Proposed method, information processing device, and program

Abstract

We provide formulation proposal technology that enables material design that takes into account resilience from the perspective of raw material supply. [Solution] The information processing device 10 comprises a candidate generation unit 110 and a calculation unit 130. The candidate generation unit 110 generates candidate information. The candidate information includes formulation information indicating a combination of multiple raw materials. The calculation unit 130 calculates a resilience index using the candidate information and a raw material index. The raw material index indicates the level of resilience related to the supply environment of each of the multiple raw materials. The resilience index indicates the level of resilience of a material manufactured using multiple raw materials.

Description

[Technical Field]

[0001] This invention relates to a proposed method, an information processing device, and a program. [Background technology]

[0002] Attempts are being made to use computers in the formulation design process to obtain desired materials.

[0003] Patent Document 1 describes how to improve the predictability and profitability of an operation to manufacture an intermediate or final product by combining and processing a series of raw materials by optimizing the cost structure of the raw materials and the output of the final or intermediate product. [Prior art documents] [Patent Documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2001-192679 [Overview of the project] [Problems that the invention aims to solve]

[0005] However, the technology described in Patent Document 1 did not take into consideration resilience from the perspective of raw material supply.

[0006] One aspect of the present invention provides a formulation proposal technology that enables material design considering resilience from the standpoint of raw material supply. [Means for solving the problem]

[0007] According to one embodiment of the present invention, the following proposed method, information processing device, and program are provided.

[0008] [1] A proposed method that is performed by one or more computers, A candidate generation step that generates candidate information including formulation information showing combinations of multiple raw materials, A calculation step of calculating a resilience index indicating the level of resilience of a material manufactured using the plurality of raw materials, using the candidate information and a raw material index indicating the level of resilience related to the supply environment of each of the plurality of raw materials Proposed method [2] In the proposed method described in [1], Repeat the candidate generation step and the calculation step until a predetermined end condition is satisfied Proposed method [3] In the proposed method described in [2], In the candidate generation step, generate next candidate information based on the calculation result in the calculation step for one piece of candidate information Proposed method [4] In the proposed method described in [3], In the candidate generation step, use an optimization algorithm to generate the next candidate information Proposed method [5] In the proposed method described in [3] or [4], The formulation information further indicates the blending ratio of each of the plurality of raw materials, The method further includes a prediction step of predicting a characteristic value of the material using the candidate information, In the candidate generation step, generate the next candidate information further based on the prediction result in the prediction step for the one piece of candidate information Proposed method [6] In the proposed method described in [5], In the prediction step, predict the characteristic value of the material further using a feature amount of at least any one of the plurality of raw materials Proposed method [7] In the proposed method described in [5] or [6], The method further includes a constraint condition determination step of determining whether a predetermined constraint condition is satisfied using the prediction result in the prediction step Proposed method [8] In the proposed method described in any one of [5] to [7], The candidate information further includes manufacturing condition information indicating the manufacturing conditions of the material, In the prediction step, the characteristic values ​​of the material manufactured according to the manufacturing conditions are predicted. Proposal method. [9] In the proposed method described in any one of [1] to [8], The raw material index for each of the aforementioned raw materials is based on one or more of the following: the number of businesses that can supply the raw material, the number of countries that produce the raw material, alternative raw materials for the raw material, and the risk value of the country or region associated with the raw material. Proposal method.

[10] In the proposed method described in any one of [1] to [9], In the calculation step described above, the cost index of the material is further calculated using the candidate information and the cost of each of the multiple raw materials. Proposal method.

[11] In the proposed method described in any one of [1] to

[10] , The process further includes a constraint determination step of determining whether predetermined constraint conditions are met using the candidate information. Proposal method.

[12] A candidate generation unit that generates candidate information including formulation information showing combinations of multiple raw materials, The system includes a calculation unit that uses the candidate information and a raw material index indicating the level of resilience related to the supply environment of each of the multiple raw materials to calculate a resilience index indicating the level of resilience of a material manufactured using the multiple raw materials. Information processing device.

[13] Computers, Candidate generation means for generating candidate information including formulation information indicating combinations of multiple raw materials, and The system functions as a calculation means for calculating a resilience index that indicates the level of resilience of a material manufactured using the aforementioned candidate information and a raw material index that indicates the level of resilience related to the supply environment of each of the aforementioned multiple raw materials. program. [Effects of the Invention]

[0009] According to one aspect of the present invention, a formulation proposal technology is provided that enables material design that takes into account resilience from the standpoint of raw material supply. [Brief explanation of the drawing]

[0010] [Figure 1] This is a diagram showing an overview of the information processing device according to the first embodiment. [Figure 2] This is a diagram illustrating the outline of the proposed method according to the first embodiment. [Figure 3] This diagram illustrates the functional configuration of the information processing device according to the first embodiment. [Figure 4] This is a flowchart illustrating the processing flow performed by the information processing device according to the first embodiment. [Figure 5] This diagram illustrates a computer used to implement an information processing device. [Figure 6] This diagram illustrates the functional configuration of an information processing device related to a modified example. [Figure 7] This diagram illustrates the processing flow performed by the information processing device in the modified example. [Figure 8] This figure illustrates the functional configuration of an information processing device according to the second embodiment. [Figure 9] This is a flowchart illustrating the processing flow performed by the information processing device according to the second embodiment. [Figure 10] This figure illustrates the functional configuration of an information processing device according to the third embodiment. [Figure 11] This is a flowchart illustrating the processing flow performed by the information processing device according to the third embodiment. [Figure 12] This figure illustrates the functional configuration of an information processing device according to the fifth embodiment. [Figure 13] This is a flowchart illustrating the processing flow performed by the information processing device according to the fifth embodiment. [Figure 14] This figure illustrates the functional configuration of an information processing device according to the sixth embodiment. [Figure 15]This is a flowchart illustrating the processing flow performed by the information processing device according to the sixth embodiment. [Modes for carrying out the invention]

[0011] Embodiments of the present invention will be described below with reference to the drawings. In all drawings, similar components are denoted by the same reference numerals, and their descriptions are omitted as appropriate.

[0012] (First Embodiment) Figure 1 is a diagram showing an overview of the information processing device 10 according to the first embodiment. The information processing device 10 comprises a candidate generation unit 110 and a calculation unit 130. The candidate generation unit 110 generates candidate information. The candidate information includes formulation information that indicates a combination of multiple raw materials. The calculation unit 130 calculates a resilience index using the candidate information and a raw material index. The raw material index indicates the level of resilience related to the supply environment of each of the multiple raw materials. The resilience index indicates the level of resilience of a material manufactured using multiple raw materials.

