Intelligent Juncao transplanting method and system based on Internet of Things technology

Abstract

The invention discloses an intelligent Juncao transplanting method and system based on the Internet of Things technology, and relates to the technical field of intelligent agriculture, the intelligent Juncao transplanting method and system collects key environment data such as soil microbial environment, wind speed and pressure, mechanical stress, soil moisture and illumination conditions in real time, and establishes a transplanting environment prediction model by using the convolutional neural network technology. Therefore, the Juncao transplanting adaptive capacity of each sub-region can be screened, the transplanting success rate can be improved, and resource allocation can be optimized. In the pennisetum sinese transplanting growth process, root exudate compatibility data and pest attraction effect data are continuously collected, a dynamic growth data set is established, and a growth risk coefficient is monitored in real time. In the process, the bad trend in growth can be found in time, and it is ensured that countermeasures are taken at the beginning of the problem. And according to a real-time risk assessment result, an environment optimization strategy is adjusted, healthy growth of the Juncao in the whole growth period is ensured, and unnecessary resource waste is reduced.

Description

Technical Field

[0001] The present invention relates to the field of intelligent agricultural technology, and specifically to an intelligent mushroom grass transplanting method and system based on Internet of Things technology. Background Art

[0002] Juncao transplanting technology is an agricultural technology that combines specific fungi with herbaceous plants through human intervention, and uses appropriate transplanting methods to enable them to quickly adapt to and grow healthily in the new growth environment. This technology is widely used in ecological restoration, soil remediation, and agricultural production, especially in areas with poor or damaged soil. Juncao transplanting can effectively improve soil quality, improve land use efficiency, and promote the restoration of ecological balance. However, traditional Juncao transplanting technology often relies on manual experience and lacks comprehensive monitoring and real-time feedback of environmental data, resulting in unstable transplanting effects and certain risks.

[0003] The success of Juncao transplanting is affected by a variety of environmental factors, such as the soil microbial environment, climate conditions, water conditions and light. Traditional Juncao transplanting methods usually fail to fully consider these complex environmental factors. They only select the appropriate time and location for transplanting through manual judgment, lacking accurate perception and real-time monitoring of environmental factors. This method that relies on manual experience makes the transplanting effect susceptible to environmental changes and difficult to achieve refined management and regulation. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides an intelligent mushroom grass transplanting method and system based on Internet of Things technology to solve the problems mentioned in the background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent mushroom grass transplanting method based on Internet of Things technology, comprising the following steps: S1. Divide the transplanting area into several sub-areas, and use distributed Internet of Things sensing devices to collect environmental biological data in the sub-areas, wherein the environmental biological data include: soil microbial environment data, wind speed and wind pressure data, mechanical stress data of the roots of the grass, soil moisture data, and spatial variation data of light conditions; S2. Preprocess the collected environmental biological data, remove outliers and fill in missing values; standardize the environmental biological data using dimensionless technology to build a transplant environment database in a unified format; S3. Use convolutional neural network technology to establish a transplanting environment prediction model. After training, extract and calculate the features of the transplanting environment database to obtain the microbial environmental impact coefficient of the i-th sub-area. , root mechanical stress coefficient , soil moisture uniformity coefficient , Wind environmental impact coefficient and the spatial coefficient of variation of illumination ; and associate to obtain the comprehensive impact index of the Juncao transplanting environment in the i-th sub-region ; S4, preset the first risk threshold Y1, and set the comprehensive impact index of the Juncao transplanting environment in the i-th sub-area Compare and evaluate with the first risk threshold Y1 to obtain the environmental adaptability level, and generate the corresponding environmental optimization strategy according to the corresponding level; S5. After the corresponding environmental optimization strategy is executed, the Juncao transplanting operation is performed, and the compatibility data of the Juncao root secretions and the pest attraction effect data after transplanting are continuously collected during the growth of the Juncao transplanting, and a growth data set is established. Based on the growth data set, the growth risk coefficient of the i-th sub-area is constructed. , and preset the second risk threshold Y2, and set the growth risk coefficient of the i-th sub-region The value is compared with the second risk threshold Y2 to obtain a growth risk assessment result.

[0006] Preferably, S1 comprises: S11. Use UAV remote sensing mapping equipment to obtain high-definition images of the transplanting area and calculate the total area, mark low-lying areas, highlands, and shaded areas, divide the transplanting area into several sub-areas, use GIS geographic information system to draw a regional network, and simultaneously number several sub-areas in the regional network as A1, A2, ..., A n , n is the number of sub-regions; S12. Set a sampling point in each sub-area, arrange soil sensors, pH sensors, temperature sensors and microbial sensors with microfluidic chips, and collect soil microbial environmental data in real time. The soil microbial environmental data include: microbial species, microbial density, soil pH value sjd, soil temperature wd and microbial metabolite CO2 concentration htcd; S13. Set a sampling point in each sub-area, arrange anemometers and wind pressure sensors, and set the arrangement heights of anemometers and wind pressure sensors to 1 meter, 2 meters and 3 meters respectively. Collect wind speed and wind pressure data in real time. The sampling interval is set to record data every 10 minutes. The wind speed and wind pressure data include: wind speed v and wind pressure p. Combined with the geographic coordinates of the sampling points, generate a spatiotemporal distribution map of wind speed and pressure in the sub-area.

[0007] Preferably, S1 further comprises: S14. Set sampling points in each sub-area, install pressure sensors at depths of 5 cm, 10 cm and 20 cm from the ground surface, and collect mechanical stress data of the roots of the Juncao. The mechanical stress data of the roots of the Juncao include mechanical stress ; S15, a sampling point is arranged at an interval of 5-20 square meters in each sub-area, and a humidity sensor is installed at a depth of 0-20 cm from the ground surface at each sampling point to collect soil moisture data, the soil moisture data including soil moisture content M; S16. Arrange a sampling point at an interval of 5-20 square meters in each sub-area, and arrange a light intensity sensor at a distance of one meter from the ground at each sampling point to collect spatial variation data of light conditions, where the spatial variation data of light conditions includes light intensity L; S17. Summarize the soil microbial environment data, wind speed and pressure data, mechanical stress data of the grass root system, soil moisture data and spatial variation data of light conditions collected in S12-S16, and summarize and establish environmental biological data.

[0008] Preferably, S2 comprises: S21, matching the environmental biological data of several transplanting sub-areas collected in S1 with the numbers of each sub-area one by one to form an original data set; S22. Check the original data set to see if there are any missing values, any abnormal values, and whether the timestamps and geographic coordinates of the original data table are complete; missing values ​​include Null or NaN data; S23. Setting a threshold range to determine whether there are abnormal values, including: The pH value sjd threshold range of soil is 4.5-9; The soil temperature wd threshold range is -10℃ to 50℃; The htcd threshold range of CO2 concentration of microbial metabolites is 0-500ppm; The wind speed v threshold range is 0-20m / s; The wind pressure p threshold range is 0-1.5 kPa; The soil moisture content M threshold range is 5%-50%; S24. Mark the data beyond the threshold range as outliers and remove them. Use the box plot analysis method to mark the original data set below the first quartile Q1×1.5 times IQR or above the third quartile Q3×1.5 times IQR as outliers. IQR means position, which means the middle 50% range of the original data set distribution. Q1 is the first quartile of the original data set, which is the value corresponding to the lower 25% position of the original data set after the original data set is centrally sorted. Q3 is the third quartile of the original data set, which is the value corresponding to the upper 25% position of the original data set after the original data set is centrally sorted. S25. After filling the missing values ​​between adjacent moments using linear interpolation or spline interpolation, the original data set is dimensionless and then imported into a transplant environment database in a unified format.

[0009] Preferably, S3 includes: S31, using a convolutional neural network to construct an initial model of the convolutional neural network, and using the transplanting environment database to train and test the initial model of the convolutional neural network, and using the trained initial model of the convolutional neural network as a transplanting environment prediction model, and using the intermediate layer output of the transplanting environment prediction model as a feature vector to identify feature information, and using the acquired feature information to train and test the transplanting environment prediction model, and using the trained transplanting environment prediction model as data to run prediction; S32. Use the transplanting environment prediction model to extract and calculate the characteristics of the transplanting environment database to obtain the microbial environmental impact coefficient of the i-th sub-area , root mechanical stress coefficient , soil moisture uniformity coefficient , Wind environmental impact coefficient and the spatial coefficient of variation of illumination .

