Soil big data analysis method and device based on artificial intelligence and storage medium

Abstract

The embodiment of the invention relates to the technical field of artificial intelligence, and discloses a soil big data analysis method and equipment based on artificial intelligence and a storage medium, and the method realizes multi-dimensional soil data dynamic acquisition and analysis through hardware equipment integrating a telescopic sampling module, a soil humidity detection module and a heavy metal content detection module. Firstly, after an instruction is triggered in different preset time periods, a telescopic sampling module is used for obtaining soil samples in a layered mode, then humidity and heavy metal content data of each layer of soil are synchronously detected and input into a multi-mode model for analysis, and finally the dynamic correlation between the soil humidity and the heavy metal content and strength evaluation are output. Thus, through multi-depth and multi-time-point sampling and modal data integration, limitation of traditional single-point static analysis is broken through, spatial heterogeneity and time evolution characteristics of soil pollution are accurately captured, and accurate data support is provided for soil pollution remediation strategy optimization and environmental policy making.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and particularly to a method, device and storage medium for soil big data analysis based on artificial intelligence. Background Art

[0002] Soil pollution includes heavy metal pollution and persistent organic pollutant pollution, etc. Therefore, sampling and detection of polluted soil, analysis of pollution data and feedback of pollution status have become important issues to be studied.

[0003] With the development of technology, multi-modal data fusion analysis has gradually become a trend. However, existing soil analysis devices have deficiencies in sampling and data processing, and the evaluation of soil quality is not accurate enough to meet the needs of environmental risk assessment. Summary of the Invention

[0004] The main object of the present invention is to provide a method, device and storage medium for soil big data analysis based on artificial intelligence, aiming to solve the technical problem that the evaluation of soil quality in the prior art is not accurate enough to meet the needs of environmental risk assessment.

[0005] To achieve the above object, in a first aspect, an embodiment of the present application provides a method for soil big data analysis based on artificial intelligence, which is applied to a soil analysis device. The soil analysis device includes a telescopic sampling module, a soil humidity inspection module and a heavy metal content inspection module. The method includes: Obtain soil analysis instructions triggered at preset different time periods, and control the telescopic sampling module to perform multi-modal soil sampling according to the soil analysis instructions to obtain first-modal soil and second-modal soil at different depths; Obtain the first-modal soil humidity data and the second-modal soil humidity data according to the detection data of the soil humidity inspection module; Obtain the first-modal soil heavy metal content data and the second-modal soil heavy metal content data according to the detection data of the heavy metal content inspection module; Input the first-modal soil humidity data, the second-modal soil humidity data, the first-modal soil heavy metal content data and the second-modal soil heavy metal content data into an analysis model to obtain evaluation information of the soil to be analyzed. The evaluation information of the soil to be analyzed at least includes the correlation relationship and correlation strength between soil humidity and soil heavy metal content.

[0006] In a possible implementation manner, the soil humidity inspection module includes a soil humidity detection capacitor. The soil humidity detection capacitor includes a first electrode plate and a second electrode plate. The control of the telescopic sampling module to perform multi-modal soil sampling to obtain first-modal soil and second-modal soil at different depths includes: Control the telescopic sampling module to penetrate into the soil layer at the first depth for soil sampling to obtain the first-mode soil; Place the first-mode soil between the first electrode plate and the second electrode plate to form a first target capacitor, where the first-mode soil serves as the dielectric material of the first target capacitor; and / or, Control the telescopic sampling module to penetrate into the soil layer at the second depth for soil sampling to obtain the second-mode soil, where the second depth soil is different from the first depth soil layer; Place the second-mode soil between the first electrode plate and the second electrode plate to form a second target capacitor, where the second-mode soil serves as the dielectric material of the second target capacitor.

[0007] In a possible implementation manner, obtaining the first-mode soil humidity data and the second-mode soil humidity data according to the detection data of the soil humidity detection module includes: Obtain the initial humidity value data of the first-mode soil at preset different time periods according to the detection data of the first target capacitor; Correct the initial humidity value data of the first-mode soil according to the environmental air humidity to obtain the target humidity value data of the first-mode soil; Sort the target humidity value data of the first-mode soil in chronological order to form the humidity curve data of the first-mode soil; and / or, Obtain the initial humidity value data of the second-mode soil at preset different time periods according to the detection data of the second target capacitor; Correct the initial humidity value data of the second-mode soil according to the environmental air humidity to obtain the target humidity value data of the second-mode soil; Sort the target humidity value data of the second-mode soil in chronological order to form the humidity curve data of the second-mode soil.

