Generation apparatus, generation method, and generation program

Abstract

This invention provides a generation device that can effectively generate test data for material design by utilizing past data. [Solution] The generation device comprises an acquisition unit that acquires information to be generated or data related to the information to be generated, and a generation unit that inputs the information to be generated to a trained model generated by machine learning using features extracted from training data related to the information to be generated, and generates data by obtaining output from the trained model. The predetermined operation involves duplicating the first table in which the training data is stored to generate a second table, cross-joining the first table and the second table based on an identification column for data identification to generate a new third table, calculating the difference between the explanatory variable column of the first table and the explanatory variable column of the second table in the generated third table, storing it in a newly generated column in the third table, and extracting features from the generated column.

Description

Technical Field

[0001] The present disclosure relates to a generation device, a generation method, and a generation program.

Background Art

[0002] The design of materials is carried out by repeating prototyping while adjusting the composition based on the experience of material developers. For example, Patent Document 1 discloses a material design device, a material design method, and a material design program for a polymer material that simultaneously satisfies a plurality of desired material properties.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Past experimental data incorporates various ideas and perspectives, and it is considered that test data for material design can be effectively generated by utilizing past experimental data.

[0005] In view of the above points, the present disclosure aims to provide a generation device, a generation method, and a generation program that can effectively generate test data for material design by utilizing past data.

Means for Solving the Problems

[0006] A generation device according to a first aspect of this disclosure includes an acquisition unit that acquires information to be generated or data related to the information to be generated, and a generation unit that generates data by inputting the information to be generated or data related to the information to be generated to a trained model generated by machine learning using features extracted by a predetermined operation on training data related to the information to be generated, and obtaining output from the trained model. The predetermined operation is an operation that generates a second table by duplicating a first table in which the training data is stored, generates a new third table by cross-joining the first table and the second table based on an identification column for identifying the data, calculates the difference between the explanatory variable column of the first table and the explanatory variable column of the second table in the generated third table, stores it in a newly generated column in the third table, and extracts the features from the generated column.

[0007] The generation apparatus according to the second aspect of this disclosure is the generation apparatus according to the first aspect, wherein the learning data is experimental conditions or manufacturing conditions.

[0008] A generation apparatus according to a third aspect of this disclosure is a generation apparatus according to a first aspect, wherein the acquisition unit acquires, as information to be generated, instructions for generating test data of a material, or related test data that reflects the ideas used when planning past test data.

[0009] A generation apparatus according to a fourth aspect of this disclosure is a generation apparatus according to a first aspect, wherein the feature quantity is information related to the identification sequence used in the cross-combination.

[0010] The generation apparatus according to the fifth aspect of this disclosure is the generation apparatus according to the first aspect, wherein the feature quantities are extracted by dimensionality reduction processing.

[0011] A generation method according to a sixth aspect of this disclosure is a method in which a processor acquires information to be generated, inputs the information to be generated into a trained model generated by machine learning using features extracted by a predetermined operation on training data related to the information to be generated, and obtains output from the trained model to perform a process to generate data. The predetermined operation involves duplicating a first table in which the training data is stored to generate a second table, cross-joining the first table and the second table based on an identification column for identifying the data to generate a new third table, calculating the difference between the explanatory variable column of the first table and the explanatory variable column of the second table in the generated third table, storing it in a newly generated column in the third table, and extracting the features from the generated column.

[0012] The generation program according to the seventh aspect of this disclosure causes a computer to perform a process of generating data by acquiring information to be generated, inputting the information to be generated into a trained model generated by machine learning using features extracted by a predetermined operation on training data related to the information to be generated, and obtaining output from the trained model. The predetermined operation involves duplicating the first table in which the training data is stored to generate a second table, cross-joining the first table and the second table based on an identification column for identifying the data to generate a new third table, calculating the difference between the explanatory variable column of the first table and the explanatory variable column of the second table in the generated third table, storing it in a newly generated column in the third table, and extracting the features from the generated column. [Effects of the Invention]

[0013] According to this disclosure, it is possible to provide a generation device, generation method, and generation program that can effectively generate test data for material design by utilizing past data. [Brief explanation of the drawing]

[0014] [Figure 1]It is a diagram showing a schematic configuration of a generation device according to an embodiment of the disclosed technology. [Figure 2] It is a block diagram showing the hardware configuration of the generation device. [Figure 3] It is a block diagram showing an example of the functional configuration of the generation device. [Figure 4] It is a diagram showing an example of replication processing. [Figure 5] It is a diagram showing an example of combining processing. [Figure 6] It is a diagram showing an example of arithmetic processing. [Figure 7] It is a diagram showing an example of extraction processing. [Figure 8] It is a diagram explaining the effect of data processing. [Figure 9] It is a block diagram showing an example of the functional configuration of a learning device for constructing a learned model. [Figure 10] It is a flowchart showing the flow of generation processing by the generation device.

