Search system, search method, and search program

Abstract

The exploration system obtains search conditions related to candidate downstream substance characteristics, which are characteristics of candidate downstream substances that are substances obtained in the downstream process of manufacturing. The system extracts one or more data records corresponding to the search conditions from a database that stores a plurality of data records indicating combinations of candidate downstream substance characteristics and related physical properties that are physical properties related to the candidate downstream substance characteristics. The system sets, as a search target, the related physical properties indicated by one data record selected from the one or more extracted data records. For each of two or more candidate upstream substances that are substances used in the upstream process of manufacturing, the system obtains candidate upstream substance physical properties that are physical properties of the candidate upstream substances, and executes an optimization method using the search target and the candidate upstream substance physical properties of each of the two or more candidate upstream substances to determine a blending ratio among the two or more candidate upstream substances.

Description

Technical Field

[0001] One aspect of the present disclosure relates to a search system, a search method, and a search program.

Background Art

[0002] Materials informatics (MI), which is an effort to improve the efficiency of material development using information science, has been introduced in various material development scenarios. For example, the following techniques related to or potentially related to MI are known.

[0003] Patent Document 1 describes an analyzer for combinatorial optimization problems. The computer used in this analyzer starts from an initial combinatorial state, determines the state to transition to using an evaluation function from among the combinatorial states defined as neighboring states, and sequentially performs a search that repeats the transition to the determined transition destination. The computer attempts to discover an optimal combinatorial state that minimizes or maximizes the function value of an evaluation function composed of the sum of the function to be minimized or maximized and a penalty function representing the amount of constraint violation through the search.

[0004] Patent Document 2 describes a combinatorial optimization device having a storage unit that stores the values of a plurality of state variables included in a first energy function to which terms representing constraint conditions for the plurality of state variables are given, and a processing unit that performs a search for the values of the plurality of state variables that minimize the value of the first energy function. The search by the processing unit includes a first search performed using the first energy function, a second search performed using a second energy function obtained by removing the terms representing the constraint conditions from the first energy function after the first search, and a third search performed using the first energy function after the second search.

[0005] Patent Document 3 describes a parameter generation device including input means for receiving an input of a first objective function and constraint conditions defining a combination of elements related to the production of a material, objective function generation means for generating a second objective function in which probabilistic fluctuations are set for parameters of the first objective function, optimization processing means for optimizing a model including the second objective function and the constraint conditions, and output means for outputting, as a parameter set, the values of the variables of the second objective function obtained by the optimization.

[0006] Patent Document 4 describes a composition proposal device that proposes a type and mass ratio of one polymer and components other than the one polymer included as constituent components in a polymer composite material. This device includes a setting unit for setting a target value of the physical properties of a virtual polymer composite material, and an optimization unit for changing parameters including descriptors of the virtual polymer composite material so that the physical properties of the virtual polymer composite material predicted by inputting the parameters including the descriptors of the virtual polymer composite material into a learned model approach the target value.

[0007] Patent Document 5 describes a learning model generation program that causes a computer to execute a learning model generation step of generating a learning model by performing machine learning using learning data in which the blending ratio of raw materials constituting a known thermoplastic aromatic polyester resin composition is an explanatory variable and the physical property value of the thermoplastic aromatic polyester resin composition is an objective variable.

Prior Art Documents

Patent Documents

[0008]

Patent Document 1

Patent Document 2

Patent Document 3

Patent Document 4

Patent Document 5

SUMMARY OF THE INVENTION

PROBLEMS TO BE SOLVED BY THE INVENTION

[0009] There is a demand for a mechanism to search for the formulation of substances used in the upstream process of manufacturing in a shorter time to achieve desired characteristics for substances obtained in the downstream process of manufacturing.

MEANS FOR SOLVING THE PROBLEMS

[0010] A search system according to an aspect of the present disclosure includes at least one processor. The at least one processor acquires search conditions related to candidate downstream substance characteristics, which are characteristics of a candidate downstream substance that is a substance obtained in the downstream process of manufacturing, and extracts one or more data records corresponding to the search conditions from a database that stores a plurality of data records indicating combinations of candidate downstream substance characteristics and related physical properties that are physical properties related to the candidate downstream substance characteristics. The related physical properties indicated by one data record selected from the one or more extracted data records are set as a search target, and for each of two or more candidate upstream substances that are substances used in the upstream process of manufacturing, candidate upstream substance physical properties, which are physical properties of the candidate upstream substance, are acquired, and an optimization method using the search target and the candidate upstream substance physical properties of each of the two or more candidate upstream substances is executed to determine a blending ratio among the two or more candidate upstream substances.

[0011] In such an aspect, first, based on search conditions related to the characteristics of candidate downstream substances (candidate downstream substance characteristics) obtained in the downstream process of manufacturing, one or more data records indicating combinations of candidate downstream substance characteristics and related physical properties are extracted. Then, an optimization method is executed using the related physical properties indicated by one of the data records selected from those data records as a search target, and the blending ratio between two or more candidate upstream substances used in the upstream process of manufacturing is determined. A two-stage process of searching for related physical properties corresponding to a downstream substance having desired characteristics and searching for the blending ratio between two or more upstream substances to obtain those related physical properties is continuously executed. With this mechanism, it is possible to search for the blending of substances used in the upstream process of manufacturing that realizes desired characteristics for the substances obtained in the downstream process of manufacturing in a shorter time.

Advantages of the Invention

[0012] According to one aspect of the present disclosure, it is possible to search for the blending of substances used in the upstream process of manufacturing that realizes desired characteristics for the substances obtained in the downstream process of manufacturing in a shorter time.

Brief Description of the Drawings

[0013]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Modes for Carrying Out the Invention

[0014] Hereinafter, various examples in the present disclosure will be described in detail with reference to the accompanying drawings. In the description of the drawings, the same or equivalent elements are denoted by the same reference numerals, and duplicate descriptions are omitted.