[0013] Figure 2 is a diagram illustrating an overview of the proposed method according to this embodiment. The proposed method according to this embodiment is executed by one or more computers. The proposed method according to this embodiment includes a candidate generation step S10 and a calculation step S20. In the candidate generation step S10, one or more computers generate candidate information. The candidate information includes formulation information that shows combinations of multiple raw materials. In the calculation step S20, one or more computers calculate a resilience index using the candidate information and raw material indices. The raw material indices indicate the level of resilience related to the supply environment of each of the multiple raw materials. The resilience index indicates the level of resilience of a material manufactured using multiple raw materials.

[0014] In materials obtained by blending multiple raw materials, there is a risk that if the supply of any of the raw materials is disrupted, it may become impossible to manufacture that material, or it may become necessary to consider alternative raw materials. This risk increases as the number of types of raw materials blended into the material increases. On the other hand, this risk can be reduced by appropriately selecting raw materials. In other words, it is important to design highly resilient materials. Here, resilience can be said to be the ability to withstand and recover from the risk of supply instability of the raw materials used to manufacture the material.

[0015] According to the information processing device 10 and proposed method of this embodiment, a resilience index is calculated that quantifies the level of resilience of candidate information. Therefore, it becomes possible to design materials that take into account resilience from the perspective of raw material supply.

[0016] Figure 3 is a diagram illustrating the functional configuration of the information processing device 10 according to this embodiment. In the example in Figure 3, the information processing device 10 further comprises an output unit 190 and a raw material storage unit 101. However, the raw material storage unit 101 may be provided outside the information processing device 10. Figure 4 is a flowchart illustrating the processing flow performed by the information processing device 10 according to this embodiment.

[0017] Candidate information includes at least formulation information. Formulation information is information that indicates at least a combination of multiple raw materials. Candidate information can also be said to be information that indicates a recipe for obtaining the material. Formulation information can be, for example, a vector. Formulation information may be, for example, information indicating whether or not each raw material included in a given group of raw materials is included in the material. Furthermore, formulation information may further indicate the mixing ratio of each of the multiple raw materials. In that case, formulation information may be, for example, information indicating the mixing ratio of each raw material included in a given group of raw materials. The mixing ratio may be, for example, a value that indicates the volume ratio or mass ratio of the raw materials in the material. In formulation information, the mixing ratio may be normalized so that the sum of the mixing ratios of all multiple raw materials is 1. Formulation information is raw material M i(i is the identification number for the raw material) Blending ratio x i It may also be a vector with elements. Here, in the formulation information, zero may be shown as the formulation ratio of raw materials that are not included in the material.

[0018] The candidate information may also include manufacturing condition information that indicates the manufacturing conditions of the material. For example, the manufacturing condition information may include one or more of the following: heating temperature, heating time, and the type of equipment used in manufacturing.

[0019] The material is, for example, a composition manufactured using multiple raw materials. The material may be an organic material, an inorganic material, or an organic-inorganic composite material. The application of the material is not particularly limited, but examples include electronic or semiconductor devices, energy-related applications, medical applications, bio-applications, automotive applications, and aerospace applications. Examples of materials for electronic or semiconductor devices include semiconductor encapsulants. The material may be a liquid material or a solid material. The material may be in paste form.

[0020] Examples of raw materials include resins, fillers, and additives. Multiple raw materials may contain multiple different fillers. Multiple raw materials may contain multiple different resins. Multiple raw materials may be identified by part numbers or the like.

[0021] The resin is not particularly limited, but for example, the raw materials may include one or more resins selected from the group consisting of epoxy resins, phenolic resins, melamine resins, unsaturated polyester resins, divinylbenzene polymers, divinylbenzene-styrene copolymers, divinylbenzene-acrylic acid ester copolymers, diallyl phthalate polymers, triallyl isocyanurate polymers, and benzoguanamine polymers.

[0022] The fillers are not particularly limited, but for example, multiple raw materials may include one or more fillers selected from the group consisting of conductive particles and non-conductive particles. Examples of conductive particles include gold, silver, copper, carbon black, tin oxide, metal plating particles, etc. Examples of non-conductive particles include silica, alumina, diamond, boron nitride, organic fillers, etc. Multiple raw materials may include one or more fillers selected from the group consisting of silver, gold, copper, carbon black, tin oxide, metal plating particles, silica, alumina, diamond, boron nitride, and organic fillers.

[0023] Furthermore, the multiple raw materials may include one or more selected from the group consisting of curing agents, coupling agents, curing accelerators, diluents, radical initiators, and stress reducers. The multiple raw materials may or may not contain solvents. In addition, the multiple raw materials may include compositions as raw materials.

[0024] However, the raw materials are not limited to these examples.

[0025] A raw material index is defined for each raw material. The raw material index can be described as a value that quantifies the supply stability of the raw material. For example, the raw material index for each raw material included in the predetermined group of raw materials described above is stored in advance in the raw material storage unit 101.

[0026] A raw material index for each of several raw materials can be determined based on one or more of the following: the number of businesses that can supply the raw material, the number of countries that produce the raw material, alternative raw materials for the raw material, and the risk value of the country or region associated with the raw material. Specific examples of methods for calculating raw material indexes are described below. However, the methods for calculating raw material indexes are not limited to the examples below.

[0027] Raw material M i S is the raw material index for res,i Expressed as follows: Raw material index S res,i is, S res,i =N m A iIt is obtained by / (1 + G). In this example, it can be said that the higher the raw material index, the higher the resilience of the raw material. N m is the number of suppliers (i.e., available operators) of raw material M i and can be said to be a value indicating the diversity of supply. A i is a value indicating the presence or absence of alternative raw materials for raw material M i and the supply stability of the alternative raw materials. Specifically, when there is no alternative raw material for raw material M i , A i is set to 1. When there is an alternative raw material for raw material M i , A i can be calculated using the following formula (1).

[0028]

Equation

[0029] ω is a parameter for adjusting the influence of alternative raw materials on A i and is preset within the range where 0 < ω < 1 holds. N alt is the total number of alternative raw materials for raw material M i .

[0030] When there are multiple raw materials that can be alternative raw materials for each other, for those raw materials, the obtained S res,i = N m A i / (1 + G) formula is solved as a system of simultaneous equations to obtain the value of A i for each raw material.

[0031] G is a value based on the supply ratio and location of each supplier of raw material M[[ID=5I]] i . G can be said to be the geopolitical risk value of raw material M i . Specifically, G can be calculated using the following formula (2). Note that an upper limit of acceptable G may be defined. And in a predetermined group of raw materials, there may not be a raw material whose G value exceeds the predetermined upper limit.