[0010] Preferably, the S32 includes: S321, Microbial environmental impact coefficient of the ith sub-region Calculated by the following formula: ;in, is the density of the jth type of microorganism in the soil of the ith sub-region, is the adaptability score of the j-th microorganism in the soil of the ith sub-region to Juncao, obtained through experimental data. represents the number of microbial species in the soil of the ith sub-region, represents the pH value of the soil in the ith sub-region, represents the soil temperature of the ith sub-region, represents the CO2 concentration of microbial metabolites in the ith sub-region; , , and Indicates the weight value; S322, root mechanical stress coefficient of the i-th sub-region Calculated by the following formula: ;in, and are the maximum test volume boundary and the minimum test volume boundary in the i-th sub-region, respectively. represents the soil mechanical stress in the ith sub-region, represents the test volume of the ith sub-region, dV represents a tiny volume unit, and represents the volume part accumulated during the integration process; S323, soil moisture uniformity coefficient of the i-th sub-region Calculated by the following formula: ;in, represents the average soil moisture content in the ith sub-region, represents the number of sampling points in the i-th sub-region, represents the soil moisture content at the kth sampling point in the ith sub-area; S324, wind environment impact coefficient of the ith sub-area Calculated by the following formula: ;in, Indicates that the kth sampling point in the i-th sub-region is at height The wind speed, The kth sampling point in the i-th sub-region is at height The wind pressure, and Represents the weight value; represents the number of sampling points in the i-th sub-region; S325, spatial variation coefficient of illumination of the i-th sub-area Calculated by the following formula: ;in, Represents the light intensity of the kth sampling point in the i-th sub-area; represents the average light intensity of the ith sub-region, represents the number of sampling points in the i-th sub-area; S326, the microbial environmental impact coefficient of the i-th sub-region , root mechanical stress coefficient , soil moisture uniformity coefficient , Wind environmental impact coefficient and the spatial coefficient of variation of illumination After dimensionless processing, the comprehensive impact index of the Juncao transplanting environment in the i-th sub-region is obtained by the following correlation formula: ; ;in, , , , and Represent the microbial environmental impact coefficient of the i-th sub-region , root mechanical stress coefficient , soil moisture uniformity coefficient , Wind environmental impact coefficient and the spatial coefficient of variation of illumination The weight value of Represents the first correction constant.

[0011] Preferably, S4 includes: S41, preset the first risk threshold Y1, and set the comprehensive impact index of the Juncao transplanting environment in the i-th sub-region Compare and evaluate with the first risk threshold Y1 to obtain the environmental adaptability level, including: If the comprehensive impact index of the Juncao transplanting environment in the i-th sub-region > The first risk threshold Y1×150% indicates that the adaptability of the current sub-area is unqualified and unsuitable for Juncao transplanting. The sub-area is directly screened out and marked; If the first risk threshold Y1×120%≤the comprehensive impact index of the Juncao transplanting environment in the i-th sub-region ≤ the first risk threshold Y1×150%, indicating that the adaptability of the current sub-region is unqualified and obtains the first level; If the first risk threshold Y1≤the comprehensive impact index of the Juncao transplanting environment in the i-th sub-region < the first risk threshold Y1×120%, indicating that the adaptability of the current sub-region is unqualified and obtains the second level; If the comprehensive impact index of the Juncao transplanting environment in the i-th sub-region < the first risk threshold Y1, indicating that the current sub-region is suitable for adaptation and obtains the third level; S42. After obtaining the environmental adaptability level, a corresponding environmental optimization strategy is generated, including: The first environmental optimization strategy is generated according to the first level, including: the current sub-area needs to be fully optimized, 5 grams of nitrogen-fixing bacteria, phosphate-dissolving bacteria and microbial preparations are added per square meter, and the application is repeated twice a week; the sub-area is plowed to a depth of 11-20 cm, and 200 grams of organic fertilizer is applied per square meter; the soil is loosened evenly in each sub-area, and 1 kg of sawdust / square meter is added; the coverage rate of the sunshade net is increased by 30%-50%, and a sunshade net is installed in each sub-area to reduce the light intensity to the target value L=200 lumens; a windbreak wall is arranged around the sub-area or a 2-meter-high windbreak forest is planted; after the first environmental optimization strategy is executed, the grass is transplanted, and the first transplanting depth of the sub-area is set to 5 cm; The second environmental optimization strategy is generated according to the second level, including: the current sub-area needs to be partially optimized, 3 grams of nitrogen-fixing bacteria, phosphate-dissolving bacteria and microbial preparations are added per square meter, and the application is repeated once a week; the sub-area is plowed to a depth of 5-10 cm, and 100 grams of organic fertilizer is applied per square meter; the soil is loosened evenly in each sub-area, and 0.5 kg of sawdust / square meter is added; the coverage rate of the sunshade net is increased by 10%-15%, and a sunshade net is installed in each sub-area to reduce the light intensity to the target value L=300 lumens; a windbreak wall is arranged around the sub-area or a 1-meter-high windbreak forest is planted; after the second environmental optimization strategy is executed, the grass is transplanted, and the second transplanting depth of the sub-area is set to 6-7 cm; The third environmental optimization strategy is generated according to the third level, including: direct transplanting of Juncao, and setting the third transplanting depth of the sub-area to 8-9 cm.

[0012] Preferably, S5 includes: S51. After the corresponding environmental optimization strategy is executed, the Juncao transplanting operation is performed, and during the growth of Juncao transplanting, the compatibility data of Juncao root secretions, the pest attraction effect data after transplanting and the soil density disturbance data are continuously collected to establish a growth data set; and the root secretion compatibility coefficient of the i-th sub-area is constructed based on the growth data set. , Pest attraction coefficient and soil disturbance influence coefficient , and associated with the root secretion compatibility coefficient of the i-th sub-region , Pest attraction coefficient and soil disturbance influence coefficient , get the growth risk coefficient of the i-th sub-region ; S511. Within the sampling point range of each sub-area, install a liquid collection device in the Juncao root distribution area, set the sampling depth to 10-20 cm, obtain root secretion liquid samples, set the collection frequency to once every 2 days, and keep collecting for 6-8 weeks. Perform experimental measurements on the root secretion liquid samples to obtain the organic acid concentration nd1, enzyme concentration nd2 and secretion pH value tj3, and establish compatibility data of Juncao root secretions; S512. Pest monitoring equipment is arranged at sampling points in each sub-area. The pest monitoring equipment includes insect monitoring lights and ground traps. The pest monitoring equipment is arranged at intervals of 10-20 square meters to collect flying pest density. and underground pest density , establish pest attraction effect data after transplanting; S513. Install soil density sensors at sampling points in each sub-area at a distance of 1-9 cm from the surface layer and 10-20 cm from the sub-surface layer to collect soil density disturbance data. The soil density disturbance data includes soil density before transplanting. and soil density after transplanting ; S514, root secretion compatibility coefficient of the i-th sub-region Calculated by the following formula: ;in, represents the organic acid concentration in the ith sub-region, represents the enzyme concentration in the ith sub-region, represents the secretion pH value tj3 of the i-th sub-region; Pest attraction coefficient of the i-th sub-region Calculated by the following formula: ;in, represents the density of flying pests in the ith sub-area, represents the underground pest density in the ith sub-area ; represents the area of ​​the i-th sub-region; Soil disturbance influence coefficient of the i-th sub-area Calculated by the following formula: ;in, represents the soil density before transplanting in the i-th sub-area , represents the soil density after transplanting in the ith sub-area; S515, the root secretion compatibility coefficient of the i-th sub-region , Pest attraction coefficient and soil disturbance influence coefficient After dimensionless processing, the growth risk coefficient of the ith sub-region is obtained through the following correlation formula: : ;in, , and are the root secretion compatibility coefficients of the i-th sub-region , Pest attraction coefficient and soil disturbance influence coefficient The weight value of Represents the second correction constant.