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of the present disclosure will be described while referring to the drawings. In each drawing, the same or equivalent components and parts are given the same reference numerals. Also, the dimensional ratios in the drawings are exaggerated for the convenience of explanation and may be different from the actual ratios.

[0016] FIG. 1 is a diagram showing a schematic configuration of a generation device according to the present embodiment. The generation device 10 according to the present embodiment inputs information to be generated or data related to the information to be generated into a learned model 20 generated in advance by machine learning, and obtains an output from the learned model 20, or inputs information to be generated expected from the output of the learned model 20 and performs inverse analysis on the learned model 20 to generate data. The information to be generated includes an explanatory variable to be generated, an objective variable to be generated, information input in generation using the learned model 20, and output information expected in generation using the learned model 20. The learned model 20 is a model generated by machine learning using feature amounts extracted by a predetermined operation on learning data related to the information to be generated input to the learned model 20. Details of the predetermined operation on the learning data will be described later in detail, but it is an operation for extracting feature amounts reflecting the idea incorporated in the learning data.

[0017] The information to be generated is, for example, information regarding the purpose of an experiment, the composition of materials, the use, etc., and the learning data related to the information to be generated is, for example, composition data of materials when an experiment was conducted in the past. In this case, the generation device 10 generates data using the learned model 20 generated by machine learning using feature amounts extracted by a predetermined operation on the composition data of materials.

[0018] By generating data using the learned model 20, the generation device 10 according to the present embodiment can generate data reflecting the idea incorporated in the learning data, the intention and know-how of past experimenters.

[0019] FIG. 2 is a block diagram showing the hardware configuration of the generation device 10.

[0020] As shown in Figure 2, the generation device 10 includes a CPU (Central Processing Unit) 11, ROM (Read Only Memory) 12, RAM (Random Access Memory) 13, storage 14, input unit 15, display unit 16, and communication interface (I / F) 17. Each component is connected to the others via a bus 19 so that they can communicate with each other.

[0021] The CPU 11 is a central processing unit that executes various programs and controls each component. Specifically, the CPU 11 reads a program from the ROM 12 or storage 14 and executes the program using the RAM 13 as a working area. The CPU 11 controls each of the above components and performs various calculations according to the program recorded in the ROM 12 or storage 14. In this embodiment, the ROM 12 or storage 14 stores a generation program that generates data by inputting information to be generated and obtaining output from a trained model.

[0022] ROM12 stores various programs and data. RAM13 temporarily stores programs or data as a working area. Storage14 consists of a storage device such as an HDD (Hard Disk Drive), SSD (Solid State Drive), or flash memory, and stores various programs, including the operating system, and various data.

[0023] The input unit 15 includes a pointing device such as a mouse and a keyboard, and is used for various types of input.

[0024] The display unit 16 is, for example, a liquid crystal display and displays various information. The display unit 16 may also function as an input unit 15 by employing a touch panel system.

[0025] The communication interface 17 is an interface for communicating with other devices, and standards such as Ethernet®, FDDI, and Wi-Fi® can be used.

[0026] When executing the above generation program, the generation device 10 uses the above hardware resources to implement various functions.

[0027] Next, the functional configuration of the generation device 10 will be described.

[0028] Figure 3 is a block diagram showing an example of the functional configuration of the generation device 10.

[0029] As shown in Figure 3, the generation device 10 has an acquisition unit 101 and a generation unit 102 as its functional configuration. Each functional configuration is realized by the CPU 11 reading and executing a generation program stored in the ROM 12 or storage 14.

