A smart agricultural control system and method based on big data

Abstract

The present application provides a smart agricultural control system and method based on big data. The present application first performs stress response feature learning on the crop texture features and environmental humidity features corresponding to each crop distribution area to obtain a static shading stress response array; then, based on each static shading stress response value in the static shading stress response array and the corresponding crop distribution area, controls the driving trajectory of an agricultural plant protection vehicle during low-position spraying on a drivable path; finally, collects environmental parameters of the current crop distribution area to determine a dynamic shading stress response value, and corrects the spraying direction of the agricultural plant protection vehicle according to the dynamic shading stress response value and the static shading stress response value of the current crop distribution area. The present application can control the driving trajectory of the agricultural plant protection vehicle according to the different degrees of shading stress in different crop distribution areas, thereby performing targeted spraying, thereby improving the efficiency of the agricultural plant protection vehicle in spraying plant growth regulators.

Description

Technical Field

[0001] The present application relates to the technical field of agricultural vehicle trajectory control, and in particular to a smart agricultural control system and method based on big data. Background Art

[0002] Agricultural intercropping (also known as intercropping) is a method of planting two or more crops in the same space, making full use of the complementary relationship between crops. By combining different types of crops together, a multi-level, multifunctional composite planting system is formed. Compared with monocropping, the main advantage of intercropping is that it can more efficiently utilize resources such as light, heat, water, and fertilizer, thereby increasing the total yield per unit area. It can play an important role both in high-input intensive agricultural systems and in low-input or resource-limited agricultural systems.

[0003] In the intercropping mode, the combination of high-position crops and low-position crops forms a unique three-dimensional canopy structure, which changes the distribution of light in the group. The shading stress of high-position crops on low-position crops puts the low-position crops at a disadvantage in light energy, reduces the interception of limited light energy by low-position crops, restricts the growth and development of low-position crops, affects the establishment of a reasonable canopy structure, reduces the photosynthetic characteristics of the group, and ultimately leads to a decrease in yield. The existing technology mainly uses agricultural plant protection vehicles to spray plant growth regulators according to a preset trajectory to reduce the adverse effects of shading stress on high-position crops. However, this method does not carry out targeted spraying on crop distribution areas with different degrees of shading stress, resulting in very low efficiency of agricultural plant protection vehicles when spraying plant growth regulators. Summary of the invention

[0004] The present application provides a smart agricultural control system and method based on big data, which can control agricultural plant protection vehicles to perform targeted spraying according to the different degrees of shading stress in different crop distribution areas, thereby improving the efficiency of agricultural plant protection vehicles in spraying plant growth regulators.

[0005] On the first aspect, the present application provides a smart agriculture control method based on big data, which can be executed by a network device, or by a chip configured in the network device, and the present application does not limit this.

[0006] Specifically, the method includes:

[0007] Obtain a crop distribution scatter plot through the agricultural big data center, collect light from the crop distribution center based on the crop distribution scatter plot, and obtain the center light intensity;

[0008] Collecting features according to each crop distribution area in the crop distribution scatter plot to obtain crop texture features and environmental humidity features corresponding to each crop distribution area;

[0009] Using the central light intensity, stress response feature learning is performed on the crop texture features and environmental humidity features corresponding to each crop distribution area to obtain a static shading stress response array;

[0010] Acquire a drivable path of the agricultural plant protection vehicle, and control the driving trajectory of the agricultural plant protection vehicle when performing low-position spraying on the drivable path based on each static shading stress response value in the static shading stress response array and the corresponding crop distribution area;

[0011] During the spraying of the regulator, the environmental parameters of the current crop distribution area are collected to determine the dynamic shading stress response value, and the spraying direction of the agricultural plant protection vehicle is corrected according to the dynamic shading stress response value and the static shading stress response value of the current crop distribution area.

[0012] In combination with the first aspect, in certain implementations of the first aspect, performing feature collection according to each crop distribution area in the crop distribution scatter plot to obtain crop texture features and environmental humidity features corresponding to each crop distribution area specifically includes:

[0013] Acquire the crop distribution scatter plot, and perform region segmentation based on the distribution density in the crop distribution scatter plot to obtain a plurality of crop distribution regions;

[0014] Acquire the illumination direction, select an initial distribution area according to the illumination direction to collect crop texture features, select the next crop distribution area based on the illumination direction to collect crop texture features, until the crop texture features corresponding to each crop distribution area are determined;

[0015] Obtain a spatial wind direction vector, reselect an initial distribution area based on the spatial wind direction vector to collect environmental humidity characteristics, and select the next crop distribution area based on the spatial wind direction vector to collect environmental humidity characteristics until the environmental humidity characteristics corresponding to each crop distribution area are determined.

[0016] In combination with the first aspect, in certain implementations of the first aspect, before collecting features according to each crop distribution area in the crop distribution scatter plot, it also includes: obtaining the light direction and wind direction vector at the current moment through the big data center of the agricultural control system.

[0017] In combination with the first aspect, in certain implementations of the first aspect, stress response feature learning is performed on crop texture features and environmental humidity features corresponding to each crop distribution area respectively by the central light intensity to obtain a static shading stress response array, specifically including:

[0018] Determining the depth of the contrast area according to the central illumination intensity;

[0019] Acquire crop texture features and environmental humidity features corresponding to the first crop distribution area, select a comparison distribution area for stress response feature learning according to the position coordinates of the first crop distribution area and the depth of the comparison area, and obtain a static shading stress response value corresponding to the first crop distribution area;

[0020] After obtaining the crop texture features and environmental humidity features corresponding to other crop distribution areas, the static shading stress response values ​​corresponding to each crop distribution area are determined in the same manner, and the array is filled according to the crop distribution scatter plot to obtain the static shading stress response array.