[0008] In a possible implementation manner, correcting the initial humidity value data of the first-mode soil according to the environmental air humidity to obtain the target humidity value data of the first-mode soil includes: Correct the initial humidity value data of the first-mode soil according to the environmental air humidity value sensed by the air humidity sensor to obtain the target humidity value data of the first-mode soil; Wherein, when the environmental air humidity value is greater than the preset humidity value, perform reverse correction on the initial humidity value of the first-mode soil; when the environmental air humidity value is less than the preset humidity value, perform forward correction on the initial humidity value of the first-mode soil.

[0009] In a possible implementation manner, obtaining the initial humidity value data of the first-mode soil at preset different time periods according to the detection data of the first target capacitor includes: Obtain the capacitance detection value of the first target capacitor; Input the capacitance detection value of the first target capacitor into a pre-trained humidity prediction model to obtain the initial humidity value of the first-modal soil, where the humidity prediction model satisfies the following expression: (C≥16.4 pF), where is the humidity value, with the unit of %, and C is the capacitance value, with the unit of pF.

[0010] In a possible implementation manner, the heavy metal content inspection module includes a fluorescence detection camera. Obtaining the first-modal soil heavy metal content data and the second-modal soil heavy metal content data according to the detection data of the heavy metal content inspection module includes: Obtain a first target image by acquiring the detection images taken by the fluorescence detection camera for the first-modal soil at preset different time periods; Obtain a second target image by acquiring the detection images taken by the fluorescence detection camera for the second-modal soil at preset different time periods; Input the first target image and the second target image into a soil heavy metal image analysis model respectively to obtain the first-modal soil heavy metal content value data and the second-modal soil heavy metal content value data; Sort the first-modal soil heavy metal content value data in time sequence to obtain the first-modal soil heavy metal content curve data; Sort the second-modal soil heavy metal content value data in time sequence to obtain the second-modal soil heavy metal content curve data.

[0011] In a possible implementation manner, inputting the first-modal soil humidity data, the second-modal soil humidity data, the first-modal soil heavy metal content data, and the second-modal soil heavy metal content data into an analysis model to obtain the evaluation information of the soil to be analyzed includes: Input the first-modal soil humidity curve data, the second-modal soil humidity curve data, the first-modal soil heavy metal content curve data, and the second-modal soil heavy metal content curve data into an analysis model to obtain the correlation relationship and correlation strength between soil humidity and soil heavy metal content.

[0012] In a possible implementation manner, inputting the first-modal soil humidity curve data, the second-modal soil humidity curve data, the first-modal soil heavy metal content curve data, and the second-modal soil heavy metal content curve data into an analysis model to obtain the correlation relationship and correlation strength between soil humidity and soil heavy metal content includes: Identify the changing trend of the curve according to the image analysis technology, and divide the curve into a first relevant part and a second relevant part according to the changing trend of the curve. The first relevant part represents that the soil humidity and the soil heavy metal content satisfy a first correlation relationship, and the second relevant part represents that the soil humidity and the soil heavy metal content satisfy a second correlation relationship; Calculate the correlation strength between the soil humidity and the soil heavy metal content in different modal soils of the first relevant part and the second relevant part respectively by using the correlation coefficient formula. Among them, the correlation coefficient formula satisfies the following expression: ; Among them, r represents the correlation coefficient of the correlation strength. The closer the absolute value of r is to 1, the stronger the correlation between the two; the closer r is to 0, the weaker the correlation between the two; n is the number of samples; xi represents the i-th soil humidity data, is the average value of the soil humidity data; yi represents the i-th soil heavy metal content data, is the average value of the soil heavy metal content data.

[0013] In a second aspect, an embodiment of the present application further provides a soil analysis device, including: a memory and a processor. The memory is used to store program codes; the processor is used to call the program codes to execute the method as described in the first aspect.

[0014] In a third aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described in the first aspect are implemented.

[0015] Different from the prior art, an artificial intelligence-based soil big data analysis method provided by an embodiment of the present application realizes dynamic acquisition and analysis of multi-dimensional soil data through a hardware device integrating a telescopic sampling module, a soil humidity detection module, and a heavy metal content detection module. First, after triggering an instruction at different preset time periods, the telescopic sampling module is used to obtain soil samples (first and second modal soils) layer by layer, and then the humidity and heavy metal content data of each layer of soil are synchronously detected and input into a multi-modal DBM model for analysis. Finally, the dynamic correlation relationship and strength evaluation between the soil humidity and the heavy metal content are output. In this way, through multi-depth, multi-time point sampling and modal data integration, the limitations of traditional single-point static analysis are broken through, and the spatial heterogeneity and time evolution characteristics of soil pollution are accurately captured, providing accurate data support for the optimization of soil pollution repair strategies and the formulation of environmental policies. Description of the Drawings

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on the structures shown in these drawings.

