AI-based analysis method and AI analysis device

Abstract

To provide an AI analysis method and a device thereof for enabling easy, highly accurate, and automated analysis evaluation without being affected by measurement conditions including external factors, human factors and other contingent errors.SOLUTION: Provided is an AI analysis method for obtaining an estimation function 45 of a first objective variable using measurement data that serves as an explanatory variable to be obtained for analyzing the first objective variable pertaining to the feature quantity included in an analysis object. When a correlation value between the estimation function and a quantitative value of the first objective variable cannot be uniquely determined as 0.7 or less, the analysis method uses multiple estimation functions to define the number of such multiple estimation functions as a classification number and estimates the measurement data through classification into multiple objective variables using the multiple estimation functions.SELECTED DRAWING: Figure 3

Description

Technical Field

[0001] The present invention relates to an analysis method using AI, which is characterized in that it cannot be evaluated by a unique function, and uses functions prepared for each classification after classifying events and data. 、 AI analyzer and the program to make the AI ​​analysis device work. For example, regarding soil analysis, it relates to an analysis method of soil samples for evaluating soil fertility traits including component analysis and chemical properties such as cation exchange capacity CEC (Cation Exchange Capacity) and anion exchange capacity AEC (Anion Exchange Capacity). It is also a technology applicable to cases where the properties of materials are unknown in welding, etc.

Background Art

[0002] As an analysis method using AI, Patent Document 1 discloses a learning method of a prediction model, a learning device of the prediction model, and a plant control system. In the learning of the prediction model of Patent Document 1, a prediction model for predicting an objective variable from at least one explanatory variable is updated based on a first evaluation value and a second evaluation value. The first evaluation value is calculated as an index indicating the prediction error of the prediction model, and the second evaluation value is calculated as an index indicating the degree of coincidence between a feature amount related to the sensitivity direction of at least a part of the explanatory variable with respect to the objective variable and an allowable range set for the feature amount based on known information.

[0003] In this case, the relationship between the explanatory variable and the objective variable is classified, and the explanatory variable itself is also expressed as a sensitivity direction error. That is, classification of the correlation of the relationship between the explanatory variable and the objective variable is performed in advance, and based on the classification of the correlation relationship, the error is predicted. Therefore, it is necessary to use different calculation formulas for each pre-classified error when estimating the error. That is, the explanatory function for obtaining the explanatory variable is always unique, and by classifying the relationships included in the error in advance, the learning efficiency is improved.

[0004] Conventionally, for soil analysis, a soil analysis apparatus and method described in Patent Document 2 are known. According to Patent Document 2, an alternating magnetic field is applied to the soil to be analyzed, the detection signal output from the detection coil is measured and processed by the measurement unit, and the soil fertility characteristics, including the CEC of the soil to be analyzed, are estimated by the estimation unit using data relating to the correlation between the quantitative values ​​of the soil fertility characteristics stored in the memory unit and the estimated values ​​of the soil fertility characteristics obtained from the detection signal. Here, the estimation unit can accurately estimate the values ​​of the soil fertility characteristics, including the CEC of the soil, by creating the correlation data using so-called PLS regression analysis when estimating the soil fertility characteristics.

[0005] Furthermore, according to the third embodiment described in Patent Document 2, the estimation unit can perform PLS regression analysis and estimation using the detection signal output from the detection coil as a parameter for the excitation signal, thereby enabling the estimation of CEC in a simple manner, and also enabling the measurement of soil fertility traits other than CEC. [Prior art documents] [Patent Documents]

[0006] [Patent Document 1] Patent No. 6831030 [Patent Document 2] Patent No. 6562490 [Non-patent literature]

[0007] [Non-Patent Document 1] National Agriculture and Food Research Organization, Japan Soil Inventory, https: / / soil-inventory.dc.affrc.go.jp / [Overview of the project] [Problems that the invention aims to solve]

[0008] The prediction model learning method described in Patent Document 1 uses a pre-built prediction model, and although it can be updated by machine learning, it cannot make predictions using any model other than the one newly trained with data prepared separately for that purpose.

[0009] Regarding errors in measurement data, there are variations due to the measurement object itself, variations due to external factors, and variations due to human factors. However, so-called systematic errors can be easily classified using other methods, therefore, in this invention, only so-called random errors are considered as errors.

[0010] Incidentally, in soil analysis according to Patent Document 2, the accuracy of the analysis sometimes decreased depending on the type and condition of the soil, making it difficult to perform an accurate soil analysis. As with the soil analysis described above, measurement targets where the accuracy of the analysis decreases depending on the type and condition are often found in phenomena that depend on the natural environment or the skills of the worker.

[0011] Classification is typically performed by academic experts based on a comprehensive evaluation of analysis results using various analytical methods, but this is far from feasible in the industrial field in terms of immediacy and ease of use. Therefore, the inventors have discovered an AI-based analysis method that allows for the selection of various predictive models and the construction of new models based on the state of explanatory variables, thereby completing the present invention.

[0012] In view of the above, the present invention provides an AI-based analysis method that enables easy and highly accurate automation of analysis and evaluation without being affected by measurement conditions including accidental errors such as external factors and human factors. 、 AI analysis device and the program to make this AI analysis device work. The purpose is to provide this. [Means for solving the problem]

[0013] The above objective is that, according to the present invention, in order to analyze the first objective variable relating to the features included in the object of analysis , obtain measurement data from the object to be analyzed, and obtain the measurement data Explanatory variables and And the first Obtain the estimated function This allows us to estimate the first dependent variable.In the AI analysis method, The object of analysis is any of the following: soil, concrete structure, ceramic structure, metal including alloys, and metal structure including alloys that has undergone processing involving alteration, wherein the material, material properties, crystalline state, material morphology, and material structure exhibit multiple states. when the correlation value between the First estimation function Estimated value and the quantitative value of the first objective variable is 0.7 or less and cannot be uniquely determined, 、 The system is configured to classify the aforementioned measurement data into multiple target variables using a second estimation function, and to obtain multiple first estimation functions for each classification. In the first step, In order to select the first estimation function to be used from among the multiple first estimation functions created for each classification, the second objective variable is estimated by classifying the second estimation function using the measurement data, and the first estimation function to be used is selected. In the second step, Using the measurement data related to the first estimation function selected in the first step as explanatory variables, the first objective variable is estimated using the first estimation function. it is achieved by the AI analysis method.