[0021] In combination with the first aspect, in certain implementations of the first aspect, based on each static shading stress response value in the static shading stress response array and the corresponding crop distribution area, controlling the driving trajectory of the agricultural plant protection vehicle when performing low-position spraying on the drivable path specifically includes:

[0022] Acquire each static shading stress response value in the static shading stress response array and the corresponding crop distribution area;

[0023] Obtain all drivable path segments of the agricultural plant protection vehicle; obtain each drivable path segment and the adjacent crop distribution area corresponding to the drivable path segment;

[0024] The starting point of the driving trajectory of the agricultural plant protection vehicle is obtained, and the static shading stress response values ​​of all adjacent crop distribution areas corresponding to the drivable path segment are accumulated as the pheromone concentration corresponding to the drivable path segment. The ant colony algorithm is used to determine the driving trajectory of the agricultural plant protection vehicle when it performs low-position spraying of the regulator starting from the starting point of the driving trajectory.

[0025] In combination with the first aspect, in certain implementations of the first aspect, correcting the spraying direction of the agricultural plant protection vehicle according to the dynamic shading stress response value and the static shading stress response value of the current crop distribution area specifically includes:

[0026] Obtaining the response difference between the dynamic shading stress response value and the static shading stress response value of the current crop distribution area;

[0027] When the response difference is higher than a preset threshold, a correction depth is determined according to the illumination parameters of the current crop distribution area, and a dynamic shading stress response value and a static shading stress response value of the adjacent crop distribution area are obtained based on the correction depth;

[0028] The spraying direction of the agricultural plant protection vehicle is corrected according to the dynamic shading stress response value and the static shading stress response value of the adjacent crop distribution area.

[0029] In combination with the first aspect, in certain implementations of the first aspect, a light sensor is used to collect light at the crop distribution center to obtain the central light intensity.

[0030] In a second aspect, the present application provides a smart agricultural control system based on big data, including an agricultural control unit, characterized in that the agricultural control unit includes:

[0031] A data collection module is used to obtain a crop distribution scatter plot through an agricultural big data center, collect light from the crop distribution center based on the crop distribution scatter plot, and obtain the center light intensity;

[0032] The data collection module is further used to collect features according to each crop distribution area in the crop distribution scatter plot, so as to obtain crop texture features and environmental humidity features corresponding to each crop distribution area;

[0033] A data processing module, used for learning stress response characteristics of crop texture characteristics and environmental humidity characteristics corresponding to each crop distribution area based on the central light intensity, and obtaining a static shading stress response array;

[0034] An agricultural plant protection vehicle control module, used to obtain a drivable path of the agricultural plant protection vehicle, and control the driving trajectory of the agricultural plant protection vehicle when performing low-position spraying on the drivable path based on each static shading stress response value in the static shading stress response array and the corresponding crop distribution area;

[0035] The agricultural plant protection vehicle control module is also used to collect environmental parameters of the current crop distribution area to determine the dynamic shading stress response value during the regulator spraying process, and correct the spraying direction of the agricultural plant protection vehicle according to the dynamic shading stress response value and static shading stress response value of the current crop distribution area.

[0036] In a third aspect, the present application provides a computer terminal device, comprising a memory and a processor, wherein the memory stores a code, and the processor is configured to obtain the code and execute the above-mentioned smart agriculture control method based on big data.

[0037] In a fourth aspect, the present application provides a computer-readable storage medium, which stores at least one computer program, and the computer program is loaded and executed by a processor to implement the operations performed by the above-mentioned big data-based smart agriculture control method.

[0038] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects:

[0039] In a smart agriculture control system and method based on big data provided by the present application, a crop distribution scatter plot is first obtained through an agricultural big data center, and light collection is performed on the crop distribution center based on the crop distribution scatter plot to obtain the central light intensity; feature collection is performed according to each crop distribution area in the crop distribution scatter plot to obtain the crop texture features and environmental humidity features corresponding to each crop distribution area; stress response feature learning is performed on the crop texture features and environmental humidity features corresponding to each crop distribution area based on the central light intensity to obtain a static shading stress response array; a drivable path of an agricultural plant protection vehicle is obtained, and based on each static shading stress response value in the static shading stress response array and the corresponding crop distribution areas, the driving trajectory of the agricultural plant protection vehicle during low-position spraying on the drivable path is controlled; during the spraying of the regulator, the environmental parameters of the current crop distribution area are collected to determine the dynamic shading stress response value, and the spraying direction of the agricultural plant protection vehicle is corrected according to the dynamic shading stress response value and the static shading stress response value of the current crop distribution area.

[0040] It can be seen that the present application accurately reflects the growth environment of each area through the acquisition of light collection and crop texture characteristics and environmental humidity characteristics, helps to judge the health status of crops under shading conditions, and establishes a static shading stress response array by learning the relationship between the central light intensity and the characteristics of each area, so that the stress degree of different areas can be quantified and visualized. Combined with the static shading stress response value and the crop distribution area, the agricultural plant protection vehicle can optimize the driving trajectory on the drivable path, ensure path planning under different shading stress conditions to achieve targeted spraying, and continuously collect environmental parameters of the current crop distribution area during the spraying process to determine the dynamic shading stress response value, so that the agricultural plant protection vehicle can form a closed-loop feedback according to the real-time dynamic and static shading stress response values, flexibly adjust the spraying direction, improve the accuracy and efficiency of spraying, enhance the system's adaptability, and ultimately enable the plant protection vehicle to select the most effective spraying trajectory, significantly improving the application efficiency of plant growth regulators and the accuracy of crop management.