[0015] [Overview of the System] The search system according to the present disclosure is a computer system that searches for a blending of raw materials that realizes the ingredients constituting a composition having desired properties. To execute the search, the search system accesses ingredient / composition data indicating a combination of the properties of candidate ingredients and the properties of candidate compositions, and raw material data indicating the properties of candidate raw materials for generating candidate ingredients. The search system extracts ingredient / composition data corresponding to the search conditions regarding the properties of candidate compositions. Then, based on the properties of the candidate ingredients selected from the extraction results and the properties of two or more candidate raw materials selected for the candidate ingredients, the search system determines the blending ratio between the two or more candidate raw materials for realizing the properties of the candidate ingredients. In this way, the search system continuously executes a two-step process of searching for ingredients corresponding to a composition having desired properties and searching for the blending ratio between two or more raw materials constituting the ingredients. By using the search system, the user can obtain the blending of raw materials that realizes the ingredients constituting a composition having desired properties in a shorter time.

[0016] A candidate composition refers to a composition that may be searched for by the user. The properties of a candidate composition refer to the physical properties specific to the candidate composition, and are also referred to as "candidate composition properties" in the present disclosure. A candidate ingredient refers to a substance constituting a candidate composition. The properties of a candidate ingredient refer to the physical properties of the candidate ingredient, and are also referred to as "candidate ingredient properties" in the present disclosure. A candidate raw material refers to a raw material that may be selected for generating a candidate ingredient. The properties of a candidate raw material refer to the physical properties of the candidate raw material, and are also referred to as "candidate raw material properties" in the present disclosure. The properties of a candidate composition can be expressed by one or more parameters. The candidate ingredient properties and the candidate raw material properties can be expressed by one or more common parameters.

[0017] In one example, each candidate composition is a photosensitive resin composition, each candidate ingredient is a polymer, and each candidate raw material is a monomer.

[0018] When the candidate composition is a photosensitive resin composition, the candidate composition characteristics include the minimum time for developing the photosensitive resin composition, the sensitivity to light, the light transmittance, the resolution indicating the density of the developable image, the minimum resist line width, the adhesion to the substrate, the foaming property or the aggregating property when developing the photosensitive resin composition using a developer, the edge fuse characteristics (the amount of the photosensitive resin composition protruding outward from the end face of the dry film roll due to the winding pressure during the storage of the dry film roll), the flexibility of the developed photocurable photosensitive resin composition, the adhesiveness between the dry film and the base film or the cover film, the stability of the color tone of the photosensitive resin composition, the peelability when peeling the photosensitive resin composition from the substrate, the size of the photosensitive resin composition (peeled piece) peeled from the substrate, and the breakage rate when tenting the tent holes of the substrate with the dry film, and may be expressed by at least one parameter among them.

[0019] The polymer as the candidate contained component may be an alkali-soluble polymer, an ethylenically unsaturated bond-containing compound, a photopolymerization initiator, a resin having a repeating unit containing an acid-decomposable group (a group deprotected by an acid as an example), a phenol resin, a photoacid generator, a dissolution inhibitor, a sensitizer, a polymerization inhibitor, an adhesive, or a plasticizer. When the candidate contained component is a polymer, the candidate contained component physical properties may be expressed by at least one parameter among the solubility parameter, the number of predetermined functional groups, the total number of atoms per repeating unit, the number of atoms of each element per repeating unit, the average molecular weight, the acid dissociation constant (pKa), the polar surface area, the partition coefficient (LogP), the glass transition temperature (Tg), the melting point, the boiling point, the refractive index, the density, the viscosity, and the specific gravity.

[0020] When the candidate raw material is a monomer, the candidate raw material physical properties may be expressed by at least one parameter among the solubility parameter, the number of predetermined functional groups, the total number of atoms per repeating unit, the number of atoms of each element per repeating unit, the average molecular weight, pKa, the polar surface area, LogP, the glass transition temperature (Tg), the melting point, the boiling point, the refractive index, the density, the viscosity, and the specific gravity.

[0021] The mixing ratio between two or more candidate raw materials is represented by the mixing ratio of each candidate raw material. For example, the mixing ratio of six candidate raw materials Ma, Mb, Mc, Md, Me, and Mf is represented as Ra:Rb:Rc:Rd:Re:Rf by the mixing ratio Ra of candidate raw material Ma, the mixing ratio Rb of candidate raw material Mb, the mixing ratio Rc of candidate raw material Mc, the mixing ratio Rd of candidate raw material Md, the mixing ratio Re of candidate raw material Me, and the mixing ratio Rf of candidate raw material Mf. The mixing ratio and the mixing proportion may be expressed by the copolymerization ratio (%) or by the molar concentration (mol / L or mol%).

[0022] As another method different from the present disclosure, it is also conceivable to determine the mixing ratio of candidate raw materials by a one-step process using a prediction model without separate optimization processing from the characteristics of the target composition. However, in this other method, it is necessary to consider not only the combination of physical property values of candidate components but also the combination of mixing ratios of candidate raw materials. Therefore, the number of combinations of numerical values input into the prediction model may become extremely large, and as a result, the calculation cost may increase. Typically, the number of combinations of physical property values of candidate components is about 10 to the 9th power, and the number of combinations of numerical values input into the prediction model is about 10 to the 20th power, so the calculation cost increases. On the other hand, according to the search system according to the present disclosure, it is possible to obtain the mixing ratio of raw materials in a short time without inputting an extremely large number of combinations into the prediction model. Furthermore, according to the search system, since the user can select the physical properties of the components for realizing the desired characteristics of the composition, etc., the transparency of the search system and the reliability of the search results can be enhanced.