[0030] The acquisition unit 101 acquires information to be generated, or data related to the information to be generated. The acquisition unit 101 acquires, as information to be generated, instructions for generating test data of materials, or related test data that reflects the ideas behind the planning of past test data. The information to be generated is input, for example, by the user of the generation device 10 using the input unit 15. Specific examples of the information to be generated include, for example, "techniques or know-how that a certain experiment planner has successfully used in the past and repeatedly conducted experiments on, the purpose of the experiment, etc."

[0031] The generation unit 102 generates data using the information to be generated, or data related to the information to be generated, acquired by the acquisition unit 101. Specifically, the generation unit 102 generates data by inputting the information to be generated or data related to the information to be generated into the trained model 20 and obtaining the output from the trained model 20. The trained model 20 is a model generated by machine learning using features extracted by a predetermined operation on the training data related to the information to be generated, acquired by the acquisition unit 101. The predetermined operation is to generate a second table by duplicating the first table in which the training data is stored, generate a new third table by cross-joining the first table and the second table based on an identification column for data identification, calculate the difference between the explanatory variable column of the first table and the explanatory variable column of the second table in the generated third table, store it in a newly generated column in the third table, and extract features from the generated column.

[0032] The following describes the data processing for calculating the features used in the machine learning of the trained model 20. The features used in the machine learning of the trained model 20 are extracted from tabular data. Tabular data can be of any type; for example, it may be stored in a database or entered in a spreadsheet. The data to be processed may include, for example, past test data for product prototyping, and may include information such as the proportions of materials used to manufacture a certain product, material features obtained from experimental results such as analysis or simulation results (molecular weight, softening point, particle shape, etc.), material processing time, and test results of the prototype product.

[0033] First, a replication process is performed to duplicate the data to be processed. That is, the replication process performs a process to duplicate the data to be processed in a table format. The data to be processed in a table format is an example of the first table in this disclosure, and the table generated by the replication process is an example of the second table in this disclosure.

[0034] Figure 4 shows an example of the replication process. The replication process replicates Table 200A to generate Table 200B, which has exactly the same data. The columns "Test Set" and "#" are columns that store information identifying the experimental data. Of these, the column "Test Set" is an identification column that stores identification information used in the join and calculation processes described later, while the columns "NR", "BR", and "BR Molecular Weight" are columns that store experimental data values, respectively. The experimental data values ​​are examples of explanatory variables in this disclosure. In the following description, Table 200A will also be referred to as "Table A", and Table 200B as "Table B". In the following description, the column "Test Set" will be referred to as column (a), the column "NR" as column (b1), the column "BR" as column (b2), and the column "BR Molecular Weight" as column (b3).

[0035] It should be noted that the structure of the table-formatted data to be processed is not limited to the example shown. In Figure 4, table 200A has only one identification column called "Test Set," but for example, the data to be processed may have multiple identification columns. In addition, any preprocessing such as feature design including ratio calculation, normalization, and nonlinear transformation may be performed before the replication process.

[0036] Next, a join process is performed to cross-join the data to be processed and the data obtained by copying the data to be processed, using the identification column as the basis. Specifically, the join process uses the identification information in the data to be processed as the key to cross-join the data to be processed and the data obtained by copying the data to be processed, using the identification column as the basis to generate new data. The table generated by the join process is an example of the third table in this disclosure.

[0037] Figure 5 shows an example of a join process. The join process performs a cross join of tables 200A and 200B for all combinations of rows with the same column (a), thereby generating a new table 200C. In the example shown, the join process performs a join of the data from the first row of table 200A with the data from four rows of table 200B where column (a) is "A0001". Similarly, the join process performs a join of the data from rows 2 to 4 of table 200A with the data from four rows of table 200B where column (a) is "A0001". In other words, in the example shown, the join process performs a process that generates 16 rows of data where column (a) is "A0001".

[0038] Furthermore, the merge process may be performed on all data in the data to be processed, or it may not be performed on all data in the data to be processed.

[0039] Next, an operation is performed on the data generated by the join process, applying calculations to arbitrary columns. Specifically, the operation involves subtracting the same column from the original two tables onto the data generated by the join process, and storing the result of the subtraction in a new column. The column where the result of the subtraction is stored is also called the difference column.