[0013] Preferably, S5 further includes: S52, presetting a second risk threshold Y2, and setting the growth risk coefficient of the i-th sub-region Compare with the second risk threshold Y2 to obtain the growth risk assessment results, including: If the growth risk coefficient of the i-th sub-region > The second risk threshold Y2 indicates that the growth environment of the sub-area is at risk, and the fourth environmental optimization strategy is generated, including: adding 1-2 kg of sandy soil per square meter to improve aeration; applying 2 grams of microbial agents per square meter, repeating once a week, and applying three times in a row; arranging 1-2 trapping lights in each sub-area, spraying biological pesticides once a week for 2-3 consecutive weeks; If the growth risk coefficient of the i-th sub-region ≤ the second risk threshold Y2, indicating that there is no risk in the growth environment of the sub-region and continuous monitoring is required.

[0014] The intelligent Juncao transplanting system based on Internet of Things technology includes: The segmentation unit is used to divide the transplanting area into several sub-areas, draw a regional network using the GIS geographic information system, and simultaneously number several sub-areas in the regional network as A1, A2, ..., A n , n is the number of sub-regions; The first IoT collection unit is used to collect environmental biological data in the sub-area using distributed IoT sensing devices, wherein the environmental biological data includes soil microbial environment data, wind speed and wind pressure data, mechanical stress data of the grass root system, soil moisture data, and spatial variation data of light conditions; Establish a model unit to establish a transplanting environment prediction model using convolutional neural network technology. After training, extract and calculate the features of the transplanting environment database to obtain the microbial environmental impact coefficient of the i-th sub-area. , root mechanical stress coefficient , soil moisture uniformity coefficient , Wind environmental impact coefficient and the spatial coefficient of variation of illumination ; and associate to obtain the comprehensive impact index of the Juncao transplanting environment in the i-th sub-region ; The first evaluation unit is used to preset the first risk threshold Y1 and calculate the comprehensive impact index of the Juncao transplanting environment in the i-th sub-area. Compare and evaluate with the first risk threshold Y1 to obtain the environmental adaptability level, and generate the corresponding environmental optimization strategy according to the corresponding level; The second IoT monitoring unit is used to perform the Juncao transplanting operation after the corresponding environmental optimization strategy is executed, and continuously collect the compatibility data of Juncao root secretions and the pest attraction effect data after transplanting during the growth of Juncao transplanting, and establish a growth data set; The second evaluation unit is used to construct the growth risk coefficient of the i-th sub-region based on the growth data set. , and preset the second risk threshold Y2, and set the growth risk coefficient of the i-th sub-region The value is compared with the second risk threshold Y2 to obtain a growth risk assessment result.

[0015] The present invention provides an intelligent mushroom grass transplanting method and system based on Internet of Things technology, which has the following beneficial effects: (1) Through the application of distributed Internet of Things sensing devices, the present invention can monitor multiple environmental data such as soil microbial environment, wind speed, wind pressure, mechanical stress of Juncao roots, soil moisture and light conditions in real time. This solves the defect of insufficient monitoring of environmental parameters in traditional methods. Traditional Juncao transplanting relies on manual experience and cannot monitor and process the impact of environmental changes in real time. The present invention can calculate the microbial environmental impact coefficient of the i-th sub-area during the environmental adaptability assessment process. , root mechanical stress coefficient , soil moisture uniformity coefficient , Wind environmental impact coefficient and the spatial coefficient of variation of illumination ; and associate to obtain the comprehensive impact index of the Juncao transplanting environment in the i-th sub-region , intelligently generate corresponding optimization strategies. Traditional methods often rely on experience to make environmental judgments, while the present invention uses a data-driven method to achieve intelligent optimization and dynamic adjustment of the environment under the influence of multiple environmental factors, which helps to improve the adaptability and growth success rate of Juncao transplanting.

[0016] (2) During the growth process of Juncao transplanting, the present invention continuously collects compatibility data of Juncao root secretions and pest attraction effect data to establish a growth data set and construct a growth risk coefficient. This method can monitor the growth status after transplanting in real time, warn of potential growth risks in advance, especially in terms of pest attraction and root growth, and improve the overall growth effect of Juncao.

[0017] (3) The present invention obtains wind speed and wind pressure data at different heights at the sub-region sampling points, and collects mechanical stress data of the Juncao root system at different depths, which can accurately reflect the growth status of the root system in the soil and the adaptability of the root system to the external environment. This avoids the data deviation caused by neglecting or singling out the sampling height in traditional methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a schematic diagram of the steps of the intelligent Juncao transplanting method based on the Internet of Things technology of the present invention; Figure 2 It is a schematic diagram of the process of the intelligent Juncao transplanting system based on the Internet of Things technology of the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] Example 1 See also Figure 1 The present invention provides an intelligent Juncao transplanting method based on Internet of Things technology, comprising the following steps: S1. Divide the transplanting area into several sub-areas, and use distributed Internet of Things sensing devices to collect environmental biological data in the sub-areas, wherein the environmental biological data include: soil microbial environment data, wind speed and wind pressure data, mechanical stress data of the roots of the grass, soil moisture data, and spatial variation data of light conditions; S2. Preprocess the collected environmental biological data, remove outliers and fill in missing values; standardize the environmental biological data using dimensionless technology to build a transplant environment database in a unified format; S3. Use convolutional neural network technology to establish a transplanting environment prediction model. After training, extract and calculate the features of the transplanting environment database to obtain the microbial environmental impact coefficient of the i-th sub-area. , root mechanical stress coefficient , soil moisture uniformity coefficient , Wind environmental impact coefficient and the spatial coefficient of variation of illumination ; and associate to obtain the comprehensive impact index of the Juncao transplanting environment in the i-th sub-region ; S4, preset the first risk threshold Y1, and set the comprehensive impact index of the Juncao transplanting environment in the i-th sub-area Compare and evaluate with the first risk threshold Y1 to obtain the environmental adaptability level, and generate the corresponding environmental optimization strategy according to the corresponding level; S5. After the corresponding environmental optimization strategy is executed, the Juncao transplanting operation is performed, and the compatibility data of the Juncao root secretions and the pest attraction effect data after transplanting are continuously collected during the growth of the Juncao transplanting, and a growth data set is established. Based on the growth data set, the growth risk coefficient of the i-th sub-area is constructed. , and preset the second risk threshold Y2, and set the growth risk coefficient of the i-th sub-region The value is compared with the second risk threshold Y2 to obtain a growth risk assessment result.

[0021] In this embodiment, through the application of distributed Internet of Things sensing devices, the present invention can monitor in real time multiple environmental data such as soil microbial environment, wind speed, wind pressure, mechanical stress of Juncao roots, soil moisture and light conditions. This comprehensive data collection can provide a more accurate environmental basis for Juncao transplanting, and solve the defect of insufficient monitoring of environmental parameters in traditional methods. Traditional Juncao transplanting relies on manual experience, and is unable to monitor and process the impact of environmental changes in real time. The present invention effectively ensures the quality and consistency of the data through data preprocessing, outlier elimination, missing value filling and standardization technology, and establishes an environmental prediction model through convolutional neural network technology, realizing real-time evaluation and feedback of environmental conditions in different sub-regions. This process can effectively avoid errors in manual operations, and timely adjust transplanting strategies and optimize environmental conditions. The present invention can calculate the microbial environmental impact coefficient of the i-th sub-region during the environmental adaptability assessment process. , root mechanical stress coefficient , soil moisture uniformity coefficient , Wind environmental impact coefficient and the spatial coefficient of variation of illumination ; and associate to obtain the comprehensive impact index of the Juncao transplanting environment in the i-th sub-region , intelligently generate corresponding optimization strategies. Traditional methods often rely on experience to make environmental judgments, while the present invention uses a data-driven method to achieve intelligent optimization and dynamic adjustment of the environment under the influence of multiple environmental factors, which helps to improve the adaptability and growth success rate of Juncao transplanting.

[0022] During the growth process of Juncao transplanting, the present invention continuously collects compatibility data and pest attraction effect data of Juncao root secretions, establishes a growth data set, and constructs a growth risk coefficient. This method can monitor the growth status after transplanting in real time, and warn of potential growth risks in advance, especially in terms of pest attraction and root growth. It can provide precise control for plant growth after transplanting, significantly reduce risk factors in traditional methods, and improve overall growth effects. According to the environmental characteristics and growth conditions of different sub-regions, the present invention can tailor transplanting strategies for each sub-region, which can better promote Juncao growth, enhance ecological restoration functions, promote soil quality recovery, and solve the problems of poor restoration effects and long cycles in traditional technologies.

