Property prediction device, property prediction method, and program

Abstract

A property prediction device for predicting a property of a composite material composed of a plurality of raw material classes, the property prediction device comprising: a prediction model creating unit that uses a learning data set for a composite material comprising a first raw material class of material species and a second raw material class of material species to create a prediction model that has machine-learned the correspondence relationship between a property of the composite material, which is an objective variable, and a compounded quantity of the first raw material class of material species and a weighted feature of the second raw material class of material species, which are explanatory variables; and a prediction unit by which a compounded quantity of the first raw material class of material species and a weighted feature of the second raw material class of material species that have been created from prediction data for the composite material for which the property is to be predicted are input to the prediction model as explanatory variables to predict the property of the composite material corresponding to the prediction data.

Description

Characteristic prediction device, characteristic prediction method, and program

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

[0002] In recent years, it has become possible to predict the properties of composite materials, such as resin composite materials, using computer-based machine learning.

[0003] Patent Document 1 describes a method for using learning data including composition data and characteristic data to perform a learning process for a model that outputs recommended composition data in response to input of target characteristic data, and inputting the target characteristics into the model to output a composition for producing a photosensitive resin composition with the target characteristics.

[0004] For example, Patent Document 1 describes that the composition indicated by the composition data may be the presence or absence of raw materials capable of producing a photosensitive resin composition, may be the compounds contained in the raw materials (for example, the names or structural formulas of specific compounds contained in the raw materials indicated by general names), or may be the content ratios of compounds contained in the raw materials.

[0005] Furthermore, Patent Document 2 describes a method of constructing a regression model for predicting physical property values ​​using experimental values ​​of the physical properties of a polymer and the number density of partial structures of the polymer, and predicting physical property values ​​corresponding to an input polymer structure using the regression model.

[0006] Japanese Patent Application Laid-Open No. 2020-77346 Public Relations Patent No. 6633820

[0007] In property prediction devices that predict the properties of composite materials composed of multiple raw material classifications, there is a growing demand for technology that can accurately predict the impact that a specific raw material classification will have on the properties of a composite material, for example, when searching for new raw materials in a specific raw material classification such as additives.

[0008] An object of the present disclosure is to provide a property prediction device, a property prediction method, and a program that can accurately predict the effect of a specific raw material classification on the properties of a composite material composed of multiple raw material classifications.

[0009] The present disclosure has the following configuration.

[0010] [1] A property prediction device for predicting the properties of a composite material composed of a plurality of raw material classifications, comprising: a prediction model creation unit that uses a training dataset of the composite material that is configured to include material types of a first raw material classification and material types of a second raw material classification to create a prediction model through machine learning of correspondences between the properties of the composite material, which are objective variables, and the blending amounts of the material types of the first raw material classification and the weighted feature values ​​of the material types of the second raw material classification, which are explanatory variables; and a prediction unit that inputs the blending amounts of the material types of the first raw material classification and the weighted feature values ​​of the material types of the second raw material classification, which are created from prediction data of the composite material whose properties are to be predicted, into the prediction model as explanatory variables, and predicts the properties of the composite material corresponding to the prediction data.

[0011] [2] The property prediction device according to [1], wherein the explanatory variables include information on blending amounts of one or more raw materials included in the material type of the first raw material classification, and information on the weighted feature values ​​that are products of the feature values ​​of each of the one or more raw materials included in the material type of the second raw material classification and the blending amounts of the raw materials.

[0012] [3] The property prediction device according to [1] or [2], wherein the prediction model creation unit sets the raw material classification of a raw material to be searched for optimization as the second raw material classification, among a plurality of raw material classifications constituting the composite material, and sets the raw material classification of a raw material other than the searched raw material classification as the first raw material classification.

[0013] [4] The property prediction device according to [3], wherein the prediction unit predicts the properties of the composite material while searching for combinations of one or more raw materials included in the material type of the second raw material classification to be optimized and changing the blending amounts of one or more raw materials included in the combinations, and identifies the raw material combinations and the blending amounts of one or more raw materials included in the combinations, in which the predicted properties approximate target properties of the composite material corresponding to the prediction data.

[0014] [5] The property prediction device according to any one of [1] to [4], wherein the prediction model creation unit includes: a dependent variable identification unit that identifies a characteristic of the composite material as a dependent variable from the training dataset; a design condition identification unit that identifies design conditions of the composite material from the training dataset; a feature creation unit that creates a feature for each of one or more raw materials included in the material type of the second raw material classification from the design conditions; an explanatory variable creation unit that creates, as explanatory variables, blending amounts of one or more raw materials included in the material type of the first raw material classification and the weighted feature for each of the one or more raw materials included in the material type of the second raw material classification; and a learning processing unit that creates a prediction model by machine learning the correspondence between the dependent variable and the explanatory variables.