[0032]

number

[0033] In equation (2), k is the raw material M i This is a number that identifies the supplier. k is raw material M in the market i Source S relative to the total supply quantity k This is the supply ratio. The supply ratio may be based on quantity or value. k is, supplier S k This is a risk value for the location (e.g., the country where it is located). The risk value for each location can be determined, for example, using various publicly available data sources on country-specific geopolitical risks.

[0034] The resilience index can be described as a quantitative value that measures the overall resilience of a material obtained by blending multiple raw materials. Specific examples of methods for calculating the resilience index are explained below. However, the methods for calculating the resilience index are not limited to the examples below.

[0035] Multiple raw materials (M1, M2, ..., M N The resilience index S of materials manufactured using ) res,total This can be calculated using the following formula (3).

[0036]

number

[0037] N is the number (type) of raw materials used in the material. i is raw material M i This is a weight representing the importance of each raw material, and can be predetermined for each raw material. However, from ω1 to ω N The sum up to this point is 1. The weight of each raw material ω i The raw materials are stored in the raw material storage unit 101. In this example, the higher the resilience index, the more resilient the material is.

[0038] Referring to Figures 3 and 4, the processing flow executed by the information processing device 10 will be described in detail below.

[0039] In step S101, the candidate generation unit 110 generates candidate information. The candidate generation unit 110 may, for example, generate candidate information randomly. Specifically, the candidate generation unit 110 may randomly select multiple raw materials to be blended into the material from the predetermined raw material group described above, and generate information indicating the selected multiple raw materials as blending information. Alternatively, the candidate generation unit 110 may randomly determine the blending ratio for each raw material included in the predetermined raw material group, and generate blending information indicating the blending ratio of each raw material. The candidate generation unit 110 includes the generated blending information in the candidate information.

[0040] The candidate generation unit 110 may further include the above-mentioned manufacturing condition information in the candidate information. The candidate generation unit 110 may use randomly identified manufacturing conditions as manufacturing condition information, or it may use manufacturing conditions randomly selected from a predetermined set of options as manufacturing condition information.

[0041] Constraints may be set for the candidate information. Constraints may be input by the user to the information processing device 10. By doing so, candidate information that satisfies the desired conditions can be obtained. Constraints on the candidate information are called first constraints. The first constraints are, for example, the sum of the blending ratios of the multiple raw materials (x1 + x2 + ... + X N The following conditions must be met: the ratio of a specific raw material to a specific raw material must be 1; the blending ratio for a specific raw material must be within a predetermined range; the specific raw material must be included among the multiple raw materials to be blended into the material; the number of multiple raw materials must be less than or equal to a predetermined number; and the number of raw materials of the same category (resin, filler, etc.) included among the multiple raw materials must be less than or equal to a predetermined number.

[0042] The candidate generation unit 110 may generate candidate information in such a way as to satisfy a predetermined first constraint. That is, the candidate generation unit 110 may generate candidate information randomly within a range that satisfies the first constraint.

[0043] In step S102, the calculation unit 130 calculates a resilience index using candidate information and raw material index. Specifically, the calculation unit 130 identifies multiple raw materials to be blended into the material using blending information from the candidate information generated by the candidate generation unit 110. Then, the calculation unit 130 calculates a raw material index S for each of the identified multiple raw materials. res,i And weight ω i This is read and obtained from the raw material storage unit 101.

[0044] The calculation unit 130 reads the raw material index S res,i and weight ω i By substituting this into equation (3) above, the resilience index S of the material can be obtained. res,total You can obtain this.

[0045] In step S103, the output unit 190 outputs output data that includes candidate information generated by the candidate generation unit 110 and the resilience index calculated by the calculation unit 130.

[0046] The output destination of the output data from the output unit 190 may be, for example, a display connected to the information processing device 10, a device other than the information processing device 10, or a storage device accessible by the information processing device 10.

[0047] According to the information processing device 10 of this embodiment, candidate information and a resilience index for the material obtained based on that candidate information are output together. Therefore, the user of the information processing device 10 can quantitatively grasp the level of resilience of the material obtained based on the candidate information.

[0048] In calculation step S20, the calculation unit 130 may further calculate a cost index for the material using the candidate information and the cost of each of the multiple raw materials. The cost index indicates the cost of manufacturing that material. Since procurement and other costs may be incurred for each raw material, the cost of each raw material greatly affects the cost of the material. By the calculation unit 130 further calculating the cost index for the material, the user of the information processing device 10 can perform material design that takes cost into consideration.

[0049] When the calculation unit 130 calculates a cost index for materials, it is preferable that the blending information shows the blending ratio of each of the multiple raw materials. Doing so improves the accuracy of the calculated cost index.

[0050] The raw material storage unit 101 stores the cost per unit quantity of each raw material. The calculation unit 130 uses the blending information from the candidate information generated by the candidate generation unit 110 to identify multiple raw materials to be blended into the material and the blending ratio of each raw material. The calculation unit 130 also reads and obtains the cost of each of the identified multiple raw materials from the raw material storage unit 101. Then, the calculation unit 130 calculates the raw material cost value for each raw material by multiplying the cost by the blending ratio. By summing the raw material cost values ​​of multiple raw materials, the calculation unit 130 can calculate a cost index for the material obtained by blending multiple raw materials.

[0051] If the calculation unit 130 calculates a cost index for materials, the output unit 190 can further include the calculated cost index in the output data.

[0052] In one example, the candidate generation unit 110 may generate multiple candidate information. The candidate generation unit 110 may generate the multiple candidate information randomly, or it may generate it using a quasi-Monte Carlo method or the like. When the candidate generation unit 110 generates multiple candidate information, the calculation unit 130 calculates a resilience index for each candidate information. The output unit 190 then associates the resilience index with each of the multiple candidate information and includes it in the output data.

[0053] When the output unit 190 outputs multiple candidate information, the output unit 190 may include in the output data the results of at least one of the following: classification, filtering, or ranking of the multiple candidate information. At least one of the following can be performed according to predetermined rules, using at least one of the candidate information, resilience indicators, and cost indicators.

[0054] The hardware configuration of the information processing device 10 is described below. Each functional component of the information processing device 10 (candidate generation unit 110, calculation unit 130, and output unit 190) can be realized by a combination of hardware and software (e.g., a combination of an electronic circuit and a program to control it).

[0055] Figure 5 illustrates a computer 1000 for implementing the information processing device 10. Computer 1000 is any computer. For example, computer 1000 could be an SoC (System on Chip), a Personal Computer (PC), a server machine, a tablet terminal, or a smartphone. Computer 1000 may be a dedicated computer designed to implement the information processing device 10, or it may be a general-purpose computer. Furthermore, the information processing device 10 may be implemented by a single computer 1000, or by a combination of multiple computers 1000.