[0023] The candidate composition is an example of a candidate downstream substance which is a substance obtained in the downstream process of manufacturing, and the candidate composition characteristics are an example of candidate downstream substance characteristics which are the characteristics of the candidate downstream substance. The candidate contained component is an example of a candidate middle stream substance which is a substance obtained in the middle stream process of manufacturing. The candidate contained component physical properties are an example of related physical properties which are physical properties related to the candidate downstream substance characteristics, and are also an example of candidate middle stream substance physical properties which are the physical properties of the candidate middle stream substance. The candidate raw material is an example of a candidate upstream substance which is a substance used in the upstream process of manufacturing, and the candidate raw material physical properties are an example of candidate upstream substance physical properties which are the physical properties of the candidate upstream substance. Therefore, it can also be said that the search system according to the present disclosure is a computer system that searches for the formulation of substances used in the upstream process of the manufacturing to achieve desired characteristics for substances obtained in the downstream process of the manufacturing in a shorter time. To execute the search, the search system accesses data (for example, contained component / composition data) indicating the combination of candidate downstream substance characteristics and related physical properties. The search system extracts one or more related physical properties corresponding to the search conditions regarding the candidate downstream substance characteristics. Then, based on the related physical properties selected from the extraction results and the physical properties of two or more candidate upstream substances, the search system determines the mixing ratio between the two or more candidate upstream substances to achieve the candidate downstream substance characteristics. In this way, the search system continuously executes two-stage processing: searching for related physical properties corresponding to a downstream substance having desired characteristics, and searching for the mixing ratio between two or more upstream substances that achieve the related physical properties. By using the search system, the user can obtain the formulation of substances used in the upstream process of the manufacturing to achieve desired characteristics for substances obtained in the downstream process of the manufacturing in a shorter time.

[0024] [Configuration of the System] The search system is composed of one or more computers. When a plurality of computers are used, these computers are connected via a communication network such as the Internet or an intranet, thereby logically constructing one search system.

[0025] The computer that constitutes the search system generally includes a processor, a storage device (memory), and a communication interface as hardware devices. The processor is, for example, a CPU or a GPU. The storage device is composed of a flash memory, a hard disk, etc. The communication interface is composed of a network card, a wireless communication module, etc. Each functional module of the search system is realized by the processor executing a program stored in the storage device.

[0026] The search program for causing the computer to function as a search system includes program codes for realizing each functional module of the search system. This search program may be provided after being recorded on a non-temporary recording medium such as a CD-ROM, a DVD-ROM, or a semiconductor memory. Alternatively, the search program may be provided via a communication network as a data signal superimposed on a carrier wave. The provided search program is recorded in, for example, the storage device.

[0027] FIG. 1 is a diagram showing the functional configuration of a search system 10 according to an example. In one example, the search system 10 is connected to a database 30 and a user terminal 40 via a communication network. The communication network is typically constructed by the Internet, an intranet, or a combination thereof. The communication network can be constructed by a wired network, a wireless network, or a combination thereof.

[0028] The database 30 is a storage device that stores various data used by the search system 10. The database 30 may be a component of the search system 10 or may be provided outside the search system 10. In one example, the database 30 stores ingredient / composition data and raw material data.

[0029] The ingredient / composition data is data indicating a plurality of combinations of the physical properties of candidate ingredients and the properties of candidate compositions. In one example, each data record of the ingredient / composition data includes an identifier of a candidate ingredient, the physical properties of the candidate ingredient, an identifier of a candidate composition, and the properties of the candidate composition. For each of the candidate ingredients and candidate compositions, the identifier may be expressed in various forms such as a number, name, chemical formula, structural formula, etc.

[0030] The raw material data is data indicating the physical properties of each of a plurality of candidate raw materials. In one example, each data record of the raw material data includes an identifier of a candidate raw material and the physical properties of the candidate raw material. The identifier of the candidate raw material may be expressed in various forms such as a number, name, chemical formula, structural formula, etc.

[0031] The user terminal 40 is a computer used by a user of the search system 10. The user terminal 40 can be various computers such as a personal computer, a workstation, a tablet terminal, a smartphone, a wearable terminal, etc. The user terminal 40 is provided with a display device such as a liquid crystal display.

[0032] The exploration system 10 includes a processor 101 that functions as a data generation unit 11, a search unit 12, and an exploration unit 13. The data generation unit 11 is a functional module that generates data records of component / composition data using the prediction model 20. The prediction model 20 is a learned model generated by machine learning so as to calculate the characteristics of a composition constituted by the components from the physical properties of the components. The physical properties of the components can be expressed by a combination of one or more physical property values (parameter values) of the components. The prediction model 20 is realized by, for example, a neural network. The prediction model 20 is an example of a prediction model generated by machine learning so as to calculate the characteristics from the physical properties related to the characteristics of the downstream substance (that is, related physical properties or candidate intermediate substance physical properties). The search unit 12 is a functional module that extracts component / composition data corresponding to search conditions related to candidate composition characteristics. The exploration unit 13 is a functional module that determines, by an optimization method, the blending ratio between two or more candidate raw materials constituting a candidate component selected from the extracted component / composition data.

[0033] [Operation of the System] Hereinafter, the operation of the exploration system 10 will be described, and the exploration method according to the present disclosure will be described.

[0034] (Generation of Component / Composition Data) With reference to FIG. 2, the process of generating component / composition data will be described. FIG. 2 is a flowchart showing an example of the process as process flow S1.

[0035] In step S11, the data generation unit 11 inputs the physical properties of a candidate contained component to the prediction model 20 for one candidate contained component to calculate the characteristics of the candidate composition. As described above, in one example, the data generation unit 11 inputs a combination of one or more physical property values (parameter values) of one candidate contained component as the physical properties of the candidate contained component to the prediction model 20 to calculate the characteristics of the candidate composition. For example, the data generation unit 11 randomly selects a parameter value within a specified range for the first parameter of the physical properties of the candidate contained component, or selects a plurality of parameter values at a predetermined interval. The data generation unit 11 also selects parameter values in the same way for the second parameter of the physical properties of the candidate contained component. The data generation unit 11 inputs the combination of the parameter values of the first parameter and the second parameter to the prediction model 20 to calculate the characteristics of the candidate composition. The number of such combinations of physical property values is, for example, about 10 to the 9th power. The data generation unit 11 may read out the physical properties of the candidate contained component stored in a predetermined storage device (memory), or may receive the physical properties of the candidate contained component from another computer such as the user terminal 40, or may accept the physical properties of the candidate contained component input by the administrator of the search system 10. The prediction model 20 calculates the characteristics of the candidate composition from the physical properties of the candidate contained component, and the data generation unit 11 acquires the characteristics of the candidate composition.

[0036] In step S12, the data generation unit 11 generates a data record indicating the combination of the physical properties of the candidate contained component input to the prediction model 20 and the calculated characteristics of the candidate composition. When including the identifiers of the candidate contained component and the candidate composition in the data record, the data generation unit 11 may automatically generate those identifiers according to a predetermined rule, or may set them according to the input by the user or the administrator.

