feature in each sub-image can be determined. In this embodiment, the crop leaf features include leaf edge features, leaf texture features, and leaf color features. The leaf edge features refer to the shape features of the leaf edge, such as the serrated feature, where the leaf edge has obvious serrations, and the shallow crack feature, where the leaf edge has shallow cracks. The leaf texture feature refers to the pattern features on the leaf surface, such as the presence of vinyl patterns, leaf vein patterns, and bird beak patterns. The leaf color feature refers to the color of the leaf surface, which is mainly determined by the pigment inside it. For example, yellowing of the leaf may indicate disease. By identifying the sub-image, at least one of the crop leaf features, including the leaf edge feature, the leaf texture feature, and the leaf color feature, can be determined.

[0087] By determining the characteristics of crop leaves, basic crop data is determined. In this embodiment, the basic crop data includes data on nutrients required by the crop, data on crop diseases and insect pests, and data on crop growth stages. The basic crop data is determined by determining the characteristics of crop leaves, that is, the nutrient data required by the crop, the crop disease and insect pest data, and the crop growth stage data are determined according to the leaf edge characteristics, leaf texture characteristics, and leaf color characteristics. For example, when the crop lacks nitrogen, the leaf color characteristics will become light green or yellow-white. When the crop lacks calcium, the leaf edge characteristics will curl up into a fishhook shape. When the leaf texture characteristics curl, the crop will have diseases. When the leaf color characteristics of the crop are different, the growth stage of the crop is also different. For example, the leaf color characteristics of tea leaves in the early growth stage are light green, and the color in the later growth stage is dark green. The basic crop data is determined by different crop leaf characteristics.

[0088] By taking crop images with drones and performing feature analysis on the crop images, we can obtain the crop leaf features of the sub-images. Based on the crop leaf features, we can get the basic crop data. We can accurately grasp the current growth status of the crops based on the crop leaf features, and make timely adjustments to the crop growth status to ensure the optimal growth state of the crops.

[0089] In one implementation of this embodiment, image recognition is performed on each sub-image to obtain at least one crop leaf feature, including:

[0090] S310, for any sub-image, performing image recognition on the sub-image, determining the edge of the crop leaf, and performing image segmentation on the sub-image based on the edge of the crop leaf to obtain the crop leaf area;

[0091] S320, extracting features from the crop leaf region to obtain at least one crop leaf feature, wherein the crop leaf feature includes a leaf edge feature, a leaf texture feature, and a leaf color feature;

[0092] Determine basic crop data based on at least one crop leaf feature, including:

[0093] S330. For a crop leaf feature, basic crop data is determined according to the leaf edge feature, leaf texture feature and leaf color feature. The basic crop data includes nutrient data required by the crop, crop disease and insect pest data and crop growth stage data.

[0094] Image recognition is performed on each sub-image to obtain at least one crop leaf feature. First, for any sub-image, image recognition is performed on the sub-image to determine the edge of the crop leaf. Specifically, the edge of the crop leaf image is detected. Edge detection is based on the grayscale change between the local area and the surrounding area in the image. When the brightness or grayscale value of a certain area in the image changes significantly, these changes usually correspond to the outline of the object, the boundary of different areas, etc. The edge detection algorithm identifies the edge in the image by analyzing these changes, and divides the pixels near the edge into different areas. The pixel points of the local features of the edge image of the crop leaf image are discontinuous with the pixel points of other parts. Therefore, detection is usually performed based on the sudden change of the image grayscale value, which can effectively separate different areas. After identifying the pixel points of the edge image of the crop leaf, the leaf image is determined and the leaf image is segmented from the background image, the leaf image is extracted, and the crop leaf area is obtained.

[0095] After obtaining the crop leaf area image, feature extraction is performed on the crop leaf area. In this embodiment, the crop leaf features are leaf edge features, leaf texture features and leaf color features. The crop leaf features are extracted mainly by image recognition to extract the leaf edge features, leaf texture features and leaf color features of the crop leaf area. In this embodiment, the leaf edge feature refers to the shape feature of the leaf edge, such as the serrated feature. The leaf texture feature refers to the texture feature of the leaf surface, such as the presence of vinyl pattern, vein pattern and bird's beak pattern. The leaf surface color feature refers to the color of the leaf surface. By extracting the leaf features of the crop leaf area, at least one leaf edge shape feature, leaf surface texture feature and leaf surface color feature are obtained.