[0056] Computer 1000 includes a bus 1020, a processor 1040, memory 1060, a storage device 1080, an input / output interface 1100, and a network interface 1120. Bus 1020 is a data transmission path for the processor 1040, memory 1060, storage device 1080, input / output interface 1100, and network interface 1120 to send and receive data to and from each other. However, the method of connecting the processor 1040 and the other components is not limited to bus connection. Examples of the processor 1040 include various processors such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), and an FPGA (Field-Programmable Gate Array). Memory 1060 is a main memory device implemented using RAM (Random Access Memory), etc. Storage device 1080 is an auxiliary storage device implemented using a hard disk, SSD (Solid State Drive), memory card, or ROM (Read Only Memory), etc.

[0057] The input / output interface 1100 is an interface for connecting the computer 1000 with input / output devices. For example, input devices such as a keyboard and output devices such as a display are connected to the input / output interface 1100. The method by which the input / output interface 1100 connects to the input and output devices may be wireless or wired.

[0058] The network interface 1120 is an interface for connecting the computer 1000 to a network. Examples of such networks include LANs (Local Area Networks) and WANs (Wide Area Networks). The network interface 1120 may connect to the network via a wireless connection or a wired connection.

[0059] The storage device 1080 stores program modules that realize each functional component of the information processing device 10. The processor 1040 reads these program modules into the memory 1060 and executes them to realize the functions corresponding to each program module.

[0060] Furthermore, if the raw material storage unit 101 is located inside the information processing device 10, for example, the raw material storage unit 101 may be implemented using a storage device 1080.

[0061] According to this embodiment, the calculation unit 130 calculates a resilience index using candidate information and raw material index. Therefore, the user of the information processing device 10 can design materials that take into account resilience from the perspective of raw material supply.

[0062] (modified version) Figure 6 is a diagram illustrating the functional configuration of the modified information processing device 10. In the example in Figure 6, the information processing device 10 further includes a constraint condition determination unit 160. Figure 7 is a diagram illustrating the processing flow executed by the information processing device 10 according to this modified example. The information processing device 10 according to this modified example is the same as the information processing device 10 according to the first embodiment, except for the points described below.

[0063] The proposed method relating to this modified example includes a constraint determination step that uses candidate information to determine whether or not a predetermined constraint (first constraint) is satisfied.

[0064] In step S105, the candidate generation unit 110 generates candidate information regardless of the first constraint. In step S106, the constraint determination unit 160 determines whether the generated candidate information satisfies the first constraint.

[0065] If the candidate information does not satisfy the first constraint (No in step S106), the candidate information is discarded. Then, step S105 is executed again, and the candidate generation unit 110 generates candidate information. If the candidate information satisfies the first constraint (Yes in step S106), steps S107 and S108 are executed using that candidate information. Steps S107 and S108 are the same as steps S102 and S103 described above, respectively. In this way, candidate information that satisfies the first constraint is output. Candidate information that does not satisfy the first constraint does not need to be output.

[0066] The hardware configuration of the computer implementing the information processing device 10 according to this modified example is shown, for example, in Figure 5, similar to the first embodiment. However, the storage device 1080 of the computer 1000 implementing the information processing device 10 according to this modified example further stores a program module that implements the functions of the constraint condition determination unit 160.

[0067] According to this modified example, the same actions and effects as in the first embodiment can be obtained.

[0068] (Second embodiment) Figure 8 is a diagram illustrating the functional configuration of the information processing device 10 according to the second embodiment. Figure 9 is a flowchart illustrating the processing flow performed by the information processing device 10 according to this embodiment. The information processing device 10 according to this embodiment is the same as the information processing device 10 according to the first embodiment or a modified example, except for the points described below.

[0069] The information processing device 10 according to this embodiment further comprises a prediction unit 150. In this embodiment, the blending information indicates the blending ratio of each of several raw materials. The prediction unit 150 predicts the characteristic values ​​of the material using the candidate information.

[0070] In the example shown in Figure 8, the information processing device 10 further includes a model storage unit 102. The model storage unit 102 holds a model for predicting material property values. If the model storage unit 102 is located inside the information processing device 10, for example, it can be implemented using a storage device 1080. However, the model storage unit 102 may be located outside the information processing device 10.

[0071] The model for predicting the material properties may be a mathematical formula or a machine learning model. The model may be a regression model or a classification model. The model takes the blending ratios of multiple raw materials as input (explanatory variables) and outputs the predicted property values ​​of the material obtained according to those raw materials and blending ratios (dependent variables). The model is prepared in advance and stored in the model storage unit 102.

[0072] The predicted characteristic values ​​may be physical properties such as mechanical properties, thermal properties, optical properties, and electromagnetic properties, or chemical properties. Specific examples of predicted characteristic values ​​include specific gravity, tensile strength, and refractive index. However, examples of characteristic values ​​are not limited to these. The prediction unit 150 may predict multiple characteristic values. In this case, the prediction unit 150 may use a model capable of predicting multiple characteristic values, or it may use multiple models.

[0073] Steps S201 and S202 are the same as steps S101 and S102, respectively. In step S203, the prediction unit 150 identifies multiple raw materials to be blended into the material and the blending ratio of each raw material based on the blending information included in the candidate information. The prediction unit 150 also reads a model from the model storage unit 102. The prediction unit 150 obtains predicted characteristic values ​​of the material by applying (inputting) the blending ratios of each of the multiple raw materials to the read model. If multiple candidate information is generated, the prediction unit 150 predicts characteristic values ​​for each candidate information.

[0074] In other examples, the prediction unit 150 may predict the properties of the material by performing a simulation based on the formulation information.

[0075] If the candidate information includes manufacturing condition information indicating the manufacturing conditions of the material, in step S203, which predicts the material's characteristic values, the prediction unit 150 may predict the material's characteristic values ​​as they would be when manufactured according to the manufacturing conditions indicated in the manufacturing condition information. In that case, the model's input (explanatory variables) includes parameters indicating the manufacturing conditions.

[0076] In step S203, which predicts the material's properties, the prediction unit 150 may further use the characteristics of at least one of the multiple raw materials to predict the material's properties. Doing so enables more accurate prediction. For example, the prediction unit 150 may use at least one of the resin characteristics and filler characteristics from the multiple raw materials for prediction. The characteristics of which raw materials to use may be predetermined. When the material's properties are predicted using the characteristics of the raw materials, the model's input (explanatory variables) includes these characteristics. For example, the characteristics may be one or more of the following: the proportion or equivalent ratio of the responsive functional groups to the whole, the logarithmic ratio conversion result of the composition data, the HOMO-LIMO energy gap, and structural information. Structural information can be extracted from raw material measurement data such as IR spectra, for example. The characteristics of the raw materials used for prediction are stored in the raw material storage unit 101 beforehand. The prediction unit 150 reads out the characteristics of at least one of the multiple raw materials from the raw material storage unit 101. Then, the prediction unit 150 can obtain the predicted properties by further inputting the read-out characteristics into the model.