[0014] In the above configuration, preferably, Evaluation data, which serves as explanatory variables, is used as training data. The first or second objective variable is obtained as a quantitative value of the training data and used as comparison data to perform AI analysis. Preferably, classification is performed using a second estimation function with evaluation data, and based on the obtained classification results, a first estimation function for the first dependent variable defined for each classification in the classification data is selected, the first dependent variable is estimated using the first estimation function with evaluation data, and the classification of the subject of analysis and the estimated value of the first dependent variable are determined. Preferably, in order to create a plurality of First classified estimation functions, when the entire measurement data is analyzed and estimated by the same analysis method, a plurality of classifications are created by classifying according to the degree of deviation of the estimated value from the teacher data. Preferably, a plurality of first estimation functions are created by classification using the similarity of the measurement data.

[0015] According to the above configuration, regarding the measurement data, first, a plurality of types of classifications are defined by comparing the quantitative value of the objective variable to be analyzed with the corresponding comparison data, and an estimation function is defined for each classification. Then, for each measurement data, the corresponding classification is selected, and the objective variable to be analyzed is analyzed and evaluated from the measurement data by the estimation function corresponding to the selected classification. Therefore, since the classification is defined using the measurement data, it is not necessary to separately acquire data for defining the classification from the measurement data, and the process can be simplified. Furthermore, before analyzing and evaluating the measurement data, the classification to which the measurement data should be assigned is selected, and the measurement data is analyzed and evaluated by the estimation function corresponding to the selected classification, so that the analysis and evaluation of the measurement data can be performed more accurately.

[0016] In the above configuration, the estimation function corresponding to the selection of classification is preferably the same as the function corresponding to the selection of classification. second The estimation function is obtained using one of the following analytical methods: linear analysis, PLS regression analysis, SVM (Support Vector Machine), neural networks, or supervised AI analysis methods. Corresponding to the dependent variable Multiple first The estimation function is preferably obtained using one of the following analysis methods: clustering, principal component analysis, unsupervised AI analysis, linear analysis, PLS regression analysis, SVM (Support Vector Machine), neural network, or supervised AI analysis. The measurement data is preferably obtained using one of the following methods: electromagnetic measurement, acoustic measurement, or optical measurement, utilizing multiple frequency bands. Preferably, the primary objective variable is an agricultural indicator of the soil, such as cation exchange capacity (CEC), base saturation, silicic acid, iron oxide, and potassium as a nutrient component. Estimated values ​​of soil fertility characteristics, including um, magnesium, calcium, iron, manganese, zinc, copper, molybdenum, boron, chlorine, nickel, nitrogen, carbon, and phosphorus, are obtained. Preferably, the measurement data is used to generate alternating magnetic flux by applying multiple excitation signals of different frequencies to an excitation coil, and the disturbed magnetic flux, depending on the state of the object being analyzed, is detected using a detection coil. Preferably, the excitation signals have a frequency band of approximately 5 to 100 times from the lowest frequency to the highest frequency. Preferably, the excitation signals consist of 5 or more different frequencies, and the number of excitation signals is at least 1 greater than the sum of the number of analyses and the number of classifications. Preferably, 1 When evaluating the total number of each of the above analysis items using the same evaluation function, 、 Using that standard deviation, we classify the data based on the degree of deviation from the correlation, such as below -3σ, between -3σ and -1σ, ±1σ, between 1σ and 3σ, and above 3σ. Furthermore, the present invention, The material, composition, crystalline state, material morphology, and material structure exhibit multiple states, and the analysis targets one of the following: soil, concrete structures, ceramic structures, metals including alloys, and metal structures including alloys that have undergone processing involving alteration. To analyze a first objective variable related to the features contained in the analysis target, measurement data is obtained from the analysis target, and the first objective variable is estimated by obtaining a first estimation function of the first objective variable using the measurement data as explanatory variables. AI analysis device, A sensor having a coil, A measurement unit that generates excitation signals for each frequency to be input to a coil in order to apply an alternating magnetic field to the object to be analyzed, and processes the detection signal output from the coil based on the generated excitation signals, A storage unit that stores data relating to the correlation between the quantitative value of the target variable of each analysis target and the sensor and measurement unit, for multiple analysis targets, An estimation unit estimates the target variable to be analyzed using the data stored in the memory unit, based on the detection signal processed by the measurement unit. It is equipped with, The estimation unit obtains the complex amplitude ratio from the detection signal to the excitation signal as measurement data, and defines multiple types of classifications from the quantitative values ​​of multiple different target variables stored in the memory unit and the corresponding complex amplitude ratios of the detection signals as comparison data, and for each classification First estimation function Define, The estimation unit, with respect to each measurement data, Using the second estimation function, Select the classification corresponding to the measurement data, and then select the classification corresponding to the selected classification. First estimation function Therefore, the analysis target from the measurement data First This is achieved by an AI analysis device that estimates the target variable. The above-mentioned AI analysis device program is achieved by a program that enables a computer to function as an AI analysis device. [Effects of the Invention]

[0017] According to the present invention, by adding classifications of the objects to be analyzed, an AI analysis method can accurately determine soil fertility traits such as soil CEC. 、 AI analysis device and the program to make this AI analysis device work. We can provide this. [Brief explanation of the drawing]

[0018] [Figure 1] This flowchart illustrates an example of the AI ​​analysis method of the present invention. [Figure 2] This is a block diagram showing the overall configuration of one embodiment of the analytical apparatus according to the present invention. [Figure 3] This is an explanatory diagram illustrating the analytical method of the present invention. [Figure 4] This figure shows the relationship between the estimated and quantitative values ​​of CEC in Comparative Example 1. [Figure 5] This figure shows the relationship between the estimated and quantitative values ​​of CEC in Example 1. [Figure 6] This figure shows the relationship between the estimated and quantitative values ​​of CEC in Example 2. [Figure 7] This figure shows the results of grouping using the k-means method in Comparative Example 2. [Modes for carrying out the invention]