[0023] Example 2 This embodiment is an explanation of the embodiment 1. Specifically, S1 includes: S11. Use drone remote sensing and mapping equipment to obtain high-definition images of the transplanting area and calculate the total area, mark low-lying areas, highlands, and shaded areas, divide the transplanting area into several sub-areas, use GIS geographic information system to draw a regional network, and simultaneously number several sub-areas in the regional network as A1, A2, ..., An, where n is the number of sub-areas; obtain high-definition images through drone remote sensing technology, and efficiently divide and calculate the area of ​​the entire transplanting area. Compared with traditional manual measurement methods, drone remote sensing has higher work efficiency and accuracy, and can identify and mark different terrain features such as low-lying areas, highlands, and shaded areas, providing a scientific basis for the subsequent transplanting plan design. In addition, use GIS geographic information system to draw a regional network and assign a unique number to each sub-area, so that subsequent management and data collection are more orderly, easy to track and analyze.

[0024] S12. Set up a sampling point in each sub-area, arrange soil sensors, pH sensors, temperature sensors and microbial sensors with microfluidic chips, and collect soil microbial environmental data in real time. The soil microbial environmental data include: microbial species, microbial density, soil pH value sjd, soil temperature wd and microbial metabolite CO2 concentration htcd. Traditional methods often rely on manual sampling, and there are problems such as poor sampling timeliness and insufficient data accuracy. This step ensures the timeliness and accuracy of the data by collecting data in real time, providing a scientific microbial environment monitoring method for Juncao transplanting.

[0025] S13. Set a sampling point in each sub-area, arrange anemometers and wind pressure sensors, and set the arrangement heights of anemometers and wind pressure sensors to 1 meter, 2 meters, and 3 meters respectively. Collect wind speed and wind pressure data in real time. The sampling interval is set to record data every 10 minutes. The wind speed and wind pressure data include: wind speed v and wind pressure p; and combine the geographic coordinates of the sampling points to generate a spatiotemporal distribution map of wind speed and wind pressure in the sub-area. This process helps to grasp the changes in wind speed and wind pressure, and avoids data deviations caused by neglect or single sampling height in traditional methods. In addition, the impact of wind speed and wind pressure on the growth of Juncao cannot be ignored, and real-time monitoring helps to provide a basis for transplanting strategies that adapt to different environmental conditions.

[0026] S14. Set sampling points in each sub-area, install pressure sensors at depths of 5 cm, 10 cm and 20 cm from the ground surface, and collect mechanical stress data of the roots of the Juncao. The mechanical stress data of the roots of the Juncao include mechanical stress By setting pressure sensors at multiple depths to collect mechanical stress data of Juncao roots, the growth status of the roots in the soil and the adaptability of the roots to the external environment can be accurately reflected. These data help evaluate the growth of the roots and the contact between them and the soil, thus providing a scientific basis for the growth of Juncao during transplantation. Compared with traditional manual observation methods, this high-precision monitoring can promptly detect problems in root growth, reduce root damage, and improve the success rate of Juncao growth.

[0027] S15. Arrange a sampling point at intervals of 5-20 square meters in each sub-area, install a humidity sensor at a depth of 0-20 cm from the ground surface at each sampling point to collect soil moisture data, which includes soil moisture content M; by arranging humidity sensors and collecting soil moisture data at different depths, real-time monitoring of soil moisture content can be achieved. The moisture changes in different soil layers have an important impact on the transplanting and growth of Juncao, and this step can accurately reflect the distribution of soil moisture, facilitating timely adjustment of moisture management strategies. Traditional methods often lack accurate moisture monitoring and often rely on manual regular sampling, making it difficult to ensure the timeliness and integrity of moisture data.

[0028] S16. Arrange a sampling point every 5-20 square meters in each sub-area, and arrange a light intensity sensor one meter from the ground at each sampling point to collect spatial variation data of light conditions, which includes light intensity L; by arranging light intensity sensors, it is possible to monitor light changes in different spatial positions. Light is an important environmental factor affecting the growth of Juncao. Timely grasping of changes in light conditions can effectively guide the selection of transplanting timing and location. In addition, this step can obtain spatial distribution data of light conditions, help analyze light differences in different locations, and ensure that Juncao grows under optimal light conditions.

[0029] S17. Summarize the soil microbial environment data, wind speed and wind pressure data, mechanical stress data of Juncao roots, soil moisture data and spatial variation data of light conditions collected in S12-S16, and summarize and establish environmental biological data. By summarizing the data of multiple environmental factors (including soil microbial environment, wind speed and wind pressure, root mechanical stress, soil moisture and light conditions), a comprehensive environmental biological data set can be established. This data set can comprehensively reflect the environmental characteristics of the transplanting area and provide reliable basic data for subsequent analysis, evaluation and strategy formulation. Compared with the single data collection of traditional methods, this step provides a more sophisticated analysis framework for the transplanting effect through the integration of multiple environmental data, thereby optimizing the growth conditions and management measures of Juncao.

[0030] Example 3 This embodiment is an explanation of the embodiment 1. Specifically, S2 includes: S21, matching the environmental biological data of several transplanting sub-areas collected in S1 with the numbers of each sub-area one by one to form an original data set; S22. Check the original data set to see if there are any missing values, any abnormal values, and whether the timestamps and geographic coordinates of the original data table are complete; missing values ​​include Null or NaN data; S23. Setting a threshold range to determine whether there are abnormal values, including: The pH value sjd threshold range of soil is 4.5-9; The soil temperature wd threshold range is -10℃ to 50℃; The htcd threshold range of CO2 concentration of microbial metabolites is 0-500ppm; The wind speed v threshold range is 0-20m / s; The wind pressure p threshold range is 0-1.5 kPa; The soil moisture content M threshold range is 5%-50%; S24. Mark the data beyond the threshold range as outliers and remove them. Use the box plot analysis method to mark the original data set below the first quartile Q1×1.5 times IQR or above the third quartile Q3×1.5 times IQR as outliers. IQR means position, which means the middle 50% range of the original data set distribution. Q1 is the first quartile of the original data set, which is the value corresponding to the lower 25% position of the original data set after the original data set is centrally sorted. Q3 is the third quartile of the original data set, which is the value corresponding to the upper 25% position of the original data set after the original data set is centrally sorted. S25. After filling the missing values ​​between adjacent moments using linear interpolation or spline interpolation, the original data set is dimensionless and then imported into a transplant environment database in a unified format.

[0031] In this embodiment, step S2 ensures the accuracy and integrity of the data through rigorous data preprocessing, including data verification, outlier removal, missing value filling and data standardization. This provides reliable data support for subsequent transplant environment analysis and decision-making, while improving the efficiency of data management and the operability of the data set.

[0032] Example 4 This embodiment is an explanation of the embodiment 1. Specifically, S3 includes: S31, using a convolutional neural network to construct an initial model of the convolutional neural network, and using the transplanting environment database to train and test the initial model of the convolutional neural network, and using the trained initial model of the convolutional neural network as a transplanting environment prediction model, and using the intermediate layer output of the transplanting environment prediction model as a feature vector to identify feature information, and using the acquired feature information to train and test the transplanting environment prediction model, and using the trained transplanting environment prediction model as data to run prediction; By building a convolutional neural network and training the transplanting environment database, step S31 uses the neural network to learn the potential features in the data to establish a transplanting environment prediction model. This not only improves the prediction accuracy, but also captures the complex relationships in the environmental data, making the transplanting environment prediction more refined and targeted. In addition, using the output of the intermediate layer as a feature vector further optimizes the data extraction method, making the feature information more prominent, thereby improving the training effect of the subsequent model.

[0033] S32. Use the transplanting environment prediction model to extract and calculate the characteristics of the transplanting environment database to obtain the microbial environmental impact coefficient of the i-th sub-area , root mechanical stress coefficient , soil moisture uniformity coefficient , Wind environmental impact coefficient and the spatial coefficient of variation of illumination The quantitative calculation of each factor helps to understand the specific impact of different environmental factors on transplanting effects, and thus provides a basis for the formulation of optimization plans.