[0041] In summary, the present application can control the driving trajectory of the agricultural plant protection vehicle according to the different degrees of shading stress in different crop distribution areas so as to carry out targeted spraying, thereby improving the efficiency of the agricultural plant protection vehicle in spraying plant growth regulators. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 is an exemplary flow chart of a smart agriculture control method based on big data according to some embodiments of the present application;

[0043] Figure 2 is an exemplary flow chart of determining a static shading stress response array according to some embodiments of the present application;

[0044] Figure 3 is a schematic diagram of the structure of an agricultural control unit according to some embodiments of the present application;

[0045] Figure 4 It is a structural diagram of a computer terminal device for implementing a smart agriculture control method based on big data as shown in some embodiments of the present application. DETAILED DESCRIPTION

[0046] The present application obtains a crop distribution scatter plot through an agricultural big data center, collects light at the crop distribution center based on the crop distribution scatter plot, and obtains the central light intensity; collects features according to each crop distribution area in the crop distribution scatter plot, and obtains the crop texture features and environmental humidity features corresponding to each crop distribution area; performs stress response feature learning on the crop texture features and environmental humidity features corresponding to each crop distribution area based on the central light intensity, and obtains a static shading stress response array; obtains a drivable path for an agricultural plant protection vehicle, and based on each static shading stress response array The invention relates to a method for controlling the driving trajectory of an agricultural plant protection vehicle during low-position spraying on a drivable path according to the dynamic shading stress response value and the corresponding crop distribution area; collecting the environmental parameters of the current crop distribution area during the spraying of the regulator to determine the dynamic shading stress response value; and correcting the spraying direction of the agricultural plant protection vehicle according to the dynamic shading stress response value and the static shading stress response value of the current crop distribution area. The present application can control the driving trajectory of the agricultural plant protection vehicle according to the different degrees of shading stress in different crop distribution areas, thereby performing targeted spraying, thereby improving the efficiency of the agricultural plant protection vehicle in spraying plant growth regulators.

[0047] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Figure 1 , which is an exemplary flow chart of a smart agriculture control method based on big data according to some embodiments of the present application. The smart agriculture control method 100 based on big data mainly includes the following steps:

[0048] In step S101, a crop distribution scatter plot is obtained through the agricultural big data center, and light collection is performed on the crop distribution center based on the crop distribution scatter plot to obtain the central light intensity.

[0049] It should be noted that the crop distribution scatter plot includes high-position agricultural crop data points and low-position agricultural crop data points; in some embodiments, when controlling an agricultural seeder to sow, the crop seed data and sowing location are uploaded to the big data center of the agricultural control system (agricultural big data center) for recording to obtain the crop distribution scatter plot. The crop distribution center can be determined based on the agricultural crop distribution data, or the pattern centroid of the crop distribution scatter plot can be used as the crop distribution center.

[0050] Optionally, in some embodiments, a light sensor is used to collect light at the crop distribution center to obtain the central light intensity. The light sensor is a sensor used to measure ambient light intensity. It can monitor light intensity changes in real time and is widely used in agriculture, environmental monitoring and other fields. The light sensor detects through a photodiode or a phototransistor, and the output electrical signal is proportional to the light intensity.

[0051] In step S102, feature collection is performed according to each crop distribution area in the crop distribution scatter plot to obtain crop texture features and environmental humidity features corresponding to each crop distribution area.

[0052] It should be noted that the crop texture features described in the present application are the leaf texture features of agricultural crops collected and used to reflect the growth and health of crops; the environmental humidity features are used to reflect the transpiration humidity of crop leaves under light conditions. Preferably, in some embodiments, feature collection is performed according to each crop distribution area in the crop distribution scatter plot, and the crop texture features and environmental humidity features corresponding to each crop distribution area can be obtained by the following steps:

[0053] Acquire the crop distribution scatter plot, and perform region segmentation based on the distribution density in the crop distribution scatter plot to obtain a plurality of crop distribution regions;

[0054] The illumination direction is obtained, an initial distribution area is selected according to the illumination direction for crop texture feature collection, and the next crop distribution area is selected based on the illumination direction for crop texture feature collection, until the crop texture features corresponding to each crop distribution area are determined.

[0055] Obtain a spatial wind direction vector, reselect an initial distribution area based on the spatial wind direction vector to collect environmental humidity characteristics, and select the next crop distribution area based on the spatial wind direction vector to collect environmental humidity characteristics until the environmental humidity characteristics corresponding to each crop distribution area are determined.