[0015] [6] The characteristic prediction device according to any one of [1] to [5], characterized in that the composite material is a resin composite material containing a main raw material that is a material type of the first raw material classification and an additive that is a material type of the second raw material classification and has a smaller blending amount than the main raw material.

[0016] [7] The characteristic prediction device according to any one of [1] to [6], wherein the raw material classification is a monomer, an oligomer, a polymer, a filler, a catalyst, a polymerization initiator, a polymerization inhibitor, a crosslinking agent, or a curing agent.

[0017] [8] The property prediction device according to any one of [1] to [7], wherein the feature amount is information obtained by quantifying structural features of molecules or information obtained by quantifying chemical features of molecules.

[0018] [9] The characteristic prediction device according to any one of [1] to [7], wherein the feature amount is information described by a dummy variable representing a brand or model number of the material type of the second raw material classification using “0” and “1”.

[0019]

[10] A property prediction method in which a computer predicts properties of a composite material composed of a plurality of raw material classifications, the property prediction method comprising: a step of using a training dataset of the composite material composed of material types of a first raw material classification and material types of a second raw material classification to create a prediction model by machine learning of correspondences between the properties of the composite material, which are objective variables, and the blending amounts of the material types of the first raw material classification and the weighted feature values ​​of the material types of the second raw material classification, which are explanatory variables; and a step of inputting the blending amounts of the material types of the first raw material classification and the weighted feature values ​​of the material types of the second raw material classification, which are created from prediction data of the composite material whose properties are to be predicted, into the prediction model as explanatory variables, and predicting the properties of the composite material corresponding to the prediction data.

[0020]

[11] A program for causing a computer to execute the following steps in a computer that predicts the properties of a composite material composed of a plurality of raw material classifications: using a training dataset for the composite material that is composed of material types of a first raw material classification and material types of a second raw material classification, to create a prediction model by machine learning of correspondences between the properties of the composite material, which are objective variables, and the blending amounts of the material types of the first raw material classification and the weighted feature values ​​of the material types of the second raw material classification, which are explanatory variables; and inputting the blending amounts of the material types of the first raw material classification and the weighted feature values ​​of the material types of the second raw material classification, which are created from prediction data for the composite material whose properties are to be predicted, into the prediction model as explanatory variables, and predicting the properties of the composite material corresponding to the prediction data.

[0021] According to the present disclosure, it is possible to accurately predict the effect of a specific raw material classification on the properties of a composite material composed of multiple raw material classifications.

[0022] FIG. 1 is a configuration diagram of an example of an information processing system according to the present embodiment. FIG. 2 is a hardware configuration diagram of an example of a computer according to the present embodiment. FIG. 3 is a functional configuration diagram of an example of an information processing system according to the present embodiment. FIG. 4 is a configuration diagram of an example of design conditions for a resin composite material. FIG. 5 is a configuration diagram of an example of weighted feature amounts for a resin composite material. FIG. 6 is a configuration diagram of an example of weighted feature amounts for a resin composite material. FIG. 7 is a configuration diagram of an example of weighted feature amounts for a resin composite material. FIG. 8 is a configuration diagram of an example of weighted feature amounts for a resin composite material. FIG. 9 is a configuration diagram of an example of blending amounts of main raw materials and weighted feature amounts of additives for a resin composite material. FIG. 10 is a configuration diagram of an example of blending amounts of main raw materials and weighted feature amounts of additives for a resin composite material. FIG. 11 is a configuration diagram of an example of blending amounts of main raw materials and weighted feature amounts of additives for a resin composite material. FIG. 12 is an explanatory diagram of an example of an outline of a characteristic prediction method of the information processing system according to the present embodiment. FIG. 13 is a configuration diagram of an example of design conditions. FIG. 14 is an explanatory diagram of an example of a process for creating weighted feature amounts of additives. FIG. 15 is an explanatory diagram of an example of a process for creating weighted feature amounts of additives. FIG. 16 is an explanatory diagram of an example of created explanatory variables. FIG. 17 is a flowchart of an example of a learning stage process of the information processing system according to the present embodiment. FIG. 18 is an image diagram of an example of a screen for selecting a material to be searched for. FIG. 19 is a configuration diagram of an example of explanatory variables. FIG. 19 is a flowchart of an example of a prediction stage process of the information processing system according to the present embodiment.

[0023] Next, an embodiment of the present invention will be described in detail. However, the present invention is not limited to the following embodiment. In this embodiment, a resin composite material will be described as an example of a composite material composed of multiple raw material classes. The multiple raw material classes include monomers, oligomers, polymers, fillers, catalysts, polymerization initiators, polymerization inhibitors, crosslinking agents, and curing agents. Monomers, oligomers, and polymers are examples of main raw materials. Fillers, catalysts, polymerization initiators, polymerization inhibitors, crosslinking agents, and curing agents are examples of additives.