[0017] Figure 1 It is a schematic structural diagram of a soil analysis device in some embodiments of the present application; Figure 2 It is a schematic flowchart of a soil big data analysis method based on artificial intelligence in some embodiments of the present application; Figure 3 It is a schematic flowchart of step S600 of the soil big data analysis method based on artificial intelligence in some embodiments of the present application; Figure 4 It is a schematic diagram of a soil data curve in some embodiments of the present application; Figure 5 It is a schematic hardware structure diagram of a soil analysis device in some embodiments of the present application.

[0018] The realization of the purpose of the present invention, its functional features and advantages will be further described with reference to the embodiments and the drawings. Detailed Embodiments

[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, rather than all, embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0020] It should be noted that all directional indications (such as up, down, left, right, front, back...) in the embodiments of the present invention are only used to explain the relative positional relationship and movement conditions between components in a specific posture (as shown in the drawings). If the specific posture changes, the directional indications will also change accordingly.

[0021] In addition, the descriptions involving "first", "second", etc. in the present invention are for descriptive purposes only, and should not be construed as indicating or implying their relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In addition, "and / or" throughout the text includes three scenarios. Taking A and / or B as an example, it includes the technical solution of A, the technical solution of B, and the technical solution where both A and B are satisfied simultaneously. In addition, the technical solutions between various embodiments can be combined with each other, but it must be based on what can be achieved by those of ordinary skill in the art. When the combination of technical solutions results in contradictions or cannot be achieved, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0022] Soil pollution includes heavy metal pollution, persistent organic pollutant pollution, etc. Therefore, sampling and detection of polluted soil, analysis of pollution data, and feedback of pollution status have become important issues to be studied.

[0023] With the development of technology, multi-modal data fusion analysis has gradually become a trend. However, existing soil analysis equipment has deficiencies in sampling and data processing, and the evaluation of soil quality is not accurate enough to meet the needs of environmental risk assessment.

[0024] To solve the above problems, as Figure 1 shown, an embodiment of the present application provides a soil analysis device 100. The device includes a telescopic sampling module (not shown), a soil humidity inspection module 110, and a heavy metal content inspection module 120.

[0025] Among them, the soil humidity inspection module 110 uses a capacitance sensor. Its working principle is that when the soil is used as a dielectric material and placed in the capacitance sensor, the sensor can detect the corresponding capacitance value, and then based on the relationship between the capacitance value and humidity, the humidity value of the soil can be deduced inversely.

[0026] The heavy metal content inspection module 120 uses fluorescence detection technology to measure the heavy metal content in the soil. The specific operation is to take an image of the soil through a fluorescence camera, and then analyze and process the captured image to finally obtain the heavy metal content data of the soil.

[0027] Specifically, the soil humidity inspection module 110 includes an upper electrode plate 111 and a lower electrode plate 112. The upper electrode plate 111, the soil 130, and the lower electrode plate 112 together form a target capacitor for detecting soil humidity.

[0028] As Figures 1 - 4As shown below, the following takes the soil analysis equipment executing the artificial intelligence-based soil big data analysis method as an example for illustration. It should be noted that although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here. Please refer to the appendix Figure 2 , the method includes the following steps S200 - step S800: Step S200, obtain soil analysis instructions triggered at preset different time periods, and control the telescopic sampling module to perform multi-modal soil sampling according to the soil analysis instructions to obtain the first-modal soil and the second-modal soil at different depths; Specifically, set the soil analysis equipment on the soil to be analyzed, and then preset different times (such as every 20 minutes or every 1 day) to trigger the soil collection and analysis instructions. After the soil analysis equipment receives the soil analysis instructions, control the telescopic sampling module to perform multi-modal soil sampling to obtain the first-modal soil and the second-modal soil at different depths. That is, after one analysis instruction is triggered, the telescopic sampling module will perform two soil collections, respectively collecting the soil at the first depth (such as the soil at a depth of 2 cm on the surface) and the soil at the second depth (such as the soil at a depth of 20 cm at the bottom).

[0029] In one embodiment, the step: controlling the telescopic sampling module to perform multi-modal soil sampling to obtain the first-modal soil and the second-modal soil at different depths includes: controlling the telescopic sampling module to penetrate into the soil layer at the first depth for soil sampling to obtain the first-modal soil; placing the first-modal soil between the first electrode plate and the second electrode plate to form a first target capacitor, where the first-modal soil serves as the dielectric material of the first target capacitor; and / or, controlling the telescopic sampling module to penetrate into the soil layer at the second depth for soil sampling to obtain the second-modal soil, where the second depth soil is different from the first depth soil layer; placing the second-modal soil between the first electrode plate and the second electrode plate to form a second target capacitor, where the second-modal soil serves as the dielectric material of the second target capacitor.