[0034] The S32 includes: S321, Microbial environmental impact coefficient of the ith sub-region Calculated by the following formula: ;in, is the density of the jth type of microorganism in the soil of the ith sub-region, is the adaptability score of the j-th microorganism in the soil of the ith sub-region to Juncao, obtained through experimental data. represents the number of microbial species in the soil of the ith sub-region, represents the pH value of the soil in the ith sub-region, represents the soil temperature of the ith sub-region, represents the CO2 concentration of microbial metabolites in the ith sub-region; , , and Represents the weight value; S322, root mechanical stress coefficient of the i-th sub-region Calculated by the following formula: ;in, and are the maximum test volume boundary and the minimum test volume boundary in the i-th sub-region, respectively. represents the soil mechanical stress in the ith sub-region, represents the test volume of the ith sub-region, dV represents a tiny volume unit, and represents the volume part accumulated during the integration process; S323, soil moisture uniformity coefficient of the i-th sub-region Calculated by the following formula: ;in, represents the average soil moisture content in the ith sub-region, represents the number of sampling points in the i-th sub-region, represents the soil moisture content at the kth sampling point in the ith sub-area; S324, wind environment impact coefficient of the ith sub-area Calculated by the following formula: ;in, Indicates that the kth sampling point in the i-th sub-region is at height The wind speed, The kth sampling point in the i-th sub-region is at height The wind pressure, and Indicates the weight value; represents the number of sampling points in the i-th sub-region; S325, spatial variation coefficient of illumination of the i-th sub-area Calculated by the following formula: ;in, Represents the light intensity of the kth sampling point in the i-th sub-area; represents the average light intensity of the ith sub-region, represents the number of sampling points in the i-th sub-area; S326, the microbial environmental impact coefficient of the i-th sub-region , root mechanical stress coefficient , soil moisture uniformity coefficient , Wind environmental impact coefficient and the spatial coefficient of variation of illumination After dimensionless processing, the comprehensive impact index of the Juncao transplanting environment in the i-th sub-region is obtained by the following correlation formula: ; ;in, , , , and Represent the microbial environmental impact coefficient of the i-th sub-region , root mechanical stress coefficient , soil moisture uniformity coefficient , Wind environmental impact coefficient and the spatial coefficient of variation of illumination The weight value of; and the weight value sum is 1, Represents the first correction constant.

[0035] In this embodiment, step S326 makes the environmental impact factors of each sub-region comparable by dimensionless processing of different influencing factors. This process ensures that parameters of different units or dimensions can compete fairly in the same evaluation system, avoiding the deviation caused by unit differences. Finally, the comprehensive impact index of the transplanting environment of Juncao calculated by the correlation formula provides a comprehensive and integrated score for the transplanting environment of different sub-regions, which is convenient for comparison and selection of the best solution.

[0036] By comprehensively considering multiple environmental factors (microorganisms, soil, water, wind, light, etc.) and their changes in different sub-areas, the S3 step can achieve a comprehensive assessment of the transplanting environment. The comprehensive impact index provides a quantitative comparison standard for transplanting effects under different environmental conditions, thereby helping to formulate scientific and reasonable transplanting strategies, optimize transplanting effects and increase success rates. S3 not only improves prediction accuracy, but also provides a strong decision-making basis for optimizing the transplanting environment, and promotes scientific and precise agricultural or environmental management.

[0037] Example 5 This embodiment is an explanation of the embodiment 1. Specifically, S4 includes: S41, preset the first risk threshold Y1, and set the comprehensive impact index of the Juncao transplanting environment in the i-th sub-region Compare and evaluate with the first risk threshold Y1 to obtain the environmental adaptability level, including: If the comprehensive impact index of the Juncao transplanting environment in the i-th sub-region > The first risk threshold Y1×150% indicates that the adaptability of the current sub-area is unqualified and unsuitable for Juncao transplanting. The sub-area is directly screened out and marked; If the first risk threshold Y1×120%≤the comprehensive impact index of the Juncao transplanting environment in the i-th sub-region ≤ the first risk threshold Y1×150%, indicating that the adaptability of the current sub-region is unqualified and obtains the first level; If the first risk threshold Y1≤the comprehensive impact index of the Juncao transplanting environment in the i-th sub-region < the first risk threshold Y1×120%, indicating that the adaptability of the current sub-region is unqualified and obtains the second level; If the comprehensive impact index of the Juncao transplanting environment in the i-th sub-region < the first risk threshold Y1, indicating that the current sub-region is suitable for adaptation and obtains the third level; S42. After obtaining the environmental adaptability level, a corresponding environmental optimization strategy is generated, including: The first environmental optimization strategy is generated according to the first level, including: the current sub-area needs to be fully optimized, 5 grams of nitrogen-fixing bacteria, phosphate-dissolving bacteria and microbial preparations are added per square meter, and the application is repeated twice a week; the sub-area is plowed to a depth of 11-20 cm, and 200 grams of organic fertilizer is applied per square meter; the soil is loosened evenly in each sub-area, and 1 kg of sawdust / square meter is added; the coverage rate of the sunshade net is increased by 30%-50%, and a sunshade net is installed in each sub-area to reduce the light intensity to the target value L=200 lumens; a windbreak wall is arranged around the sub-area or a 2-meter-high windbreak forest is planted; after the first environmental optimization strategy is executed, the grass is transplanted, and the first transplanting depth of the sub-area is set to 5 cm; The second environmental optimization strategy is generated according to the second level, including: the current sub-area needs to be partially optimized, 3 grams of nitrogen-fixing bacteria, phosphate-dissolving bacteria and microbial preparations are added per square meter, and the application is repeated once a week; the sub-area is plowed to a depth of 5-10 cm, and 100 grams of organic fertilizer is applied per square meter; the soil is loosened evenly in each sub-area, and 0.5 kg of sawdust / square meter is added; the coverage rate of the sunshade net is increased by 10%-15%, and a sunshade net is installed in each sub-area to reduce the light intensity to the target value L=300 lumens; a windbreak wall is arranged around the sub-area or a 1-meter-high windbreak forest is planted; after the second environmental optimization strategy is executed, the grass is transplanted, and the second transplanting depth of the sub-area is set to 6-7 cm; The third environmental optimization strategy is generated according to the third level, including: direct transplanting of Juncao, and setting the third transplanting depth of the sub-area to 8-9 cm.

[0038] In this embodiment, S41 performs a graded assessment by comparing the comprehensive impact index of the Juncao transplanting environment of the i-th sub-region with the preset risk threshold (Y1). This method can scientifically and objectively judge the environmental adaptability of each sub-region, and divide the sub-regions into different levels according to the index size, ensuring that only suitable areas are used for Juncao transplanting. This grading method can avoid waste of resources by screening out areas that are not suitable for transplanting. According to the sub-regions of different levels, S42 formulates a specific environmental optimization strategy for each level. The strategy for each level includes targeted adjustment measures to ensure that environmental conditions can be optimized in a timely manner to meet the growth needs of Juncao. Optimization measures of different intensities are implemented for each level of sub-region, avoiding a one-size-fits-all approach. The needs of each sub-region are accurately responded to, improving management efficiency. By applying different types of fertilizers, microbial preparations, wood chips, shade nets and other materials, and performing tillage operations, the required growth conditions are provided for Juncao, and the soil quality, light and water conditions are optimized. By increasing windbreak measures, adjusting light intensity and other environmental adjustments, Juncao is helped to adapt to changes in the external environment, thereby improving its survival rate and growth rate.

