Machine learning system and machine learning method

Abstract

The invention relates to a machine learning system and a machine learning method. A machine learning system includes a display device and a learning device. A learning device causes a variable selection unit in a learning execution screen of a display device to display a result of extracting an interpretation variable candidate and a target variable candidate from a target file specified by a user. The learning device displays, on a result display unit in a learning execution screen, a result obtained by analyzing, by machine learning, the relationship between an explanatory variable and a target variable selected by a user from among the explanatory variable candidates and the target variable candidates displayed on the variable selection unit.

Description

Technical Field

[0001] The present disclosure relates to a machine learning system and a machine learning method. Background Art

[0002] For example, in Japanese Unexamined Patent Application Publication No. 2023-34011, a technique for optimizing control parameters in a battery manufacturing process using machine learning is described. Summary of the Invention

[0003] Generally, in machine learning, a predetermined algorithm is used to learn the relationship between explanatory variables (inputs) and target variables (outputs). Conventionally, in order to perform machine learning, complex coding and specialized knowledge are required, which are not user-friendly.

[0004] The present disclosure has been made to solve the above problems, and an object thereof is to enable machine learning to be performed by simple operations.

[0005] (Item 1) The machine learning system of the present disclosure includes a display device and a learning device connected to the display device. The learning device causes the display device to display the result of extracting explanatory variable candidates and target variable candidates from an object file specified by a user, and causes the display device to display the result obtained by analyzing the relationship between the explanatory variables and target variables selected by the user from the explanatory variable candidates and target variable candidates displayed on the display device by machine learning.

[0006] (Item 2) In the machine learning system according to Item 1, the learning device generates a plurality of prediction models for predicting a target variable from explanatory variables respectively by performing machine learning on the explanatory variables and target variables selected by the user according to a plurality of algorithms, calculates the coefficient of determination of each of the generated plurality of prediction models, and causes the display device to display the prediction model with the highest coefficient of determination as the best model.

[0007] (Item 3) In the machine learning system according to Item 2, the learning device causes the display device to display a plurality of algorithms, and causes the display device to display information on the best model or information on a selection model, which is a prediction model according to an algorithm selected by the user from the plurality of algorithms displayed on the display device.

[0008] (Item 4) In the machine learning system according to Item 3, the learning device obtains an explanatory variable input by the user, and causes the display device to display the result obtained by calculating the target variable corresponding to the explanatory variable input by the user using the best model or the selection model.

[0009] (Item 5) In the machine learning system according to any one of Items 1 to 4, the learning device obtains the division ratio of the training data and the test data requested by the user, and causes the display device to display the result obtained by performing machine learning by dividing the data included in the object file into the training data and the test data according to the obtained division ratio.

[0010] (Item 6)In the machine learning system according to any one of Items 1 to 4, the explanatory variable is a variable related to the material of the battery, and the objective variable is a variable related to the characteristics of the battery.

[0011] (Item 7)The machine learning method of the present disclosure includes a step of causing the display device to display the result of extracting explanatory variable candidates and objective variable candidates from an object file specified by the user, and a step of causing the display device to display the result obtained by analyzing the relationship between the explanatory variables and the objective variables selected by the user from the explanatory variable candidates and the objective variable candidates displayed on the display device by machine learning.

[0012] The above and other objects, features, aspects, and advantages of the present invention will become apparent from the following detailed description of the present invention understood in association with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 is a diagram schematically showing the overall structure of the machine learning system.

[0014] Figure 2 is a diagram schematically showing an example of a learning execution screen displayed on the display device.

[0015] Figure 3 is a diagram schematically showing an example of a learning effective utilization screen displayed on the display device.

[0016] Figure 4 is a flowchart showing an outline of the processing order executed by the learning device in the learning stage.

[0017] Figure 5 is a flowchart showing an outline of the processing order executed by the learning device in the effective utilization stage. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] With reference to the accompanying drawings, embodiments of the present disclosure will be described in detail. In addition, the same or corresponding parts in the drawings are denoted by the same reference numerals, and their description will not be repeated.

[0019] [System Structure]

[0020] Figure 1 is a diagram schematically showing the overall structure of the machine learning system 1 of the present embodiment.

[0021] The machine learning system 1 is equipped with a display device 2, a keyboard 3, a mouse 4, a removable disk 5, and a learning device 6.