[0019] Embodiments of the present invention will be described below with reference to the drawings. The AI ​​analysis method of the present invention has the following features. In other words, in an AI analysis method that obtains an estimation function for a first objective variable using measurement data that serves as explanatory variables acquired to analyze a first objective variable related to features included in the analysis target, if the correlation between the estimation function and the quantitative value of the first objective variable is 0.7 or less and cannot be uniquely determined, multiple estimation functions are used, the number of such estimation functions is defined as the number of classifications, and the measurement data is classified into multiple objective variables using the multiple estimation functions for estimation. The reason for setting the correlation value to 0.7 or less when classification is unnecessary is that statistically, a value of 0.7 or less is the criterion for whether the estimation is correct. If estimation accuracy is required, the correlation value may be further set to 0.8 or less or 0.9 or less. The explanatory variables acquired to analyze the first objective variable related to features included in the analysis target are, for example, the detection signals from the detection coil 12 described later, and are called measurement data. An estimation function for the first objective variable is obtained from the measurement data. Note that AI (Artificial Intelligence) analysis refers to the calculation methods and algorithms used when estimating the objective variable from explanatory variables.

[0020] Classification is necessary when, after analyzing one or more analysis targets using an AI analysis method without classification, the correlation between the estimation function and the quantitative value of the first objective variable is insufficient, resulting in a correlation of 0.7 or less. When a single evaluation function is insufficient for estimation, it becomes necessary to use multiple estimation functions that classify the targets.

[0021] In this invention, measurement data acquired for analysis is used to classify the data for selecting the estimation function for the analysis. Figure 1 is a flowchart illustrating an example of the preparation and actual measurement for AI analysis requiring classification. As shown in Figure 1, the preparation involves measuring measurement data, considering classification methods, and preparing an estimation function for the analysis from the measurement data. The estimation function is also called the evaluation formula. Specifically, this method includes a first step of using multiple estimation functions as classification items and estimating a second dependent variable using measurement data in order to analyze the selection of such classification items as a second dependent variable, and a second step of selecting a classification related to the first estimation function from the results of the first step and estimating the first dependent variable using measurement data for that classification. For the estimation function of the first dependent variable, classification is performed to obtain a high correlation by creating multiple estimation functions. Preferably, measurement data is used for estimating the first and second dependent variables. Preferably, in order to create the multiple classified estimation functions, when the entire measurement data is analyzed and estimated using the same analytical method, multiple classifications are created by classifying the degree of deviation of the estimated values ​​from the training data. Multiple estimation functions may also be created by classification using the similarity of the measurement data.

[0022] With the above configuration, by utilizing these analytical methods, the estimation function can be easily and accurately defined based on measurement data without having to separately acquire measurement data for defining the estimation function.

[0023] Examples of materials for which the estimation function cannot be uniquely determined include materials, material properties, crystalline states, material forms, and material structures that can exist in multiple states, such as soil, concrete structures, ceramic structures, metals containing alloys, or metal structures containing alloys that have undergone alteration-related processing. Examples of materials for which definitive classification is not possible include: in the case of soil, differences due to regional formation as well as differences due to human-induced changes such as agricultural work; in the case of concrete structures, differences due to the origin of the concrete, moisture content, type of reinforcing steel, etc.; in the case of ceramic structures, differences due to the origin of the raw materials for sintered ceramic structures; and in the case of metals, differences due to changes in the state of alloying elements, crystalline states, transformations, alloying, grain refinement or enlargement, etc., resulting from nitriding, carbonization, plasma, ion, or heat treatment and processing.

[0024] For example, when the object of analysis is soil, it is possible to utilize known data such as soil inventories (non-patent literature) or classify the data using unsupervised learning analyses such as clustering and principal component analysis, but a high correlation is not always obtained. The classification is performed in a way that allows for accurate estimation of the first objective variable. For example, when analyzing the welding strength of spot welds made by spot welding two identical metals, if the metal material is a mixture of iron and aluminum, classifying the measurement data into iron and aluminum, and then estimating the welding strength of the spot welds between irons using the first objective variable, makes correlation easier, and it becomes possible to estimate a correlation of 0.9 or higher.

[0025] For example, if the entire training data used to estimate the first target variable is analyzed by AI, the estimation will not be accurate, resulting in an estimated function with a low correlation function. The results obtained here are then classified based on their degree of deviation from the estimated function. The degree of deviation can be classified using, for example, the standard deviation σ, with values ​​of 1x and 3x of the standard deviation σ. This allows for classification into groups such as those with results more than -3x (-3σ or less), those between -3x and -1x (-3σ to -σ), those between -1x and +1x (-σ to +σ), those between +1x and +3x (+σ to +3σ), and those more than +3x (+3σ). However, care must be taken to ensure that the number of measurement data points for each group is not too small compared to the training data. Furthermore, based on the results of analysis using these group classification methods, the threshold values ​​of 1x and 3x above may be reviewed and adjusted so that the correlation of the data in each group is appropriate.

[0026] The above example is just one illustration; while clear classification is possible in learning, in actual measurements, there are cases where classification is not easily determined, and using known classifications can lead to highly accurate analysis.

[0027] The primary objective of classification is to prepare multiple estimation functions for the first target variable and select the appropriate one from the same data. Therefore, classification only needs to be able to create groups that can be trained to produce multiple estimation formulas, each of which yields a high correlation. Furthermore, it would be beneficial if the estimation of the second target variable—which category each group belongs to—could be analyzed using the same measurement data.

[0028] (Analytical device for implementing AI analysis methods) Figure 2 shows the configuration of one embodiment of an analytical apparatus for implementing the AI ​​analysis method according to the present invention. As shown in Figure 2, the analytical apparatus 1 consists of a sensor 10, a measurement unit 20, and a data processing unit 30.

[0029] The sensor 10 comprises an excitation coil 11 and a detection coil 12 as coils, and a magnetic path forming section 13. The sensor 10 is housed in, for example, a metal sensor holder 14 to block external magnetic fields, and the sample 15 to be measured is placed in the measurement section of the sensor holder 14. The sample 15 may be housed in a container and placed in the measurement section of the sensor holder 14. Alternatively, measurement is performed by directly placing the sample 15 to be measured in the measurement section. The sensor 10 is supported, for example, by a non-magnetic gap filler (not shown) within the sensor holder 14.