[0077] Note that the execution order of steps S202 and S203 may be reversed from the example in Figure 9.

[0078] In step S204, the output data output by the output unit 190 includes the characteristic values ​​predicted by the prediction unit 150. This allows the user of the information processing device 10 to understand the predicted characteristic values ​​of the material obtained based on the candidate information.

[0079] Furthermore, if the output unit 190 outputs the results of classifying, filtering, or ranking multiple candidate information, at least one of these classifications, filters, or rankings may be performed using predicted characteristic values.

[0080] The hardware configuration of the computer implementing the information processing device 10 according to this embodiment is shown, for example, in Figure 5, similar to the first embodiment. However, the storage device 1080 of the computer 1000 implementing the information processing device 10 according to this embodiment further stores program modules that realize the functions of the prediction unit 150.

[0081] According to this embodiment, the same functions and effects as in the first embodiment can be obtained. In addition, according to this embodiment, the prediction unit 150 predicts the characteristic values ​​of the material using candidate information. Therefore, the user of the information processing device 10 can perform material design that takes material properties into consideration.

[0082] (Third embodiment) Figure 10 is a diagram illustrating the functional configuration of the information processing device 10 according to the third embodiment. Figure 11 is a flowchart illustrating the processing flow performed by the information processing device 10 according to this embodiment. The information processing device 10 according to this embodiment is the same as the information processing device 10 according to the first and second embodiments and at least one of the modified embodiments, except for the points described below.

[0083] In the proposed method according to this embodiment, the information processing device 10 repeats the step S301 of generating candidate information and the step S302 of calculating a resilience index until a predetermined termination condition is met. In this way, the user of the information processing device 10 can compare and examine multiple candidate pieces of information while considering their resilience.

[0084] In this embodiment, the information processing device 10 includes a termination determination unit 170. Although Figure 10 shows an example in which the information processing device 10 includes a prediction unit 150, the information processing device 10 does not necessarily need to include a prediction unit 150. Also, in Figure 11, step S303 may be omitted.

[0085] Steps S301 to S303 are the same as steps S201 to S203 described above. Following step S303, the termination determination unit 170 determines whether or not the termination conditions have been met (step S304).

[0086] The termination condition may be, for example, that a predetermined stop operation has been performed on the information processing device 10. This allows the user to stop the process at any time. Alternatively, the termination condition may be that the number of repetitions has reached a predetermined number, or that the elapsed time since the start of the first step S301 has reached a predetermined time. The termination condition can be at least one of these examples. The predetermined number of repetitions and the predetermined time can be determined by the user inputting them to the information processing device 10.

[0087] If the termination condition is not met (No. in step S304), the process returns to step S301, and the candidate generation unit 110 generates candidate information again. Multiple candidate information is generated through this repeated process. The candidate generation unit 110 may generate multiple candidate information randomly, or it may generate multiple candidate information using, for example, a quasi-Monte Carlo method.

[0088] If the termination condition is met (Yes in step S304), the output unit 190 then outputs the output data (step S305). The output unit 190 outputs each of the multiple candidate information generated by the candidate generation unit 110, associating it with the resilience index calculated by the calculation unit 130 and the characteristic value predicted by the prediction unit 150.

[0089] The hardware configuration of the computer implementing the information processing device 10 according to this embodiment is shown, for example, in Figure 5, similar to the first embodiment. However, the storage device 1080 of the computer 1000 implementing the information processing device 10 according to this embodiment further stores a program module that implements the functions of the termination determination unit 170.

[0090] According to this embodiment, the same functions and effects as in the first embodiment can be obtained. In addition, according to this embodiment, the information processing device 10 repeats the step S301 of generating candidate information and the step S302 of calculating the resilience index until a predetermined termination condition is met. Therefore, the user of the information processing device 10 can compare and examine multiple candidate information while considering their resilience.

[0091] (Fourth embodiment) The functional configuration of the information processing device 10 according to the fourth embodiment is illustrated by Figure 10, similar to the third embodiment. The processing flow executed by the information processing device 10 according to this embodiment is illustrated by Figure 11, similar to the third embodiment. The information processing device 10 according to this embodiment is the same as the information processing device 10 according to the third embodiment, except for the points described below.

[0092] In this embodiment, the candidate generation unit 110 generates the next candidate information based on at least one of the calculation result of the resilience index and the prediction result of the characteristic value for one candidate information. More specifically, in step S301, the candidate generation unit 110 can generate the next candidate information using an optimization algorithm. By doing so, candidate information that is closer to the desired conditions can be obtained. In optimization, at least one of the resilience index and the characteristic value can be the target of optimization, i.e., the objective variable. The user can set target values ​​for each objective variable and input them into the information processing device 10. In optimization, the candidate information can be said to be a candidate solution.

[0093] In order to obtain candidate information with high resilience indicators while obtaining the desired characteristics, it is preferable to perform multi-objective optimization that targets both the resilience indicator and the characteristic value for optimization.

[0094] Furthermore, when the calculation unit 130 calculates a cost index for a material, the candidate generation unit 110 may generate the next candidate information based on the calculation result of the cost index for one candidate piece of information.

[0095] Optimization algorithms that can be used include genetic algorithms, the Nelder-Mead method, or particle swarm optimization.

[0096] In step S301, which generates candidate information, the candidate generation unit 110 may generate the next candidate information based on the calculation result in step S302, which calculates a resilience index for one candidate information. That is, in the second and subsequent steps S301, the candidate generation unit 110 generates candidate information based on the resilience index calculated using the candidate information generated in the previous step S301. In this way, new candidate information is generated to further increase the obtained resilience index. By quantifying resilience, it can be treated as an objective variable for optimization in this way. Note that the candidate generation unit 110 may generate candidate information not only based on the resilience index calculated using the previous candidate information, but also based on multiple resilience indices calculated up to that point.