[0022] The learning device 6 is a device for performing machine learning. The learning device 6 includes an auxiliary device 10 and an analysis device 60. The analysis device 60 is a device that actually performs machine learning and analyzes the learning results. The auxiliary device 10 is a device for assisting the utilization of machine learning implemented by the analysis device 60.

[0023] As the main hardware elements, the auxiliary device 10 includes an arithmetic unit 11, a storage unit 12, a display interface 15, a peripheral device interface 16, a reading unit 17, and a communication unit 18. In addition, the auxiliary device 10 can be implemented, for example, by a general-purpose computer or a dedicated computer for machine learning assistance.

[0024] The arithmetic unit 11 is an arithmetic circuit (arithmetic device) that executes various processes by executing various programs and is an example of a computer. The arithmetic unit 11 is constituted by, for example, a CPU (Central Processing Unit). All or part of the functions of the arithmetic unit 11 can also be provided in a server device (for example, a cloud-type server device) not shown.

[0025] The storage unit 12 stores program codes, working memories, etc. when the arithmetic unit 11 executes any program. The storage unit 12 stores learning data 13 used in the machine learning of the analysis device 60. In addition, the learning data 13 includes multiple combinations of explanatory variables and target variables.

[0026] The display interface 15 is an interface for connecting the display device 2 and realizes the input / output of data between the auxiliary device 10 and the display device 2.

[0027] The peripheral device interface 16 is an interface for connecting peripheral devices such as the keyboard 3 and the mouse 4 and realizes the input / output of data between the auxiliary device 10 and the peripheral devices.

[0028] The reading unit 17 reads out various data stored in the removable disk 5 as a storage medium. The learning data 13 is read out from the removable disk 5 by the reading unit 17 and stored in the storage unit 12, for example.

[0029] The communication unit 18 transmits and receives data to and from the analysis device 60 via wired communication or wireless communication.

[0030] If the analysis device 60 receives a learning instruction from the auxiliary device 10, it performs machine learning based on the received learning instruction and analyzes the learning results. In the learning instruction, in addition to the above-mentioned learning data 13, information such as the division ratio of the learning data 13 is also included. The division ratio of the learning data 13 is the ratio of dividing the multiple combined data of the explanatory variables and the target variables included in the learning data 13 into training data (data for generating the prediction model 61) and test data (data for verifying the prediction model 61).

[0031] The analysis device 60 can use machine learning to generate a prediction model 61 (learning stage), or effectively utilize the generated prediction model 61 to perform various processes (effective utilization stage). The prediction model 61 is a model for predicting the target variable based on the explanatory variable. The prediction model 61 outputs the value of the target variable corresponding to the input explanatory variable by being input with the explanatory variable.

[0032] If the analysis device 60 receives a learning instruction from the auxiliary device 10 in the learning stage, it reads in the learning data 13 included in the learning instruction and automatically performs preprocessing of the learning data. For example, as one of the preprocessings, when there are missing values in the read learning data 13, the analysis device 60 performs a process of compensating the values with similar data. The analysis device 60 divides the preprocessed learning data into training data and test data according to the division ratio included in the learning instruction. Then, the analysis device 60 generates a prediction model 61 that predicts the relationship between the explanatory variables and the target variables included in the training data. In addition, for example, the explanatory variable is a variable related to the material of the battery, and the target variable is a variable related to the characteristics of the battery. By setting the variables in this way, a prediction model 61 that predicts the relationship between the material of the battery and the characteristics of the battery can be generated.

[0033] The prediction model 61 is generated separately using multiple algorithms. That is, the analysis device 60 uses multiple algorithms to generate multiple prediction models 61. Then, the analysis device 60 uses the test data to verify the generated prediction model 61. Further, the analysis device 60 performs an analysis of the generated prediction model 61 (calculation of correlation coefficient, determination coefficient, etc.). In addition, the generation method, verification method, and analysis method of the prediction model implemented by the analysis device 60 are the same as the known methods, so detailed descriptions are not repeated here.

[0034] If the analysis device 60 receives a utilization instruction including the value of the explanatory variable from the auxiliary device 10 in the effective utilization stage, it uses the prediction model 61 to calculate the predicted value of the target variable for the value of the explanatory variable included in the utilization instruction, and sends the calculated predicted value of the target variable to the auxiliary device 10.