[0030] The magnetic path forming section 13 consists of, for example, a bottom section 13a, a cylindrical section 13b, and a shaft section 13c, with the bottom section 13a supporting the cylindrical section 13b and the shaft section 13c. An excitation coil 11 and a detection coil 12 are mounted on the shaft section 13c. Since the sensor 10 has the detection coil 12 and the sample 15 positioned in the magnetic path formed by the excitation coil 11 and the magnetic path forming section 13, the signal detected by the detection coil 12 can be influenced according to the permeability of the sample 15 to be analyzed. The sensor 10 described above is just one example of a configuration, and other configurations with similar functions may also exist; for example, the excitation coil 11 and the detection coil 12 may be composed of a single coil.

[0031] The measurement unit 20 comprises an oscillation unit 21, a signal processing unit 22, and a control unit 23. The oscillation unit 21 repeatedly generates a signal of a certain frequency and increases or decreases the frequency of the signal in steps. The signal oscillated from the oscillation unit 21 is split into an excitation signal and a reference signal. The excitation signal is transmitted to the excitation coil 11 and output to the signal processing unit 22 as a reference signal. The signal processing unit 22 calculates the temporal change of the detection signal from the detection coil 12 relative to the excitation signal using the reference signal from the oscillation unit 21. At this time, the signal processing unit 22 has a Fourier transform function and converts the time-axis signal into a frequency-axis signal. The signal processing unit 22 also digitizes the detection signal from the sensor 10 and outputs it to the data processing unit 30. The control unit 23 inputs and outputs data and various control signals to and from the data processing unit 30 and controls the oscillation unit 21 and the signal processing unit 22.

[0032] In this case, the data processing unit 30 estimates the target variable for analysis from the digital data of the detection signal processed by the signal processing unit 22. In the following explanation, the target of analysis will be soil, the target variable will be soil fertility traits, and the estimation of CEC will be performed as an example of soil fertility traits. The data processing unit 30 is a computer comprising an input / output interface unit 31 that interfaces with the control unit 23, a storage device 32 equipped with a main memory and an auxiliary storage device, an arithmetic unit that performs calculations such as arithmetic operations, and a control device that controls the storage device and the arithmetic unit. The data processing program is stored in the auxiliary storage device, and when the data processing program is deployed to the arithmetic unit and executed, the data processing unit 30 functionally provides the storage unit 33 and estimation unit 34 shown in Figure 2.

[0033] The memory unit 33 stores data relating to the correlation between the quantitative value of the target variable and the estimated value of the target variable obtained from the processed detection signal measured using the sensor 10 and the measurement unit 20, with respect to the object of analysis. The estimation unit 34 applies an alternating magnetic field to the object of analysis using the sensor 10 and estimates the CEC of the object of analysis using the data stored in the memory unit 33, based on the detection signal processed using the measurement unit 20.

[0034] In the estimation unit 34, the quantitative value of the target variable to be analyzed, which has been determined in advance, can be used to analyze the target variable according to the following analytical method. Figure 3 is an explanatory diagram showing an example of the analytical method of the present invention, using soil CEC analysis as an example.

[0035] As shown in Figure 3, the analysis is performed as follows. (Step ST1: Preparation of learning samples) In step ST1, a learning sample 41 is prepared that corresponds to the final sample 47 to be analyzed. The learning sample 41 may be part or all of the sample 47 to be analyzed. One soil or multiple soils with different compositions are prepared. If necessary, the soil to be analyzed may be air-dried and then crushed using a mortar and pestle, and the resulting air-dried crushed soil may be used as the soil sample.

[0036] In step ST1, the learning sample 41 is an object measured by the sensor 10, and examples include soil, metal members joined by spot welding, and metals such as reinforcing bars in concrete. If the learning sample 41 is soil, the target variable may be soil fertility characteristics such as CEC (cation exchange capacity).

[0037] Furthermore, the learning sample 41 can be used not only to estimate CEC but also to estimate other soil fertility traits. These other soil fertility traits include AEC, total carbon (TC), total nitrogen (TN), available phosphorus (Av-P), total phosphorus (P), iron (Fe), aluminum (Al), and important elements for plant nutrition such as K (potassium), Ca (calcium), and Mg (magnesium). While these other soil fertility traits can also be estimated using the analytical method described in Example 4 of Patent Document 2 (Patent Document 2, paragraphs 0083-0086 and 0087-0094), if the soil deviates from a specific type, or if soil classification is required, the classification estimation method of this invention must be applied.

[0038] (Step ST2: Training data and Step ST3: Comparison data) In step ST2, the training sample 41 to be analyzed is measured with the sensor 10 to obtain training data 42, i.e., training measurement data. At this time, the sensor 10 may be placed in close proximity to the soil that will be the training sample 41, or the sensor 10 may be placed in close proximity to the air-dried pulverized soil described above. Then, in step ST3, for each soil sample 41, the quantitative value of CEC, which will be comparative data 43, is determined using, for example, the known Schorenberger method. Thus, in step ST2, training data 42 and comparison data 43 necessary for AI learning and estimation are obtained in order to obtain the estimation function 45 for obtaining the first target variable in step ST4. The training data 42 and comparison data 43 are linked to characteristic information such as field location and academic soil classification results related to soil classification and stored in the database of the memory unit 33.

[0039] Here, the actual classification of soil depends on the soil condition at the time of measurement, making the evaluation of that condition difficult. As shown in Non-Patent Literature 1, it is possible to use the results of several academic classifications, but the challenges are that they do not cover all fields and land, and do not necessarily match the condition of the soil being measured at the time of measurement. In particular, soil components, structure, and composition such as CEC can be used as a guideline in agricultural land because the soil condition changes due to agricultural work, but they may be insufficient as a classification for estimation in AI analysis. Therefore, it is necessary to understand the classification of each soil from its current state, and AI analysis using measurement data is performed.

