Prediction device, prediction method, and prediction program

Abstract

The present invention provides a prediction device that predicts the performance of a target using information about a comparison target, or that searches for a change in the target that corresponds to a comparison target. [Solution] A prediction device is provided, comprising: an acquisition unit that acquires information of a target to be predicted; a recording unit that records information of a comparison target of the target to be predicted; and a prediction unit that inputs the information of the target to be predicted to a trained model generated by machine learning using features extracted by predetermined calculations on training data related to the information of the target to be predicted, and obtains output from the trained model to predict the performance of the target to be predicted relative to the comparison target.

Description

[Technical Field]

[0001] This disclosure relates to a prediction device, a prediction method, and a prediction program. [Background technology]

[0002] Material design is carried out by repeatedly creating prototypes while adjusting the composition based on the experience of the material developer. For example, Patent Document 1 discloses a material design apparatus, a material design method, and a material design program for polymer materials that simultaneously satisfy multiple desired material properties. [Prior art documents] [Patent Documents]

[0003] [Patent Document 1] International Publication No. 2021 / 045058 [Overview of the project] [Problems that the invention aims to solve]

[0004] The performance data obtained from past experiments incorporates various ideas and perspectives, and it is believed that by utilizing the performance data obtained from past experiments, the performance of the experimental subject can be effectively predicted.

[0005] This disclosure is made in view of the above points, and aims to provide a prediction device, prediction method, and prediction program that predict the performance of a target using information of a comparison target of the target, or that search for the amount of change of a target that corresponds to a comparison target of the target. [Means for solving the problem]

[0006] The prediction device according to the first aspect of the present disclosure includes an acquisition unit that acquires information on a prediction target, a recording unit that records information on a comparison target of the prediction target, and a learned model generated by machine learning using feature amounts extracted by a predetermined operation on learning data related to the information on the prediction target. The prediction unit inputs the information on the prediction target to the learned model and obtains an output from the learned model, thereby predicting the performance of the prediction target with respect to the comparison target.

[0007] The prediction device according to the second aspect of the present disclosure is the prediction device according to the first aspect, wherein the predetermined operation replicates a first table in which the learning data is stored to generate a second table, cross-joins the first table and the second table based on an identification column for identifying the learning data to generate a new third table, 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 the difference in a newly generated column in the third table, and extracts the feature amounts for the generated column.

[0008] The prediction device according to the third aspect of the present disclosure is the prediction device according to the first aspect, wherein the prediction unit predicts the absolute value of the performance of the prediction target from the information on the comparison target and the amount of change of the prediction target with respect to the comparison target.

[0009] The prediction device according to the fourth aspect of the present disclosure is the prediction device according to the first aspect, wherein the learning data is data of an experimental design or data of experimental results.

[0010] The prediction device according to the fifth aspect of the present disclosure is the prediction device according to the first aspect, wherein the acquisition unit acquires information on experimental conditions or manufacturing conditions as the information on the prediction target, or the performance of an object manufactured under the predicted experimental conditions or manufacturing conditions.

[0011] The prediction device according to the sixth aspect of the present disclosure is the prediction device according to the fifth aspect, wherein when the acquisition unit acquires information on experimental conditions or manufacturing conditions as information on the prediction target, as the predetermined calculation, a feature amount based on the amount of change in the experimental conditions or manufacturing conditions is calculated, and the prediction unit executes a process of predicting the amount of change in the performance of the target based on the feature amount. When the acquisition unit acquires the performance of the target produced under the predicted experimental conditions or manufacturing conditions as information on the prediction target, as the predetermined calculation, a feature amount based on the amount of change in the performance of the target produced under the experimental conditions or manufacturing conditions is calculated, and the prediction unit executes a process of predicting or searching for the amount of change in the experimental conditions or manufacturing conditions.

[0012] The prediction device according to the seventh aspect of the present disclosure is the prediction device according to the second aspect, wherein the feature amount is information related to the identification column used for the cross-linking.

[0013] The prediction device according to the eighth aspect of the present disclosure is the prediction device according to the second aspect, wherein the feature amount is extracted by dimensionality reduction processing.