[0096] After obtaining at least one crop leaf feature, the crop basic data is determined according to the at least one crop leaf feature. Specifically, the leaf edge feature, leaf texture feature and leaf color feature of the crop leaf region are obtained through image recognition, and the crop basic data is determined according to the leaf edge feature, leaf texture feature and leaf color feature. In this embodiment, the crop basic data includes the nutrient data required by the crop, the crop disease and insect pest data and the crop growth stage data. The crop basic data can be determined by the crop leaf feature, and the crop basic data corresponding to the crop leaf feature can be queried in the preset database through the preset database, so as to obtain the crop basic data. For example, the leaf edge feature is curled, the leaf texture feature is vinyl pattern, and the leaf color feature is yellow. The three features are respectively input into the preset database to obtain the crop basic data corresponding to the three features. For example, when the leaf edge feature is curled, the leaf texture feature is vinyl pattern, and the leaf color feature is yellow, the crop nutrient data required is nitrogen fertilizer, and the crop disease data is aphids, red spiders, etc., which will absorb the leaf juice, causing the leaves to lose green and turn yellow, and whether the crop growth stage data is normal stage data is determined.

[0097] Figure 2 A schematic diagram of a process for determining basic crop data according to an embodiment of the present application is shown schematically. Figure 2 As shown, determine whether the leaf color feature is a preset feature; if so, determine whether the color feature is uniform; if not, determine whether the leaf texture feature is a preset feature; if the texture is not obvious, determine whether the edge feature is a preset feature, if not, determine whether an irregular pixel area appears, and comprehensively determine the nutrients, pests and diseases, and growth stage required by the crop.

[0098] In another embodiment, the implementation method for determining the basic data of the crop based on the leaf edge features, leaf texture features and leaf color features may be, first, determining whether the leaf color feature is a preset color feature, such as the preset color feature is light green, and determining whether the currently extracted leaf color feature is consistent with the preset color feature. If the colors are consistent, such as both are light green, then determine whether the crop leaf color features are uniform. The determination of whether the color features are uniform is mainly based on the pixel values ​​of the crop leaves. When the pixel values ​​of the crop leaves are within the preset pixel value range, it is determined that the crop leaf color features are uniform. When it is determined that the crop leaf color features are uniform and the leaf color features meet the preset features, it can be preliminarily determined that the current crop is free of pests and diseases and lacks the elements required for crop growth.

[0099] Secondly, when the preset color feature is light green, and the extracted leaf color feature is yellow and light yellow, the leaf color feature is not the preset color feature. It is judged whether the current crop leaf color feature is uniform. If not, it is judged whether the leaf texture feature is the preset texture feature. For example, the preset texture feature is obvious texture. If the current leaf texture feature is unclear texture, and the current leaf texture feature is inconsistent with the preset texture feature, it is judged whether the edge feature meets the preset edge feature. For example, the preset edge feature is charred, brown, and irregular. It is judged whether the current edge feature is charred, brown, and irregular. The current edge feature is not charred, brown, and irregular. Then, the leaf color feature, leaf texture feature, and leaf edge feature are used to comprehensively determine whether nutrients need to be supplemented, whether it is in the stage of pests and diseases, and whether the current crop growth stage meets the growth stage, thereby comprehensively determining the basic data of the crop.

[0100] By performing image recognition on sub-images and determining the characteristics of crop leaves, we can obtain basic crop data, accurately obtain basic crop information, and obtain the growth elements, pests and diseases, and growth stages required for the next step of the crop. We can adjust the basic crop growth data in time to provide a suitable growth environment for the crop.