[0039] Example 6 This embodiment is an explanation of the embodiment 1. Specifically, S5 includes: S51. After the corresponding environmental optimization strategy is executed, the Juncao transplanting operation is performed, and during the growth of Juncao transplanting, the compatibility data of Juncao root secretions, the pest attraction effect data after transplanting and the soil density disturbance data are continuously collected to establish a growth data set; and the root secretion compatibility coefficient of the i-th sub-area is constructed based on the growth data set. , Pest attraction coefficient and soil disturbance influence coefficient , and associated with the root secretion compatibility coefficient of the i-th sub-region , Pest attraction coefficient and soil disturbance influence coefficient , get the growth risk coefficient of the i-th sub-region ; S511. Within the sampling point range of each sub-area, install a liquid collection device in the Juncao root distribution area, set the sampling depth to 10-20 cm, obtain root secretion liquid samples, set the collection frequency to once every 2 days, and keep collecting for 6-8 weeks. Perform experimental measurements on the root secretion liquid samples to obtain the organic acid concentration nd1, enzyme concentration nd2 and secretion pH value tj3, and establish compatibility data of Juncao root secretions; S512. Pest monitoring equipment is arranged at sampling points in each sub-area. The pest monitoring equipment includes insect monitoring lights and ground traps. The pest monitoring equipment is arranged at intervals of 10-20 square meters to collect flying pest density. and underground pest density , establish pest attraction effect data after transplanting; S513. Install soil density sensors at sampling points in each sub-area at a distance of 1-9 cm from the surface layer and 10-20 cm from the sub-surface layer to collect soil density disturbance data. The soil density disturbance data includes soil density before transplanting. and soil density after transplanting ; S514, root secretion compatibility coefficient of the i-th sub-region Calculated by the following formula: ;in, represents the organic acid concentration in the ith sub-region, represents the enzyme concentration in the ith sub-region, represents the secretion pH value tj3 of the i-th sub-region; Pest attraction coefficient of the i-th sub-region Calculated by the following formula: ;in, represents the density of flying pests in the ith sub-area, represents the underground pest density in the ith sub-area ; represents the area of ​​the i-th sub-region; Soil disturbance influence coefficient of the i-th sub-area Calculated by the following formula: ;in, represents the soil density before transplanting in the i-th sub-area , represents the soil density after transplanting in the ith sub-area; S515, the root secretion compatibility coefficient of the i-th sub-region , Pest attraction coefficient and soil disturbance influence coefficient After dimensionless processing, the growth risk coefficient of the ith sub-region is obtained through the following correlation formula: : ;in, , and are the root secretion compatibility coefficients of the i-th sub-region , Pest attraction coefficient and soil disturbance influence coefficient The weight value of; and the weight value sum is 1, Represents the second correction constant.

[0040] In this embodiment, the present invention can realize accurate monitoring and optimization of the growth process of Juncao transplanting by collecting and analyzing relevant data of root secretions, pest attraction effects and soil disturbance during the process of Juncao transplanting. By monitoring the compatibility data of root secretions and the impact of soil disturbance, it is possible to provide a quantitative basis for improving soil quality, provide guidance for the implementation of subsequent soil improvement measures, and promote soil health and ecological restoration. Combined with the analysis results of the pest attraction coefficient, it is possible to provide accurate data support for the formulation of pest control strategies, reduce the threat of pests to transplanted Juncao, thereby reducing management costs and improving crop growth effects. Through a comprehensive evaluation of the environmental factors of each sub-region, the present invention can provide a personalized optimization plan for transplanting operations, effectively improving the survival rate and growth rate of Juncao.

[0041] Example 7 This embodiment is an explanation of the embodiment 6. Specifically, S5 also includes: S52, presetting a second risk threshold Y2, and setting the growth risk coefficient of the i-th sub-region Compare with the second risk threshold Y2 to obtain the growth risk assessment results, including: If the growth risk coefficient of the i-th sub-region > The second risk threshold Y2 indicates that the growth environment of the sub-area is at risk, and the fourth environmental optimization strategy is generated, including: adding 1-2 kg of sandy soil per square meter to improve aeration; applying 2 grams of microbial agents per square meter, repeating once a week, and applying three times in a row; arranging 1-2 trapping lights in each sub-area, spraying biological pesticides once a week for 2-3 consecutive weeks; If the growth risk coefficient of the i-th sub-region ≤ the second risk threshold Y2, indicating that there is no risk in the growth environment of the sub-region and continuous monitoring is required.

[0042] In this embodiment, when the growth risk coefficient exceeds the second risk threshold value Y2, the soil aeration is improved by adding sandy soil, the soil permeability and the root growth environment are improved, which helps to enhance the development of the root system of Juncao and improve its growth potential. The application of microbial agents can accelerate the reproduction of beneficial microorganisms in the soil, improve the biological characteristics of the soil, promote the decomposition of organic matter and the circulation of nutrients, and effectively enhance the health and sustainability of the soil. By setting trapping lights and spraying biological pesticides, the threat of pests to Juncao can be effectively reduced, the negative impact of pesticides on the environment can be avoided, and the sustainable development of agricultural ecology can be guaranteed. When the growth risk coefficient is lower than the second risk threshold value Y2, the present invention can continuously monitor and evaluate environmental changes, adjust management strategies in time, ensure that the ecological environment of the sub-region is always maintained in a state suitable for the growth of Juncao, and improve the accuracy and operability of management. The present invention promotes ecological restoration in the agricultural production process by comprehensively evaluating environmental factors, flexibly adjusting strategies, effectively combining agricultural production and environmental protection, and meeting the needs of sustainable agricultural development.

[0043] Example 8 Please refer to Figure 2 , the intelligent Juncao transplanting system based on Internet of Things technology includes: The segmentation unit is used to divide the transplanting area into several sub-areas, draw a regional network using the GIS geographic information system, and simultaneously number several sub-areas in the regional network as A1, A2, ..., A n , n is the number of sub-regions; The first IoT collection unit is used to collect environmental biological data in the sub-area using distributed IoT sensing devices, wherein the environmental biological data includes soil microbial environment data, wind speed and wind pressure data, mechanical stress data of the grass root system, soil moisture data, and spatial variation data of light conditions; Establish a model unit to establish a transplanting environment prediction model using convolutional neural network technology. After training, extract and calculate the features of the transplanting environment database to obtain the microbial environmental impact coefficient of the i-th sub-area. , root mechanical stress coefficient , soil moisture uniformity coefficient , Wind environmental impact coefficient and the spatial coefficient of variation of illumination ; and associate to obtain the comprehensive impact index of the Juncao transplanting environment in the i-th sub-region ; The first evaluation unit is used to preset the first risk threshold Y1 and calculate the comprehensive impact index of the Juncao transplanting environment in the i-th sub-area. Compare and evaluate with the first risk threshold Y1 to obtain the environmental adaptability level, and generate the corresponding environmental optimization strategy according to the corresponding level; The second IoT monitoring unit is used to perform the Juncao transplanting operation after the corresponding environmental optimization strategy is executed, and continuously collect the compatibility data of Juncao root secretions and the pest attraction effect data after transplanting during the growth of Juncao transplanting, and establish a growth data set; The second evaluation unit is used to construct the growth risk coefficient of the i-th sub-region based on the growth data set. , and preset the second risk threshold Y2, and set the growth risk coefficient of the i-th sub-region The value is compared with the second risk threshold Y2 to obtain a growth risk assessment result.

[0044] In this embodiment, through the first Internet of Things acquisition unit, key environmental data such as soil microbial environment, wind speed and pressure, mechanical stress, soil moisture and light conditions are collected in real time, and a transplanting environment prediction model is established using convolutional neural network technology. In this way, the environmental impact of each sub-area can be accurately evaluated and potential risk factors can be discovered in a timely manner. The system compares the comprehensive environmental impact index with the preset risk threshold Y1 to formulate a personalized environmental optimization strategy for each sub-area to ensure that Juncao can grow under the most suitable environmental conditions. This can not only improve the success rate of transplanting, but also optimize resource allocation. During the growth of Juncao transplanting, the second Internet of Things monitoring unit continuously collects root secretion compatibility data and pest attraction effect data, establishes a dynamic growth data set, and monitors the growth risk coefficient in real time. This process can promptly discover adverse trends in growth and ensure that countermeasures are taken when problems first appear. Through the second evaluation unit, the growth risk coefficient is compared with the second risk threshold Y2. The system can adjust the environmental optimization strategy based on the real-time risk assessment results to ensure the healthy growth of Juncao throughout the growth cycle and reduce unnecessary waste of resources.

[0045] The threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technicians in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0046] The above formulas are obtained by collecting a large amount of data for software simulation and selecting a formula that is close to the actual value. The coefficients in the formula are set by technical personnel in this field according to actual conditions. The above is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited to this. Any technical personnel familiar with the technical field within the technical scope disclosed by the present invention, according to the technical solution and the inventive concept of the present invention, make equivalent replacement or change, which should be covered within the protection scope of the present invention.