[0037] As shown in step S13, the data generation unit 11 can repeatedly execute the generation of data records. If the generation of data records continues (NO in step S13), the process returns to step S11. In the repeated step S11, the data generation unit 11 inputs the candidate component physical properties of another candidate component into the prediction model 20 to calculate the candidate composition properties. In the repeated step S12, the data generation unit 11 generates another data record indicating the combination of the candidate component physical properties and the candidate composition properties. On the other hand, if the generation of data records is to be terminated (YES in step S13), the process proceeds to step S14. In step S14, the data generation unit 11 stores the set of one or more generated data records in the database 30 as component / composition data.

[0038] As shown in the processing flow S1, for each of one or more candidate components, the data generation unit 11 inputs the candidate component physical properties into the prediction model 20 to calculate the candidate composition properties, and stores a data record indicating the combination of the candidate component physical properties and the candidate composition properties in the database 30 as one of the multiple data records of the component / composition data. The processing flow S1 is an example of a process of inputting the relevant physical properties into the prediction model to calculate the candidate downstream substance properties for each of one or more relevant physical properties, and storing a data record indicating the combination of the relevant physical properties and the candidate downstream substance properties in the database as one of the multiple data records. The search system 10 may execute the processing flow S1 when the component / composition data is not stored in the database 30. Alternatively, the search system 10 may execute the processing flow S1 when one or more data records of the component / composition data are already stored in the database 30 to increase the component / composition data.

[0039] (Determination of Mixing Ratio) With reference to FIG. 3, the process of determining the mixing ratio will be described. FIG. 3 is a flowchart showing an example of the process as the processing flow S2.

[0040] In step S21, the search unit 12 receives search conditions related to candidate composition characteristics from the user terminal 40. This reception process is an example of a process for acquiring search conditions. In one example, the search unit 12 provides the user terminal 40 with a user interface for executing a two-stage process of searching for contained components and searching for the blending ratio between two or more raw materials constituting the contained components. The user terminal 40 displays the user interface on a display device and accepts search conditions input by the user via the user interface. The search conditions are expressed, for example, by the respective numerical ranges of one or more parameters representing candidate composition characteristics. The user terminal 40 transmits the input search conditions to the search system 10, and the search unit 12 receives the search conditions.

[0041] In step S22, the search unit 12 extracts ingredient / composition data corresponding to the search conditions from the database 30. The search unit 12 accesses the database 30 and extracts one or more data records of ingredient / composition data corresponding to the search conditions, that is, one or more data records that match the search conditions, from the database 30.

[0042] In step S23, the search unit 12 transmits the extracted ingredient / composition data to the user terminal 40. The user terminal 40 receives and displays the data. That is, the search unit 12 displays one or more data records of the extracted ingredient / composition data on the display device of the user terminal 40.

[0043] In step S24, the search unit 13 sets, as a search target, the physical properties of a candidate contained component selected by the user. On the user terminal 40, the user interface receives a user operation of selecting one data record from one or more displayed data records, and transmits the physical properties of the candidate contained component indicated by the selected one data record to the search system 10. The search unit 13 sets the physical properties of the candidate contained component as the search target. That is, the search unit 13 sets, in response to a user operation of selecting one data record from one or more data records displayed on the display device of the user terminal 40, the physical properties of the candidate contained component indicated by the one data record as the search target. For each of one or more parameters expressing the physical properties of the candidate contained component, it can be said that the parameter value is the target value for the parameter.

[0044] In step S25, the search unit 13 transmits a plurality of candidate raw materials to the user terminal 40. For example, the search unit 13 reads out raw material data pre-stored in the database 30 and transmits the identifier of each of the plurality of candidate raw materials to the user terminal 40. The user terminal 40 receives and displays the data. That is, the search unit 13 displays a plurality of candidate raw materials on the display device of the user terminal 40.

[0045] In step S26, the search unit 13 acquires the physical properties of each of two or more candidate raw materials selected by the user. On the user terminal 40, the user interface receives a user operation of selecting two or more candidate raw materials from the plurality of displayed candidate raw materials, and transmits the identifiers of the selected two or more candidate raw materials to the search system 10. The selected two or more candidate raw materials are information selected for a candidate contained component having the physical properties of the candidate contained component set as the search target in step S24. For each of the identifiers of the two or more selected candidate raw materials, the search unit 13 reads out the physical properties of the candidate raw material corresponding to the identifier from the raw material data in the database 30. That is, the search unit 13 acquires the physical properties of each of the two or more candidate raw materials in response to a user operation of selecting two or more candidate raw materials from the plurality of candidate raw materials displayed on the display device of the user terminal 40.

[0046] In step S27, the search unit 13 executes an optimization method using the search target and the respective candidate raw material physical properties of two or more selected candidate raw materials, and determines the blending ratio between the two or more candidate raw materials. In one example, the search unit 13 uses the simulated annealing (SA) method as the optimization method. With reference to FIG. 4, the search using the simulated annealing method will be described. FIG. 4 is a flowchart showing an example of the search.

[0047] In step S271, the search unit 13 sets an initial value of the temperature. The temperature is a parameter for controlling the amount of change in the state (explanatory variables in the search space). The higher the temperature, the higher the probability that the state changes in the direction of deteriorating the solution. As the search progresses, the temperature gradually decreases and the amount of change in the state gradually becomes smaller.

[0048] In step S272, the search unit 13 sets an initial value of the blending ratio between two or more candidate raw materials, calculates an initial tentative solution of the candidate contained component physical properties based on the blending ratio as the current tentative solution, and calculates an initial evaluation value indicating the difference between the tentative solution and the search target. An example of this series of processes will be described below.

[0049] First, the search unit 13 randomly sets an initial value of the blending ratio. The blending ratio may be set to 0 for at least one candidate raw material.

[0050] Subsequently, for each of one or more parameters, the search unit 13 calculates the parameter value of the candidate contained component based on the respective parameter values and blending ratios of two or more candidate raw materials. Then, the search unit 13 expresses an initial tentative solution of the candidate contained component physical properties with one or more parameter values of the candidate contained component. The search unit 13 calculates the parameter value of the candidate contained component for each of one or more parameters by any one of the following two calculation methods.