[0035] [Assistance for Machine Learning]

[0036] In conventional machine learning tools, specialized knowledge such as complex coding and machine learning processes is required. However, it is difficult for general users to learn the specialized knowledge of machine learning in advance, so it is not user-friendly.

[0037] Therefore, the learning device 6 of the present embodiment provides assistance so that users can easily execute machine learning and effectively utilize the machine learning results through simple operations.

[0038] <Learning Phase (Phase of Executing Machine Learning)>

[0039] Figure 2 FIG. is a diagram schematically showing an example of the learning execution screen 70a displayed on the display device 2. The learning device 6 causes the display device 2 to display Figure 2 the learning execution screen 70a shown. Without the need for the user to perform complex coding or the like, the user can perform machine learning implemented by the learning device 6 only by performing simple operations in accordance with the display content of the learning execution screen 70a. Hereinafter, the display content of the learning execution screen 70a and the operations performed by the user while observing the learning execution screen 70a will be described.

[0040] (1)Designation of Object File

[0041] At the upper part of the learning execution screen 70a, a label 80 marked as "Search for Prediction Model" and a label 90 marked as "Display of Predicted Value" are displayed in a selectable manner. If the user performs an operation of selecting the label 80, the learning execution screen 70a shown Figure 2 is displayed on the screen of the display device 2.

[0042] Below the labels 80 and 90, a file selection icon 81a, a path display section 81b, and a read-in icon 81c are displayed. If the user performs an operation of aligning the cursor with the file selection icon 81a and clicking, the storage destination and file name of the learning data (the above-mentioned learning data 13) are automatically searched and displayed in the path display section 81b. When there are multiple learning data files, the storage destinations and file names of the multiple files are displayed in the path display section 81b. The user can simply specify the object file for machine learning by performing an operation of aligning the cursor with the part where the desired file name is displayed and clicking. If the user performs an operation of aligning the cursor with the read-in icon 81c and clicking in the state where the object file is specified (hereinafter also referred to as "file read-in operation"), the reading of the object file starts, and a status bar 81d is pop-up displayed during the period until the reading of the object file is completed. At the status bar 81d, for example, the read-in information of the object file, the read-in time, etc. are displayed.

[0043] (2) Method for dividing learning data and selection of division ratio

[0044] Below the file selection icon 81a, a division selection section 82 is displayed. According to the display of the division selection section 82, the user can select the division method and division ratio of the learning data included in the object file read in.

[0045] Specifically, in the division selection section 82, there is a method selection section 82a that includes options for displaying the division method. In Figure 2 it, as options for the division method, "Random" for randomly dividing the learning data and "Keep Line Numbers" for dividing while maintaining the arrangement order of the learning data are displayed, and the state of default selection of "Random" is shown. When the division method can be maintained as the default "Random", the user does not need to perform special operations. By performing an operation of aligning the cursor with the display part such as "Keep Line Numbers" and clicking, the user can simply change the division method to "Keep Line Numbers".

[0046] Furthermore, in the division selection section 82, there is a ratio selection section 82b that displays the division ratio with a scroll bar. In Figure 2 it, an example is shown where the default value of the division ratio (the ratio of training data to the whole of the learning data) is set to "80%". In addition, the division ratio is generally set in the range of 70 - 90%. By operating the scroll bar of the ratio selection section 82b, the user can arbitrarily change the division ratio.

[0047] (3) Selection of explanatory variables and target variables

[0048] Below the division selection section 82, a variable selection section 83 is displayed. If the reading of the object file is completed, a process of extracting explanatory variable candidates and target variable candidates from the learning data included in the object file is performed, and the title names of the extracted explanatory variable candidates and target variable candidates are respectively displayed in a selectable manner in the explanatory variable selection section 83b and the target variable selection section 83a.

[0049] The user can easily select explanatory variables by performing an operation of selecting and clicking on one or more desired explanatory variables from the explanatory variable candidates displayed in the explanatory variable selection unit 83b (hereinafter also referred to as the "operation of selecting explanatory variables"). Similarly, the user can easily select the target variable by performing an operation of selecting and clicking on one target variable desired from the target variable candidates displayed in the target variable selection unit 83a (hereinafter also referred to as the "operation of selecting the target variable"). The explanatory variables and the target variable selected by the user are displayed in the selected variable display unit 83c. Hereinafter, the operation of selecting explanatory variables and the operation of selecting the target variable will also be collectively referred to as the "variable selection operation".