[0030] Specifically, through remote control or a preset program, the telescopic sampling module is inserted into the specified first-depth soil layer to obtain a soil sample of this depth layer, that is, the first-mode soil. Then, the obtained first-mode soil is placed between the first electrode plate and the second electrode plate. In this way, the first-mode soil becomes the dielectric material of the first target capacitor. After the analysis of the first-mode soil is completed, the position of the telescopic sampling module is adjusted so that it penetrates into the second-depth soil layer to obtain a soil sample of this depth layer, that is, the second-mode soil. The obtained second-mode soil is placed between the first electrode plate and the second electrode plate. In this way, the second-mode soil becomes the dielectric material of the second target capacitor. That is to say, two capacitance sensors are set to perform soil analysis in different modes.

[0031] Based on this, in the embodiment of the present application, by controlling the telescopic sampling module, multi-mode (i.e., different depths) sampling of the soil is performed, and the obtained soil sample is placed between the electrode plates to form a capacitor, with the soil as the dielectric material of the capacitor. In this way, the characteristics of the capacitor can be used to analyze the humidity value of the soil.

[0032] Step S400: Obtain the first-mode soil humidity data and the second-mode soil humidity data according to the detection data of the soil humidity inspection module; It should be noted that the result output by the capacitance sensor is a capacitance value, and there is a certain correlation between the humidity value of the dielectric material and the capacitance value sensed by the capacitance sensor. Specifically, when the water content in the soil is large enough and increasing, the voids between soil particles are filled with water, and the polarity of water molecules makes the polarization ability of the soil in the electric field enhanced, resulting in an increase in the dielectric constant. And when other parameters are certain, the larger the dielectric constant of the soil, the larger the capacitance value. That is to say, when the water content in the soil is greater than a certain threshold, the capacitance value output by the capacitance sensor is positively correlated with the humidity of the soil.

[0033] It can be understood that since there is not only soil but also air between the two electrode plates of the capacitor, and the air humidity will also have a certain impact on the properties such as the humidity of the soil. Therefore, in one embodiment, the step S400: Obtain the first-mode soil humidity data and the second-mode soil humidity data according to the detection data of the soil humidity inspection module, includes: Obtain the first-mode soil initial humidity value data for preset different time periods according to the detection data of the first target capacitor; Correct the first-mode soil initial humidity value data according to the ambient air humidity to obtain the first-mode soil target humidity value data; Sort the first-mode soil target humidity value data in time sequence to form the first-mode soil humidity curve data; and / or, Obtain the initial humidity value data of the second-mode soil for preset different time periods based on the detection data of the second target capacitor; Correct the initial humidity value data of the second-mode soil according to the ambient air humidity to obtain the target humidity value data of the second-mode soil; Sort the target humidity value data of the second-mode soil in time sequence to form the humidity curve data of the second-mode soil.

[0034] Specifically, for the first target capacitor, its detection data is used to obtain the initial humidity value data of the first-mode soil for preset different time periods. That is, at each preset time point, the capacitance value is recorded once and converted into a humidity value. Since there is not only soil but also air between the capacitor electrode plates, and the air humidity will affect the capacitance value (and thus affect the calculation of the humidity value), it is necessary to correct the initial humidity value data of the first mode, sort the corrected target humidity value data of the first-mode soil in time sequence to form the humidity curve data of the first-mode soil. In this way, while ensuring the accuracy of the soil humidity data, it is convenient for the analysis model to analyze the change trend of humidity over time. The data processing method for the second target capacitor is the same as that for the first target capacitor, which will not be elaborated here. As Figure 4 shown, curve S1 is the humidity curve data of the first-mode soil, and curve S2 is the humidity curve data of the second-mode soil. It can be seen that the humidity of the first-mode soil is higher than that of the second-mode soil.

[0035] In a specific embodiment, obtaining the initial humidity value data of the first-mode soil for preset different time periods based on the detection data of the first target capacitor includes: obtaining the capacitance detection value of the first target capacitor; inputting the capacitance detection value of the first target capacitor into a pre-trained humidity prediction model to obtain the initial humidity value of the first-mode soil, where the humidity prediction model satisfies the following expression: (C≥16.4 pF), where is the humidity value, with the unit of %, and C is the capacitance value, with the unit of pF.