[0040] Figure 6 shows an example of the calculation process. The "ΔNR" column is a difference column that stores the value obtained by subtracting the value of the "NR" column from Table B from the value of the "NR" column from Table A. The "ΔBR" column is a difference column that stores the value obtained by subtracting the value of the "BR" column from Table B from the value of the "BR" column from Table A. The "ΔMolecular Weight" column is a difference column that stores the value obtained by subtracting the value of the "BR Molecular Weight" column from Table B from the value of the "BR Molecular Weight" column from Table A.

[0041] The calculation process subtracts the value from Table B from the value from Table A for the same column in Table 200C, and stores the result in a new column. In the example in Figure 6, for the first row, the values ​​from Table A and Table B are the same, so the calculation process stores 0 in the "ΔNR", "ΔBR", and "ΔMolecular Weight" columns. For the second row and beyond, there is a difference between the values ​​from Table A and Table B, so the calculation process stores the values ​​obtained by subtracting the values ​​from Table B from the values ​​from Table A in the "ΔNR", "ΔBR", and "ΔMolecular Weight" columns, respectively.

[0042] Furthermore, before subtraction, any preprocessing such as feature design (including ratio calculation), normalization, or nonlinear transformation may be performed.

[0043] The extraction process extracts features from each difference column where the results of the calculation process are stored. Specifically, the extraction process extracts information related to the discriminant column used by the join process for the cross-join of the two tables as features for each difference column. In other words, the extraction process extracts information representing the differences in the discriminant column used by the join process for the cross-join of the two tables as features for each difference column. In other words, the extraction process extracts information common to each element of the discriminant column used by the join process for the cross-join of the two tables as features for each difference column. The extraction process can extract features using any method, but examples include dimensionality reduction (ICA (Independent Component Analysis), PCA (Principal Component Analysis), LSI (Latent Semantic Indexing), LDA (Linear Discriminant Analysis), IA, MDS, NMF, etc.), unsupervised learning to generate latent variables (t-SNE), and supervised learning (NN). The extracted features can be used for data analysis of the processed data.

[0044] Here, we show an example where data to be processed is subjected to merging and arithmetic operations before being extracted.

[0045] Figure 7 shows an example of the extraction process. In table 200C in Figure 7, the "IC component 1", "IC component 2", and "IC component 3" columns are columns that store feature quantities corresponding to the values ​​stored in the "ΔNR", "ΔBR", and "Δ molecular weight" columns. In this embodiment, the extraction unit 104 uses ICA to extract feature quantities from the values ​​stored in the "ΔNR", "ΔBR", and "Δ molecular weight" columns using an arbitrary method as described above, and stores the extracted feature quantities in the "IC component 1", "IC component 2", and "IC component 3" columns, respectively.

[0046] If we let X be the matrix containing the values ​​before the subtraction operation, ΔX be the matrix containing the values ​​after the subtraction operation, and ΔS be the matrix containing the features, then the feature calculation on the matrix after the subtraction operation is: ΔS=W DI ·ΔX (1) It can be expressed by the following equation. ΔS is the explanatory variable. In other words, ΔX is a matrix that stores the differences in experimental conditions and manufacturing conditions (composition, temperature, etc.), and W DI This matrix represents the weights that are optimized to maximize or minimize the parameters used to find the features.

[0047] Furthermore, during the extraction process, any preprocessing, such as normalization or nonlinear transformation, may be performed on each difference sequence when extracting features.

[0048] Figure 8 illustrates the effects of the series of data processing described above. Figure 8 shows graphs of the relationship between IC component 1 column and IC component 3, the relationship between IC component 2 column and IC component 3, and the relationship between IC component 1 column and IC component 2, as shown in Figure 7.

[0049] As shown in the graph in Figure 8, it can be seen that there is a predetermined relationship between the features extracted as a result of the series of data processing described above. In other words, when combining and arithmetic operations are performed on the data to be processed and then extraction is carried out, it becomes easy to understand what kind of characteristics the extracted features have.

[0050] Furthermore, since the trained model 20 is trained using features extracted as a result of the series of data processing described above, it becomes possible to generate data that reflects the ideas embedded in the training data. That is, the difference in the target variable Y (for example, relative physical properties corresponding to differences in experimental conditions) ΔY is expressed using ΔS, ΔY=F(ΔS) (2) The model created using this method is the trained model 20.