[0051] In the first calculation method, for each of two or more candidate raw materials, the search unit 13 calculates the product of the parameter value and the blending ratio. Then, the search unit 13 calculates the sum of two or more products corresponding to two or more candidate raw materials as the parameter value of the candidate contained component. Let the number of types of candidate raw materials be N, and the parameter value and the blending ratio of the i-th candidate raw material be p i , w i respectively. Then, the parameter value v y of the candidate contained component is obtained by Equation (1).

Equation

[0052] In the second calculation method, for each of two or more candidate raw materials, the search unit 13 calculates the quotient obtained by dividing the blending ratio by the parameter value. Then, the search unit 13 calculates the reciprocal of the sum of two or more quotients corresponding to two or more candidate raw materials as the parameter value of the candidate contained component. Let the number of types of candidate raw materials be N, and the parameter value and the blending ratio of the i-th candidate raw material be p i , w i respectively. Then, the parameter value v y of the candidate contained component is obtained by Equation (2).

Equation

[0053] In one example, the search unit 13 calculates the parameter value by the first calculation method for parameters other than the glass transition temperature, and calculates the parameter value by the second calculation method for the glass transition temperature.

[0054] Subsequently, the search unit 13 calculates an initial evaluation value indicating the difference between the initial tentative solution (current tentative solution) and the search target. In one example, for each of one or more parameters, the search unit 13 calculates the difference between the calculated parameter value and the target value of the search target, and calculates an error rate which is the ratio of the difference to the target value. Then, the search unit 13 calculates the sum of one or more error rates corresponding to one or more parameters as the evaluation value. The smaller this evaluation value is, the closer the tentative solution is to the search target. Let the number of types of parameters be M, and let the parameter value and the target value for the j-th parameter be v j ,g j respectively. Then, the evaluation value E indicating the difference between the tentative solution and the search target is obtained by Equation (3).

Equation

[0055] In step S273, the search unit 13 changes the blending ratio between two or more candidate raw materials, calculates a new tentative solution of the physical properties of the candidate contained components based on the blending ratio, and calculates a new evaluation value indicating the difference between the tentative solution and the search target.

[0056] First, the search unit 13 changes the blending ratio based on a predetermined transition rule in the annealing method. In one example, the search unit 13 selects two candidate raw materials from two or more candidate raw materials, and changes the blending ratio between the two candidate raw materials so that the sum of the blending ratios between the two candidate raw materials does not change. FIG. 5 is a diagram showing an example of such a transition rule. The search unit 13 may exchange the blending ratios between two candidate raw materials (Example 201), or transfer a part of the blending ratio of one candidate raw material to the blending ratio of the other candidate raw material (Example 202). Alternatively, the search unit 13 may average the blending ratios between two candidate raw materials, in which case the blending ratios of both sides become the same (Example 203). Alternatively, the search unit 13 may exchange the blending ratio between one candidate raw material with the minimum blending ratio and one candidate raw material with a blending ratio of 0, and this process can be said to be an exchange of raw materials (Example 204).

[0057] Subsequently, for each of the one or more parameters, the search unit 13 calculates the parameter values of the candidate constituent components based on the parameter values and blending ratios of each of the two or more candidate raw materials. Subsequently, the search unit 13 expresses a new tentative solution for the physical properties of the candidate constituent components using one or more parameter values of the candidate constituent components. Then, the search unit 13 calculates a new evaluation value indicating the difference between the new tentative solution and the search target. The search unit 13 executes these series of processes by the same method as in step S272.

[0058] In step S274, the search unit 13 determines whether to adopt a new tentative solution, using the probability based on the temperature as needed. The search unit 13 adopts the new tentative solution when a better evaluation value is obtained. When the evaluation value E obtained by the above formula (3) is used, a better evaluation value means an evaluation value lower than all the evaluation values calculated so far in step S27. When a better evaluation value is not obtained, the search unit 13 probabilistically determines whether to adopt the new tentative solution based on the probability p = exp(−ΔE / T). ΔE indicates the difference between the current tentative solution and the new tentative solution, and T indicates the temperature. When adopting the new tentative solution, the search unit 13 updates the current tentative solution with the new tentative solution. When not adopting the new tentative solution, the search unit 13 discards the new tentative solution and maintains the current tentative solution.

[0059] As shown in step S275, the search unit 13 repeats steps S273 and S274 until reaching an equilibrium state at the current temperature. The equilibrium state refers to a situation where the current tentative solution does not change even when the process is repeated.

[0060] When reaching the equilibrium state (YES in step S275), the process proceeds to step S276. In step S276, the search unit 13 updates the temperature. This update is a process of decreasing the temperature and is realized, for example, by exponential annealing.

[0061] As shown in step S277, the search unit 13 repeats the processes of steps S273 to S276 until a predetermined end condition is satisfied. The end condition may be that a better evaluation value cannot be obtained, that is, the evaluation value is not updated. Alternatively, the end condition may be that a predetermined processing time has elapsed.

[0062] When the end condition is satisfied (YES in step S277), the process proceeds to step S278. In step S278, the search unit 13 determines the blending ratio. The search unit 13 determines the blending ratio corresponding to the finally adopted tentative solution as the solution of the optimization method (annealing method). That is, the search unit 13 determines the blending ratio that minimizes the evaluation value indicating the difference between the tentative solution of the candidate component physical properties calculated based on the respective candidate raw material physical properties of two or more candidate raw materials and the search target. This process is an example of determining the blending ratio based on the evaluation value.

[0063] As described with reference to FIG. 4, in the annealing method, the search unit 13 repeats the search for the blending ratio while changing the blending ratio between two candidate raw materials selected from two or more candidate raw materials so that the sum of the blending ratios between the two candidate raw materials does not change, and determines the blending ratio.

[0064] Returning to FIG. 3, in step S28, the search unit 13 transmits the determined blending ratio to the user terminal 40. This transmission is an example of the process of outputting the blending ratio. The user terminal 40 receives the blending ratio. The user terminal 40 may display the blending ratio on a display device or store the blending ratio in a predetermined storage device (memory).