Claims

1. An intelligent Juncao transplanting method based on Internet of Things technology, characterized in that: The following steps are involved: S1. Divide the transplanting area into several sub-areas, and use distributed Internet of Things sensing devices to collect environmental biological data in the sub-areas, wherein the environmental biological data include: soil microbial environment data, wind speed and wind pressure data, mechanical stress data of the roots of the grass, soil moisture data, and spatial variation data of light conditions; S2. Preprocess the collected environmental biological data, remove outliers and fill in missing values; standardize the environmental biological data using dimensionless technology to build a transplant environment database in a unified format; S3. Use convolutional neural network technology to establish a transplanting environment prediction model. After training, extract and calculate the features of the transplanting environment database to obtain the microbial environmental impact coefficient of the i-th sub-area. , root mechanical stress coefficient , soil moisture uniformity coefficient , Wind environmental impact coefficient and the spatial coefficient of variation of illumination ; and associate to obtain the comprehensive impact index of the Juncao transplanting environment in the i-th sub-region ; S4, preset the first risk threshold Y1, and set the comprehensive impact index of the Juncao transplanting environment in the i-th sub-area Compare and evaluate with the first risk threshold Y1 to obtain the environmental adaptability level, and generate the corresponding environmental optimization strategy according to the corresponding level; S5. After the corresponding environmental optimization strategy is executed, the Juncao transplanting operation is performed, and the compatibility data of the Juncao root secretions and the pest attraction effect data after transplanting are continuously collected during the growth of the Juncao transplanting, and a growth data set is established. Based on the growth data set, the growth risk coefficient of the i-th sub-area is constructed. , and preset the second risk threshold Y2, and set the growth risk coefficient of the i-th sub-region The value is compared with the second risk threshold Y2 to obtain a growth risk assessment result.

2. The intelligent Juncao transplanting method based on Internet of Things technology according to claim 1 is characterized in that: S1 includes: S11. Use UAV remote sensing mapping equipment to obtain high-definition images of the transplanting area and calculate the total area, mark low-lying areas, highlands, and shaded areas, divide the transplanting area into several sub-areas, use GIS geographic information system to draw a regional network, and simultaneously number several sub-areas in the regional network as A1, A2, ..., A n , n is the number of sub-regions; S12. Set a sampling point in each sub-area, arrange soil sensors, pH sensors, temperature sensors and microbial sensors with microfluidic chips, and collect soil microbial environmental data in real time. The soil microbial environmental data include: microbial species, microbial density, soil pH value sjd, soil temperature wd and microbial metabolite CO2 concentration htcd; S13. Set a sampling point in each sub-area, arrange anemometers and wind pressure sensors, and set the arrangement heights of anemometers and wind pressure sensors to 1 meter, 2 meters and 3 meters respectively. Collect wind speed and wind pressure data in real time. The sampling interval is set to record data every 10 minutes. The wind speed and wind pressure data include: wind speed v and wind pressure p. Combined with the geographic coordinates of the sampling points, generate a spatiotemporal distribution map of wind speed and pressure in the sub-area.

3. The intelligent Juncao transplanting method based on Internet of Things technology according to claim 2 is characterized in that: S1 also includes: S14. Set sampling points in each sub-area, install pressure sensors at depths of 5 cm, 10 cm and 20 cm from the ground surface, and collect mechanical stress data of the roots of the Juncao. The mechanical stress data of the roots of the Juncao include mechanical stress ; S15, a sampling point is arranged at an interval of 5-20 square meters in each sub-area, and a humidity sensor is installed at a depth of 0-20 cm from the ground surface at each sampling point to collect soil moisture data, the soil moisture data including soil moisture content M; S16. Arrange a sampling point at an interval of 5-20 square meters in each sub-area, and arrange a light intensity sensor at a distance of one meter from the ground at each sampling point to collect spatial variation data of light conditions, where the spatial variation data of light conditions includes light intensity L; S17. Summarize the soil microbial environment data, wind speed and pressure data, mechanical stress data of the grass root system, soil moisture data and spatial variation data of light conditions collected in S12-S16, and summarize and establish environmental biological data.

4. The intelligent Juncao transplanting method based on Internet of Things technology according to claim 1 is characterized in that S2 include: S21, matching the environmental biological data of several transplanting sub-areas collected in S1 with the numbers of each sub-area one by one to form an original data set; S22. Check the original data set to see if there are any missing values, check if there are any abnormal values, and check if the timestamps and geographic coordinates of the original data table are complete; S23. Setting a threshold range to determine whether there are abnormal values, including: The pH value sjd threshold range of soil is 4.5-9; The soil temperature wd threshold range is -10℃ to 50℃; The htcd threshold range of CO2 concentration of microbial metabolites is 0-500ppm; The wind speed v threshold range is 0-20m / s; The wind pressure p threshold range is 0-1.5 kPa; The soil moisture content M threshold range is 5%-50%; S24. Mark the data beyond the threshold range as outliers and remove them. Use the box plot analysis method to mark the original data set below the first quartile Q1×1.5 times IQR or above the third quartile Q3×1.5 times IQR as outliers. IQR means position, which means the middle 50% range of the original data set distribution. Q1 is the first quartile of the original data set, which is the value corresponding to the lower 25% position of the original data set after the original data set is centrally sorted. Q3 is the third quartile of the original data set, which is the value corresponding to the upper 25% position of the original data set after the original data set is centrally sorted. S25. After filling the missing values ​​between adjacent moments using linear interpolation or spline interpolation, the original data set is dimensionless and then imported into a transplant environment database in a unified format.

5. The intelligent Juncao transplanting method based on Internet of Things technology according to claim 1 is characterized in that S3 include: S31, using a convolutional neural network to construct an initial model of the convolutional neural network, and using the transplanting environment database to train and test the initial model of the convolutional neural network, and using the trained initial model of the convolutional neural network as a transplanting environment prediction model, and using the intermediate layer output of the transplanting environment prediction model as a feature vector to identify feature information, and using the acquired feature information to train and test the transplanting environment prediction model, and using the trained transplanting environment prediction model as data to run prediction; S32. Use the transplanting environment prediction model to extract and calculate the characteristics of the transplanting environment database to obtain the microbial environmental impact coefficient of the i-th sub-area , root mechanical stress coefficient , soil moisture uniformity coefficient , Wind environmental impact coefficient and the spatial coefficient of variation of illumination .

6. The intelligent Juncao transplanting method based on Internet of Things technology according to claim 5 is characterized in that: The S32 includes: S321, Microbial environmental impact coefficient of the ith sub-region Calculated by the following formula: ;in, is the density of the jth type of microorganism in the soil of the ith sub-region, is the adaptability score of the j-th microorganism in the soil of the ith sub-region to Juncao, obtained through experimental data. represents the number of microbial species in the soil of the ith sub-region, represents the pH value of the soil in the ith sub-region, represents the soil temperature of the ith sub-region, represents the CO2 concentration of microbial metabolites in the ith sub-region; , , and Represents the weight value; S322, root mechanical stress coefficient of the i-th sub-region Calculated by the following formula: ;in, and are the maximum test volume boundary and the minimum test volume boundary in the i-th sub-region, respectively. represents the soil mechanical stress in the ith sub-region, represents the test volume of the ith sub-region, dV represents a tiny volume unit, and represents the volume part accumulated during the integration process; S323, soil moisture uniformity coefficient of the i-th sub-region Calculated by the following formula: ;in, represents the average soil moisture content in the ith sub-region, represents the number of sampling points in the i-th sub-region, represents the soil moisture content at the kth sampling point in the ith sub-area; S324, wind environment impact coefficient of the ith sub-area Calculated by the following formula: ;in, Indicates that the kth sampling point in the i-th sub-region is at height The wind speed, The kth sampling point in the i-th sub-region is at height The wind pressure, and Represents the weight value; represents the number of sampling points in the i-th sub-region; S325, spatial variation coefficient of illumination of the i-th sub-area Calculated by the following formula: ;in, Represents the light intensity of the kth sampling point in the i-th sub-area; represents the average light intensity of the ith sub-region, represents the number of sampling points in the i-th sub-area; S326, the microbial environmental impact coefficient of the i-th sub-region , root mechanical stress coefficient , soil moisture uniformity coefficient , Wind environmental impact coefficient and the spatial coefficient of variation of illumination After dimensionless processing, the comprehensive impact index of the Juncao transplanting environment in the i-th sub-region is obtained by the following correlation formula: ; ;in, , , , and Represent the microbial environmental impact coefficient of the i-th sub-region , root mechanical stress coefficient , soil moisture uniformity coefficient , Wind environmental impact coefficient and the spatial coefficient of variation of illumination The weight value of Represents the first correction constant.