[0051] Figure 9 is a block diagram showing an example of the functional configuration of a learning device 30 for constructing a trained model 20. As shown in Figure 9, the learning device 30 includes an acquisition unit 301, a calculation unit 302, and a recording unit 303. The learning device 30 may be configured as the same device as the prediction device 10, or as a separate device.

[0052] The acquisition unit 301 acquires training data to be used for learning. The acquisition unit 301 acquires, for example, past experimental data X as training data. Past experimental data is data that records experimental conditions and experimental results for said experimental conditions, for example, as shown in table 200A in Figure 4.

[0053] The calculation unit 302 performs the above-described replication, joining, and calculation processes to extract the feature quantities ΔS of the training data, and then uses the extracted features to perform calculations to obtain a trained model 20 that models the relative difference of the target variable using equation (2).

[0054] The recording unit 303 records the trained model 20 modeled using the calculation formula for feature extraction shown in formula (1) and the formula represented by formula (2). The trained model 20 recorded by the recording unit 303 is used by the generation unit 102 to generate data.

[0055] The generation device 10, by executing a generation process using the trained model 20, can generate experimental data that reflects the principles behind the generation of past experimental data when generating test data for experimenting with materials.

[0056] For example, if the trained model 20 is a model trained based on features extracted from test data previously created by an experimental designer, the generation device 10 can use the trained model 20 when generating test data for a certain material, thereby generating test data based on the experimental designer's experience, knowledge, experimental philosophy, and hypotheses.

[0057] For example, if the trained model 20 is a model trained based on features extracted from test data previously created for a certain development stage, the generating device 10 can use the trained model 20 when generating test data for testing a certain material, thereby generating test data based on the experimental level or evaluation target that should be carefully evaluated at that development stage.

[0058] For example, if the trained model 20 is a model trained based on features extracted from test data created in the past during a certain year, the generating device 10 can use the trained model 20 when generating test data for a certain material, thereby generating test data based on technologies or know-how discovered or developed in that year.

[0059] For example, if the trained model 20 is a model trained based on features extracted from test data previously created for a particular commercial application, the generating device 10 can use the trained model 20 when generating test data for a particular material, thereby generating test data based on the technology, experience, experimental ideas, and hypotheses in the domain of that commercial application.

[0060] For example, if the trained model 20 is a model trained based on features extracted from test data previously created for a particular component application, the generation device 10 can use the trained model 20 when generating test data for a particular material, thereby generating test data based on the technology, experience, experimental ideas, and hypotheses in the domain of that component application.

[0061] For example, if the trained model 20 is a model trained based on features extracted from test data previously created for a certain experimental purpose, the generating device 10 can use the trained model 20 when generating test data for testing a certain material, thereby generating test data based on a technique or hypothesis that is particularly effective in achieving that experimental purpose.

[0062] For example, if the trained model 20 is a model trained based on features extracted from test data previously created for testing a certain evaluation test method, the generating device 10 can use the trained model 20 when generating test data for testing a certain material, thereby generating test data based on techniques and hypotheses that are particularly effective in improving or optimizing experimental results in that evaluation test method.

[0063] For example, if the trained model 20 is a model trained based on features extracted from test data previously created by a sample provider, the generating device 10 can use the trained model 20 when generating test data for a material, thereby generating test data based on the technical expertise of that provider.

[0064] Next, the operation of the generating device 10 will be explained.

[0065] Figure 10 is a flowchart showing the flow of the generation process by the generation device 10. The CPU 11 reads the generation program from the ROM 12 or storage 14, loads it into the RAM 13, and executes it, thereby performing the generation process.

[0066] In step S101, the CPU 11 acquires the information to be generated. The information to be generated is input, for example, by a user of the generation device 10 using the input unit 16.

[0067] Following step S101, in step S102, the CPU 11 generates data using the acquired information to be generated. Specifically, the CPU 11 inputs the information to be generated into the trained model 20 and generates data by obtaining the output from the trained model 20.

[0068] The generation device 10 generates experimental data using the trained model 20 through the series of processes described above, thereby generating experimental data that reflects the principles behind the generation of past test data when generating test data for experimenting with materials.