[0065] [Modification Example] The technology of the present disclosure has been described in detail based on various examples. However, the technology of the present disclosure is not limited to the above examples. Various modifications are possible without departing from the gist of the present disclosure.

[0066] In the above example, the optimization method is the annealing method. However, the search system (search unit) may execute other types of optimization methods to determine the blending ratio between two or more candidate raw materials. For example, the search system (search unit) may use random search as the optimization method.

[0067] In the above example, the data generation unit 11 generates component / composition data (one or more data records indicating combinations of candidate component physical properties and candidate composition characteristics) using the prediction model 20. However, the component / composition data may be generated by a computer system different from the search system or may be generated manually. Therefore, the search system does not necessarily have functions corresponding to the data generation unit 11 and the prediction model 20, and does not necessarily execute the processing flow S1.

[0068] In the above example, the search unit 13 displays a plurality of candidate raw materials on the display device of the user terminal 40, and acquires candidate raw material physical properties for each of the two or more candidate raw materials in response to a user operation of selecting two or more candidate raw materials from the plurality of candidate raw materials. As a modification of this, the search system (search unit) may acquire the candidate raw material physical properties of each of a predetermined two or more candidate raw materials prepared without depending on a user operation. Alternatively, the search system (search unit) may acquire the candidate raw material physical properties for each of the two or more candidate raw materials in response to a user operation of selecting one or more candidate raw materials from the plurality of candidate raw materials. In this modification, when only one candidate raw material is selected by a user operation, the search system (search unit) automatically selects one or more other candidate raw materials, and acquires the candidate raw material physical properties for each of the one candidate raw material selected by the user operation and the one or more other candidate raw materials automatically selected.

[0069] In the above example, the search system 10 plays the role of a server in a client-server system. As another example, the functions of the search system 10 and the database 30 may be implemented in a stand-alone computer. Alternatively, the search system may be implemented in a user terminal that can access the database 30 via a communication network.

[0070] In the above example, the related physical property is the physical property of the candidate-containing component, but the related physical property may also be the physical property of the candidate composition. As another example, the candidate downstream substance may be the candidate-containing component, the candidate downstream substance property may be the property of the candidate-containing component, and the related physical property may be the physical property of the candidate-containing component. Each substance considered in the search system can be appropriately selected according to the manufacturing process. For example, the search system may determine the mixing ratio among the candidate upstream substances based on the substances in each of the upstream process and the downstream process, or based on the substances in each of the upstream process, the midstream process, and the downstream process.

[0071] The processing procedures of the method executed by at least one processor are not limited to the above examples. For example, some of the above-described steps may be omitted, or each step may be executed in a different order. Also, any two or more of the above-described steps may be combined, or a part of the steps may be modified or deleted. Alternatively, other steps may be executed in addition to each of the above steps.

[0072] In the comparison of the magnitude relationship between two numerical values in the present disclosure, either of the two criteria of "greater than or equal to" and "greater than" may be used, and either of the two criteria of "less than or equal to" and "less than" may be used.

[0073] In the present disclosure, the expression "at least one processor executes the first process, executes the second process,... executes the nth process." or a corresponding expression indicates a concept including the case where the execution subject of the n processes from the first process to the nth process, that is, the processor, changes midway. That is, this expression indicates a concept including both the case where all of the n processes are executed by the same processor and the case where the processor changes in an arbitrary manner in the n processes.