[0040] (Steps ST4 and ST6 (AI pre-training)) AI analysis is performed using comparison data 43, which are quantitative values ​​of soil samples obtained in steps ST2 and ST3 and stored in the memory unit 33, to create a first estimation function 45 for obtaining the first target variable. A second estimation function 46 for obtaining the second classification target variable is created for each item of the classification data 44. Step ST3 is also called pre-training. The results are stored in the memory unit 33. For the classification data 44, which is the second dependent variable, if the analysis results from the first estimation function 45 do not yield good agreement, such as a correlation coefficient of 0.7 or less, the data that is particularly difficult to agree with will be separated and classified using the method described later in order to improve the overall results. The AI ​​analysis in steps ST4 and ST5, which obtains the first and second target variables, is performed using one of the following analysis methods: unsupervised AI analysis methods such as clustering and principal component analysis, or supervised AI analysis methods such as linear analysis, SVM (Support Vector Machine), PLS regression analysis, and neural networks. The methods used in step ST4 to obtain the first estimation function 45 and step ST5 to obtain the second estimation function 46 may be the same or different. After obtaining the first estimation function 45 through AI learning in step ST4, the process may proceed to step ST7 to determine whether the verification result of the first estimation function 45 is appropriate or not. If the verification result is not appropriate (NO), the process returns to step ST5 to prepare for classification. If the verification result is appropriate (YES), the process proceeds to the actual evaluation (step ST8) as described later. Here, as a method for obtaining a second estimation function 46, clustering is a commonly used classification method. However, depending on the classification data 44, clustering may be inappropriate if it contains strong features, and in such cases, deep learning methods such as neural networks, which are supervised AI analysis methods, may be effective. The classification in Step ST6 may also be performed using academic classification or human judgment, without employing AI analysis methods.

[0041] If a second estimation function 46 and the classifications based thereon are defined, a first estimation function 45 for analysis and evaluation is defined for each classification defined as classification data 44 in step ST5.

[0042] With the above configuration, by utilizing these analytical methods, a classification evaluation function can be easily and accurately created based on the measurement data.

[0043] (Actual evaluation from Step ST8) Next, we move on to the actual evaluation process. An actual sample 47 to be analyzed, whose CEC and soil classification-related characteristics are unknown, is prepared in the same way as the soil sample in step ST1, and evaluation data 48 consisting of complex amplitude and phase within a predetermined frequency range is acquired by the sensor 10. Specifically, the evaluation data 48 is obtained by generating an alternating magnetic flux by applying an alternating current to the excitation coil 11, and detecting the disturbed magnetic flux depending on the state of the analysis target using the detection coil 12. In this case, multiple excitation signals of different frequencies may be applied to the excitation coil 11. The excitation signals may have a frequency band of about 5 to 100 times from the lowest frequency to the highest frequency. Furthermore, the excitation signals may have five or more different frequencies and be one or more greater than the sum of the number of analyses and the number of classifications.

[0044] After defining the classification data 44 and the first estimation function 45 for each classification in this manner, as described later, from step ST8, evaluation data 48 is measured for the analyte sample 47, a classification determination is made using the second estimation function 46, the corresponding classification is selected in step ST11, and the analysis result 50 is obtained from the evaluation data 48 in step ST14 using the first estimation function 45 corresponding to the selected classification, and the evaluation result is finalized in step ST16.

[0045] (Step ST10: Consider the necessity of classification) In this case, if it is clear that the sample to be analyzed 47 belongs to a specific classification, for example, if the first estimation function 45 can be identified for the evaluation data 48, then classification by calculation of the second estimation function 46 is unnecessary, and the process can proceed from step ST12 to step ST13, and in step ST14, the CEC of the soil that will result in the desired analysis result 50 may be estimated.

[0046] (Step ST11: Performing classification) In step ST11, estimation is performed using a second estimation function 46 to select the estimation function to be used from among the first estimation functions 45 created for each classification of the evaluation data 48. Based on the calculation results using the second estimation function 46, it is determined which classification of the classification data 44 the evaluation data 48 corresponds to, and the first estimation function 45 is selected.

[0047] (Step ST13: Consider the necessity of analysis) After the classification in step ST11, you choose whether or not to estimate the soil's CEC. If you only want to perform classification without analysis, for example, to determine which classification the soil belongs to for crop selection in the target soil, you can proceed to step ST16 via step ST15, confirm the classification result 49 obtained in step ST11, and finish.

[0048] (Step ST14 Analysis) In step ST14, when obtaining the analysis result 50 of the sample 47 to be analyzed, that is, when estimating the CEC of the soil, in step ST11, the soil is classified using the evaluation data 48 and a second estimation function 46 for the objective variable for the second classification. Based on the obtained classification result 49, a first estimation function 45 for the first objective variable, created in step ST4, is selected for each classification defined in the classification data 44. The CEC of the soil, which will be the analysis result 50, is estimated using the evaluation data 48, and in step ST16, the soil classification and the estimated CEC value are finalized and the process is completed.

[0049] (Step ST16) This completes the soil classification and CEC analysis estimation. However, if the results indicate that the estimated values ​​are inappropriate, the process will be restarted from step ST3 for retraining, the classification will be redone in steps ST5 and ST6, and the analysis will be redone in steps ST11 and ST14. If necessary, the method for acquiring training data in step ST2 will also be reviewed.

[0050] (Measurement method using electromagnetic measurement) The following provides a detailed explanation of how to obtain training data 42 and measurement data 48, as well as soil classification and analytical estimation, when the target of analysis is soil and measurements are taken using the electromagnetic measurement method shown in Figure 2, with CEC and other quantitative values ​​of soil fertility traits as the objective variables.

[0051] In the soil analysis device 1, a learning sample 41 is placed in the measurement section of the sensor holding unit 14 as a soil sample 15. Under the control of the control unit 23, the oscillation unit 21 oscillates signals at each frequency, increasing the frequency stepwise at arbitrary intervals (e.g., several kHz to several hundred kHz) within a specified frequency range (e.g., several kHz to several hundred kHz), and outputs them to the excitation coil 11. The signal detected by the detection coil 12 is processed by the signal processing unit 22, converted into a digital signal, and output to the data processing unit 30. In the estimation unit 34, the processed detection signal output from the signal processing unit 22 is stored in the storage unit 33. This value becomes the learning data 42.

[0052] The frequency range of the AC generated by the oscillator 21 can be, for example, 1Hz to 80Hz, 50Hz to 5kHz, 500Hz to 2.5kHz, or 1kHz to 100kHz. In other words, the frequency band of the AC can be approximately 5 to 100 times from the lowest frequency to the highest frequency. Alternatively, the AC frequencies can be set to be 5 or more distinct frequencies, and to be at least 1 greater than the sum of the number of analyses and the number of classifications.