[0036] In the embodiment of the present application, first, the above expression is obtained by pre-training the humidity prediction model based on a large amount of data, and then the capacitance detection value of the first target capacitor is input into the above pre-trained humidity prediction model to obtain the initial humidity value of the first-mode soil. That is, for each input of the capacitance detection value of a preset time period, a corresponding initial humidity value of the first-mode soil can be obtained. The calculation process of the initial humidity value of the second-mode soil is similar to that of the initial humidity value of the first-mode soil, which will not be elaborated here.

[0037] The above correction of the first-mode soil initial humidity value data can correct the first-mode soil initial humidity value data according to the ambient air humidity value sensed by the air humidity sensor to obtain the first-mode soil target humidity value data; similarly, the correction of the second-mode soil initial humidity value data can correct the second-mode soil initial humidity value data according to the ambient air humidity value sensed by the air humidity sensor to obtain the second-mode soil target humidity value data.

[0038] Specifically, when the ambient air humidity value is greater than the preset humidity value, it indicates that there is more moisture in the air, which may cause the capacitance value of the capacitor to increase, resulting in a higher soil humidity value calculated through the capacitance value. Therefore, it is necessary to perform a reverse correction on the first-mode soil initial humidity value, that is, reduce the humidity value, to obtain a more accurate target humidity value. When the ambient air humidity value is less than the preset humidity value, it indicates that there is less moisture in the air, which may cause the capacitance value of the capacitor to decrease, resulting in a lower soil humidity value calculated through the capacitance value. Therefore, it is necessary to perform a forward correction on the first-mode soil initial humidity value, that is, increase the humidity value, to obtain a more accurate target humidity value. The specific forward correction amplitude and reverse correction amplitude can be determined according to the actual situation (such as soil type, capacitor characteristics, environmental conditions, etc.).

[0039] Step S600: Obtain the first-mode soil heavy metal content data and the second-mode soil heavy metal content data according to the detection data of the heavy metal content inspection module; In an embodiment, the step S600: Obtain the first-mode soil heavy metal content data and the second-mode soil heavy metal content data according to the detection data of the heavy metal content inspection module, includes: S610: Obtain the first target image by acquiring the detection images of the first-mode soil captured by the fluorescence detection camera at preset different time periods; S620: Obtain the second target image by acquiring the detection images of the second-mode soil captured by the fluorescence detection camera at preset different time periods; S630: Input the first target image and the second target image into the soil heavy metal image analysis model respectively to obtain the first-mode soil heavy metal content value data and the second-mode soil heavy metal content value data; S640: Sort the first-mode soil heavy metal content value data in time sequence to obtain the first-mode soil heavy metal content curve data; S650: Sort the second-mode soil heavy metal content value data in time sequence to obtain the second-mode soil heavy metal content curve data.

[0040] Specifically, a fluorescence detection camera is used to photograph the first-mode soil at preset different time periods. Image data of the first-mode soil at different time points is obtained for subsequent analysis. A series of detection images of the first-mode soil are obtained as the first target images. Similarly, a fluorescence detection camera is used to photograph the second-mode soil at the same or different preset time periods. Image data of the second-mode soil at different time points is obtained. A series of detection images of the second-mode soil are obtained as the second target images. Then, the first target images and the second target images are respectively input into the soil heavy metal image analysis model. This model can analyze the fluorescence signals in the images and convert them into numerical values of heavy metal content. The content values of soil heavy metals are extracted from the image data, thereby obtaining the first-mode soil heavy metal content value data and the second-mode soil heavy metal content value data. Finally, the first-mode soil heavy metal content value data and the second-mode soil heavy metal content value data are sorted in chronological order to obtain the first-mode soil heavy metal content curve data and the second-mode soil heavy metal content curve data. As Figure 4 shown, curve H1 is the first-mode soil heavy metal content curve data, and curve H2 is the second-mode soil heavy metal content value data. It can be seen that the heavy metal content of the first-mode soil is lower than that of the second-mode soil.

[0041] Step S800: Input the first-mode soil humidity data, the second-mode soil humidity data, the first-mode soil heavy metal content data, and the second-mode soil heavy metal content data into the analysis model to obtain the evaluation information of the soil to be analyzed. The evaluation information of the soil to be analyzed at least includes the correlation relationship and the correlation strength between the soil humidity and the soil heavy metal content.

[0042] After obtaining the first-mode soil humidity data, the second-mode soil humidity data, the first-mode soil heavy metal content data, and the second-mode soil heavy metal content data, the evaluation analysis of the relationship between the two variables of humidity and heavy metal content can be carried out according to each data.

[0043] In one embodiment, the first-mode soil humidity curve data, the second-mode soil humidity curve data, the first-mode soil heavy metal content curve data, and the second-mode soil heavy metal content curve data can be input into the analysis model to obtain the correlation relationship and the correlation strength between the soil humidity and the soil heavy metal content.