[0024] [First Embodiment] <System Configuration> Fig. 1 is a configuration diagram of an example of an information processing system according to this embodiment. The information processing system 1 in Fig. 1 includes a characteristic prediction device 10 and a user terminal 12. The characteristic prediction device 10 and the user terminal 12 are connected to each other so as to be able to communicate data via a communication network 18 such as a local area network (LAN) or the Internet.

[0025] The user terminal 12 is an information processing terminal such as a PC, tablet terminal, or smartphone operated by a user. The user terminal 12 accepts input of information necessary for predicting the properties of a resin composite material composed of multiple raw material classifications from the user, and causes the property prediction device 10 to predict the properties of the resin composite material. The user terminal 12 also receives information such as the properties of the resin composite material predicted by the property prediction device 10, and displays the information on a display device, for example, for the user to confirm.

[0026] The property prediction device 10 is an information processing device such as a PC or workstation that predicts the properties of a resin composite material. The property prediction device 10 creates a prediction model by machine learning using a training dataset as described below. When the property prediction device 10 receives information necessary for predicting the properties of the resin composite material from a user terminal 12, it predicts the properties of the resin composite material using the prediction model. The property prediction device 10 transmits information such as the predicted properties of the resin composite material to the user terminal 12.

[0027] The information processing system 1 in Fig. 1 is merely an example, and it goes without saying that there are various system configuration examples depending on the application and purpose. For example, the characteristic prediction device 10 may be realized by multiple computers, or may be realized as a cloud computing service. Furthermore, the information processing system 1 in Fig. 1 may be realized by a standalone computer.

[0028] <Hardware Configuration> The characteristic prediction device 10 and the user terminal 12 in FIG. 1 are realized by, for example, a computer 500 having the hardware configuration shown in FIG.

[0029] Fig. 2 is a diagram showing an example of the hardware configuration of a computer according to this embodiment. The computer 500 in Fig. 2 includes an input device 501, a display device 502, an external I / F 503, a RAM 504, a ROM 505, a CPU 506, a communication I / F 507, and an HDD 508, all of which are interconnected by a bus B. The input device 501 and the display device 502 may be connected to each other for use.

[0030] The input device 501 includes a touch panel, operation keys, buttons, a keyboard, a mouse, etc., which are used by the user to input various signals. The display device 502 includes a display such as a liquid crystal or organic EL display for displaying a screen, a speaker for outputting audio data such as voice and sound, etc. The communication I / F 507 is an interface for the computer 500 to perform data communication.

[0031] The HDD 508 is an example of a non-volatile storage device that stores programs and data. The stored programs and data include an OS, which is basic software that controls the entire computer 500, and applications that provide various functions on the OS. Note that the computer 500 may use a drive device that uses flash memory as a storage medium (e.g., a solid-state drive (SSD)) instead of the HDD 508.

[0032] The external I / F 503 is an interface with an external device. The external device may be a recording medium 503a. This allows the computer 500 to read and / or write data from and to the recording medium 503a via the external I / F 503. The recording medium 503a may be a flexible disk, a CD, a DVD, an SD memory card, a USB memory, or the like.

[0033] The ROM 505 is an example of a non-volatile semiconductor memory (storage device) that can retain programs and data even when the power is turned off. The ROM 505 stores programs and data such as the BIOS, OS settings, and network settings that are executed when the computer 500 starts up. The RAM 504 is an example of a volatile semiconductor memory (storage device) that temporarily retains programs and data.

[0034] The CPU 506 is a computing device that reads programs and data from storage devices such as the ROM 505 and the HDD 508 onto the RAM 504 and executes processing to realize overall control and functions of the computer 500. By executing programs, the computer 500 according to this embodiment can realize various functions of the characteristic prediction device 10 and the user terminal 12, which will be described later. The programs may be read from a recording medium 503a in which the programs are stored via the external I / F 503 and executed.

[0035] <Functional Configuration> The configuration of the information processing system 1 according to this embodiment will be described. Fig. 3 is a functional configuration diagram of an example of the information processing system according to this embodiment. Note that in the configuration diagram of Fig. 3, portions that are not necessary for explaining this embodiment are omitted as appropriate.

[0036] 3 includes a prediction model creation unit 30, a prediction unit 32, an output unit 34, a learning dataset storage unit 40, and a prediction model storage unit 42. The user terminal 12 includes an information display unit 20, an operation reception unit 22, a request transmission unit 24, and a response reception unit 26.

[0037] The information display unit 20 of the user terminal 12 displays information for the user to confirm on the display device 502. The operation accepting unit 22 accepts various operations from the user, such as input of information necessary for predicting the properties of a resin composite material. The request sending unit 24 sends a request for processing, such as predicting the properties of a resin composite material, to the property prediction device 10. In addition, the response receiving unit 26 receives a response to the request for processing, such as predicting the properties of a resin composite material, sent by the request sending unit 24.