[0101] In one implementation of this embodiment, a soil-crop association model is constructed based on soil parameter data and crop basic data, including:

[0102] S410, obtaining a training set corresponding to soil parameter data, the training set including pH value and organic matter;

[0103] S420, inputting the training set into the initial model to train the initial model to obtain a trained initial model, and the trained initial model is used to characterize the soil-crop association model.

[0104] A soil-crop association model is constructed based on soil parameter data and basic crop data. Specifically, first, a training set corresponding to the soil parameter data is obtained. The training set refers to a data set used to establish and train the model. The main function of the training set is to adjust the parameters of the model by analyzing the sample data so that the model can accurately predict or classify new data. The initial model is trained by obtaining a training set of soil parameter data. In this embodiment, the training set includes pH value and organic matter. pH value refers to the acidity and alkalinity data in the soil, and organic matter refers to the various plant and animal residues and microorganisms contained in the soil and the amount of organic matter decomposed and synthesized by them. The initial model is trained by the pH value and organic matter in the soil to obtain a soil-crop association model.

[0105] After obtaining the training set corresponding to the soil parameter data, the training set is input into the initial model. In this embodiment, the initial model is a preset neural network model. The training set is input into the initial model to train the initial model to obtain a trained initial model. The initial model is trained with a large amount of soil parameter data. The trained initial model can be directly used in the analysis of the relationship between soil and crops, thereby obtaining a soil-crop relationship model.

[0106] By training the initial model with the training set corresponding to the soil parameter data, a soil-crop association model is obtained, which can not only improve the model performance and make the data analysis between soil and crops more accurate, but also effectively promote crop growth, increase crop yield and quality, and reduce the occurrence of diseases and pests, thus providing a solid foundation for the sustainable development of agriculture.

[0107] In one implementation of this embodiment, building an environment model based on environment data includes:

[0108] S510, obtaining a training set corresponding to environmental data, the training set including temperature, humidity and light intensity;

[0109] S520: Input the training set into the initial model to train the initial model and obtain a trained initial model. The trained initial model is used to characterize the environment model.

[0110] The environmental model is constructed based on the environmental data. Specifically, first, a training set corresponding to the environmental data is obtained. The training set refers to a data set used to establish and train the model. The main function of the training set is to adjust the parameters of the model by analyzing the sample data so that the model can accurately predict or classify new data. The initial model is trained by obtaining the training set corresponding to the environmental data. In this embodiment, the training set includes temperature, humidity and light intensity. Temperature refers to the most suitable temperature for plant growth, humidity refers to the most suitable humidity for plant growth, mainly refers to the most suitable moisture content for crop growth, and light intensity refers to the most suitable light intensity for crop growth. Light is crucial to the growth of plants. Light not only provides energy for plants and promotes photosynthesis, but also regulates the growth and development of plants. Appropriate light intensity and light time contribute to the normal growth and development of plants. The initial model is trained by the temperature, humidity and light intensity in the environment to obtain an environmental model.

[0111] After obtaining the training set corresponding to the environmental data, the training set is input into the initial model. In this embodiment, the initial model is a preset initial environmental model. The training set is input into the initial model to train the initial model to obtain a trained initial model. The initial model is trained with a large amount of environmental data. The trained initial model can be directly used in the analysis of the environmental data, thereby obtaining an environmental model.

[0112] By training the initial model with the training set corresponding to the environmental data to obtain the environmental model, not only can the model performance be improved and the environmental data analysis be more accurate, but it can also effectively promote crop growth, increase crop yield and quality, and reduce the occurrence of diseases and pests, thus providing a solid foundation for the sustainable development of agriculture.

[0113] In one implementation of this embodiment, the environmental model and the soil and crop association model are integrated to obtain a microclimate environmental model, and the association between soil properties, environmental factors and crop status is determined, including:

[0114] S610, determining a first change data set of soil properties and crop status at a future time node through a soil and crop association model;

[0115] S620, determining a second changed data set of environmental data at a future time node through the environmental model;

[0116] S630, performing data fitting on the first change data set and the second change data set to obtain a correlation analysis function;

[0117] S640, constructing a microclimate environment model based on the correlation analysis function;

[0118] S650: Input the soil property data, environmental data or crop status data of the target time node into the association analysis function to obtain the association relationship between the soil property data, environmental data and crop status data at a preset time node in the future.