[0056] It should be noted that according to the journal "Response of Leaf Morphology and Photosynthetic Characteristics of Wild and Cultivated Soybeans to Shade" published by the College of Agriculture of Sichuan Agricultural University in April 2023, shade stress will affect the leaf morphology of crops, including leaf thickness, leaf morphological anatomical structure and physiological metabolic processes, thereby affecting the growth and development and final yield of plants. Under shade stress, the weakening of light intensity reduces the elongation process of palisade tissue and spongy tissue, thereby reducing the area of ​​chloroplast channels for CO2 entry. Therefore, the thickness and photosynthetic capacity of crop leaves are significantly reduced. Crops resist shade stress by significantly increasing the proportion of palisade tissue, that is, increasing the number of chloroplasts inside the leaves (increase in green). In the present application, an image acquisition device can be used to acquire images of agricultural crop leaves. After positioning and converting the leaf images into three-dimensional coordinates, the green components in the leaf images are extracted for grayscale conversion, and then the grayscale deviation between the overall grayscale value of the leaf and the grayscale value of the vein texture is determined, and then the ratio between the grayscale deviation and the standard deviation value is used as the crop texture feature. The crop texture feature is used for health analysis of agricultural crops under shade stress. By monitoring and analyzing the crop texture features, the growth state and adaptability of crops under shade stress can be evaluated, thereby controlling the driving trajectory of the agricultural plant protection vehicle to perform correct growth regulator spraying, ensuring the scientific nature of the driving trajectory of the agricultural plant protection vehicle and improving the spraying efficiency of the growth regulator. In some embodiments, crop texture features can also be extracted by acquiring agricultural crop leaf images in other ways, which are not limited here.

[0057] Optionally, in some embodiments, the environmental humidity characteristics are collected by a humidity sensor.

[0058] In some embodiments, during specific implementation, the entire area is segmented based on the density information of crop distribution, and areas with different densities are divided into multiple crop distribution areas, so as to more accurately collect differentiated features according to the crop density characteristics of different areas; in some embodiments, since the agricultural crop planning range is usually a regular rectangle, the crop distribution scatter map can also be segmented into multiple crop distribution areas by equally spaced area division.

[0059] Optionally, in some embodiments, the first crop distribution area in the lighting direction can be used as the initial distribution area, and the second crop distribution area in the lighting direction can be used as the next crop distribution area; when the environmental humidity characteristics are collected and the initial distribution area is reselected, the first crop distribution area in the vector direction of the spatial wind direction vector can be used as the initial distribution area, and the second crop distribution area in the vector direction of the spatial wind direction vector can be used as the next crop distribution area.

[0060] Preferably, in some embodiments, before collecting crop texture features for each distribution area in the crop distribution scatter plot based on the illumination direction, it also includes: acquiring the illumination direction and wind direction vector at the current moment through the big data center of the agricultural control system. In specific implementation, the wind direction vector can be collected through a wind vane, and then the three-dimensional wind direction is two-dimensionally planarized in the crop distribution scatter plot to obtain the wind direction vector, wherein the vector magnitude of the wind direction vector is the wind speed value at the current moment, and the vector direction is the two-dimensional wind direction at the current moment.

[0061] In step S103, stress response feature learning is performed on the crop texture features and environmental humidity features corresponding to each crop distribution area based on the central light intensity to obtain a static shading stress response array.

[0062] It should be noted that the static shading stress response array contains each crop distribution area and the corresponding static shading stress response value, and the static shading stress response value is used to reflect the growth of low-lying crops in the crop distribution area under shading stress. The trajectory of the plant protection vehicle is controlled according to the static shading stress response array to ensure that crops with high shading stress are given priority and improve the efficiency of the plant protection vehicle in spraying growth regulators. Optionally, in some embodiments, reference Figure 2 As shown in FIG. 1 , this figure is an exemplary flow chart for determining a static shading stress response array in some embodiments of the present application. The stress response feature learning is performed on the crop texture features and environmental humidity features corresponding to each crop distribution area respectively according to the central light intensity. The static shading stress response array can be obtained by the following steps:

[0063] In step S1031, the depth of the contrast area is determined according to the central illumination intensity;

[0064] In step S1032, the crop texture features and the environmental humidity features corresponding to the first crop distribution area are obtained, and a comparative distribution area is selected for stress response feature learning according to the position coordinates of the first crop distribution area and the depth of the comparative area to obtain a static shading stress response value corresponding to the first crop distribution area;

[0065] In step S1033, after obtaining the crop texture features and environmental humidity features corresponding to other crop distribution areas, the static shading stress response values ​​corresponding to each crop distribution area are determined in the same manner, and the array is filled according to the crop distribution scatter plot to obtain the static shading stress response array.

[0066] Preferably, in some embodiments, selecting a comparative distribution area for stress response feature learning based on the position coordinates of the first crop distribution area and the depth of the comparative area, and obtaining a static shading stress response value corresponding to the first crop distribution area can be achieved by the following steps:

[0067] Acquire the position coordinates of the first crop distribution area and the depth of the comparison area;

[0068] According to the depth of the comparison area, multiple crop distribution areas adjacent to the position coordinates of the first crop distribution area are selected as comparison distribution areas, and crop texture features and environmental humidity features respectively corresponding to the comparison distribution areas are obtained;

[0069] Correlation learning is performed based on the crop texture features and environmental humidity features respectively corresponding to the first crop distribution area and the comparison distribution area to obtain a static shading stress response value corresponding to the first crop distribution area.

[0070] Optionally, in some embodiments, the corresponding comparison area depth can be obtained by mapping according to the light intensity range interval in which the central light intensity is located through a preset linear mapping table. The comparison area depth is the number of samples when performing stress response feature learning. For example, when the central light intensity is 550 µmol / m² / s, it is in the moderate shading stress range of 500–1000 µmol / m² / s. The comparison area depth is 8 obtained by mapping according to the preset linear mapping table. At this time, the 8 comparison distribution areas closest to the current crop distribution area are selected for stress response feature learning to obtain the static shading stress response value corresponding to the crop distribution area.