[0014] The prediction method according to the ninth aspect of the present disclosure is such that a processor acquires information on a prediction target, inputs the information on the prediction target to a learned model generated by machine learning using a feature amount extracted by a predetermined calculation on learning data related to the information on the prediction target, and obtains an output from the learned model, thereby executing a process of predicting the performance of the prediction target with respect to a recorded comparison target.

[0015] [[ID=十六]]The prediction program according to the tenth aspect of the present disclosure causes a computer to acquire information on a prediction target, input the information on the prediction target to a learned model generated by machine learning using a feature amount extracted by a predetermined calculation on learning data related to the information on the prediction target, and obtain an output from the learned model, thereby executing a process of predicting the performance of the prediction target with respect to a recorded comparison target.

Advantages of the Invention

[0016] According to this disclosure, it is possible to provide a prediction device, prediction method, and prediction program that predict the performance of a target using information of a comparison target, or that search for a change in the target that corresponds to a comparison target. [Brief explanation of the drawing]

[0017] [Figure 1] This figure shows a schematic configuration of a prediction device according to an embodiment of the disclosed technology. [Figure 2] This is a block diagram showing the hardware configuration of the prediction device. [Figure 3] This is a block diagram showing an example of the functional configuration of a prediction device. [Figure 4] This figure shows an example of the duplication process. [Figure 5] This figure shows an example of a merge process. [Figure 6] This figure shows an example of arithmetic processing. [Figure 7] This figure shows an example of the extraction process. [Figure 8] This diagram illustrates the effects of data processing. [Figure 9] This is a block diagram showing an example of the functional configuration of a learning device for building a pre-trained model. [Figure 10] This is a flowchart showing the flow of the prediction process performed by the prediction device. [Modes for carrying out the invention]

[0018] Hereinafter, an example of an embodiment of this disclosure will be described with reference to the drawings. In each drawing, identical or equivalent components and parts are given the same reference numerals. Also, the dimensional ratios in the drawings are exaggerated for illustrative purposes and may differ from the actual ratios.

[0019] Figure 1 shows a schematic configuration of the prediction device according to this embodiment. The prediction device 10 according to this embodiment is a device that predicts the absolute value of the performance of a target by inputting information to be predicted into a pre-trained model 20 generated by machine learning and obtaining output from the pre-trained model 20. The pre-trained model 20 is a model generated by machine learning using features extracted by predetermined operations on the information to be predicted and related training data that are input into the pre-trained model 20. Details of the predetermined operations on the training data will be described in detail later, but it is an operation that extracts features based on experimental design data used in past experiments and experimental result data obtained from past experiments, which are used as training data.

[0020] The information to be predicted input to the prediction device 10 is experimental conditions, for example, the absolute value of the wear performance of a certain product that is to be obtained as the result of the prediction. Specifically, information such as the formulation required to achieve the wear performance of a certain product is input to the prediction device 10 as the information to be predicted. In this case, the prediction device 10 uses the trained model 20 to output the absolute value of the wear performance of that product.

[0021] The prediction device 10 according to this embodiment predicts the performance of the target to be predicted using the trained model 20, thereby enabling prediction of data that reflects features based on experimental conditions used in past experiments and performance data obtained from past experiments.

[0022] Figure 2 is a block diagram showing the hardware configuration of the prediction device 10.

[0023] As shown in Figure 2, the prediction 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.

[0024] The CPU 11 is a central processing unit that executes various programs and controls various components. 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 prediction program that predicts the performance of the experimental target.

[0025] 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.

[0026] The input unit 15 includes a pointing device such as a mouse and a keyboard, and is used for various types of input.

[0027] 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.

[0028] The communication interface 17 is an interface for communicating with other devices, and standards such as Ethernet®, FDDI, and Wi-Fi® can be used.

[0029] When executing the above generation program, the prediction device 10 uses the above hardware resources to implement various functions.

[0030] Next, the functional configuration of the prediction device 10 will be described.

[0031] Figure 3 is a block diagram showing an example of the functional configuration of the prediction device 10.

[0032] As shown in Figure 3, the prediction device 10 has an acquisition unit 101, a storage unit 102, and a prediction unit 103 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.