[0053] A portion of the soil sample, which is the learning sample 41, is taken and analyzed using a known quantitative analysis method such as the Schorenberger method, as shown below, and the resulting value is used as comparison data 43. In addition to CEC, an example of a method for measuring quantitative values ​​of various soil fertility traits is: CEC, potassium, magnesium, calcium, etc. (e.g., Schörenberger method) Total carbon (TC): Combustion methods using a C / N coder, etc. Total Nitrogen (TN): Combustion methods using a C / N coder, etc. Available phosphate (Av-P): Truog method, etc. Potassium, magnesium, calcium, iron, manganese, zinc, copper, molybdenum, boron, chlorine, nickel: Elemental analysis equipment such as X-ray fluorescence analysis is available. In this case, if a quantitative analysis method is available for the analysis target, a supervised learning method can be used as the AI ​​analysis method. If quantitative analysis is not possible for the analysis target, an unsupervised learning AI analysis method can be used without using the comparison data 43. It is also possible to perform supervised learning using qualitative analysis including ambiguity or images as the comparison data 43.

[0054] In the estimation unit 34, pre-training (step ST4) is performed using AI analysis with training data 42 as the explanatory function and comparison data 43 as the target variable. AI analysis means that one of the following analysis methods is used: supervised AI analysis methods such as linear analysis, SVM, PLS regression analysis, neural networks, etc., or unsupervised AI analysis methods such as clustering analysis, principal component analysis, etc., if comparison data 43 cannot be prepared. This is executed by the estimation unit 34 using a program stored in the storage device 32 in the data processing unit 30. When the comparison data 43 consists of quantitative values ​​of each soil fertility trait, including CEC, the first estimation function 45 is obtained by AI analysis.

[0055] In electromagnetic measurement methods and other measurement techniques, the results are affected by the material and structure of the object being measured, and, if multiple materials are mixed or combined, by their ratios and distribution. Therefore, it is necessary to change the measurement conditions and the estimation function depending on the object being measured. In the case of soil, the first estimation function 45 cannot be uniquely determined due to the influence of soil type and soil improvement by agricultural work. Therefore, it is necessary to create a first estimation function 45 for each by dividing the above learning into classifications that group the objects being measured. These grouped classifications become the classification data 44.

[0056] In this case, as classification data 44, there is the "Soil Classification" (see Non-Patent Document 1) from the National Agriculture and Food Research Organization's Japan Soil Inventory, which is an academic classification for soils and can be used as a reference. However, since farms managing each field may be implementing soil improvement measures, it is difficult to classify appropriately using only the above classification. Furthermore, soil classification requires work such as deep soil sampling and analysis of its cross-sectional condition, making soil analysis not easy.

[0057] Therefore, with soil classification as the second target variable, in order to obtain a second estimation function 46, AI learning (step ST6) is also performed on soil classification estimation using the training data 42 described above. Both analysis and classification can be performed from the same training data 42.

[0058] For soil classification, referencing the aforementioned academic soil classifications, a first estimation function 45 is created for each classification defined in the classification data 44, and the analysis is performed. If the results are insufficient, particularly for mismatched data, reclassification is performed, referring to the value of the standard deviation σ, and the analysis estimates created for each classification are selected to yield desirable results. The classification here may deviate from academic classifications, but it is used as a classification that reflects the actual situation. Furthermore, if academic classifications are not available, unsupervised learning methods such as clustering analysis and principal component analysis can be used. In this case, as will be discussed later, it is important to note that appropriate classification may not be possible due to the influence of other factors. The determined classification is used as the classification data 44, which is the target variable, and the training data 42 is used as the explanatory variable to perform AI learning. The resulting estimation function becomes the second estimation function 46 for the classification, which is the second target variable.

[0059] Next, in the actual measurement, the soil sample 47, which is the sample to be analyzed, is prepared in step ST9. Specifically, similar to step ST2, the sample 15 is placed on the measurement unit of the sensor holding unit 14, or the sensor 10 is brought into direct contact with the soil sample 15 in a field, and under the same conditions as during learning, the control unit 23 controls the oscillation unit 21 to oscillate signals at each frequency, gradually increasing the frequency within a specified frequency range (e.g., several kHz to several hundred kHz) and at interval frequencies (e.g., several kHz), and outputting these signals to the excitation coil 11. For each frequency signal, the signal detected by the detection coil 12 is processed by the signal processing unit 22, converted into a digital signal, and output to the data processing unit 30. In the estimation unit 34, the processed detection signal output from the signal processing unit 22 is stored in the storage unit 33. This value becomes the evaluation data 48.

[0060] The obtained evaluation data 48 is used to select a classification using the second estimation function 46 obtained in pre-training, and the analysis is estimated using the first estimation function 45 based on the classification result 49. As a result, in step ST16, the classification result 49 and analysis result 50 of the analyte sample 47 are obtained.

[0061] Furthermore, as the amount of measurement data increases, the accuracy of analysis and evaluation can be improved by increasing the amount of data used for AI training while sampling, and then re-evaluating the results.

[0062] An example of soil analysis is described. Here, for the purpose of verification, the sample to be analyzed 47 is used as the training sample 41, and the training data 42, which has comparison data 43, is used as the evaluation data 48. The correlation is examined based on the results of recalculation using the first estimation function 45 and the second estimation function 46 obtained after training.

[0063] In this analysis example, soil samples were collected from five fields: A, G, S1, S2, N1, and N2. The soil samples used are classified as four types according to the academic soil classification in Patent Document 1: gravelly ordinary brown lowland soil (A), humus sublayer lowland allophanic black soil (G), typical ordinary humid black soil (S1, S2), and gravelly ordinary allophanic black soil (N1, N2), with the fields in parentheses corresponding to each type.

[0064] Each soil sample (training sample 41) is analyzed and evaluated using the soil analyzer 1. First, the soil sample is irradiated with a magnetic field, for example, varying the frequency from 10 kHz to 200 kHz in 1.5 kHz increments. The transmitted magnetic field is then passed through the detection coil 12 of the soil analyzer 1, and the detection signal is measured by the signal processing unit 22. The real and imaginary parts of the detection signal are used as training data 42. The same training sample 41 is also subjected to CEC analysis using the Schorenberger method, and the results are used as comparison data 43. Using this training data 42 and comparison data 43, a neural network is implemented as an AI analysis method.