[0119] The environmental model and the soil-crop association model are integrated to obtain a microclimate environmental model. Specifically, first, the first change data set of soil properties and crop status at future time nodes is determined through the soil-crop association model. That is, the historical soil parameter data is input into the soil-crop association model to obtain the first change data set of soil properties and crop status at future time nodes. In this embodiment, the first change data set refers to a set of soil property and crop status change data at future time nodes. The first change data set is composed of multiple soil property and crop status change data at future time nodes. For example, soil parameter data lasting three years is input into the soil-crop association model. Based on the soil parameter data lasting three years, soil and crop association data in the next three years are obtained, such as soil parameter changes in the next three years and crop growth status. The soil property and crop status data constitute a data set to obtain the first change data set.

[0120] Secondly, the second change data set of environmental data at future time nodes is determined through the environmental model. That is to say, the historical environmental data is input into the environmental model to obtain environmental change data at future time nodes. In this embodiment, the second change data set is a data set of environmental data changes at future time nodes. Multiple environmental change data sets at future time nodes constitute the second change data set. For example, environmental data within three years of history are input into the environmental model. Based on the environmental data within three years of history, environmental data within the next three years are obtained, such as the environmental conditions and crop growth status within the next three years. The data on soil properties and crop status constitute a data set, thereby obtaining the second change data set.

[0121] Data fitting is performed on the first change data set and the second change data set to obtain a correlation analysis function. Specifically, the first change data set and the second change data set are fitted. First, a first reference number series and a second reference number series are determined. In this embodiment, the first reference number series is the first change data set, and the second reference number series is the second change data set.

[0122] Secondly, the first reference series and the second reference series are initialized and dimensionless. The main purpose of dimensionless data is to eliminate the dimensional influence between different features or indicators and make the data comparable for subsequent analysis. The first reference series and the second reference series are fitted by the fitting formula. The data fitting formula is as follows:

[0123]

[0124] Among them, min j is the minimum value of the second reference sequence, min t is the minimum value of time, y i (t) is the first reference sequence, x j (t) is the second reference sequence, ρ is the resolution coefficient, and the usual value range is (0,1). In this embodiment, ρ can be 0.5, and max j is the maximum value of the first reference sequence, max t is the maximum value of time.

[0125] The first reference number series and the second reference number series are fitted by a fitting formula to obtain a correlation analysis function. In this embodiment, the correlation analysis function is a function obtained by fitting the first change data set and the second change data set by using a fitting formula.

[0126] After the correlation analysis function is obtained, a microclimate environment model is constructed according to the correlation analysis function. The microclimate environment model refers to a microclimate environment formed by the spatial differences in climatic factors such as temperature, humidity, wind speed and sunshine in a specific area. In this embodiment, the microclimate environment model is a microclimate environment model of the planting area to be monitored in the greenhouse. The environmental model and the soil-crop correlation model are fused to obtain the correlation analysis function, thereby obtaining the microclimate environment model.

[0127] The soil property data, environmental data or crop status data of the target time node are input into the association analysis function to obtain the association relationship between the soil property data, environmental data and crop status data at the preset time node in the future. In this embodiment, the target time node can be determined according to the actual situation. That is to say, the soil property data, environmental data or crop status data of the target time node are input into the association analysis function. For example, the target time node is three years, and the pH value and organic matter in the soil within three years, the temperature, humidity, light intensity or crop status data in the environmental data are input into the association analysis function to obtain the association relationship between the soil property data, environmental data and crop status data at the preset time node in the future. For example, after the corresponding data is input into the association analysis function, when the soil pH value and organic matter and the temperature, humidity and light intensity change, the change of the crop status data and the relationship between their changes can be obtained.

[0128] By fitting the first change data set and the second change data set to obtain the correlation analysis function, and constructing a microclimate environment model based on the correlation analysis function, the microclimate environment conditions in the greenhouse can be clearly displayed, which is helpful to effectively regulate the microclimate environment in the greenhouse, ensure the best growth environment for crops, and protect farmers' economic income.