[0097] The formulation information indicates the formulation ratio of each of several raw materials. If the proposed method executed by the information processing device 10 includes a step S303 in which the characteristic values ​​of the material are predicted using candidate information, the candidate generation unit 110 may generate the next candidate information in step S301 based on the prediction result in step S303 for one candidate information. That is, in the second and subsequent steps S301, the candidate generation unit 110 generates candidate information based on the characteristic values ​​predicted using the candidate information generated in the previous step S301. In this way, new candidate information is generated to obtain characteristic values ​​that are closer to the desired values. The candidate generation unit 110 may generate candidate information not only based on the characteristic values ​​predicted using the previous candidate information, but also based on multiple characteristic values ​​predicted up to that point. Furthermore, the candidate generation unit 110 may generate the next candidate information based on the prediction results of characteristic values ​​for multiple characteristics.

[0098] Steps S302 to S305 are as described in the third embodiment. However, examples of termination conditions in this embodiment further include conditions relating to the amount of improvement and conditions relating to the convergence of the search space. The condition relating to the amount of improvement is, for example, that the amount of improvement of the target variable has fallen below a predetermined threshold. The amount of improvement of the target variable is the value obtained by |ΔP1-ΔP2|, where ΔP1 is the difference between the target variable and the target value for the candidate information newly generated in step S301, and ΔP2 is the difference between the target variable and the target value for the candidate information generated in the previous step S301. The condition relating to the convergence of the search space is, for example, whether the most recent sample point falls within the convex hull of the search space so far.

[0099] In step S305, the output unit 190 outputs at least the candidate information last generated by the candidate generation unit 110, the resilience index calculated using that candidate information, and the characteristic value predicted using that candidate information in the output data. The output unit 190 may also output multiple candidate information generated by the candidate generation unit 110, the resilience index calculated using each candidate information, and the characteristic value predicted using each candidate information, not limited to the candidate information last generated by the candidate generation unit 110.

[0100] Furthermore, if multi-objective optimization is performed, the output unit 190 may also include graphs or other data to visualize the set of Pareto solutions in the output data.

[0101] According to this embodiment, the same functions and effects as in the first embodiment can be obtained. In addition, according to this embodiment, the candidate generation unit 110 generates the next candidate information based on at least one of the calculation result of the resilience index for a given candidate information and the prediction result of the characteristic value. Therefore, candidate information that is closer to the desired conditions can be obtained.

[0102] (Fifth embodiment) Figure 12 is a diagram illustrating the functional configuration of the information processing device 10 according to the fifth embodiment. Figure 13 is a flowchart illustrating the processing flow performed by the information processing device 10 according to this embodiment. The information processing device 10 according to this embodiment is the same as the information processing device 10 according to the fourth embodiment, except for the points described below.

[0103] In the fourth embodiment, the optimization performed by the information processing device 10 can be described as static optimization that does not involve updating the model. In contrast, in the fifth embodiment, the information processing device 10 can be described as performing dynamic optimization that involves updating the model. In this embodiment, the information processing device 10 can generate candidate information or update the model using, for example, a Bayesian optimization method.

[0104] The information processing device 10 according to this embodiment includes an acquisition unit 140 and an update unit 180. Steps S402 and S406 are the same as steps S302 and S305 according to the fourth embodiment, respectively.

[0105] In step S403, the acquisition unit 140 acquires characteristic values ​​for the candidate information generated by the candidate generation unit 110. For example, a user prepares a material according to the candidate information and measures its characteristic values. The user then inputs the measured characteristic values ​​into the information processing device 10, and the candidate generation unit 110 acquires the input characteristic values.

[0106] The model storage unit 102 holds a model that shows the relationship between candidate information and characteristic values. The accuracy of the model in the initial state is not considered. In step S404, the update unit 180 updates the model held in the model storage unit 102 based on the combination of candidate information and the characteristic values ​​acquired by the acquisition unit 140 for that candidate information.

[0107] In step S401, the candidate generation unit 110 generates an acquisition function based on the model stored in the model storage unit 102. Then, the candidate generation unit 110 generates new candidate information using the acquisition function. The candidate generation unit 110 may generate candidate information that satisfies the constraints, as described in the first embodiment and its modifications.

[0108] Step S405 is the same as step S304. However, the example of the termination condition in this embodiment further includes a condition relating to the convergence of the acquisition function. The condition relating to the convergence of the acquisition function is, for example, that the output result for candidate information of the acquisition function becomes smaller than a predetermined criterion.

[0109] Furthermore, the information processing device 10 may perform a combination of the static optimization described in the fourth embodiment and the dynamic optimization described in the fifth embodiment. For example, the information processing device 10 may switch between static optimization and dynamic optimization in the first and second halves of a plurality of iterative processes. In addition, the information processing device 10 may use a multifidelity optimization method.

[0110] The hardware configuration of the computer implementing the information processing device 10 according to this embodiment is shown, for example, in Figure 5, similar to the first embodiment. However, the storage device 1080 of the computer 1000 implementing the information processing device 10 according to this embodiment further stores program modules that implement the functions of the acquisition unit 140 and the update unit 180.

[0111] According to this embodiment, the same actions and effects as those of the first embodiment can be obtained. In addition, the same actions and effects as those of the fourth embodiment can be obtained.

[0112] (Sixth embodiment) Figure 14 is a diagram illustrating the functional configuration of the information processing device 10 according to the sixth embodiment. Figure 15 is a flowchart illustrating the processing flow performed by the information processing device 10 according to this embodiment. The information processing device 10 according to this embodiment is the same as the information processing device 10 according to at least one of the second to fifth embodiments, except for the points described below.

[0113] The information processing device 10 according to this embodiment includes a constraint condition determination unit 160. The proposed method executed by the information processing device 10 according to this embodiment may include a constraint condition determination step (step S504) in which a predetermined constraint condition is determined to be satisfied using the prediction results from the step of predicting the material's characteristic values. Although Figure 15 shows an example in which step S504 is added to the flowchart of Figure 11, the proposed method according to this embodiment is not limited to this example. For example, step S504 may be added to the flowchart of Figure 9 or Figure 13.

[0114] In this embodiment, the constraint determination unit 160 can determine in step S504 whether the characteristic value for the candidate information satisfies predetermined constraint conditions. The constraint conditions for the candidate information described above are referred to as the first constraint conditions, while the constraint conditions for the characteristic value are referred to as the second constraint conditions.

[0115] An example of a second constraint is that the characteristic value must be within a predetermined range. A predetermined range may be defined for each characteristic. In that case, a second constraint may be set for each characteristic. The second constraint may be input to the information processing device 10 by the user. This allows for the identification of candidate information for obtaining a material with the desired characteristics.

[0116] The constraint determination unit 160 may, in step S504, determine whether the candidate information satisfies the first constraint. Even if it is the first constraint, conditions that were not taken into account when the candidate generation unit 110 generated the candidate information, or conditions that were not handled in step S106 as described in the modified example, i.e., constraints that are not essential constraints, may be subject to determination in step S504. The first constraint and the second constraint are collectively referred to as constraints.