[0069] While embodiments of the present disclosure have been described in detail above with reference to the attached drawings, the technical scope of the present disclosure is not limited to these examples. It is clear that a person with ordinary skill in the art of the present disclosure may conceive of various modifications or alterations within the scope of the technical idea set forth in the claims, and these modifications or alterations are also understood to fall within the technical scope of the present disclosure.

[0070] Furthermore, the effects described in the above embodiments are descriptive or illustrative, and are not limited to those described in the above embodiments. In other words, the technology relating to this disclosure may produce other effects that would be obvious to a person of ordinary skill in the art of this disclosure from the descriptions in the above embodiments, in addition to or in lieu of the effects described in the above embodiments.

[0071] Furthermore, the generation process that the CPU reads and executes in each of the above embodiments may be executed by various processors other than the CPU. Examples of such processors include PLDs (Programmable Logic Devices) such as FPGAs (Field-Programmable Gate Arrays) whose circuit configuration can be changed after manufacturing, and dedicated electrical circuits that are processors with circuit configurations specifically designed to execute specific processes, such as ASICs (Application Specific Integrated Circuits). The generation process may be executed by one of these various processors, or by a combination of two or more processors of the same or different types (for example, multiple FPGAs, and a combination of a CPU and an FPGA). More specifically, the hardware structure of these various processors is an electrical circuit that combines circuit elements such as semiconductor elements.

[0072] Furthermore, while the above embodiments describe a configuration in which the generation process program is pre-stored (installed) in ROM or storage, the invention is not limited to this. The program may be provided in a form recorded on a non-transitory recording medium such as a CD-ROM (Compact Disk Read Only Memory), DVD-ROM (Digital Versatile Disk Read Only Memory), or USB (Universal Serial Bus) memory. Alternatively, the program may be provided in a form that can be downloaded from an external device via a network. [Explanation of Symbols]

[0073] 10 Generator 20 Pre-trained Models

Claims

1. An acquisition unit that acquires the information to be generated, or data related to the information to be generated, The system includes a generation unit that generates data by inputting the information to be generated, or data related to the information to be generated, into a trained model generated by machine learning using features extracted by predetermined calculations on training data related to the information to be generated, and obtaining output from the trained model. The aforementioned predetermined calculation is, The first table containing the aforementioned training data is duplicated to generate a second table. The first table and the second table are cross-joined based on the identification column for identifying the data to generate a new third table. The difference between the explanatory variable column in the first table and the explanatory variable column in the second table in the generated third table is calculated and stored in a newly generated column in the third table. This is an operation to extract the aforementioned features from the generated column. generator.

2. The generating apparatus according to claim 1, wherein the learning data is experimental conditions or manufacturing conditions.

3. The generation apparatus according to claim 1, wherein the acquisition unit acquires, as information to be generated, instructions for generating test data of materials, or related test data that reflects the ideas used when planning past test data.

4. The generation apparatus according to claim 1, wherein the feature quantities are information related to the identification sequence used in the cross-combination.

5. The generation apparatus according to claim 1, wherein the aforementioned feature quantities are extracted by dimensionality reduction processing.

6. The processor, Obtain the information to be generated, or data related to the information to be generated, Data is generated by inputting the information to be generated, or data related to the information to be generated, into a trained model generated by machine learning using features extracted by predetermined operations on training data related to the information to be generated, and obtaining the output from the trained model. Execute the process, The aforementioned predetermined calculation is, The first table containing the aforementioned training data is duplicated to generate a second table. The first table and the second table are cross-joined based on the identification column for identifying the data to generate a new third table. The difference between the explanatory variable column in the first table and the explanatory variable column in the second table in the generated third table is calculated and stored in a newly generated column in the third table. This is an operation to extract the aforementioned features from the generated column. Generation method.

7. On the computer, Obtain the information to be generated, or data related to the information to be generated, Data is generated by inputting the information to be generated, or data related to the information to be generated, into a trained model generated by machine learning using features extracted by predetermined operations on training data related to the information to be generated, and obtaining the output from the trained model. Execute the process, The aforementioned predetermined calculation is, The first table containing the aforementioned training data is duplicated to generate a second table. The first table and the second table are cross-joined based on the identification column for identifying the data to generate a new third table. The difference between the explanatory variable column in the first table and the explanatory variable column in the second table in the generated third table is calculated and stored in a newly generated column in the third table. This is an operation to extract the aforementioned features from the generated column. Generation program.

Images