[0129] In one implementation of this embodiment, constructing a microclimate environment model includes:

[0130] S710, obtaining greenhouse space data and carbon dioxide concentration data;

[0131] S720, correcting the correlation analysis function according to the space influencing factor and the air circulation influencing factor to obtain a corrected correlation analysis function;

[0132] S730. Obtain an optimized microclimate environment model through the corrected correlation analysis function.

[0133] Construct a microclimate environment model. Specifically, first, obtain greenhouse space data and carbon dioxide concentration data. The carbon dioxide concentration data is mainly obtained by detecting the carbon dioxide concentration in the greenhouse through a sensor, thereby obtaining the carbon dioxide concentration data. The carbon dioxide concentration plays a vital role in the growth process of plants and mainly affects the photosynthesis efficiency and plant growth rate. In this embodiment, the carbon dioxide concentration is used to characterize the air circulation conditions of the greenhouse.

[0134] After obtaining the greenhouse space data and carbon dioxide concentration data, the correlation analysis function is corrected by the spatial influencing factors and the air circulation influencing factors. That is to say, the greenhouse space data and the carbon dioxide concentration data will affect the correlation analysis function. Therefore, the correlation analysis function needs to be corrected based on the greenhouse space data and the carbon dioxide concentration data. To correct the correlation analysis function, specifically, first, the greenhouse space data and the carbon dioxide concentration data are used as the third reference series and the fourth reference series respectively.

[0135] Among them, the first reference sequence is Y i = {Y i (t)}; the second reference sequence is X j ={X j (t)};

[0136] The third reference sequence is Z i = {Z i (t)}; the fourth reference sequence is K j ={K j (t)};

[0137] The first correction sequence = the first reference sequence + the preset weight × the greenhouse space data;

[0138] First correction series = second reference series + preset weight × carbon dioxide concentration data;

[0139] The corrected correlation analysis function formula is as follows:

[0140]

[0141] Among them, the first correction sequence is α i (t); The second correction sequence β i (t), the minimum value of the first correction sequence is min i , the minimum value of the second correction sequence is min j , the maximum value of the first correction sequence is max j , the maximum value of the second correction sequence is max i , ρ is the resolution coefficient, and its usual value range is (0,1). In this embodiment, ρ can be 0.5.

[0142] The correlation analysis function is corrected by combining the first correction series and the second correction series to obtain a corrected correlation analysis function; through the corrected correlation analysis function, an optimized microclimate environment model is obtained. Microclimate refers to a microclimate environment formed by spatial differences in climate factors such as temperature, humidity, wind speed and sunshine in a specific area. In this embodiment, the microclimate environment model is a microclimate environment model of the planting area to be monitored in the greenhouse. After the corrected correlation analysis function is used, the corrected correlation analysis function formula can be fitted by a preset software to obtain an optimized microclimate environment model.

[0143] By correcting the correlation analysis function and obtaining the optimized microclimate environment model, not only can an accurate microclimate environment model be obtained, but also the relationship between the microclimate environment and the crop growth status can be determined by analyzing the optimized microclimate environment model, which helps to build the best crop growth environment and provide crop growth status.

[0144] In one implementation of this embodiment, the planning strategy of the planting area to be monitored is determined through the association relationship, including:

[0145] S810, for a crop leaf feature, determining a crop adjustment strategy for a target crop corresponding to the crop leaf feature according to basic crop data;

[0146] S820, determining the sub-image where the target crop is located, and obtaining positioning data in the planting area to be monitored corresponding to the sub-image;

[0147] S830, determining an adjustment area of ​​the planting area to be monitored according to the positioning data;

[0148] S840, obtaining soil attribute data of the adjustment area, and inputting the soil attribute data into a microclimate environment model to obtain environmental data and crop status data associated with the soil attribute data;

[0149] S850, determining suitable environmental data of the target crop according to the basic crop data of the target crop, and determining a first adjustment strategy for environmental data associated with the soil attribute data according to the suitable environmental data;

[0150] S860, determining standard state data corresponding to the growth stage data of the target crop through a preset state database, and determining a second adjustment strategy for the crop state data associated with the soil attribute data according to the standard state data;

[0151] S870: Integrate the first adjustment strategy, the second adjustment strategy, and the crop adjustment strategy to obtain a planning strategy for the adjustment area of ​​the planting area to be monitored.