[0065] (Comparative Example 1) For reference, we performed CEC estimation using a neural network from all measurement data without classification. Figure 4 shows the relationship between the estimated and quantitative values ​​of CEC for Comparative Example 1. The horizontal axis of Figure 4 represents the estimated value (meq / 100g) obtained from the first estimation function 45 of CEC, and the vertical axis of Figure 4 represents the quantitative value (meq / 100g) of CEC for the comparison data 44. The squares (■), black circles (●), and triangles (△) in the figure represent the classification categories AZ, SN, and S, respectively. As shown in Figure 4, the correlation between the estimated and quantitative values ​​of CEC for 455 subjects was 0.71. At this time, it was 0.66 for the lower 95% and 0.75 for the upper 95%, and the p-value was less than 0.0001. Although there is a certain degree of correlation, improvement will be made by classification.

[0066] In the results, the estimated results were examined based on their deviation from the comparison data 44, and selections were made on a field-by-field basis. For this data, it was appropriate to classify the fields into three categories: Fields A and G, and Fields S1, S2, N1, and N2.

[0067] (Example 1) In Example 1, AI learning was performed using a neural network with CEC estimation as the first objective variable for each of the three classifications, and a first estimation function 45 corresponding to each classification was obtained. Figure 5 shows the relationship between the estimated value and the quantitative value of CEC in Example 1. The horizontal axis of Figure 5 is the estimated value (meq / 100g) obtained from the first estimation function 45 of CEC, and the vertical axis is the quantitative value of CEC (meq / 100g) for the comparison data 44. The square marks (■), black circles (●), and triangle marks (△) in the figure represent the classification categories AZ, SN, and S, respectively. As shown in Figure 5, the correlation between the estimated value and the quantitative value of CEC was 0.92 for 455 subjects. At this time, it was 0.90 for the lower 95%, 0.93 for the upper 95%, and the p-value was 0.0001 or less. In Example 1, the correlation improved from 0.71 in Comparative Example 1 to 0.92 by applying the classification.

[0068] (Example 2) In Example 2, AI learning was performed using a neural network with the three groups as the target variables and the training data 42 as the explanatory variables for these three classifications, creating a second estimation function 46, which is a second target variable for classification. Using this second estimation function 46, evaluation estimation of the training data 42 was performed in place of the actual evaluation data 48, and the training data 42 was reclassified. This reclassification reclassifies the data into closer groups. Based on this reclassification result, AI learning was performed for each classification to obtain a first estimation function 45 for the first CEC analysis. CEC estimation was performed using the reclassification result and the respective first estimation functions 45. Figure 6 shows the relationship between the estimated value and the quantitative value of CEC in Example 2. The horizontal axis of Figure 6 is the estimated value of CEC (meq / 100g), and the vertical axis is the quantitative value of CEC (meq / 100g). The squares (■), black circles (●), and triangles (△) in the figure represent the classification categories AZ, SN, and S, respectively. As shown in Figure 6, the correlation between the estimated and quantitative values ​​of CEC was 0.98 for 455 subjects. At this time, the correlation was 0.97 for the lower 95% and 0.98 for the upper 95%, with a p-value of 0.0001 or less.

[0069] Thus, it can be seen that the correlation was 0.72 when the analysis and evaluation was performed without classification in Comparative Example 1, 0.92 in Example 1 when classification was performed, and improved to 0.98 in Example 2 when reclassification was performed using AI-based classification estimation.

[0070] In other words, by using AI-based reclassification estimation, we were able to perform CEC estimation with an even higher correlation.

[0071] (Comparative Example 2) In AI learning and analysis, clustering is sometimes used for analysis, and this was compared as Comparative Example 2. Clustering analysis groups similar data together. Common methods include hierarchical clustering and k-means. Figure 7 shows an example where the results of grouping using the k-means method were used as the second estimation function 46 for subsequent analysis. The horizontal axis shows the distribution of the data in an exaggerated state by the real and imaginary parts, which are parameters of the measured data. The k-means method allows for grouping similar data based on the characteristics of the data (1, 2, 3 in Figure 7). Even if the grouping shown in Figure 7 is used as the classification result, and the first estimation function 45 from step ST3 onwards is created for each classification using the same training data 42, and the classification analysis from step ST8 onwards is performed using the same training data 42 as evaluation data 48, the estimated value of the CEC in the analysis result 50 will be the coefficient of determination R as the validation value for the above groups 1, 2, and 3. 2 The values ​​were 0.36, 0.70, and 0.48, respectively. These values ​​indicate that the accuracy of the estimates is significantly worse compared to the correlation coefficients of Examples 1 and 2 above. This differs from the results obtained using the academic soil classification-based classification used in Examples 1 and 2, and is therefore due to some feature included in the measurement data, which does not match the purpose of this study. This is because the classification results differed from the classification based on the actual object of analysis, and, as in Comparative Example 2, this is an example where caution is needed in unsupervised learning.

[0072] The present invention can be implemented in various forms without departing from its spirit. For example, in the embodiments described above, the acquisition of the second estimation function 46 for the definition of classification and the acquisition of the first estimation function 45 for the inference of CEC are both performed using neural analysis. However, it is clear that the invention is not limited to this, and other analytical methods, such as linear analysis, SVM (Support Vector Machine), PLS regression analysis, supervised AI analysis methods, and unsupervised AI analysis methods, may also be used to perform the definitions.

[0073] Furthermore, while the above-described embodiment explained the case of estimating CEC among soil kinetic traits, it is clear that the method is not limited to this and can also be applied to the estimation of other soil kinetic traits, or to AI analysis of welding strength of spot welds, concrete structures with reinforcing bars, etc.

[0074] Furthermore, the system may learn using soil taxonomy classifications as classification criteria for soil analysis targets, and then perform classification using the re-estimation results based on those learning outcomes.