[0074] [Appendix] As can be understood from the various examples above, the present disclosure includes the aspects shown below. (Appendix 1) comprising at least one processor, wherein the at least one processor acquires search conditions related to candidate downstream substance characteristics, which are characteristics of a candidate downstream substance that is a substance obtained in a downstream process of manufacturing, extracts one or more data records corresponding to the search conditions from a database that stores a plurality of data records indicating combinations of the candidate downstream substance characteristics and related physical properties that are physical properties related to the candidate downstream substance characteristics, sets, as a search target, the related physical property indicated by one data record selected from the one or more extracted data records, for each of two or more candidate upstream substances that are substances used in an upstream process of manufacturing, acquires candidate upstream substance physical properties that are physical properties of the candidate upstream substance, executes an optimization method using the search target and the candidate upstream substance physical properties of each of the two or more candidate upstream substances to determine a mixing ratio between the two or more candidate upstream substances, a search system. (Appendix 2) wherein the candidate downstream substance is a candidate composition, the candidate downstream substance characteristics are candidate composition characteristics that are characteristics of the candidate composition, the related physical properties are candidate contained component physical properties that are physical properties of candidate contained components constituting the candidate composition, the candidate upstream substance is a candidate raw material selected for the candidate contained component, the candidate upstream substance physical properties are candidate raw material physical properties that are physical properties of the candidate raw material, the search system according to Appendix 1. (Appendix 3) wherein the at least one processor, for each of the plurality of related physical properties, inputs the related physical property into a prediction model generated by machine learning so as to calculate the characteristics of the downstream substance from the physical properties related to the characteristics of the downstream substance, and calculates the candidate downstream substance characteristics, Storing the data record indicating the combination of the related physical properties input to the prediction model and the calculated candidate downstream substance properties in the database as one of the plurality of data records. The search system according to appendix 1 or 2. (Appendix 4) The at least one processor Displaying the extracted one or more data records on a display device. In response to a user operation of selecting the one data record from the one or more displayed data records, setting the related physical properties indicated by the one data record as the search target. Displaying the determined mixing ratio on the display device. The search system according to any one of appendices 1 to 3. (Appendix 5) The at least one processor Displaying the plurality of candidate upstream substances on a display device. In response to a user operation of selecting one or more of the candidate upstream substances from the plurality of displayed candidate upstream substances, obtaining the candidate upstream substance physical properties for each of the two or more candidate upstream substances. The search system according to any one of appendices 1 to 4. (Appendix 6) The related physical properties are candidate intermediate substance physical properties that are physical properties of a candidate intermediate substance that is a substance obtained in the middle process of the production. In the execution of the optimization method, the at least one processor determines the mixing ratio based on an evaluation value indicating the difference between a tentative solution of the candidate intermediate substance physical properties calculated based on the candidate upstream substance physical properties of each of the two or more candidate upstream substances and the search target. The search system according to any one of appendices 1 to 5. (Appendix 7) Each of the candidate upstream substance physical properties and the candidate intermediate substance physical properties is represented by one or more parameters. The at least one processor For each of the parameters of 1 or more, calculate the parameter value of the candidate intermediate substance based on the parameter values and blending ratios of each of the 2 or more candidate upstream substances. Express the provisional solution of the candidate intermediate substance physical properties with one or more of the parameter values of the candidate intermediate substance. The search system according to Supplementary Note 6. (Supplementary Note 8) For each of at least one parameter selected from the above 1 or more parameters by the at least one processor, For each of the 2 or more candidate upstream substances, calculate the product of the parameter value and the blending ratio. Calculate the sum of the 2 or more products corresponding to the 2 or more candidate upstream substances as the parameter value of the candidate intermediate substance. The search system according to Supplementary Note 7. (Supplementary Note 9) For each of at least one parameter selected from the above 1 or more parameters by the at least one processor, For each of the 2 or more candidate upstream substances, calculate the quotient obtained by dividing the blending ratio by the parameter value. Calculate the reciprocal of the sum of the 2 or more quotients corresponding to the 2 or more candidate upstream substances as the parameter value of the candidate intermediate substance. The search system according to Supplementary Note 7. (Supplementary Note 10) The optimization method is the simulated annealing method, The at least one processor In the simulated annealing method, while changing the blending ratio between two candidate upstream substances selected from the 2 or more candidate upstream substances so that the sum of the blending ratios between the two candidate upstream substances does not change, repeat the search for the blending ratio to determine the blending ratio. The search system according to any one of Supplementary Notes 1 to 9. (Supplementary Note 11) A search method executed by a search system including at least one processor, A step of obtaining search conditions related to candidate downstream substance characteristics, which are characteristics of substances obtained in the downstream process of manufacturing; A step of extracting one or more data records corresponding to the search conditions from a database that stores a plurality of data records indicating combinations of the candidate downstream substance characteristics and related physical properties that are physical properties related to the candidate downstream substance characteristics; A step of setting, as a search target, the related physical property indicated by one data record selected from the one or more extracted data records; A step of obtaining, for each of two or more candidate upstream substances that are substances used in the upstream process of manufacturing, candidate upstream substance physical properties that are physical properties of the candidate upstream substance; A step of executing an optimization method using the search target and the candidate upstream substance physical properties of each of the two or more candidate upstream substances to determine a blending ratio between the two or more candidate upstream substances; A search method including the above. (Appendix 12) A step of obtaining search conditions related to candidate downstream substance characteristics, which are characteristics of substances obtained in the downstream process of manufacturing; A step of extracting one or more data records corresponding to the search conditions from a database that stores a plurality of data records indicating combinations of the candidate downstream substance characteristics and related physical properties that are physical properties related to the candidate downstream substance characteristics; A step of setting, as a search target, the related physical property indicated by one data record selected from the one or more extracted data records; A step of obtaining, for each of two or more candidate upstream substances that are substances used in the upstream process of manufacturing, candidate upstream substance physical properties that are physical properties of the candidate upstream substance; A step of executing an optimization method using the search target and the candidate upstream substance physical properties of each of the two or more candidate upstream substances to determine a blending ratio between the two or more candidate upstream substances; A search program that causes a computer to execute the above.

[0075] According to Supplementary Note 1, 11, and 12, first, based on search conditions related to the characteristics of candidate downstream substances (candidate downstream substance characteristics) obtained in the downstream process of manufacturing, one or more data records indicating combinations of candidate downstream substance characteristics and related physical properties are extracted. Then, an optimization method is executed using the related physical properties indicated by one of the data records selected from those data records as the search target, and the mixing ratio between two or more candidate upstream substances used in the upstream process of manufacturing is determined. A two-step process of searching for related physical properties corresponding to a downstream substance having desired characteristics and searching for the mixing ratio between two or more upstream substances to obtain those related physical properties is continuously executed. With this mechanism, it is possible to search for the combination of substances used in the upstream process of manufacturing that realizes the desired characteristics for the substances obtained in the downstream process of manufacturing in a shorter time. The greater the variety of candidate upstream substances, the more enormous the possible patterns of mixing ratios become. However, even in this case, it is possible to search for the combination of upstream substances to realize a downstream substance having desired characteristics in a shorter time.

[0076] According to Supplementary Note 2, first, based on search conditions related to candidate composition characteristics, one or more data records indicating combinations of candidate composition characteristics and candidate contained component physical properties are extracted. Then, an optimization method is executed using the candidate contained component physical properties indicated by one of the data records selected from those data records as the search target, and the mixing ratio between two or more candidate raw materials for generating the selected candidate contained component is determined. Since a two-step process of searching for contained components corresponding to a composition having desired characteristics and searching for the mixing ratio between two or more raw materials constituting the contained components is continuously executed, it is possible to search for the combination of raw materials that realizes the contained components constituting a composition having desired characteristics in a shorter time.

[0077] According to Supplementary Note 3, candidate downstream substance properties are calculated from related physical properties using a prediction model, and a data record showing a combination of the related physical properties and the candidate downstream substance properties is automatically stored in the database. Therefore, the database used by the search system can be prepared in a short time. For example, a data set showing a plurality of combinations of related physical properties and candidate downstream substance properties can be prepared in a short time without repeating experiments for specifying candidate downstream substance properties or collecting information on candidate downstream substance properties.

[0078] According to Supplementary Note 4, two-stage processing results, namely, a search result of related physical properties corresponding to a downstream substance having desired properties and a search result of mixing ratios between two or more upstream substances for obtaining the related physical properties, are continuously displayed on the display device. With such a mechanism for the user interface, the two-stage processing results can be provided to the user in an easy-to-understand format.

[0079] According to Supplementary Note 5, since the user is provided with an opportunity to select two or more candidate upstream substances for which the mixing ratio is to be determined, the user's desires in determining the mixing ratio can be more flexibly reflected in the search. This contributes to an improvement in the convenience of the search system.

[0080] According to Supplementary Note 6, the mixing ratio is determined based on an evaluation value indicating the difference between the provisional solution of the candidate intermediate substance physical properties and the search target. By adopting this mixing ratio, it becomes possible to increase the probability of realizing a downstream substance having desired properties.