[0044] Taking Figure 5 the obtained first-mode soil humidity curve data, the second-mode soil humidity curve data, the first-mode soil heavy metal content curve data, and the second-mode soil heavy metal content curve data as the basic analysis data as an example.

[0045] Specifically, the analysis model pre-trained in the embodiments of the present application first identifies the change trend of the curve according to image analysis technology, and divides the curve into a first relevant part B1 and a second relevant part B2 according to the change trend of the curve. It can be seen from the change trend that the first relevant part B1 indicates that the soil heavy metal content increases with the increase of soil humidity (the first correlation), and the second relevant part B2 shows that the soil heavy metal content decreases with the increase of soil humidity (the second correlation). Finally, the correlation coefficient formula can be used to calculate the correlation intensity between soil humidity and soil heavy metal content in different modalities of the first relevant part and the second relevant part. Among them, the correlation coefficient formula satisfies the following expression: ; where r represents the correlation coefficient of the correlation intensity. The closer the absolute value of r is to 1, the stronger the correlation between the two; the closer r is to 0, the weaker the correlation between the two; n is the number of samples; xi represents the i-th soil humidity data, is the average value of the soil humidity data; yi represents the i-th soil heavy metal content data, is the average value of the soil heavy metal content data.

[0046] In this way, based on the correlation relationship and the quantified correlation intensity between soil humidity and heavy metal content, it can be used as a basis for soil environmental governance and improvement. For example, when it is analyzed that there is a significant negative correlation between soil humidity and heavy metal content (such as r = -0.75), a directional regulation strategy can be adopted: the soil moisture content can be increased to the range of 60%-70% of the field capacity through a drip irrigation system to trigger the water-seeking response mechanism of plant roots. Theoretical knowledge shows that when the soil humidity reaches a certain value, continuing to moderately moisten the environment can increase the surface area of plant roots by 23%-35%, and at the same time promote the secretion of organic acids by roots (such as citric acid and malic acid), and their concentration increases by 1.8-2.5 times. These secretions convert the insoluble heavy metals in the soil into bioavailable forms through chelation, and combined with the mass flow transport driven by transpiration pull, the heavy metal content such as cadmium in the surface soil (0-20 cm) decreases, meeting the risk control standards for agricultural land soil pollution. The quantified correlation relationship between soil humidity and heavy metal content obtained by the above model analysis can also be combined with theoretical knowledge for other soil environmental governance and improvement, which will not be exemplified one by one here.

[0047] Based on this, a method for soil big data analysis based on artificial intelligence provided by an embodiment of the present application realizes dynamic acquisition and analysis of multi-dimensional soil data by integrating hardware devices of a telescopic sampling module, a soil humidity detection module, and a heavy metal content detection module. First, after triggering instructions at different preset time periods, the telescopic sampling module is used to obtain soil samples (first and second modal soils) in layers. Then, the humidity and heavy metal content data of each layer of soil are synchronously detected and input into a multi-modal DBM model for analysis. Finally, the dynamic correlation relationship and intensity evaluation between soil humidity and heavy metal content are output. In this way, through multi-depth and multi-time point sampling and modal data integration, the limitations of traditional single-point static analysis are broken through, the spatial heterogeneity and time evolution characteristics of soil pollution are accurately captured, and high-resolution and accurate data support is provided for the optimization of soil pollution repair strategies and the formulation of environmental policies.

[0048] As Figure 5 shown, Figure 5 is a schematic diagram of the hardware structure of the soil analysis device in some embodiments of the present application. The soil analysis device provided by the embodiment of the present application further includes a memory 1000 and a processor 2000. Among them, the memory 1000 is used to store computer-readable instructions, and the processor 2000 is used to call the computer-readable instructions to execute the method for soil big data analysis based on artificial intelligence as described above.

[0049] Among them, the processor 2000 is used to provide computing and control capabilities to control the soil analysis device to perform corresponding tasks. For example, the processor 2000 controls the soil analysis device to execute the method for soil big data analysis based on artificial intelligence in any of the above method embodiments. The method includes: obtaining soil analysis instructions triggered at different preset time periods, and controlling the telescopic sampling module to perform multi-modal soil sampling according to the soil analysis instructions to obtain the first modal soil and the second modal soil at different depths; obtaining the first modal soil humidity data and the second modal soil humidity data according to the detection data of the soil humidity inspection module; obtaining the first modal soil heavy metal content data and the second modal soil heavy metal content data according to the detection data of the heavy metal content inspection module; inputting the first modal soil humidity data, the second modal soil humidity data, the first modal soil heavy metal content data, and the second modal soil heavy metal content data into an analysis model to obtain evaluation information of the soil to be analyzed, and the evaluation information of the soil to be analyzed at least includes the correlation relationship and the correlation intensity between soil humidity and soil heavy metal content.