[0152] The planning strategy of the planting area to be monitored is determined through the association relationship. Specifically, first, for a crop leaf feature, the crop adjustment strategy of the target crop corresponding to the crop leaf feature is determined based on the crop basic data. In this embodiment, the crop adjustment strategy refers to a strategy for adjusting the most suitable environment for crop growth through the crop basic data, such as determining the growth elements missing from the crop through the crop basic data and adjusting the missing elements of the crop. The crop basic data can be determined through the crop leaf features. The crop basic data corresponding to the crop leaf features can be queried in the preset database through the preset database to obtain the crop basic data. For example, the leaf edge feature is curled, the leaf texture feature is vinyl pattern, and the leaf color feature is yellow. These three features are respectively input into the preset database to obtain the crop basic data corresponding to the three features. According to the basic crop data, the crop adjustment strategy of the target crop corresponding to the crop leaf characteristics is determined. That is, according to the crop nutrient data, crop disease and pest data and crop growth stage data, the crop adjustment strategy of the target crop corresponding to the crop leaf characteristics is determined. For example, by analyzing the color characteristics of the crop leaves, the nitrogen element of the nutrient data required by the crop is obtained, and the nitrogen element is supplemented to the target crop according to the nutrient data required by the crop. In this embodiment, the target crop is a crop whose basic crop data needs to be adjusted, and the crop adjustment strategy of the target crop corresponding to the crop leaf characteristics is determined according to the basic crop data.

[0153] Determine the sub-image where the target crop is located, and obtain the positioning data in the planting area to be monitored corresponding to the sub-image. In this embodiment, the sub-image is an image obtained by segmenting the crop image through image recognition. The positioning data in the planting area to be monitored is determined through the sub-image of the target crop. That is to say, based on the basic data of the crop, the target crops whose nutrient data, crop disease and pest data, and crop growth stage data of the crops in the planting area to be monitored need to be adjusted are judged, the positions of these target crops that need to be adjusted are obtained, and the positioning data in the planting area to be monitored is determined.

[0154] After determining the positioning data of the target crop in the monitored planting area, the adjustment area of ​​the monitored planting area is determined according to the positioning data. That is to say, after determining the position of the target crop whose basic crop data needs to be adjusted in the monitored planting area, the adjustment area can be generated for the position of the target crop according to the preset range. In this embodiment, the preset range can be determined according to the actual situation. For example, the positioning data of the target crop whose crop disease and insect pest data needs to be adjusted is obtained through the characteristics of the crop leaves, and the crops within the preset range are subjected to disease and insect pest control according to the preset range. For example, the preset range is one meter, and a circle with a radius of n meters is drawn with the position of the target crop as the center. The crops within the circle are subjected to disease and insect pest control, and the circular area is used as the adjustment area of ​​the monitored planting area. n can be set freely.

[0155] In another embodiment, the implementation method may be to obtain the soil state of the target crop by determining the positioning data of the target crop in the planting area to be monitored. In this embodiment, the soil state includes soil moisture, pH value, organic matter, and soil color. The crops with consistent soil state and located in the surrounding area are determined through the positioning data of the target crop, and the crop positioning data with soil state consistent with the soil state of the target crop is obtained, and the adjustment area is determined through the positioning data. For example, after determining the position of the target crop, the soil state of the target crop is obtained, and an area with a soil state consistent with the target crop is found near the target crop, and the area of ​​m square meters of this area is used as the adjustment area, where the value of m can be freely set.