[0117] Step S501 is the same as at least one of the steps S101, S105, S201, S301, and S401 described above. Step S502 is the same as step S102 described above. Step S503 is the same as step S203 described above.

[0118] In step S504, the constraint determination unit 160 determines whether the constraints are met. The constraint determination unit 160 determines whether the characteristic values ​​for the candidate information generated in step S501 satisfy a predetermined second constraint. The constraint determination unit 160 may also determine whether the candidate information generated in step S501 satisfies a predetermined first constraint. Then, the constraint determination unit 160 associates the determination result with the candidate information.

[0119] Step S505 is the same as step S304. Step S506 is the same as at least one of steps S103, S204, S305, and S406. However, in step S506, the output unit 190 may associate the candidate information with the determination result in step S504 and include it in the output data. Alternatively, the output unit 190 may include the candidate information extracted based on the determination result in the output data, but may not include the candidate information that was not extracted. For example, the output unit 190 may extract candidate information that is determined to satisfy a predetermined number or more of the constraint conditions among a plurality of constraint conditions and include it in the output data.

[0120] In this embodiment, the termination condition may be a condition relating to the constraints. If multiple constraints are set, each constraint may be assigned an importance level. For example, some of the constraints may be mandatory, and the remaining some may be non-mandatory. The termination condition may then be that candidate information has been obtained in which all mandatory constraints are met and a predetermined number or more of the non-mandatory constraints are met.

[0121] According to this embodiment, the same operation and effects as in the first embodiment can be obtained. In addition, according to this embodiment, the constraint condition determination unit 160 determines whether or not predetermined constraint conditions are met. Therefore, candidate information that satisfies the desired conditions can be identified.

[0122] The embodiments of the present invention have been described above with reference to the drawings, but these are merely examples of the present invention, and various other configurations can also be adopted.

[0123] Furthermore, while the flowcharts used in the above description show multiple steps (processes) in sequence, the execution order of the steps performed in each embodiment and modification is not limited to the order in which they are described. In each embodiment and modification, the order of the illustrated steps can be changed to the extent that it does not impede the content. Also, the above embodiments and modifications can be combined to the extent that their content is not contradictory. [Explanation of Symbols]

[0124] 10 Information Processing Devices 101 Raw material storage section 102 Model Memory Unit 110 Candidate generation section 130 Calculation Unit 140 Acquisition Department 150 Prediction Section 160 Constraint condition judgment part 170 Termination Determination Unit 180 Update Department 190 Output section 1000 calculator 1020 Bus 1040 processor 1060 memory 1080 storage devices 1100 Input / Output Interface 1120 Network Interface

Claims

1. A proposed method that is executed by one or more computers, A candidate generation step that generates candidate information including formulation information showing combinations of multiple raw materials, The process includes a calculation step of calculating a resilience index that indicates the level of resilience of a material manufactured using the multiple raw materials, using the candidate information and a raw material index that indicates the level of resilience related to the supply environment of each of the multiple raw materials. The candidate generation step and the calculation step are repeated until a predetermined termination condition is met. In the candidate generation step, based on the calculation result in the calculation step for one candidate piece of information, the next candidate piece of information is generated using an optimization algorithm. The optimization algorithm is a combination of a genetic algorithm, the Nelder-Mead method, or particle swarm optimization with Bayesian optimization, or a genetic algorithm, the Nelder-Mead method, particle swarm optimization, Bayesian optimization, or multifidelity optimization. The raw material index for each of the aforementioned raw materials is based on the number of businesses that can supply that raw material, the number of countries that produce that raw material, and one or more alternative raw materials for that raw material. Proposal method.

2. A proposed method that is executed by one or more computers, A candidate generation step that generates candidate information including formulation information showing combinations of multiple raw materials, The process includes a calculation step of calculating a resilience index that indicates the level of resilience of a material manufactured using the multiple raw materials, using the candidate information and a raw material index that indicates the level of resilience related to the supply environment of each of the multiple raw materials. In the candidate generation step, multiple candidate pieces of information are generated randomly or using a quasi-Monte Carlo method. The raw material index for each of the aforementioned raw materials is based on the number of businesses that can supply that raw material, the number of countries that produce that raw material, and one or more alternative raw materials for that raw material. Proposal method.

3. A proposed method that is executed by one or more computers, A candidate generation step that generates candidate information including combinations of multiple raw materials and blending ratios of each of the multiple raw materials, A calculation step of calculating a resilience index that indicates the level of resilience of a material manufactured using the multiple raw materials, using the candidate information and a raw material index that indicates the level of resilience related to the supply environment of each of the multiple raw materials, The process includes a prediction step of predicting the characteristic values ​​of the material using the candidate information, The raw material index for each of the aforementioned raw materials is based on the number of businesses that can supply that raw material, the number of countries that produce that raw material, and one or more alternative raw materials for that raw material. Proposal method.

4. A proposed method that is executed by one or more computers, A candidate generation step that generates candidate information including formulation information showing combinations of multiple raw materials, The process includes a calculation step of calculating a resilience index that indicates the level of resilience of a material manufactured using the multiple raw materials, using the candidate information and a raw material index that indicates the level of resilience related to the supply environment of each of the multiple raw materials. The candidate information further includes manufacturing condition information indicating the manufacturing conditions of the material, The raw material index for each of the aforementioned raw materials is based on the number of businesses that can supply that raw material, the number of countries that produce that raw material, and one or more alternative raw materials for that raw material. Proposal method.

5. In the proposed method described in claim 3 or 4, The candidate generation step and the calculation step are repeated until a predetermined termination condition is met. In the candidate generation step, multiple candidate pieces of information are generated randomly or using a quasi-Monte Carlo method. Proposal method.

6. In the proposed method described in claim 3 or 4, The candidate generation step and the calculation step are repeated until a predetermined termination condition is met. In the candidate generation step, based on the calculation result in the calculation step for one candidate piece of information, the next candidate piece of information is generated using an optimization algorithm. The optimization algorithm is a combination of a genetic algorithm, the Nelder-Mead method, or particle swarm optimization with Bayesian optimization, or a genetic algorithm, the Nelder-Mead method, particle swarm optimization, Bayesian optimization, or multifidelity optimization. Proposal method.

7. In the proposed method described in claim 3, The candidate generation step and the calculation step are repeated until a predetermined termination condition is met. In the candidate generation step, based on the calculation result in the calculation step for one candidate piece of information and the prediction result in the prediction step for one candidate piece of information, an optimization algorithm is used to generate the next candidate piece of information. The optimization algorithm is a combination of a genetic algorithm, the Nelder-Mead method, or particle swarm optimization with Bayesian optimization, or a genetic algorithm, the Nelder-Mead method, particle swarm optimization, Bayesian optimization, or multifidelity optimization. Proposal method.