[0075] In the embodiment described above, the measurement data was acquired solely by electromagnetic measurement using a detection coil 12 that utilizes multiple frequency bands. However, it may also be acquired by acoustic measurement such as ultrasound, or by optical measurement using light. [Explanation of Symbols]

[0076] 1. Soil analysis device 10 sensors 11 Excitation coil 12 detection coils 13 Magnetic path forming part 14 Sensor holding part 15 samples 20 Measurement section 21 Oscillator 22 Signal Processing Unit 23 Control Unit 30 Data Processing Unit 31 Input / Output Interface Section 32 Storage device 33 Storage section 34 Estimation part 41. Samples for learning 42 Training Data 43. Comparative Data 44 Classification Data 45. First Estimation Function (Analysis) 46. ​​Second estimation function (classification) 47. Samples to be analyzed 48 Evaluation data 49 Classification results 50 Analysis results

Claims

1. In an AI analysis method that estimates a first objective variable related to features included in the object of analysis by obtaining measurement data from the object of analysis and obtaining a first estimation function using the measurement data as explanatory variables, The object of analysis is any of the following: soil, concrete structure, ceramic structure, metal including alloys, and metal structure including alloys that has undergone processing involving alteration, wherein the material, material properties, crystalline state, material morphology, and material structure exhibit multiple states. If the correlation between the estimated value of the first estimation function and the quantitative value of the first dependent variable is 0.7 or less and cannot be uniquely determined, The system is configured to classify the aforementioned measurement data into multiple target variables using a second estimation function, and to obtain multiple first estimation functions for each classification. In the first step, In order to select the first estimation function to be used from among the multiple first estimation functions created for each classification, the second objective variable is estimated by classifying the second estimation function using the measurement data, and the first estimation function to be used is selected. In the second step, An AI analysis method that uses measurement data related to the first estimation function selected in the first step as explanatory variables, and estimates the first target variable using the first estimation function.

2. The AI ​​analysis method according to Claim 1, wherein the evaluation data that serves as the explanatory variables are used as training data, the first objective variable or the second objective variable is obtained as a quantitative value of the training data and used as comparison data, and AI analysis is performed.

3. Using the evaluation data, classification is performed using a second estimation function, and based on the obtained classification results, a first estimation function for the first target variable defined for each classification in the classification data is selected. Using the evaluation data, the first target variable is estimated using the first estimation function. The AI ​​analysis method according to claim 2, which determines the classification of the object to be analyzed and the estimated value of the first objective variable.

4. The AI ​​analysis method according to claim 1, wherein, in order to create a plurality of classified first estimation functions, the entire measurement data is analyzed and estimated using the same analysis method, and a plurality of classifications are created by classifying the estimated values ​​according to the degree of deviation from the training data.

5. The AI ​​analysis method according to claim 1, wherein a plurality of first estimation functions are created by classification using the similarity of the measurement data.

6. The AI ​​analysis method according to claim 1, wherein a second estimation function corresponding to the selection of the above classification is obtained by any of the following analysis methods: linear analysis, PLS regression analysis, SVM (Support Vector Machine), neural network, or supervised AI analysis method.

7. The AI ​​analysis method according to claim 1, wherein a plurality of first estimation functions corresponding to the objective variable are obtained by any of the following analysis methods: clustering, principal component analysis, unsupervised AI analysis method, linear analysis, PLS regression analysis, SVM (Support Vector Machine), neural network, or supervised AI analysis method.

8. The AI ​​analysis method according to any one of claims 1 to 7, wherein the measurement data is acquired by electromagnetic measurement, acoustic measurement, or optical measurement using multiple frequency bands.

9. An AI analysis method according to any one of claims 1 to 8, wherein the first objective variable is to obtain an estimated value of soil fertility characteristics, which include soil agricultural indicators such as cation exchange capacity (CEC), base saturation, silicic acid, iron oxide, and nutrients such as potassium, magnesium, calcium, iron, manganese, zinc, copper, molybdenum, boron, chlorine, nickel, nitrogen, carbon, and phosphorus.

10. The AI ​​analysis method according to any one of claims 1 to 9, wherein the measurement data is used to generate an alternating magnetic flux by applying a plurality of excitation signals of different frequencies to an excitation coil, and the magnetic flux that is disturbed by the state of the object to be analyzed is detected using a detection coil.

11. The AI ​​analysis method according to claim 10, wherein the excitation signal has a frequency bandwidth of approximately 5 to 100 times from the lowest frequency to the highest frequency.

12. The AI ​​analysis method according to claim 10, wherein the excitation signals have five or more distinct frequencies and are one or more greater than the sum of the number of analyses to be performed and the number of classifications.

13. An AI analysis method according to any one of claims 1 to 12, wherein when the total number of each of the one or more items to be analyzed is evaluated using the same evaluation function, the standard deviation is used to classify the items into categories such as -3σ or less, -3σ to -1σ, ±1σ, 1σ to 3σ, and 3σ or more, based on the degree of deviation from the correlation.

14. An AI analysis device that analyzes any of the following, where the material, composition, crystalline state, material form, or material structure exhibits multiple states: soil, concrete structure, ceramic structure, metal including alloys, and metal structure including alloys that have undergone processing involving alteration; and in order to analyze a first objective variable relating to the features contained in the analysis object, measurement data is obtained from the analysis object, and the measurement data is used as explanatory variables to obtain a first estimation function of the first objective variable, thereby estimating the first objective variable, A sensor having a coil, A measurement unit that generates excitation signals for each frequency to be input to the coil in order to apply an alternating magnetic field to the object to be analyzed, and processes the detection signal output from the coil using the generated excitation signals, A storage unit that stores data relating to the correlation between the quantitative value of the target variable of each analysis target and the sensor and the measurement unit, for multiple analysis targets, An estimation unit estimates the target variable of the analysis target using the data stored in the storage unit based on the detection signal processed by the measurement unit, It is equipped with, The estimation unit obtains the complex amplitude ratio of the detection signal to the excitation signal as measurement data from the detection signal, defines multiple classifications from the quantitative values ​​of multiple different target variables stored in the storage unit and the corresponding complex amplitude ratios of the detection signals as comparison data, and defines a first estimation function for each classification. An AI analysis device in which the estimation unit selects a classification corresponding to each measurement data using a second estimation function, and estimates the first target variable of the analysis target from the measurement data using a first estimation function corresponding to the selected classification.

15. A program that causes a computer to function as the AI ​​analysis device described in claim 14.

Images