[0050] In addition, the explanatory variable candidates displayed in the explanatory variable selection unit 83b can also be added later, and the machine learning results can be updated based on the added explanatory variables.

[0051] (4) Execution of Machine Learning (Generation of Prediction Model)

[0052] Below the variable selection unit 83, a learning execution icon 84 is displayed. If, when the explanatory variables and the target variable selected by the user are displayed in the selected variable display unit 83c, the user performs an operation of aligning the cursor with the learning execution icon 84 and clicking (hereinafter also referred to as the "learning execution operation"), then the machine learning performed by the learning device 6 is executed according to the learning conditions (learning data, explanatory variables, target variables, segmentation method, segmentation ratio, etc.) specified by the user in the learning execution screen 70a.

[0053] The learning device 6 generates a prediction model (the above-mentioned prediction model 61) for predicting the target variable based on the explanatory variables by performing machine learning using the learning conditions specified by the user. As described above, the prediction model outputs the value of the target variable corresponding to the input explanatory variables when the explanatory variables are input.

[0054] The learning device 6 of the present embodiment generates multiple prediction models using multiple algorithms for the learning conditions specified by the user. Further, the learning device 6 calculates the correlation coefficient (an index indicating the relationship between the explanatory variables and the target variable) and the determination coefficient (an index indicating how consistent the predicted value of the target variable is with the actual value of the target variable) for each of the multiple generated prediction models.

[0055] (5) Display of Learning Results

[0056] Below the learning execution icon 84, a result display unit 85 showing the results of machine learning is displayed. By observing the display content of the result display unit 85, the user can confirm the results of machine learning. In the result display unit 85, a model name display unit 85a, a coefficient display unit 85b, a graph display unit 85d, and a feature quantity display unit 85e are displayed.

[0057] In the model name display unit 85a, the name of the prediction model (algorithm) of the learning result to be displayed in the result display unit 85 is displayed. In the model name display unit 85a, the name of the prediction model with the highest coefficient of determination among multiple prediction models (hereinafter also referred to as the "optimal model") is displayed by default (in Figure 2 the example shown is "lar").

[0058] If the user performs an operation of pressing the drop-down button displayed at the right end of the model name display unit 85a, a selection list 85f of multiple algorithms for generating a prediction model is displayed in order of accuracy (in order of the coefficient of determination from high to low). By selecting one of the multiple prediction models (algorithms) displayed in the selection list 85f, the user can change the learning result displayed in the result display unit 85 to the learning result obtained from the prediction model (selected model) generated by the algorithm selected by the user.

[0059] In the coefficient display unit 85b, the correlation coefficient and the coefficient of determination of the prediction model displayed in the model name display unit 85a are displayed. The graph display unit 85d displays a graph representing the analysis result obtained from the prediction model displayed in the model name display unit 85a. In the feature quantity display unit 85e, the ranking of the feature quantities of the prediction model to be displayed in the model name display unit 85a is displayed.

[0060] <Effective utilization stage (stage of effectively using the results of machine learning)>

[0061] Figure 3 is a diagram schematically showing an example of the learning effective utilization screen 70b displayed on the display device 2. If the user performs an operation of selecting the label 90, the learning effective utilization screen 70b shown in Figure 3 is displayed on the screen of the display device 2. By simply performing an operation in accordance with the display content of the learning effective utilization screen 70b, the user can use the prediction model generated in the learning stage to calculate (predict) the value of the target variable for any value of the explanatory variable.

[0062] In the learning effective utilization screen 70b, an explanatory variable input unit 91, a target variable display unit 92, an inspection data display unit 93, and a model selection unit 94 are displayed.

[0063] In the explanatory variable input unit 91, a title bar 91a, an input bar 91b, a range bar 91c, a calculation execution icon 91d, and an initial value icon 91e are displayed.

[0064] The title bar 91a, the input bar 91b, and the range bar 91c are arranged and displayed in order from left to right. In the title bar 91a, the title names of a plurality of explanatory variables are arranged and displayed vertically. In the range bar 91c, the minimum value and the maximum value of each explanatory variable are displayed. In the input bar 91b, as the initial value, the median value of each explanatory variable is input. The user can change the value of the explanatory variable in the input bar 91b from the initial value to an arbitrary value within the range displayed in the range bar 91c. In addition, Figure 3 shows an example in which four items, "Classification B", "Classification a", "Classification e", and "Classification c", are set as target variables and the other items are set as fixed values among the items displayed in the title bar 91a.