[0071] In specific implementation, correlation learning is performed according to the crop texture features and environmental humidity features corresponding to the first crop distribution area and the comparison distribution area, and the static shading stress response value corresponding to the first crop distribution area can be obtained by the following steps: setting corresponding labels for each comparison distribution area, normalizing the crop texture features and environmental humidity features of the first crop distribution area and each comparison distribution area, and performing difference processing to obtain the texture feature difference sequence and environmental humidity difference sequence corresponding to the first crop distribution area and each comparison distribution area; and then obtaining the Pearson correlation coefficient of the texture feature difference sequence and the environmental humidity difference sequence, obtaining the normalized mean of the texture feature difference sequence and the environmental humidity difference sequence, and taking the product of the normalized mean and the Pearson correlation coefficient as the static shading stress response value of the first crop distribution area. In some embodiments, the static shading stress response value of other crop distribution areas can be obtained in the same manner, or the feature correlation can be evaluated by a statistical analysis method as the static shading stress response value, which is not limited in the present application.

[0072] In step S104, the drivable path of the agricultural plant protection vehicle is obtained, and based on each static shading stress response value in the static shading stress response array and the corresponding crop distribution area, the driving trajectory of the agricultural plant protection vehicle during low-position spraying on the drivable path is controlled.

[0073] It should be noted that an agricultural plant protection vehicle is a mechanical equipment specially used for plant protection and management in agricultural production. It can automatically or semi-automatically spray pesticides, fertilizers and growth regulators in the fields to control pests and diseases and promote crop growth. Low-level spraying refers to spraying pesticides, fertilizers or growth regulators at a lower height onto the surface or soil of low-lying crops that are subject to shade stress during agricultural operations. In some embodiments, the drivable path of the agricultural plant protection vehicle can be loaded through the big data center of the agricultural control system.

[0074] Preferably, in some embodiments, based on each static shading stress response value in the static shading stress response array and the corresponding crop distribution area, controlling the driving trajectory of the agricultural plant protection vehicle when performing low-position spraying on the drivable path can be achieved by adopting the following steps:

[0075] Acquire each static shading stress response value in the static shading stress response array and the corresponding crop distribution area;

[0076] Obtain all drivable path segments of the agricultural plant protection vehicle; obtain each drivable path segment and the adjacent crop distribution area corresponding to the drivable path segment;

[0077] The starting point of the driving trajectory of the agricultural plant protection vehicle is obtained, and the static shading stress response values ​​of all adjacent crop distribution areas corresponding to the drivable path segment are accumulated as the pheromone concentration corresponding to the drivable path segment. The ant colony algorithm is used to determine the driving trajectory of the agricultural plant protection vehicle when it performs low-position spraying of the regulator starting from the starting point of the driving trajectory.

[0078] In specific implementation, each static shading stress response value and its corresponding crop distribution area are extracted from the static shading stress response array, and the static shading stress response value reflects the health status of crops in each area under the shading stress of high-position crops; the starting point of the driving trajectory of the agricultural plant protection vehicle is selected, and the static shading stress response values ​​of the path segments adjacent to the starting point are accumulated to obtain the pheromone concentration corresponding to the drivable path segment, and the pheromone concentration value is used to reflect the specific number and health status of the crops that can be sprayed on the path segment; finally, the ant colony algorithm is used to determine the driving trajectory of the agricultural plant protection vehicle. The ant colony algorithm can simulate the foraging behavior of ants, guide the vehicle to select the optimal path through the pheromone concentration, and realize the priority spraying of important areas. In addition, on the determined driving trajectory, the agricultural plant protection vehicle can spray the regulator at a low position to ensure that the spraying is uniform and targeted, so that the agricultural plant protection vehicle can scientifically select the driving trajectory under the condition of static shading stress, and improve the accuracy and efficiency of crop management through trajectory planning of the agricultural plant protection vehicle, maximize the use of resources, and reduce the impact of shading stress on crops.

[0079] Optionally, in some embodiments, the process of using an ant colony algorithm to determine the driving trajectory of the agricultural plant protection vehicle when performing low-position spraying of the regulator from the starting point of the driving trajectory can be implemented by the following steps:

[0080] Initialize the pheromone matrix to represent the initial pheromone concentration of each drivable path. Usually, the initial values ​​of all paths are set to the same value.

[0081] Determining heuristic information of each path according to the static shading stress response value, wherein the heuristic information is used as a reference for path selection;

[0082] The selection probability of each drivable path is calculated based on the heuristic information of the path and the birth pheromone concentration. The pheromone is updated according to the crop growth status of the car on the path. The path selection and update process is repeated for multiple iterations, so that the ant colony algorithm can fully explore the drivable paths and gradually converge to the optimal solution.

[0083] After multiple iterations, the path with the highest pheromone concentration is selected as the final driving trajectory.

[0084] In step S105, during the regulator spraying process, environmental parameters of the current crop distribution area are collected to determine a dynamic shading stress response value, and the spraying direction of the agricultural plant protection vehicle is corrected according to the dynamic shading stress response value and the static shading stress response value of the current crop distribution area.