[0050] The processor 2000 may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), a hardware chip, or any combination thereof; it may also be a Digital Signal Processing (DSP), an Application Specific Integrated Circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The above PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0051] The memory 1000, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the artificial intelligence-based soil big data analysis method in the embodiments of the present application. By running the non-transitory software programs, instructions, and modules stored in the memory 1000, the processor 2000 can implement the artificial intelligence-based soil big data analysis method in any of the above method embodiments.

[0052] Specifically, the memory 1000 may include volatile memory (VM), such as random access memory (RAM); the memory 1000 may also include non-volatile memory (NVM), such as read-only memory (ROM), flash memory, a hard disk drive (HDD), or a solid-state drive (SSD), or other non-transitory solid-state storage devices; the memory 1000 may further include a combination of the above types of memories.

[0053] In summary, the soil analysis device of the present application adopts the technical solution of any of the above embodiments of the artificial intelligence-based soil big data analysis method. Therefore, it has at least the beneficial effects brought by the technical solutions of the above embodiments, which will not be elaborated here one by one.

[0054] The embodiments of the present application also provide a computer-readable storage medium, such as a memory including program codes, and the above program codes can be executed by a processor to complete the method for analyzing soil big data based on artificial intelligence in the above embodiments. For example, the computer-readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CDROM), magnetic tape, floppy disk, and optical data storage device, etc.

[0055] The embodiments of the present application also provide a computer program product, which includes one or more program codes, and the program codes are stored in a computer-readable storage medium. The processor of the warning system reads the program codes from the computer-readable storage medium, and the processor executes the program codes to complete the steps of the method for analyzing soil big data based on artificial intelligence provided in the above embodiments.

[0056] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above embodiments can be completed by hardware, or can be completed by hardware related to program codes through a program. The program can be stored in a computer-readable storage medium, and the above-mentioned storage medium can be a read-only memory, a magnetic disk, or an optical disc, etc.

[0057] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0058] Through the description of the above embodiments, those of ordinary skill in the art can clearly understand that each embodiment can be implemented by means of software plus a general hardware platform, and of course, it can also be implemented by hardware. Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing related hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, the storage medium can be a magnetic disk, an optical disc, a read-only memory (ROM), or a random access memory (RAM), etc.

[0059] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention. Any equivalent structural transformation made under the inventive concept of the present invention by using the content of the specification and drawings of the present invention, or any direct / indirect application in other related technical fields is included in the patent protection scope of the present invention.

Claims

1. A soil big data analysis method based on artificial intelligence, characterized in that: Applied to soil analysis equipment, the soil analysis equipment includes a telescopic sampling module, a soil moisture detection module and a heavy metal content detection module, the method includes: Obtaining soil analysis instructions triggered by preset different time periods, and controlling the telescopic sampling module to perform multimodal soil sampling according to the soil analysis instructions to obtain first modal soil and second modal soil of different depths; Obtaining the first modal soil moisture data and the second modal soil moisture data according to the detection data of the soil moisture detection module; Obtaining first modal soil heavy metal content data and second modal soil heavy metal content data according to the detection data of the heavy metal content detection module; The first modal soil moisture data, the second modal soil moisture data, the first modal soil heavy metal content data and the second modal soil heavy metal content data are input into an analysis model to obtain evaluation information of the soil to be analyzed, and the evaluation information of the soil to be analyzed at least includes the correlation and correlation strength between soil moisture and soil heavy metal content.

2. The soil big data analysis method based on artificial intelligence according to claim 1, characterized in that: The soil moisture inspection module includes a soil moisture detection capacitor, the soil moisture detection capacitor includes a first electrode plate and a second electrode plate, and the control telescopic sampling module performs multi-modal soil sampling to obtain a first modal soil and a second modal soil of different depths, including: Controlling the telescopic sampling module to probe into a first depth soil layer to perform soil sampling to obtain a first modal soil; placing the first modal soil between the first electrode plate and the second electrode plate to form a first target capacitor, wherein the first modal soil serves as a dielectric material of the first target capacitor; and / or, Controlling the telescopic sampling module to probe into the soil layer at a second depth to sample soil and obtain a second modal soil, wherein the soil at the second depth is different from the soil layer at the first depth; The second modal soil is placed between the first electrode plate and the second electrode plate to form a second target capacitor, wherein the second modal soil serves as a dielectric material of the second target capacitor.