[0065] In the model selection unit 94, the name of the prediction model for calculating the target variable is displayed. In the model selection unit 94, the best model is displayed by default. If the user performs an operation of pressing the drop-down button displayed at the right end of the model selection unit 94, a selection list in which the names of a plurality of prediction models generated in the learning stage are arranged in order of accuracy is displayed. By selecting one prediction model from the selection list, the user can change the prediction model used to calculate the target variable to the prediction model selected by the user.

[0066] If the user performs an operation of aligning the cursor with the calculation execution icon 91d and clicking (hereinafter also referred to as "calculation execution operation"), the learning device 6 uses the prediction model displayed in the model selection unit 94 to perform processing for calculating the value of the target variable for the value of the explanatory variable input to the input bar 91b (hereinafter also referred to as "calculation processing"). The calculated value of the target variable is displayed in the target variable display unit 92. By repeating the operation of changing the value of the explanatory variable input to the input bar 91b and recalculating the value of the target variable, the user can grasp how much the target variable changes with respect to the change in the explanatory variable. For example, when the explanatory variable is a variable related to the physical properties of the battery material and the target variable is a variable related to the storage characteristics of the battery, the user can predict how much the storage characteristics of the battery change with respect to the change in the physical properties of the battery material. The physical properties of the battery material refer to, for example, the physical properties of the positive electrode, the negative electrode, the separator, and the electrolyte, as well as the physical properties of the materials used therein.

[0067] [Flowchart]

[0068] Figure 4 is a flowchart showing an outline of the processing order executed by the learning device 6 in the learning stage. This flowchart is displayed on the screen of the display device 2 when Figure 2Execute in the case of the learning execution screen 70a shown.

[0069] First, the learning device 6 determines whether the above file reading operation has been performed (step S10). If the file reading operation has not been performed (in step S10, "No"), the learning device 6 repeats the process of step S10 and waits for the file reading operation to be performed.

[0070] If the file reading operation has been performed (in step S10, "Yes"), the learning device 6 reads the target file, extracts the explanatory variable candidates and the objective variable candidates from the learning data included in the read target file, and displays the extracted explanatory variable candidates and objective variable candidates on the display device 2 in a manner that can be selected by the user (step S11).

[0071] Next, the learning device 6 determines whether the above variable selection operation has been performed (step S12). If the variable selection operation has not been performed (in step S12, "No"), the learning device 6 repeats the process of step S12 and waits for the variable selection operation to be performed.

[0072] If the variable selection operation has been performed (in step S12, "Yes"), the learning device 6 determines whether the above learning execution operation has been performed (step S13). If the learning execution operation has not been performed (in step S13, "No"), the learning device 6 repeats the process of step S13 and waits for the learning execution operation to be performed.

[0073] If the learning execution operation has been performed (in step S13, "Yes"), the learning device 6 executes the learning process of performing machine learning according to the above content (step S14). Thereafter, the learning device 6 causes the display device 2 to display the result of the learning process (step S15).

[0074] Figure 5 It is a flowchart showing an outline of the processing order executed by the learning device 6 in the effective utilization phase. This flowchart is executed when the Figure 3 shown learning effective utilization screen 70b is displayed on the screen of the display device 2.

[0075] First, the learning device 6 determines whether the above calculation execution operation has been performed (step S20). If the calculation execution operation has not been performed (in step S20, "No"), the learning device 6 repeats the process of step S20 and waits for the calculation execution operation to be performed.

[0076] In the case where a calculation execution operation is performed (Yes in step S20), the learning device 6 performs the above-described calculation process (step S21). Specifically, the learning device 6 uses the prediction model displayed in the model selection unit 94 to calculate the value of the target variable for the value of the explanatory variable input to the input field 91b.

[0077] Next, the learning device 6 causes the display device 2 to display the result of the calculation process (step S22).

[0078] As described above, the machine learning system 1 of the present embodiment includes the display device 2 and the learning device 6. The learning device 6 causes the display device 2 to display the result of extracting the explanatory variable candidates and the target variable candidates from the object file specified by the user, and causes the display device 2 to display the result obtained by machine learning and analyzing the relationship between the explanatory variable and the target variable selected by the user from the explanatory variable candidates and the target variable candidates displayed on the display device 2.