[0033] The acquisition unit 101 acquires information to be predicted. This information is input, for example, by a user of the prediction device 10 using the input unit 15. A specific example of the information to be predicted is, for example, "experimental conditions for a certain product." In this case, the experimental conditions include material composition, material characteristics, mixing conditions, product configuration conditions, heat treatment conditions, etc. A specific example of the performance to be predicted is, for example, "the absolute value of the performance of a certain product." In this case, the product is a tire for automobiles, and the product performance includes wear performance, fuel efficiency, durability, etc. Another specific example of the information to be predicted is, for example, information on the performance of an object manufactured under predicted experimental or manufacturing conditions.

[0034] The memory unit 102 records information about the comparison target of the prediction target. A specific example of the comparison target information of the prediction target is the same as the specific example of the prediction target information described above, for example, "experimental conditions for a certain product."

[0035] The prediction unit 103 inputs the information to be predicted acquired by the acquisition unit 101 into a trained model 20 generated by machine learning using features extracted by predetermined operations on the training data associated with the information to be predicted acquired by the acquisition unit 101, and obtains the output from the trained model 20 to predict the performance of the target to be predicted against the comparison target stored in the memory unit 102. The trained model 20 is a model generated by machine learning using features extracted by predetermined operations on the training data associated with the information to be predicted acquired by the acquisition unit 101. The predetermined operation is an operation to extract features from the explanatory variable column of the table in which the training data is stored.

[0036] The prediction device 10, by performing prediction processing using the trained model 20, can predict the absolute value of the performance of the target product, reflecting the underlying principles of past experimental data. The features based on past experimental results are features that reflect hypotheses, thoughts, or technical knowledge accumulated to obtain the target performance. In other words, the prediction device 10 according to this embodiment can significantly improve performance, shorten product development time, and improve the accuracy of selecting development directions by making predictions using the trained model 20 that reflects hypotheses, thoughts, or technical knowledge accumulated to obtain the target performance.

[0037] 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.

[0038] 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.

[0039] 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 result 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 the values ​​of the experimental result data, respectively. The values ​​of the experimental result data 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).

[0040] 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.

[0041] 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.

[0042] 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".

[0043] 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.

[0044] 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.

[0045] 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.

[0046] 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.

[0047] Furthermore, before subtraction, any preprocessing such as feature design (including ratio calculation), normalization, or nonlinear transformation may be performed.

[0048] 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.

[0049] Here, we show an example where data to be processed is subjected to merging and arithmetic operations before being extracted.

[0050] 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, and stores the extracted feature quantities in the "IC component 1", "IC component 2", and "IC component 3" columns, respectively.

[0051] 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.

[0052] Furthermore, during the extraction process, any preprocessing, such as normalization or nonlinear transformation, may be performed on each difference sequence when extracting features.

[0053] 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.

[0054] 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.

[0055] 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 predict 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.

[0056] 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.

[0057] 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.

[0058] 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).

[0059] 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 for prediction by the prediction unit 102.

[0060] This section will explain specific examples of predictions made by the prediction device 10. First, we will explain a specific example of a forward analysis in which the prediction device 10 predicts experimental results (e.g., physical properties) from experimental conditions. In the following explanation, we will describe a forward analysis that predicts hardness as a physical property.

[0061] As described above, the prediction unit 103 predicts the performance of the prediction target using the learned learned model 20. When predicting the absolute value of the performance of the prediction target, the prediction unit 103 uses the test condition X acquired by the acquisition unit 101 A from the past test condition X B and the known test result Y B obtained under the past test condition X B to predict the unknown test result Y A under the test condition X A . Substituting into Equation (2), the prediction unit 103 gives the difference between the test condition X A and the test condition X B to the learned model 20, and adds the known test result Y B to the output obtained from the learned model 20 to predict the unknown test result Y A . Y A -Y B =F(X A -X B ) Y A =F(X A -X B )+Y B (3)

[0062] Also, the prediction unit 103 gives the ratio between the test condition X A and the test condition X B to the learned model 20, and multiplies the output obtained from the learned model 20 by the known test result Y B to predict the unknown test result Y<00000​​​​​​​​​​​​​​​​​​​​​​​​​​​The difference or ratio is given to the trained model 20, and the output obtained from the trained model 20 is the known test result Y. B By adding or multiplying, the unknown test result Y A It can be predicted.