8. In the proposed method described in claim 7, In the prediction step, the characteristic values ​​of the material are predicted using the characteristic quantities of at least one of the multiple raw materials. Proposal method.

9. In the proposed method described in claim 7, The following steps are further included: a constraint determination step that uses the prediction results from the prediction step to determine whether or not predetermined constraint conditions are met. Proposal method.

10. In the proposed method described in claim 7, The candidate information further includes manufacturing condition information indicating the manufacturing conditions of the material, In the prediction step, the characteristic values ​​of the material manufactured according to the manufacturing conditions are predicted. Proposal method.

11. In the proposed method according to any one of claims 1 to 4, In the calculation step described above, the cost index of the material is further calculated using the candidate information and the cost of each of the multiple raw materials. Proposal method.

12. In the proposed method according to any one of claims 1 to 4, The process further includes a constraint determination step of determining whether predetermined constraint conditions are met using the candidate information. Proposal method.

13. A candidate generation unit that generates candidate information including formulation information showing combinations of multiple raw materials, The system includes a calculation unit that uses the candidate information and a raw material index indicating the level of resilience related to the supply environment of each of the multiple raw materials to calculate a resilience index indicating the level of resilience of a material manufactured using the multiple raw materials. The process of the candidate generation unit generating candidate information and the calculation unit calculating the resilience index is repeated until a predetermined termination condition is met. The candidate generation unit generates the next candidate information using an optimization algorithm based on the calculation result by the calculation unit for one candidate piece of information, The optimization algorithm is a combination of a genetic algorithm, the Nelder-Mead method, or particle swarm optimization with Bayesian optimization, or a genetic algorithm, the Nelder-Mead method, particle swarm optimization, Bayesian optimization, or multifidelity optimization. The raw material index for each of the aforementioned raw materials is based on the number of businesses that can supply that raw material, the number of countries that produce that raw material, and one or more alternative raw materials for that raw material. Information processing device.

14. A candidate generation unit that generates candidate information including formulation information showing combinations of multiple raw materials, The system includes a calculation unit that uses the candidate information and a raw material index indicating the level of resilience related to the supply environment of each of the multiple raw materials to calculate a resilience index indicating the level of resilience of a material manufactured using the multiple raw materials. The candidate generation unit generates a plurality of candidate pieces of information randomly or using a quasi-Monte Carlo method. The raw material index for each of the aforementioned raw materials is based on the number of businesses that can supply that raw material, the number of countries that produce that raw material, and one or more alternative raw materials for that raw material. Information processing device.

15. A candidate generation unit generates candidate information including combinations of multiple raw materials and blending ratios of each of the multiple raw materials, A calculation unit that calculates a resilience index indicating the resilience of a material manufactured using the multiple raw materials, using the candidate information and a raw material index indicating the level of resilience related to the supply environment of each of the multiple raw materials, The system includes a prediction unit that predicts the characteristic values ​​of the material using the candidate information, The raw material index for each of the aforementioned raw materials is based on the number of businesses that can supply that raw material, the number of countries that produce that raw material, and one or more alternative raw materials for that raw material. Information processing device.

16. A candidate generation unit that generates candidate information including formulation information showing combinations of multiple raw materials, The system includes a calculation unit that uses the candidate information and a raw material index indicating the level of resilience related to the supply environment of each of the multiple raw materials to calculate a resilience index indicating the level of resilience of a material manufactured using the multiple raw materials. The candidate information further includes manufacturing condition information indicating the manufacturing conditions of the material, The raw material index for each of the aforementioned raw materials is based on the number of businesses that can supply that raw material, the number of countries that produce that raw material, and one or more alternative raw materials for that raw material. Information processing device.

17. Computers, Candidate generation means for generating candidate information including formulation information that shows combinations of multiple raw materials, and The aforementioned candidate information and a raw material index indicating the level of resilience related to the supply environment of each of the aforementioned multiple raw materials are used to calculate a resilience index indicating the level of resilience of a material manufactured using the aforementioned multiple raw materials. The candidate generation means generates the candidate information, and the calculation means calculates the resilience index, and these processes are repeated until a predetermined termination condition is met. The candidate generation means generates the next candidate information using an optimization algorithm based on the calculation result by the calculation means for one candidate piece of information, The optimization algorithm is a combination of a genetic algorithm, the Nelder-Mead method, or particle swarm optimization with Bayesian optimization, or a genetic algorithm, the Nelder-Mead method, particle swarm optimization, Bayesian optimization, or multifidelity optimization. The raw material index for each of the aforementioned raw materials is based on the number of businesses that can supply that raw material, the number of countries that produce that raw material, and one or more alternative raw materials for that raw material. program.

18. Computers, Candidate generation means for generating candidate information including formulation information that shows combinations of multiple raw materials, and The aforementioned candidate information and a raw material index indicating the level of resilience related to the supply environment of each of the aforementioned multiple raw materials are used to calculate a resilience index indicating the level of resilience of a material manufactured using the aforementioned multiple raw materials. The candidate generation means generates a plurality of candidate pieces of information randomly or using a quasi-Monte Carlo method. The raw material index for each of the aforementioned raw materials is based on the number of businesses that can supply that raw material, the number of countries that produce that raw material, and one or more alternative raw materials for that raw material. program.

19. Computers, Candidate generation means for generating candidate information including combinations of multiple raw materials and blending information indicating the blending ratio of each of the multiple raw materials, A calculation means for calculating a resilience index that indicates the level of resilience of a material manufactured using the multiple raw materials, using the candidate information and a raw material index that indicates the level of resilience related to the supply environment of each of the multiple raw materials, and The aforementioned candidate information is used as a prediction means to predict the characteristic values ​​of the material, The raw material index for each of the aforementioned raw materials is based on the number of businesses that can supply that raw material, the number of countries that produce that raw material, and one or more alternative raw materials for that raw material. program.

20. Computers, Candidate generation means for generating candidate information including formulation information that shows combinations of multiple raw materials, and The aforementioned candidate information and a raw material index indicating the level of resilience related to the supply environment of each of the aforementioned multiple raw materials are used to calculate a resilience index indicating the level of resilience of a material manufactured using the aforementioned multiple raw materials. The candidate information further includes manufacturing condition information indicating the manufacturing conditions of the material, The raw material index for each of the aforementioned raw materials is based on the number of businesses that can supply that raw material, the number of countries that produce that raw material, and one or more alternative raw materials for that raw material. program.

Images