[0038] The training dataset storage unit 40 of the characteristic prediction device 10 stores a training dataset for a resin composite material as described below. The prediction model creation unit 30 creates a prediction model by machine learning, as described below, using the training dataset stored in the training dataset storage unit 40. The prediction model storage unit 42 stores the created prediction model.

[0039] The prediction unit 32 predicts the properties of the resin composite material corresponding to the prediction data, using the prediction data (described below) received from the user terminal 12, which is information necessary for predicting the properties of the resin composite material, and the prediction model stored in the prediction model storage unit 42, as described below. The output unit 34 transmits the properties of the resin composite material predicted by the prediction unit 32 as a response to a request from the user terminal 12 for prediction of the properties of the resin composite material.

[0040] 3 includes a response variable specification unit 50, a design condition specification unit 52, a feature quantity creation unit 54, an explanatory variable creation unit 56, and a learning processing unit 58. The response variable specification unit 50 specifies the properties of the resin composite material as response variables from the training dataset stored in the training dataset storage unit 40. The design condition specification unit 52 specifies the design conditions of the resin composite material from the training dataset stored in the training dataset storage unit 40.

[0041] The feature creation unit 54 identifies information about the additives from the design conditions of the resin composite material and creates feature quantities for the additives. Note that the feature quantities are information that quantifies the structural characteristics of the molecules or information that quantifies the chemical characteristics of the molecules. The feature quantities for the additives may be described as dummy variables represented by "0" and "1," such as the brand name and model number of the additive.

[0042] One example of a method for quantifying molecular structural features is Extended Circular Fingerprints (hereinafter referred to as ECFP). ECFP quantifies the structural features of a molecule by extracting the types and numbers of all substructures and expressing them as vectors (columns: type, values: number). Note that substructures can be expressed using notation such as Simplified Molecular Input Line Entry System (hereinafter referred to as SMILES) notation. ECFP can calculate the structural features of a molecule, for example, by inputting additive information expressed in SMILES notation into an existing library. Another example of a method for quantifying molecular structural features is graph convolutional neural networks. Graph convolutional neural networks can calculate the structural features of a molecule, for example, by inputting additive information expressed in SMILES notation into an existing library.

[0043] Furthermore, for example, one example of a method for quantifying the chemical characteristics of a molecule is to extract the physical property information of the molecule and express it as a vector (column: physical property information, value: numerical value), thereby quantifying the chemical characteristics of the molecule. In the method for quantifying the chemical characteristics of a molecule, for example, additive information expressed in SMILES notation can be input into an existing library to calculate the chemical characteristics of the molecule. The physical property information of the molecule may be, for example, molecular weight, number of valence electrons, partial charge, number of amino groups, number of hydroxyl groups, etc. Furthermore, the physical property information of the molecule may be physical property values ​​that can be calculated using quantum chemistry calculation software, such as HOMO, LUMO, charge, refractive index, or frequency, or physical property values ​​that can be measured experimentally, such as melting point, viscosity, or specific surface area.

[0044] The explanatory variable creation unit 56 identifies information about the main raw materials from the design conditions of the resin composite material and identifies the blending amount for each main raw material. Furthermore, the explanatory variable creation unit 56 calculates the product of each feature amount of an additive created by the feature amount creation unit 54 and the blending amount of that additive. The product of the feature amount of an additive and the blending amount is an example of a weighted feature amount. The explanatory variable creation unit 56 creates explanatory variables by combining the blending amount of each main raw material and the weighted feature amount of the additive.

[0045] The learning processing unit 58 also creates a prediction model by machine learning the correspondence between the objective variable and the explanatory variables. The learning processing unit 58 stores the created prediction model in the prediction model storage unit 42.

[0046] The prediction unit 32 identifies the design conditions of the resin composite material from prediction data (described below), which is information necessary for predicting the properties of the resin composite material, received from the user terminal 12. Similarly to the explanatory variable creation unit 56, the prediction unit 32 creates explanatory variables from the identified design conditions of the resin composite material, and inputs the explanatory variables into a prediction model, thereby predicting the properties of the resin composite material corresponding to the prediction data.

[0047] The output unit 34 then transmits the properties of the resin composite material corresponding to the prediction data predicted by the prediction unit 32 as a response to a request for prediction of the properties of the resin composite material from the user terminal 12. Note that the configuration diagram in Figure 3 is an example. Various configurations of the information processing system 1 according to this embodiment can be considered.