[0085] It should be noted that the dynamic shading stress response value indicates the actual degree of decrease in light intensity of low-lying plants in the crop distribution area where the current agricultural plant protection vehicle is located due to shading stress. It is determined according to the environmental parameters of the current crop distribution area. The spraying direction of the agricultural plant protection vehicle is corrected according to the dynamic shading stress response value and the static shading stress response value of the current crop distribution area. This can ensure that the area with the largest degree of actual light intensity decrease due to shading stress is sprayed first, thereby improving the accuracy and efficiency of spraying. Preferably, in some embodiments, the environmental parameters of the current crop distribution area are collected during the spraying process to determine the dynamic shading stress response value. The stress response value can be realized by the following steps: collecting the light intensity on the surface of low-lying plants during the spraying process to obtain the low-level average light intensity of the current crop distribution area, mapping the average light intensity according to a preset linear mapping table, and obtaining the dynamic shading stress response value corresponding to the current crop distribution area. Optionally, in some embodiments, the dynamic shading stress response value corresponding to the current crop distribution area = the low-level average light intensity of the current crop distribution area × the linear mapping parameter + the basic mapping value, wherein the linear mapping parameter and the basic mapping value are calibrated as constants based on historical experience.

[0086] Preferably, in some embodiments, the spraying direction of the agricultural plant protection vehicle is corrected according to the dynamic shading stress response value and the static shading stress response value of the current crop distribution area by the following steps:

[0087] Obtaining the response difference between the dynamic shading stress response value and the static shading stress response value of the current crop distribution area;

[0088] When the response difference is higher than a preset threshold, a correction depth is determined according to the illumination parameters of the current crop distribution area, and a dynamic shading stress response value and a static shading stress response value of the adjacent crop distribution area are obtained based on the correction depth;

[0089] The spraying direction of the agricultural plant protection vehicle is corrected according to the dynamic shading stress response value and the static shading stress response value of the adjacent crop distribution area.

[0090] In specific implementation, the preset threshold is calibrated as a constant as needed, and the correction depth is directly mapped according to the range interval of the illumination parameter of the current crop distribution area to obtain the corresponding correction depth. In some embodiments, the depth of the comparison area can also be used as the correction depth. The correction depth is the number of samples when correcting the spraying direction of the agricultural plant protection vehicle, and then the dynamic shading stress response value and the static shading stress response value of the adjacent crop distribution area with the same number as the correction depth can be obtained to establish a feature vector group. The direction of the feature vector is the center of the area where the current agricultural plant protection vehicle points to the adjacent crop distribution area, and the vector length is the adjacent crop distribution area. The dynamic shading stress response value and the static shading stress response value of the domain are obtained, wherein the characteristic vectors corresponding to the dynamic shading stress response value and the static shading stress response value have different vector weights, and the vector weights are calibrated as constants based on historical experience, and the vector weights of the characteristic vectors corresponding to the dynamic shading stress response value and the static shading stress response value can also be preset to be 1; vector fusion is performed according to the characteristic vector group to obtain the final fusion vector direction as the corrected spraying direction, so that the agricultural plant protection vehicle can flexibly adjust the spraying direction according to the real-time dynamic and static shading stress response values, improve the accuracy and efficiency of spraying, and ensure that the crops obtain the required nutrients and protection.

[0091] In addition, in another aspect of the present application, in some embodiments, the present application provides a smart agricultural control system based on big data, the device includes an agricultural control unit, reference Figure 3 , which is a schematic diagram of the structure of an agricultural control unit according to some embodiments of the present application, the agricultural control unit 200 includes: a data acquisition module 201, a data processing module 202 and an agricultural plant protection vehicle control module 203, which are described as follows:

[0092] The data collection module 201 is used in some specific embodiments of the present application to obtain a crop distribution scatter plot through an agricultural big data center, and collect light from the crop distribution center based on the crop distribution scatter plot to obtain the center light intensity;

[0093] The data collection module 201, in some specific embodiments of the present application, is further used to collect features according to each crop distribution area in the crop distribution scatter plot, to obtain crop texture features and environmental humidity features corresponding to each crop distribution area;

[0094] The data processing module 202 is used in some specific embodiments of the present application to perform stress response feature learning on the crop texture features and environmental humidity features corresponding to each crop distribution area based on the central light intensity to obtain a static shading stress response array;

[0095] The agricultural plant protection vehicle control module 203 is used in some specific embodiments of the present application to obtain a drivable path for the agricultural plant protection vehicle, and based on each static shading stress response value in the static shading stress response array and the corresponding crop distribution area, control the driving trajectory of the agricultural plant protection vehicle when performing low-position spraying on the drivable path;

[0096] The agricultural plant protection vehicle control module 203, in some specific embodiments of the present application, is also used to collect environmental parameters of the current crop distribution area during the regulator spraying process to determine the dynamic shading stress response value, and to correct the spraying direction of the agricultural plant protection vehicle according to the dynamic shading stress response value and static shading stress response value of the current crop distribution area.

[0097] The above describes in detail an example of a smart agricultural control system and method based on big data provided in an embodiment of the present application. It can be understood that in order to realize the above functions, the corresponding device includes a hardware structure and / or software module corresponding to executing each function.

[0098] Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed in this document, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function in the application is executed in hardware or in a computer software-driven hardware manner depends on the specific application and design constraints of the technical solution. Therefore, professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0099] In addition, the present application also provides a computer terminal device, which includes a memory and a processor, the memory stores a code, and the processor is configured to obtain the code and execute the above-mentioned big data-based smart agriculture control method.