[0064] Next, we will explain a specific example of inverse analysis in which the prediction device 10 predicts test conditions from the target performance. The acquisition unit 101 predicts test conditions X A The information Y of the performance (e.g., hardness) that we want to predict. A The prediction unit 102 then obtains the known test result Y. B Subtract or divide by . Next, the prediction unit 102 acquires the trained model 20 recorded in the recording unit 303. Next, the prediction unit 102 applies the performance information to be predicted to the trained model 20, and from the acquired performance information, determines the test condition X required to achieve that performance. A And, known test condition X B The prediction unit 102 then predicts the difference or ratio with test condition X. A and test condition X B If the difference is predicted, then the known test condition X will be used for that difference. B Add the test condition X A and test condition X B If the ratio is predicted, the difference will be the known test condition X. B Multiply by the test condition X A To predict.

[0065] When extracting features used in constructing the trained model 20 from past experimental data, using experimental data on specific themes, categories, etc., makes it possible to construct a trained model 20 that embodies the ideas behind the experimental data for those themes, categories, etc.

[0066] For example, if a trained model 20 is constructed from features extracted from experimental data for a specific year, the prediction device 10 can construct an experimental concept by predicting the absolute value of the target's performance based on technologies or know-how discovered or developed in that year, or by predicting experimental conditions to which technologies developed in that year are applied.

[0067] For example, if a trained model 20 is constructed from features extracted from the experimental data of a specific experimental designer, the prediction device 10 can predict the absolute value of the performance of the target based on the experience, knowledge, experimental philosophy, and hypotheses of that experimental designer, or it can predict the experimental conditions based on the experience, knowledge, experimental philosophy, and hypotheses of that experimental designer, thereby enabling the construction of an experimental philosophy.

[0068] For example, if a trained model 20 is constructed from features extracted from experimental data for a specific product application, the prediction device 10 can predict the absolute value of the target's performance based on the technology, experience, experimental philosophy, and hypotheses in the domain of that product application, or it can predict experimental conditions that apply the technology, experience, experimental philosophy, and hypotheses suitable for improving the target performance of that product application or for multi-objective optimization, thereby enabling the construction of an experimental philosophy.

[0069] For example, if a trained model 20 is constructed from features extracted from experimental data for a specific component application, the prediction device 10 can predict the absolute value of the target's performance based on the technology, experience, experimental philosophy, and hypotheses in the domain of that component application, or it can predict experimental conditions that apply the technology, experience, experimental philosophy, and hypotheses suitable for improving the target performance of that component application and for multi-objective optimization, thereby enabling the construction of an experimental philosophy.

[0070] For example, if a trained model 20 is constructed from features extracted from experimental data of a specific development stage, the prediction device 10 can construct an experimental plan by predicting the absolute value of the experimental level or performance to be evaluated that should be carefully evaluated at that development stage, or by predicting experimental conditions suitable for improving or optimizing the target performance that is important at that development stage.

[0071] For example, if a trained model 20 is constructed from features extracted from experimental data of a specific business function or organizational unit, the prediction device 10 can predict the absolute value of the target performance based on the technical expertise of that business function or organizational unit, or it can construct an experimental concept by predicting experimental conditions to which the technical expertise, experimental concept, and hypothesis of that business function or organizational unit are applied.

[0072] For example, if a trained model 20 is constructed from features extracted from experimental data of a specific element under specific experimental conditions, the prediction device 10 can construct an experimental concept by predicting the absolute value of the performance of the target brought about by that specific element, or by predicting experimental conditions that utilize the effect of that specific element.

[0073] For example, if a trained model 20 is constructed from features extracted from experimental data from a specific sample provider, the prediction device 10 can predict the absolute value of the target's performance based on the technical expertise of that sample provider, or it can construct an experimental concept by predicting experimental conditions to which the technical expertise, experimental concept, and hypothesis of that sample provider are applied.

[0074] For example, if a trained model 20 is constructed from features extracted from experimental data for a specific experimental purpose, the prediction device 10 can construct an experimental concept by predicting the absolute value of the performance of the target based on a technology or hypothesis that is particularly effective in achieving that experimental purpose, or by predicting experimental conditions based on a technology or hypothesis that is particularly effective in achieving that experimental purpose.