[0048] <Consideration on a method for predicting the properties of a resin composite material> The properties of a resin composite material composed of multiple raw material classifications can be predicted, for example, from the names of the main raw materials and additives and their presence or absence. Figure 4 is a configuration diagram of an example of design conditions for a resin composite material. As shown in Figure 4, the design conditions set the blending amounts of each raw material included in the material types of the resin composite material, such as "Resin 1," "Resin 2," "Resin 3," "Catalyst 1," and "Additive 1." In the design conditions in Figure 4, "Additive α" to "Additive ε" are assumed to be unlearned additives. The names of the main raw materials and additives and their presence or absence may be expressed as dummy variables represented by "0" and "1," using information that does not directly indicate physicochemical properties, such as the brand and model number of the main raw materials and additives.

[0049] In the case of the design conditions in Figure 4, the design conditions are the same except for "additive 1," so even if the names of the additives are changed to "additive α" to "additive ε," no difference is likely to appear in the predicted values, and the effect of the additive on the properties of the resin composite material cannot be accurately predicted.

[0050] Furthermore, the characteristics of a resin composite material composed of multiple raw material classifications can be predicted from the weighted feature values ​​of the main raw materials and additives. Figures 5A to 5C are diagrams illustrating an example of the configuration of weighted feature values ​​of a resin composite material. The weighted feature values ​​are information in which the feature values ​​of the main raw materials and additives are each weighted by the blending amount (or blending ratio). The total blending ratio (100%) is the total amount of the raw materials blended. The feature values ​​of the resin composite material are calculated as the sum of the weighted feature values ​​of all the raw materials.

[0051] 5A to 5C , the blending amount of the additive (Z) is smaller than that of the main raw material (A), and the weighted feature amount of the additive (Z) is also smaller than that of the main raw material (A). In this way, the weighted feature amount of the additive (Z) is smaller than that of the main raw material (A). Therefore, when the main raw material (A) and the additive (Z) have a partial structure in common, the change in the weighted feature amount of the additive (Z) is hidden. Therefore, the change in the weighted feature amount of the additive (Z) is unlikely to be reflected in the feature amount of the resin composite material, and the effect of the additive (Z) on the properties of the resin composite material cannot be accurately predicted.

[0052] Therefore, in this embodiment, the properties of a resin composite material composed of multiple raw material classifications are predicted from the blending amounts of the main raw materials and the weighted feature values ​​of the additives. Figures 6A to 6C are diagrams showing an example of the blending amounts of the main raw materials and the weighted feature values ​​of the additives in a resin composite material. In the examples of Figures 6A to 6C, the blending amounts are used instead of the feature values ​​of the main raw materials.

[0053] 6A to 6C, even if the main raw material (A) and the additive (Z) share a portion of their partial structures in common, the change in the weighted feature amount of the additive (Z) is not obscured by the weighted feature amount of the main raw material (A). Therefore, the change in the weighted feature amount of the additive (Z) is easily reflected in the feature amount of the resin composite material, and the influence of the additive (Z) on the properties of the resin composite material can be predicted with high accuracy.

[0054] <Processing> Hereinafter, details of the processing performed by the information processing system 1 according to this embodiment to predict the properties of a resin composite material composed of a plurality of raw material classifications will be described.

[0055] 7 is an explanatory diagram showing an example of an outline of a property prediction method of the information processing system according to this embodiment. Fig. 7 shows an example of creating explanatory variables for predicting the properties of a resin composite material composed of multiple raw material classes by combining a column (N-dimensional) in which the names of N types of raw materials in raw material class A, which are main raw materials, are used as variables with a column (W-dimensional) of weighted features of raw material class Z, which is an additive.

[0056] FIG. 7 is an example of explanatory variables when searching for additives of raw material category (Z). FIG. 7 can also be considered as explanatory variables when not searching for main raw materials of raw material category A. FIG. 7 shows explanatory variables created from the blend amounts of N types of raw materials of raw material category A, which are the main raw materials, and W types of weighted feature amounts (value of each feature amount x blend amount) of raw material category Z, which are additives. The blend amounts can be expressed using molar ratios, or may be expressed using weight ratios.

[0057] In this embodiment, explanatory variables created as shown in FIG. 7 are used, and a prediction model capable of predicting the properties of a resin composite material is created by machine learning using a learning dataset to determine the correspondence between the properties of the resin composite material, which are the objective variables, and the explanatory variables as shown in FIG. 7 .

[0058] Fig. 8 is a diagram showing an example of design conditions. The example in Fig. 8 shows an example of design conditions that include, as information, the blending amounts of N types of raw materials that are main raw materials and the blending amounts of "raw material O" to "raw material T" that are additives. For the main raw materials, the blending amounts are elements of the explanatory variables, as shown in the following formula (1).

[0059]

[0060] For additives, weighted features calculated as shown in the following formula (2) become elements of explanatory variables.