[0156] After determining the adjustment area of ​​the planting area to be monitored, obtain the soil property data of the adjustment area of ​​the planting area to be monitored, and input the soil property data into the microclimate environment model to obtain environmental data and crop status data associated with the soil property data. In other words, determine the linkage relationship between soil properties, environmental factors and crop status. For example, when the temperature, humidity and light intensity in the environment change, the pH value and organic matter value in the soil also change accordingly, which will affect the growth status of the crops. Determine the linkage relationship between soil properties, environmental factors and crop status, and obtain environmental data and crop status data associated with the soil property data.

[0157] According to the basic crop data of the target crop, the suitable environment data of the target crop is determined, that is, through the crop nutrient data, crop pest data and crop growth stage data of the target crop, it is judged whether the target crop needs to adjust the nutrient data, crop pest data and crop growth stage data of the target crop. If the target crop needs to adjust any one of the nutrient data, crop pest data and crop growth stage data, the basic crop data of the target crop is adjusted to determine the suitable environment data of the target crop. In this embodiment, the suitable environment data refers to the environmental data in the state where the basic crop data of the target crop does not need to be adjusted. According to the suitable environment data, the soil attribute data under the suitable environment data is determined, and according to the environmental data associated with the soil attribute data, the soil attribute data is adjusted to determine the first adjustment strategy. In this embodiment, the first adjustment strategy refers to the strategy for adjusting the soil attribute data through the environmental data associated with the soil attribute data.

[0158] After determining the first adjustment strategy, the standard state data corresponding to the growth stage data of the target crop is determined through the preset state database, and the second adjustment strategy of the crop state data associated with the soil attribute data is determined based on the standard state data. In this embodiment, the second adjustment strategy refers to a strategy for adjusting the soil attribute data through the standard state data corresponding to the growth stage data of the target crop. The growth stage data of the target crop is input into the preset state database to obtain the standard state data of the target crop, and the soil attribute data under the standard state data is obtained through the standard state data. The current soil attribute data is adjusted through the soil attribute data under the standard state data to obtain the second adjustment strategy to ensure the best growth state of the crop.

[0159] The first adjustment strategy, the second adjustment strategy and the crop adjustment strategy are integrated to comprehensively adjust the adjustment area, so as to determine the planning strategy of the adjustment area of ​​the monitored planting area. In this embodiment, the planning strategy is a strategy for adjusting the adjustment area of ​​the monitored planting area through the first adjustment strategy, the second adjustment strategy and the crop adjustment strategy.

[0160] Comprehensive adjustment of the adjustment area through the first adjustment strategy, the second adjustment strategy and the crop adjustment strategy can not only ensure the best environment for crop growth in the monitored planting area, but also provide optimized planting time for crops, improve crop management efficiency, reduce agricultural risks, promote precision agriculture, and enhance resource management capabilities.

[0161] The present application provides a machine-readable storage medium having instructions stored thereon, which are used to enable a machine to execute the above-mentioned digital twin-based GIS data visualization management method.

[0162] This application provides a GIS data visualization management system based on digital twins, including:

[0163] a memory configured to store instructions; and

[0164] The processor is configured to call instructions from the memory and implement the above-mentioned digital twin-based GIS data visualization management method when executing the instructions.

[0165] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0166] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0167] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0168] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0169] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0170] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0171] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0172] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0173] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A GIS data visualization management method based on digital twins, characterized in that: include: Obtain soil parameter data of the planting area to be monitored in the greenhouse; Acquire crop images of the planting area to be monitored, and perform image recognition on the crop images to obtain basic crop data; Constructing a soil-crop association model based on the soil parameter data and the crop basic data; Acquiring environmental data of the planting area to be monitored, and constructing an environmental model based on the environmental data; The environmental model and the soil-crop association model are integrated to obtain a microclimate environmental model, and the association between soil properties, environmental factors and crop status is determined; Determining the planning strategy of the planting area to be monitored through the association relationship; The planning strategy is visualized in a pre-built digital twin model of the planting area to be monitored.

2. The method according to claim 1, characterized in that The step of acquiring the crop image of the planting area to be monitored and performing image recognition on the crop image to obtain basic crop data includes: Using a drone to take images of the crops in the to-be-monitored planting area to obtain crop images; Performing image segmentation on the crop image to obtain a plurality of sub-images; Performing image recognition on each of the sub-images to obtain at least one crop leaf feature; Based on at least one of the crop leaf characteristics, basic crop data is determined.