[0100] In some embodiments, reference Figure 4 , which is a schematic diagram of the structure of a computer terminal device for implementing a smart agriculture control method based on big data according to some embodiments of the present application. The smart agriculture control method based on big data in the above embodiment can be achieved by Figure 4 The computer terminal device 300 shown in the figure is implemented, and the computer terminal device 300 includes at least one communication bus 301, a communication interface 302, a processor 303 and a memory 304.

[0101] Processor 303 can be a general-purpose central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more for controlling the execution of a big data-based smart agriculture control method in the present application.

[0102] The communication bus 301 may include a path for transmitting information between the above-mentioned components.

[0103] The memory 304 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including a compressed optical disc, a laser disc, an optical disc, a digital versatile disc, a Blu-ray disc, etc.), a magnetic disk or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory 304 may exist independently and be connected to the processor 303 via the communication bus 301. The memory 304 may also be integrated with the processor 303.

[0104] The memory 304 is used to store the program code for executing the solution of the present application, and the execution is controlled by the processor 303. The processor 303 is used to execute the program code stored in the memory 304. The program code may include one or more software modules. The determination of the static shading stress response array in the above embodiment can be implemented by the processor 303 and one or more software modules in the program code in the memory 304.

[0105] The communication interface 302 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0106] Optionally, the computer terminal device 300 may further include a power supply 305 for providing power to various devices or circuits in the real-time computer terminal device.

[0107] In a specific implementation, as an embodiment, a computer terminal device may include multiple processors, each of which may be a single-CPU processor or a multi-CPU processor. The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0108] The above-mentioned computer terminal device may be a general-purpose computer terminal device or a dedicated computer terminal device. In a specific implementation, the computer terminal device may be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device or an embedded device. The embodiment of the present application does not limit the type of computer terminal device.

[0109] In addition, in other aspects of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores at least one computer program, and the computer program is loaded and executed by a processor to implement the operations performed by the above-mentioned big data-based smart agriculture control method.

[0110] In summary, in a smart agriculture control system and method based on big data disclosed in an embodiment of the present application, a crop distribution scatter plot is first obtained through an agricultural big data center, and light collection is performed on the crop distribution center based on the crop distribution scatter plot to obtain the central light intensity; feature collection is performed according to each crop distribution area in the crop distribution scatter plot to obtain the crop texture features and environmental humidity features corresponding to each crop distribution area; stress response feature learning is performed on the crop texture features and environmental humidity features corresponding to each crop distribution area based on the central light intensity to obtain a static shading stress response array; a drivable path for an agricultural plant protection vehicle is obtained, and a static shading stress response array is obtained based on the central light intensity. Based on each static shading stress response value in the static shading stress response array and the corresponding crop distribution area, the driving trajectory of the agricultural plant protection vehicle during low-position spraying on the drivable path is controlled; during the regulator spraying process, the environmental parameters of the current crop distribution area are collected to determine the dynamic shading stress response value, and the spraying direction of the agricultural plant protection vehicle is corrected according to the dynamic shading stress response value and the static shading stress response value of the current crop distribution area. The present application can control the driving trajectory of the agricultural plant protection vehicle according to the different degrees of shading stress in different crop distribution areas, so as to carry out targeted spraying, thereby improving the efficiency of the agricultural plant protection vehicle in spraying plant growth regulators.

[0111] The above is only an embodiment of the present application, and the common knowledge such as the specific technical scheme or characteristics in the scheme is not described in detail here. It should be pointed out that for those skilled in the art, without departing from the technical scheme of the present application, several modifications and improvements can be made, which should also be regarded as the scope of protection of the present application, and these will not affect the effect of the implementation of the present application and the practicality of the patent.

[0112] The scope of protection claimed by this application shall be based on the content of its claims. The specific implementation methods and other records in the specification can be used to interpret the content of the claims. Obviously, those skilled in the art can make various changes and modifications to this application without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is also intended to include these modifications and variations.

Claims

1. A smart agriculture control method based on big data, characterized in that: include: Obtain a crop distribution scatter plot through the agricultural big data center, collect light from the crop distribution center based on the crop distribution scatter plot, and obtain the center light intensity; Collecting features according to each crop distribution area in the crop distribution scatter plot to obtain crop texture features and environmental humidity features corresponding to each crop distribution area; Using the central light intensity, stress response feature learning is performed on the crop texture features and environmental humidity features corresponding to each crop distribution area to obtain a static shading stress response array; Acquire a drivable path of the agricultural plant protection vehicle, and control the driving trajectory of the agricultural plant protection vehicle when performing low-position spraying on the drivable path based on each static shading stress response value in the static shading stress response array and the corresponding crop distribution area; During the spraying of the regulator, the environmental parameters of the current crop distribution area are collected to determine the dynamic shading stress response value, and the spraying direction of the agricultural plant protection vehicle is corrected according to the dynamic shading stress response value and the static shading stress response value of the current crop distribution area; The static shading stress response array includes each crop distribution area and the corresponding static shading stress response value, and the static shading stress response value is used to reflect the growth of low-lying crops in the crop distribution area under shading stress; Among them, the stress response feature learning is performed on the crop texture features and environmental humidity features corresponding to each crop distribution area respectively according to the central light intensity, and the static shading stress response array is obtained, which specifically includes: Determining the depth of the contrast area according to the central illumination intensity; Acquire crop texture features and environmental humidity features corresponding to the first crop distribution area, select a comparison distribution area for stress response feature learning according to the position coordinates of the first crop distribution area and the depth of the comparison area, and obtain a static shading stress response value corresponding to the first crop distribution area; After obtaining the crop texture features and environmental humidity features corresponding to other crop distribution areas, the static shading stress response values ​​corresponding to each crop distribution area are determined in the same manner, and array filling is performed according to the crop distribution scatter plot to obtain the static shading stress response array; Among them, collecting the environmental parameters of the current crop distribution area during the regulator spraying process to determine the dynamic shading stress response value specifically includes: collecting the light intensity of the low-level plant surface during the spraying process to obtain the low-level average light intensity of the current crop distribution area, mapping the low-level average light intensity according to a preset linear mapping table to obtain the dynamic shading stress response value corresponding to the current crop distribution area, the dynamic shading stress response value corresponding to the current crop distribution area = the low-level average light intensity of the current crop distribution area × the linear mapping parameter + the basic mapping value, wherein the linear mapping parameter and the basic mapping value are calibration constants.