[0061]

[0062] 9A and 9B are explanatory diagrams of an example of a process for creating weighted features of additives. As shown in FIG. 9A, the features can be expressed for each experiment number i using a matrix of j (type of additive) × w (type of feature). Based on the blending amounts of the additives "raw material O" to "raw material T" shown in FIG. 8 and "feature 1" to "feature W" shown in FIG. 9A, weighted features can be calculated using equation (2) as shown in FIG. 9B.

[0063] For example, Fig. 9B shows an example of calculating weighted features of additives from the design conditions of "Experiment 1" of Experiment Number "1." In the example of Fig. 9B, weighted features of "Feature 1" to "Feature W" are calculated. "Feature 1 of Experiment 1" in Fig. 9B is calculated as the sum of weighted features, which are the products of the blending amounts "0.1" to "0.5" of "Raw Material O" to "Raw Material T" in "Experiment 1" in Fig. 8 and the feature amounts "3" to "1" of "Raw Material O" to "Raw Material T" in Fig. 9A.

[0064] 9B are calculated in the same manner as "Feature 1 of Experiment 1." Although not shown, the weighted feature values ​​of additives are calculated for the design conditions of Experiments No. 2 and onward in FIG. 8 in the same manner as for the design conditions of Experiment No. 1.

[0065] By combining the column of blending amounts of the main raw materials (N-dimensional) and the column of weighted features of additives (W-dimensional), explanatory variables such as those shown in Fig. 10 can be created. Fig. 10 is an explanatory diagram of an example of the created explanatory variables. As shown in Fig. 10, the number of dimensions of the explanatory variables is N+W.

[0066] 11 is a flowchart of an example of processing in the learning stage of the information processing system according to this embodiment. In step S10, the prediction model creation unit 30 of the characteristic prediction device 10 accepts the setting of a learning dataset. The setting of the learning dataset in step S10 may be performed by selecting one or more learning datasets stored in the learning dataset storage unit 40. Alternatively, the setting of the learning dataset in step S10 may be performed by storing one learning dataset accepted from a user in the learning dataset storage unit 40.

[0067] In step S12, the objective variable identification unit 50 of the prediction model creation unit 30 identifies a column of the characteristic (objective variable) to be predicted from the training data set whose settings were accepted in step S10. In addition, the design condition identification unit 52 identifies a column of the design conditions (explanatory variables) such as those shown in FIG. 8 from the training data set whose settings were accepted in step S10.

[0068] In step S14, the explanatory variable creation unit 56 identifies a column of main ingredients from the column of design conditions identified in step S12. In addition, the feature creation unit 54 identifies a column of additives from the column of design conditions identified in step S12. In step S16, the feature creation unit 54 creates a feature, for example, as shown in FIG. 9A , for the column of additives identified in step S14.

[0069] In step S18, the explanatory variable creation unit 56 calculates weighted feature quantities of the additives as shown in FIG. 9B from the product of the feature quantities of the additives as shown in FIG. 9A created by the feature creation unit 54 in step S16 and the blending amounts of the additives as shown in FIG. 8.

[0070] In step S20, the explanatory variable creation unit 56 combines the column of blending amounts of the main raw materials identified in step S14 with the column of weighted feature amounts of the additives calculated in step S18 to create explanatory variables such as those shown in FIG. 10 .

[0071] In step S22, the learning processing unit 58 performs machine learning on the correspondence between the objective variable identified in step S12 and the explanatory variables created in step S20, and creates a prediction model. The created prediction model is stored in the prediction model storage unit 42.

[0072] Although an example of searching for additives has been described above, it may also be possible to select the raw material to be searched for from a screen 1000 as shown in Fig. 12. Fig. 12 is an image diagram of an example of a screen for selecting the material to be searched for.

[0073] Screen 1000 in Fig. 12 shows a GUI (graphical user interface) for selecting a raw material classification to be searched for from a resin composite material composed of multiple raw material classifications as the raw material classification to be optimized. The user selects the raw material classification to be optimized from the raw material classifications displayed on screen 1000, such as alcohol raw materials, isocyanate raw materials, crosslinking agents, curing agents, and catalysts. For example, Fig. 12 shows an example in which "curing agent" has been selected as the raw material classification to be optimized. When the "Predict" button is pressed in the state shown in Fig. 12, the prediction model creation unit 30 of the property prediction device 10 can create explanatory variables, for example, as shown in Fig. 13, according to the procedure of the flowchart shown in Fig. 11.

[0074] Fig. 13 is a diagram illustrating an example of explanatory variables. The explanatory variables in Fig. 13 are created by combining the weighted feature of "hardening agent" selected as the material classification to be optimized on the screen 1000 in Fig. 12 with the blending amounts of material classifications that were not selected as material classifications to be optimized. As shown in Fig. 13, the information processing system 1 according to this embodiment creates explanatory variables that combine elements that represent blending amounts of material classifications that were not selected as material classifications to be optimized with elements that represent weighted feature of material classifications that were selected as material classifications to be optimized, and can be used for machine learning.