3. The method according to claim 2, characterized in that The performing image recognition on each of the sub-images to obtain at least one crop leaf feature includes: For any one of the sub-images, performing image recognition on the sub-image to determine the edge of a crop leaf, and performing image segmentation on the sub-image based on the edge of the crop leaf to obtain a crop leaf region; Extracting features from the crop leaf region to obtain at least one crop leaf feature, wherein the crop leaf feature includes a leaf edge feature, a leaf texture feature, and a leaf color feature; Determining basic crop data according to at least one crop leaf feature includes: For one of the crop leaf features, basic crop data is determined based on the leaf edge feature, the leaf texture feature and the leaf color feature. The basic crop data includes nutrient data required by the crop, crop disease and pest data and crop growth stage data.

4. The method according to claim 1, characterized in that: The step of constructing a soil-crop association model based on the soil parameter data and the crop basic data includes: Obtaining a training set corresponding to the soil parameter data, wherein the training set includes pH value and organic matter; The training set is input into the initial model to train the initial model to obtain a trained initial model, and the trained initial model is used to characterize a soil-crop association model.

5. The method according to claim 1, characterized in that The step of constructing an environment model based on the environment data comprises: Obtaining a training set corresponding to the environmental data, wherein the training set includes temperature, humidity and light intensity; The training set is input into the initial model to train the initial model to obtain a trained initial model, and the trained initial model is used to characterize the environment model.

6. The method according to claim 3, characterized in that The step of fusing the environmental model with the soil and crop association model to obtain a microclimate environmental model and determining the association between soil properties, environmental factors and crop status includes: Determine a first change data set of soil properties and crop status at a future time node by using the soil and crop association model; Determine a second change data set of environmental data at a future time node by using the environmental model; Performing data fitting on the first change data set and the second change data set to obtain a correlation analysis function; A microclimate environment model is constructed based on the correlation analysis function; The soil property data, environmental data or crop status data at the target time node are input into the association analysis function to obtain the association relationship between the soil property data, environmental data and crop status data at a preset time node in the future.

7. The method according to claim 6, characterized in that The microclimate environment model is constructed, comprising: Obtain greenhouse space data and carbon dioxide concentration data; Correcting the correlation analysis function by using the space influencing factor and the air circulation influencing factor to obtain a corrected correlation analysis function; An optimized microclimate environment model is obtained through the corrected correlation analysis function.

8. The method according to claim 6, characterized in that Determining the planning strategy of the to-be-monitored planting area through the association relationship includes: For one of the crop leaf features, determining a crop adjustment strategy for a target crop corresponding to the crop leaf feature according to the crop basic data; Determine the sub-image where the target crop is located, and obtain positioning data in the planting area to be monitored corresponding to the sub-image; Determining an adjustment area of ​​the planting area to be monitored according to the positioning data; Acquiring soil property data of the adjustment area, and inputting the soil property data into the microclimate environment model to obtain environmental data and crop status data associated with the soil property data; Determining suitable environmental data of the target crop based on the crop basic data of the target crop, and determining a first adjustment strategy of the environmental data associated with the soil attribute data based on the suitable environmental data; Determining standard state data corresponding to the growth stage data of the target crop through a preset state database, and determining a second adjustment strategy for the crop state data associated with the soil attribute data based on the standard state data; The first adjustment strategy, the second adjustment strategy and the crop adjustment strategy are integrated to obtain the planning strategy for the adjustment area of ​​the planting area to be monitored.

9. A machine-readable storage medium, characterized in that: The machine-readable storage medium stores instructions for enabling a machine to execute a digital twin-based GIS data visualization management method according to any one of claims 1 to 8.

10. A GIS data visualization management system based on digital twins, characterized in that: include: a memory configured to store instructions; as well as A processor is configured to call the instructions from the memory and to implement the digital twin-based GIS data visualization management method according to any one of claims 1 to 8 when executing the instructions.

Images