[0075] For example, if a trained model 20 is constructed from features extracted from experimental data of a specific test evaluation method, the prediction device 10 can construct an experimental concept by predicting the absolute value of the target's performance based on techniques, hypotheses, or experimental conditions suitable for improving or optimizing the experimental results of that test evaluation method.

[0076] Next, the operation of the prediction device 10 will be explained.

[0077] Figure 10 is a flowchart showing the flow of the prediction process performed by the prediction device 10. The CPU 11 reads the prediction program from the ROM 12 or storage 14, loads it into the RAM 13, and executes it, thereby performing the prediction process.

[0078] In step S101, the CPU 11 acquires the information to be predicted and the information to be compared. The information to be predicted is input, for example, by the user of the prediction device 10 using the input unit 15.

[0079] Following step S101, in step S102, the CPU 11 uses the acquired information on the target to predict to predict the experimental data. Specifically, the CPU 11 inputs the information on the target to predict into the trained model 20, obtains the output from the trained model 20, and reflects the information on the comparison target to predict the absolute value of the target's performance.

[0080] The prediction device 10 predicts the test results using the trained model 20 through the series of processes described above, thereby predicting the absolute value of the target performance, which reflects the principles learned from past test results.

[0081] 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.

[0082] 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.

[0083] In addition, the prediction processing 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 processing, such as ASICs (Application Specific Integrated Circuits). Furthermore, the prediction processing 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.

[0084] Furthermore, while the above embodiments describe a configuration in which the prediction processing 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]

[0085] 10 Prediction device 20 Pre-trained Models

Claims

1. An acquisition unit that acquires information to be predicted, A recording unit that records information on the comparison target for the prediction target, A prediction unit that inputs the information to be predicted to a trained model generated by machine learning using features extracted by predetermined calculations on training data related to the information to be predicted, and obtains output from the trained model to predict the performance of the target to be predicted relative to the comparison target. A prediction device equipped with the following features.

2. 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 learning 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. The prediction device according to claim 1, which is an operation for extracting the feature quantities from the generated column.

3. The prediction device according to claim 1, wherein the prediction unit predicts the absolute value of the performance of the prediction target from the information of the comparison target and the amount of change of the prediction target relative to the comparison target.

4. The prediction device according to claim 1, wherein the learning data is data from an experimental design or data from an experimental result.

5. The prediction device according to claim 1, wherein the acquisition unit acquires information on experimental conditions or manufacturing conditions, or the performance of an object manufactured under predicted experimental conditions or manufacturing conditions, as information on the object to be predicted.

6. When the acquisition unit acquires information on experimental conditions or manufacturing conditions as information on the target to be predicted, it calculates a feature quantity based on the amount of change in the experimental conditions or manufacturing conditions as a predetermined calculation, and the prediction unit performs a process to predict the amount of change in the performance of the target based on the feature quantity. When the acquisition unit acquires information on the performance of an object manufactured under the predicted experimental conditions or manufacturing conditions as information on the target to be predicted, it calculates a feature quantity based on the amount of change in the performance of an object manufactured under the experimental conditions or manufacturing conditions as a predetermined calculation, and the prediction unit performs a process to predict or search for the amount of change in the experimental conditions or manufacturing conditions, as described in claim 5.

7. The prediction device according to claim 2, wherein the feature quantities are information related to the identification sequence used in the cross-combination.

8. The prediction device according to claim 2, wherein the aforementioned features are extracted by dimensionality reduction processing.

9. The processor, Obtain information to be predicted, The information to be predicted is input to a trained model generated by machine learning using features extracted through predetermined calculations on training data related to the information to be predicted, and the output from the trained model is obtained to predict the performance of the target to be predicted relative to the recorded comparison target. A prediction method for executing a process.

10. On the computer, Obtain information to be predicted, The information to be predicted is input to a trained model generated by machine learning using features extracted through predetermined calculations on training data related to the information to be predicted, and the output from the trained model is obtained to predict the performance of the target to be predicted relative to the recorded comparison target. A predictive program that executes a process.

Images