[0075] In this embodiment, an example has been described in which the raw material classification to be optimized is additives, but the raw material classification to be optimized may also be a main raw material, as shown in screen 1000 of Fig. 12. For example, if "insulinate raw material" is selected as the raw material classification to be optimized on screen 1000 of Fig. 12, an explanatory variable is created that combines the weighted feature of the "insulinate raw material" with the blending amounts of the alcohol raw material, crosslinking agent, curing agent, and catalyst. Furthermore, although screen 1000 of Fig. 12 shows an example in which one raw material classification to be optimized is selected, multiple raw material classifications may be selected.

[0076] 14 is a flowchart showing an example of processing at the prediction stage of the information processing system according to this embodiment. In step S30, the prediction unit 32 of the characteristic prediction device 10 accepts settings of prediction data. In step S32, the prediction unit 32 identifies a sequence of design conditions, such as those shown in FIG. 8, from the prediction data accepted in step S30.

[0077] In step S34, the prediction unit 32 identifies a sequence of main ingredients and a sequence of additives from the sequence of design conditions identified in step S32. In step S36, the prediction unit 32 creates feature quantities such as those shown in FIG. 9A for the sequence of additives identified in step S34.

[0078] In step S38, the prediction unit 32 calculates weighted feature quantities of the additives as shown in FIG. 9B from the product of the feature quantities of the additives as shown in FIG. 9A created in step S36 and the blending amounts of the additives as shown in FIG. 8.

[0079] In step S40, the prediction unit 32 combines the column of blending amounts of the main raw materials identified in step S34 with the column of weighted feature amounts of the additives calculated in step S38 to create explanatory variables such as those shown in Fig. 10. In step S42, the prediction unit 32 inputs the explanatory variables created in step S40 into a prediction model to predict the properties of the resin composite material corresponding to the prediction data.

[0080] 14 is repeated while searching for combinations of additive raw materials and changing the blending amounts of the raw materials included in the combinations until the predicted properties of the resin composite material achieve the target properties of the resin composite material or a set number of calculations (e.g., 10,000 times) are completed. The prediction unit 32 predicts the properties of the resin composite material by using the combinations of additive raw materials and the blending amounts of the raw materials included in the combinations as exhaustive search points.

[0081] The exhaustive search points can be generated by generating the blending amounts of the raw materials included in the combinations, for example, randomly or at predetermined intervals within a predetermined range. By using the exhaustive search points where the predicted properties of the resin composite material approximate the target properties, the prediction unit 32 can identify the combinations of additive raw materials that approximate the target properties of the resin composite material and the blending amounts of the raw materials included in the combinations.

[0082] The properties of a resin composite material predicted by the property prediction device 10 according to this embodiment can be applied to, for example, a blending design device or blending design support device for a composite material composed of a plurality of raw material classifications, a program for realizing the blending design device or blending design support device, etc. Furthermore, the property prediction device 10 according to this embodiment may supply design conditions under which the predicted properties are close to target properties to a manufacturing device for a resin composite material, thereby causing the manufacturing device to produce the resin composite material.

[0083] As described above, according to the information processing system 1 of this embodiment, for a composite material composed of multiple raw material classifications, weighted features are calculated from raw materials of a specific raw material classification, and explanatory variables are created by combining these with the blending amounts of raw materials of the other raw material classifications. This reduces the influence of the other raw material classifications, and makes it possible to accurately predict the influence of a specific raw material classification on the properties of the composite material.

[0084] For example, the information processing system 1 according to this embodiment makes it possible to accurately predict changes in the properties of a composite material when the molecular structure of an additive (additive) whose blending amount is smaller than that of the main raw material is changed. It also makes it possible to screen additives that should be used to achieve desired properties. The information processing system 1 according to this embodiment is particularly effective when the additive and the main raw material share a portion of their partial structure.

[0085] Although the present embodiment has been described above, it will be understood that various changes in form and details are possible without departing from the spirit and scope of the claims. While the present invention has been described above based on examples, the present invention is not limited to the above examples and various modifications are possible within the scope of the claims. This application claims priority from basic application No. 2021-140833 filed with the Japan Patent Office on August 31, 2021, the entire contents of which are incorporated herein by reference.