2. The method according to claim 1, characterized in that According to each crop distribution area in the crop distribution scatter plot, feature collection is performed to obtain crop texture features and environmental humidity features corresponding to each crop distribution area, specifically including: Acquire the crop distribution scatter plot, and perform region segmentation based on the distribution density in the crop distribution scatter plot to obtain a plurality of crop distribution regions; Acquire the illumination direction, select an initial distribution area according to the illumination direction to collect crop texture features, select the next crop distribution area based on the illumination direction to collect crop texture features, until the crop texture features corresponding to each crop distribution area are determined; Obtain a spatial wind direction vector, reselect an initial distribution area based on the spatial wind direction vector to collect environmental humidity characteristics, and select the next crop distribution area based on the spatial wind direction vector to collect environmental humidity characteristics until the environmental humidity characteristics corresponding to each crop distribution area are determined.

3. The method according to claim 1, characterized in that Before collecting features according to each crop distribution area in the crop distribution scatter plot, the method further includes: obtaining the illumination direction and wind direction vector at the current moment through the big data center of the agricultural control system.

4. The method according to claim 1, characterized in that Based on each static shading stress response value in the static shading stress response array and the corresponding crop distribution area, controlling the driving trajectory of the agricultural plant protection vehicle when performing low-position spraying on the drivable path specifically includes: Acquire each static shading stress response value in the static shading stress response array and the corresponding crop distribution area; Obtain all drivable path segments of the agricultural plant protection vehicle; obtain each drivable path segment and the adjacent crop distribution area corresponding to the drivable path segment; The starting point of the driving trajectory of the agricultural plant protection vehicle is obtained, and the static shading stress response values ​​of all adjacent crop distribution areas corresponding to the drivable path segment are accumulated as the pheromone concentration corresponding to the drivable path segment. The ant colony algorithm is used to determine the driving trajectory of the agricultural plant protection vehicle when it performs low-position spraying of the regulator starting from the starting point of the driving trajectory.

5. The method according to claim 1, characterized in that The spraying direction of the agricultural plant protection vehicle is corrected according to the dynamic shading stress response value and the static shading stress response value of the current crop distribution area, specifically including: Obtaining the response difference between the dynamic shading stress response value and the static shading stress response value of the current crop distribution area; When the response difference is higher than a preset threshold, a correction depth is determined according to the illumination parameters of the current crop distribution area, and a dynamic shading stress response value and a static shading stress response value of the adjacent crop distribution area are obtained based on the correction depth; The spraying direction of the agricultural plant protection vehicle is corrected according to the dynamic shading stress response value and the static shading stress response value of the adjacent crop distribution area.

6. The method according to claim 1, characterized in that Light sensors are used to collect light at the center of crop distribution to obtain the central light intensity.

7. A smart agricultural control system based on big data, the system is controlled by the method described in any one of claims 1 to 6, the system includes an agricultural control unit, characterized in that: The agricultural control unit comprises: A data collection module is used to obtain a crop distribution scatter plot through an agricultural big data center, collect light from the crop distribution center based on the crop distribution scatter plot, and obtain the center light intensity; The data collection module is further used to collect features according to each crop distribution area in the crop distribution scatter plot, so as to obtain crop texture features and environmental humidity features corresponding to each crop distribution area; A data processing module, used for learning stress response characteristics of crop texture characteristics and environmental humidity characteristics corresponding to each crop distribution area based on the central light intensity, and obtaining a static shading stress response array; An agricultural plant protection vehicle control module, used to obtain a drivable path of the agricultural plant protection vehicle, and control the driving trajectory of the agricultural plant protection vehicle when performing low-position spraying on the drivable path based on each static shading stress response value in the static shading stress response array and the corresponding crop distribution area; The agricultural plant protection vehicle control module is also used to collect environmental parameters of the current crop distribution area to determine the dynamic shading stress response value during the regulator spraying process, and correct the spraying direction of the agricultural plant protection vehicle according to the dynamic shading stress response value and static shading stress response value of the current crop distribution area.

8. A computer terminal device, characterized in that: The computer terminal device includes a memory and a processor, the memory stores a code, and the processor is configured to obtain the code and execute the big data-based smart agriculture control method as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing at least one computer program, characterized in that: The computer program is loaded and executed by a processor to implement the operations performed by the big data-based smart agriculture control method as described in any one of claims 1 to 6.

Images