[0079] According to the machine learning system 1 of the present embodiment, only by the user specifying the object file, the candidates of the explanatory variable and the target variable included in the object file are displayed on the display device 2. By performing a simple operation of selecting the variables desired by the user from the explanatory variable candidates and the target variable candidates displayed on the display device 2, the user can cause the display device 2 to display the analysis result obtained by machine learning. Therefore, the user can perform machine learning through a simple operation without performing complex operations such as coding.

[0080] Furthermore, the learning device 6 of the present embodiment generates a plurality of prediction models for predicting the target variable from the explanatory variable by performing machine learning on the explanatory variable and the target variable selected by the user according to a plurality of algorithms respectively in the learning stage, calculates the determination coefficient of each of the generated plurality of prediction models, and displays the prediction model with the highest determination coefficient as the best model on the display device 2. Thus, the user can know the best model through a simple operation.

[0081] Furthermore, the learning device 6 of the present embodiment causes the display device 2 to display a plurality of algorithms in the learning stage, and causes the display device 2 to display the information of the best model or the information of the selected model generated by the algorithm selected by the user from the plurality of algorithms. Thus, the user can change the information of the prediction model to be displayed on the display device 2 from the information of the best model to the information of the selected model by performing a simple operation of selecting any one of the plurality of algorithms displayed on the display device 2.

[0082] Further, in the effective utilization phase, the learning device 6 of the present embodiment acquires explanatory variables input by the user and causes the display device 2 to display the result obtained by calculating the objective variable corresponding to the explanatory variables input by the user using the optimal model or the selected model. Thereby, the user can predict the value of the objective variable corresponding to arbitrary explanatory variables.

[0083] Further, in the learning phase, the machine learning system 1 of the present embodiment acquires the division ratio of the training data and the test data requested by the user, divides the data included in the object file into the training data and the test data according to the acquired division ratio, performs machine learning, and causes the display device 2 to display the result. Thereby, the user can arbitrarily determine the division ratio of the training data and the test data.

[0084] Although the embodiments of the present invention have been described, it should be considered that the disclosed embodiments are exemplary in all respects and not restrictive. The scope of the present invention is represented by the claims and is intended to include all modifications within the meaning and scope equivalent to the claims.

Claims

1. A machine learning system having: display device; and a learning device, connected to the display device, The learning device causes the display device to display the results of extracting explanatory variable candidates that can be selected as explanatory variables and target variable candidates that can be selected as target variables from an object file specified by a user, and causes the display device to display the results obtained by machine learning analysis of the relationship between the explanatory variable and the target variable selected by the user from the explanatory variable candidates and the target variable candidates displayed on the display device.

2. The machine learning system according to claim 1, wherein: The learning device performs machine learning on the explanatory variables and target variables selected by the user according to multiple algorithms, thereby generating multiple prediction models each for predicting the target variable based on the explanatory variables, respectively calculating the determination coefficients of the multiple prediction models generated, and using the prediction model with the highest determination coefficient as the optimal model for display on the display device.

3. The machine learning system according to claim 2, wherein: The learning device causes the display device to display the plurality of algorithms, and causes the display device to display information of the optimal model or information of a selected model which is a prediction model generated by an algorithm selected by a user from among the plurality of algorithms displayed on the display device.

4. The machine learning system according to claim 3, wherein: The learning device obtains the explanatory variables input by the user, and causes the display device to display the result of calculating the objective variable corresponding to the explanatory variables input by the user using the optimal model or the selected model.

5. The machine learning system according to any one of claims 1 to 4, wherein: The learning device obtains a division ratio of training data and test data requested by a user, and causes the display device to display a result obtained by performing the machine learning by dividing the data included in the object file into training data and test data according to the obtained division ratio.

6. The machine learning system according to any one of claims 1 to 4, wherein: The explanatory variable is a variable related to the material of the battery, and the target variable is a variable related to the characteristics of the battery.

7. A machine learning method comprising: a step of causing a display device to display a result of extracting explanatory variable candidates that can be selected as explanatory variables and target variable candidates that can be selected as target variables from a target file specified by a user; and The step of causing the display device to display a result obtained by analyzing, by machine learning, the relationship between the explanatory variable and the target variable selected by the user from among the explanatory variable candidates and the target variable candidates displayed on the display device.

Images