[0086] REFERENCE SIGNS LIST 1 Information processing system 10 Characteristics prediction device 12 User terminal 18 Communication network 20 Information display unit 22 Operation reception unit 24 Request transmission unit 26 Response reception unit 30 Prediction model creation unit 32 Prediction unit 34 Output unit 40 Learning dataset storage unit 42 Prediction model storage unit 50 Objective variable identification unit 52 Design condition identification unit 54 Feature creation unit 56 Explanatory variable creation unit 58 Learning processing unit

Claims

1. A property prediction device for predicting properties of a composite material composed of a plurality of raw material classifications, comprising: a prediction model creation unit that uses a learning dataset of a composite material including a material type of a first raw material classification and a material type of a second raw material classification to create a prediction model by machine learning a correspondence relationship between a characteristic of the composite material, which is a target variable, and a blending amount of the material type of the first raw material classification and a weighted feature value of the material type of the second raw material classification, which are explanatory variables; a prediction unit that inputs blending amounts of the material types of the first raw material classification and weighted feature values ​​of the material types of the second raw material classification, which are created from prediction data of a composite material whose characteristics are to be predicted, into the prediction model as explanatory variables, and predicts the characteristics of the composite material corresponding to the prediction data; A characteristic prediction device having the above structure.

2. The explanatory variables include information on the blending amounts of one or more raw materials included in the material type of the first raw material classification, and information on the weighted feature amount which is a product of the feature amount of each of one or more raw materials included in the material type of the second raw material classification and the blending amount of the raw materials.

2. The characteristic prediction device according to claim 1,

3. The prediction model creation unit sets a raw material classification of a raw material to be searched for optimization among a plurality of raw material classifications constituting the composite material as the second raw material classification, and sets a raw material classification other than the raw material classification of the raw material to be searched for optimization as the first raw material classification.

3. The characteristic prediction device according to claim 1 or 2,

4. The prediction unit predicts the properties of the composite material while searching for a combination of one or more raw materials included in the material type of the second raw material classification to be optimized and changing the blending amounts of one or more raw materials included in the combination, and identifies the combination of raw materials and the blending amounts of one or more raw materials included in the combination, in which the predicted properties are approximate to the target properties of the composite material corresponding to the prediction data.

4. The characteristic prediction device according to claim 3,

5. The prediction model creation unit, a response variable specification unit that specifies a characteristic of the composite material as a response variable from the learning data set; a design condition specification unit that specifies design conditions of the composite material from the learning data set; a feature creation unit that creates a feature for each of one or more raw materials included in the material type of the second raw material classification based on the design conditions; an explanatory variable creation unit that creates, as explanatory variables, the blending amounts of one or more raw materials included in the material type of the first raw material classification and the weighted feature amounts of each of the one or more raw materials included in the material type of the second raw material classification; a learning processing unit that performs machine learning on the correspondence between the objective variable and the explanatory variable to create a prediction model; 3. The characteristic prediction device according to claim 1, further comprising:

6. The composite material is a resin composite material including a main raw material which is a material type of the first raw material classification, and an additive which is a material type of the second raw material classification and is blended in a smaller amount than the main raw material.

3. The characteristic prediction device according to claim 1 or 2,

7. The raw material classification is a monomer, an oligomer, a polymer, a filler, a catalyst, a polymerization initiator, a polymerization inhibitor, a crosslinking agent, or a curing agent; The characteristic prediction device according to claim 1 or 2.

8. The feature amount is information that quantifies structural features of a molecule or information that quantifies chemical features of a molecule. The characteristic prediction device according to claim 1 or 2.

9. The feature amount is information described by a dummy variable expressing the brand or model number of the material type of the second raw material classification with "0" and "1". The characteristic prediction device according to claim 1 or 2.

10. A method for predicting properties of a composite material composed of a plurality of raw material classifications, comprising the steps of: a step of creating a prediction model by machine learning of a correspondence relationship between a characteristic of the composite material, which is a target variable, and a blending amount of the material type of the first raw material classification and a weighted feature value of the material type of the second raw material classification, which are explanatory variables, using a learning dataset of a composite material including a material type of a first raw material classification and a material type of a second raw material classification; inputting the blending amounts of the material types of the first raw material classification and the weighted feature amounts of the material types of the second raw material classification, which are created from prediction data of the composite material whose characteristics are to be predicted, into the prediction model as explanatory variables, and predicting the characteristics of the composite material corresponding to the prediction data; The method for predicting characteristics includes:

11. A computer predicts the properties of composite materials made up of multiple raw material classes. A step of creating a prediction model by machine learning a correspondence relationship between a characteristic of the composite material, which is a target variable, and a blending amount of the material type of the first raw material classification and a weighted feature value of the material type of the second raw material classification, which are explanatory variables, using a learning dataset of the composite material including the material type of the first raw material classification and the material type of the second raw material classification; a step of inputting blending amounts of the material types of the first raw material classification and weighted feature amounts of the material types of the second raw material classification, which are created from prediction data of a composite material whose characteristics are to be predicted, into the prediction model as explanatory variables, and predicting the characteristics of the composite material corresponding to the prediction data; A program for executing the above.