3. The soil big data analysis method based on artificial intelligence according to claim 2, wherein the first modal soil moisture data and the second modal soil moisture data are obtained according to the detection data of the soil moisture detection module, comprising: Obtaining first modal soil initial moisture value data of preset different time periods according to the detection data of the first target capacitor; Correcting the first modal soil initial humidity value data according to the ambient air humidity to obtain the first modal soil target humidity value data; Sorting the first modal soil target moisture value data in time sequence to form first modal soil moisture curve data; and / or, Obtaining second modal soil initial moisture value data of preset different time periods according to the detection data of the second target capacitor; Correcting the second modal soil initial humidity value data according to the ambient air humidity to obtain the second modal soil target humidity value data; The second modal soil target moisture value data are sorted in time series to form second modal soil moisture curve data.

4. The method for analyzing soil big data based on artificial intelligence according to claim 3, wherein the first modal soil initial humidity value data is corrected according to the ambient air humidity to obtain the first modal soil target humidity value data, comprising: Correcting the first modal soil initial humidity value data according to the ambient air humidity value sensed by the air humidity sensor to obtain the first modal soil target humidity value data; When the ambient air humidity value is greater than a preset humidity value, the first modal soil initial humidity value is reversely corrected; when the ambient air humidity value is less than the preset humidity value, the first modal soil initial humidity value is forwardly corrected.

5. The method for analyzing soil big data based on artificial intelligence according to claim 3, wherein the first modal soil initial moisture value data of preset different time periods is obtained according to the detection data of the first target capacitor, comprising: Acquiring a capacitance detection value of the first target capacitor; The capacitance detection value of the first target capacitor is input into a pre-trained humidity estimation model to obtain a first modal soil initial humidity value, wherein the humidity estimation model satisfies the following expression: (C ≥ 16.4pF), where: is the humidity value in %, and C is the capacitance value in pF.

6. The soil big data analysis method based on artificial intelligence according to claim 3, wherein the heavy metal content detection module includes a fluorescence detection camera, and the first modal soil heavy metal content data and the second modal soil heavy metal content data are obtained according to the detection data of the heavy metal content detection module, including: Acquire detection images of the first modal soil taken by the fluorescence detection camera in different preset time periods to obtain a first target image; Acquire detection images of the second modal soil taken by the fluorescence detection camera at different preset time periods to obtain a second target image; Inputting the first target image and the second target image into a soil heavy metal image analysis model respectively to obtain first modal soil heavy metal content value data and second modal soil heavy metal content value data; Sorting the first modal soil heavy metal content value data in time series to obtain first modal soil heavy metal content curve data; The second modal soil heavy metal content value data is sorted in time series to obtain the second modal soil heavy metal content curve data.

7. The method for analyzing soil big data based on artificial intelligence according to claim 6, wherein the first modal soil moisture data, the second modal soil moisture data, the first modal soil heavy metal content data, and the second modal soil heavy metal content data are input into the analysis model to obtain the evaluation information of the soil to be analyzed, comprising: The first modal soil moisture curve data, the second modal soil moisture curve data, the first modal soil heavy metal content curve data, and the second modal soil heavy metal content curve data are input into the analysis model to obtain the correlation and correlation strength between soil moisture and soil heavy metal content.

8. The method for analyzing soil big data based on artificial intelligence according to claim 7, wherein the first modal soil moisture curve data, the second modal soil moisture curve data, the first modal soil heavy metal content curve data, and the second modal soil heavy metal content curve data are input into the analysis model to obtain the correlation between soil moisture and soil heavy metal content and the correlation strength, including: Identify the change trend of the curve according to the image analysis technology, and divide the curve into a first correlation part and a second correlation part according to the change trend of the curve, wherein the first correlation part indicates that the soil moisture and the soil heavy metal content satisfy a first correlation relationship, and the second correlation part indicates that the soil moisture and the soil heavy metal content satisfy a second correlation relationship; The correlation coefficient formula is used to calculate the correlation strength between soil moisture and soil heavy metal content in different modes of the first correlation part and the second correlation part, respectively, wherein the correlation coefficient formula satisfies the following expression: ； Among them, r represents the correlation coefficient of the correlation strength. The closer the absolute value of r is to 1, the stronger the correlation between the two is; the closer r is to 0, the weaker the correlation between the two is; n is the number of samples; x is i represents the i-th soil moisture data, is the average value of soil moisture data; i represents the i-th soil heavy metal content data, is the average value of soil heavy metal content data.

9. A soil analysis device, characterized in that: Also includes: A memory and a processor, wherein the memory is used to store program codes; The processor is used to call the program code to execute the method according to any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images