7. The intelligent Juncao transplanting method based on Internet of Things technology according to claim 1 is characterized in that S4 include: S41, preset the first risk threshold Y1, and set the comprehensive impact index of the Juncao transplanting environment in the i-th sub-region Compare and evaluate with the first risk threshold Y1 to obtain the environmental adaptability level, including: If the comprehensive impact index of the Juncao transplanting environment in the i-th sub-region > The first risk threshold Y1×150% indicates that the adaptability of the current sub-area is unqualified and unsuitable for Juncao transplanting. The sub-area is directly screened out and marked; If the first risk threshold Y1×120%≤the comprehensive impact index of the Juncao transplanting environment in the i-th sub-region ≤ the first risk threshold Y1×150%, indicating that the adaptability of the current sub-region is unqualified and obtains the first level; If the first risk threshold Y1≤the comprehensive impact index of the Juncao transplanting environment in the i-th sub-region < the first risk threshold Y1×120%, indicating that the adaptability of the current sub-region is unqualified and obtains the second level; If the comprehensive impact index of the Juncao transplanting environment in the i-th sub-region < the first risk threshold Y1, indicating that the current sub-region is qualified for adaptability and obtains the third level; S42. After obtaining the environmental adaptability level, a corresponding environmental optimization strategy is generated, including: The first environmental optimization strategy is generated according to the first level, including: the current sub-area needs to be fully optimized, 5 grams of nitrogen-fixing bacteria, phosphate-dissolving bacteria and microbial preparations are added per square meter, and the application is repeated twice a week; the sub-area is plowed to a depth of 11-20 cm, and 200 grams of organic fertilizer is applied per square meter; the soil is loosened evenly in each sub-area, and 1 kg of sawdust / square meter is added; the coverage rate of the sunshade net is increased by 30%-50%, and a sunshade net is installed in each sub-area to reduce the light intensity to the target value L=200 lumens; a windbreak wall is arranged around the sub-area or a 2-meter-high windbreak forest is planted; after the first environmental optimization strategy is executed, the grass is transplanted, and the first transplanting depth of the sub-area is set to 5 cm; The second environmental optimization strategy is generated according to the second level, including: the current sub-area needs to be partially optimized, 3 grams of nitrogen-fixing bacteria, phosphate-dissolving bacteria and microbial preparations are added per square meter, and the application is repeated once a week; the sub-area is plowed to a depth of 5-10 cm, and 100 grams of organic fertilizer is applied per square meter; the soil is loosened evenly in each sub-area, and 0.5 kg of sawdust / square meter is added; the coverage rate of the sunshade net is increased by 10%-15%, and a sunshade net is installed in each sub-area to reduce the light intensity to the target value L=300 lumens; a windbreak wall is arranged around the sub-area or a 1-meter-high windbreak forest is planted; after the second environmental optimization strategy is executed, the grass is transplanted, and the second transplanting depth of the sub-area is set to 6-7 cm; The third environmental optimization strategy is generated according to the third level, including: direct transplanting of Juncao, and setting the third transplanting depth of the sub-area to 8-9 cm.

8. The intelligent Juncao transplanting method based on Internet of Things technology according to claim 1 is characterized in that S5 include: S51. After the corresponding environmental optimization strategy is executed, the Juncao transplanting operation is performed, and during the growth of Juncao transplanting, the compatibility data of Juncao root secretions, the pest attraction effect data after transplanting and the soil density disturbance data are continuously collected to establish a growth data set; and the root secretion compatibility coefficient of the i-th sub-area is constructed based on the growth data set. , Pest attraction coefficient and soil disturbance influence coefficient , and associated with the root secretion compatibility coefficient of the i-th sub-region , Pest attraction coefficient and soil disturbance influence coefficient , get the growth risk coefficient of the i-th sub-region ; S511. Within the sampling point range of each sub-area, install a liquid collection device in the Juncao root distribution area, set the sampling depth to 10-20 cm, obtain root secretion liquid samples, set the collection frequency to once every 2 days, and keep collecting for 6-8 weeks. Perform experimental measurements on the root secretion liquid samples to obtain the organic acid concentration nd1, enzyme concentration nd2 and secretion pH value tj3, and establish compatibility data of Juncao root secretions; S512. Pest monitoring equipment is arranged at sampling points in each sub-area. The pest monitoring equipment includes insect monitoring lights and ground traps. The pest monitoring equipment is arranged at intervals of 10-20 square meters to collect flying pest density. and underground pest density , establish pest attraction effect data after transplanting; S513. Install soil density sensors at sampling points in each sub-area at a distance of 1-9 cm from the surface layer and 10-20 cm from the sub-surface layer to collect soil density disturbance data. The soil density disturbance data includes soil density before transplanting. and soil density after transplanting ; S514, root secretion compatibility coefficient of the i-th sub-region Calculated by the following formula: ;in, represents the organic acid concentration in the ith sub-region, represents the enzyme concentration in the ith sub-region, represents the secretion pH value tj3 of the i-th sub-region; Pest attraction coefficient of the i-th sub-region Calculated by the following formula: ;in, represents the density of flying pests in the ith sub-area, represents the underground pest density in the ith sub-area ; represents the area of ​​the i-th sub-region; Soil disturbance influence coefficient of the i-th sub-area Calculated by the following formula: ;in, represents the soil density before transplanting in the i-th sub-area , represents the soil density after transplanting in the ith sub-area; S515, the root secretion compatibility coefficient of the i-th sub-region , Pest attraction coefficient and soil disturbance influence coefficient After dimensionless processing, the growth risk coefficient of the ith sub-region is obtained through the following correlation formula: : ;in, , and are the root secretion compatibility coefficients of the i-th sub-region , Pest attraction coefficient and soil disturbance influence coefficient The weight value of Represents the second correction constant.

9. The intelligent Juncao transplanting method based on Internet of Things technology according to claim 8 is characterized in that: S5 also includes: S52, presetting a second risk threshold Y2, and setting the growth risk coefficient of the i-th sub-region Compare with the second risk threshold Y2 to obtain the growth risk assessment results, including: If the growth risk coefficient of the i-th sub-region > The second risk threshold Y2 indicates that the growth environment of the sub-area is at risk, and the fourth environmental optimization strategy is generated, including: adding 1-2 kg of sandy soil per square meter to improve aeration; applying 2 grams of microbial agents per square meter, repeating once a week, and applying three times in a row; arranging 1-2 trapping lights in each sub-area, spraying biological pesticides once a week for 2-3 consecutive weeks; If the growth risk coefficient of the i-th sub-region ≤ the second risk threshold Y2, indicating that there is no risk in the growth environment of the sub-region and continuous monitoring is required.

10. An intelligent Juncao transplanting system based on Internet of Things technology, applied to the intelligent Juncao transplanting method based on Internet of Things technology described in any one of claims 1 to 9, characterized in that: include: The segmentation unit is used to divide the transplanting area into several sub-areas, draw a regional network using the GIS geographic information system, and simultaneously number several sub-areas in the regional network as A1, A2, ..., A n , n is the number of sub-regions; The first IoT collection unit is used to collect environmental biological data in the sub-area using distributed IoT sensing devices, wherein the environmental biological data includes soil microbial environment data, wind speed and wind pressure data, mechanical stress data of the grass root system, soil moisture data, and spatial variation data of light conditions; Establish a model unit to establish a transplanting environment prediction model using convolutional neural network technology. After training, extract and calculate the features of the transplanting environment database to obtain the microbial environmental impact coefficient of the i-th sub-area. , root mechanical stress coefficient , soil moisture uniformity coefficient , Wind environmental impact coefficient and the spatial coefficient of variation of illumination ; and associate to obtain the comprehensive impact index of the Juncao transplanting environment in the i-th sub-region ; The first evaluation unit is used to preset the first risk threshold Y1 and calculate the comprehensive impact index of the Juncao transplanting environment in the i-th sub-area. Compare and evaluate with the first risk threshold Y1 to obtain the environmental adaptability level, and generate the corresponding environmental optimization strategy according to the corresponding level; The second IoT monitoring unit is used to perform the Juncao transplanting operation after the corresponding environmental optimization strategy is executed, and continuously collect the compatibility data of Juncao root secretions and the pest attraction effect data after transplanting during the growth of Juncao transplanting, and establish a growth data set; The second evaluation unit is used to construct the growth risk coefficient of the i-th sub-region based on the growth data set. , and preset the second risk threshold Y2, and set the growth risk coefficient of the i-th sub-region The value is compared with the second risk threshold Y2 to obtain a growth risk assessment result.

Images