[0081] According to Supplementary Note 7, for each of one or more parameters representing the physical properties of a candidate intermediate substance, the parameter value of the candidate intermediate substance is calculated based on the parameter values and blending ratios of each of two or more candidate upstream substances. Then, a provisional solution of the physical properties of the candidate intermediate substance is represented by one or more parameter values of the candidate intermediate substance. By means of a mechanism in which the individual parameters are calculated independently of each other while expressing the physical properties by one or more parameters, even when the physical properties of the candidate intermediate substance are complex, the calculations necessary to obtain the blending ratio can be made relatively simple. This leads to the simplification of the search process and can contribute to the reduction of the calculation time.

[0082] According to Supplementary Note 8, it can be expected that a specific parameter can be calculated more accurately by using a so-called weighted sum calculation method. Consequently, the physical properties of the candidate intermediate substance represented by one or more parameters can be determined more accurately.

[0083] According to Supplementary Note 9, it can be expected that a specific parameter can be calculated more accurately by calculating the reciprocal of the sum of the quotients obtained by dividing the blending ratio by the parameter value as the parameter value of the physical properties of the candidate intermediate substance. Consequently, the physical properties of the candidate intermediate substance represented by one or more parameters can be determined more accurately.

[0084] According to Supplementary Note 10, in the annealing method, the process related to the state transition can be simplified by transitioning the state (blending ratio) so that the sum of the blending ratios does not change between two candidate upstream substances.

Explanation of Signs

[0085] 10…Search system, 11…Data generation unit, 12…Search unit, 13…Search section, 20…Prediction model, 30…Database, 40…User terminal.

Claims

1. Equipped with at least one processor, The at least one processor, We obtain search criteria related to the characteristics of candidate downstream substances, which are substances obtained in the downstream processes of manufacturing. From a database storing multiple data records that show combinations of candidate downstream material properties and related physical properties which are physical properties related to the candidate downstream material properties, one or more data records corresponding to the search conditions are extracted. The relevant physical property indicated by one data record selected from the one or more extracted data records is set as the search target. For each of the two or more candidate upstream substances used in the upstream process of the aforementioned manufacturing, the physical properties of the candidate upstream substance are obtained. An optimization method is performed using the search target and the properties of each of the two or more candidate upstream materials to determine the mixing ratio between the two or more candidate upstream materials. Search system.

2. The candidate downstream substance is a candidate composition, The candidate downstream material properties are the candidate composition properties, which are the properties of the candidate composition. The aforementioned related physical properties are the physical properties of the candidate constituent components that constitute the candidate composition, The candidate upstream substance is a candidate raw material selected for the candidate component containing the candidate substance. The properties of the candidate upstream material are the properties of the candidate raw material, which are the properties of the candidate raw material. The search system according to claim 1.

3. The at least one processor, with respect to each of the plurality of related physical properties, The relevant physical properties are input into a predictive model generated by machine learning to calculate the properties of a downstream material from the physical properties related to the properties of the downstream material, and the candidate downstream material properties are calculated. The data record showing the combination of the relevant physical properties input to the prediction model and the calculated candidate downstream material properties is stored in the database as one of the plurality of data records. The search system according to claim 1 or 2.

4. The at least one processor, The extracted one or more data records are displayed on the display device. In response to a user operation to select one data record from the one or more data records displayed, the related physical properties indicated by the one data record are set as the search target. The determined mixing ratio is displayed on the display device. The search system according to claim 1 or 2.

5. The at least one processor, Multiple candidate upstream substances are displayed on a display device, In response to a user operation to select one or more candidate upstream materials from the displayed list of candidate upstream materials, the physical properties of each of the two or more candidate upstream materials are obtained. The search system according to claim 1 or 2.

6. The aforementioned related physical properties are the properties of the candidate intermediate material, which is a substance obtained in the intermediate process of the manufacturing process. The at least one processor, in the execution of the optimization method, determines the blending ratio based on an evaluation value that shows the difference between the provisional solution of the candidate midstream material properties calculated based on the property of each of the two or more candidate upstream materials and the search target. The search system according to claim 1 or 2.

7. Each of the candidate upstream material properties and the candidate midstream material properties is expressed by one or more parameters, The at least one processor, For each of the one or more parameters mentioned above, the parameter value of the candidate midstream substance is calculated based on the respective parameter values ​​and blending ratios of the two or more candidate upstream substances. The provisional solution for the properties of the candidate midstream material is expressed by one or more parameter values ​​of the candidate midstream material. The search system according to claim 6.

8. The at least one processor, for each of the at least one parameter selected from the one or more parameters, For each of the two or more candidate upstream substances, the product of the parameter value and the blending ratio is calculated. The sum of the two or more products corresponding to the two or more candidate upstream materials is calculated as the parameter value of the candidate midstream material. The search system according to claim 7.

9. The at least one processor, for each of the at least one parameter selected from the one or more parameters, For each of the two or more candidate upstream substances, the quotient obtained by dividing the blending ratio by the parameter value is calculated. The reciprocal of the sum of the two or more quotients corresponding to the two or more candidate upstream substances is calculated as the parameter value of the candidate midstream substance. The search system according to claim 7.

10. The optimization method is simulated annealing, The at least one processor, In the aforementioned annealing method, the mixing ratio is determined by repeatedly searching for the mixing ratio while changing the mixing ratio between two candidate upstream materials selected from the two or more candidate upstream materials, so that the sum of the mixing ratios between the two candidate upstream materials remains unchanged. The search system according to claim 1 or 2.

11. A search method performed by a search system comprising at least one processor, A step of obtaining search criteria related to candidate downstream material properties, which are the properties of candidate downstream materials, which are materials obtained in the downstream processes of manufacturing, The steps include extracting one or more data records corresponding to the search criteria from a database that stores multiple data records showing combinations of candidate downstream material properties and related physical properties which are physical properties related to the candidate downstream material properties, The steps include setting the relevant physical property indicated by one data record selected from the one or more extracted data records as the search target, A step of obtaining the physical properties of the candidate upstream material for each of the two or more candidate upstream materials used in the upstream process of the aforementioned manufacturing, The steps include: determining the blending ratio between the two or more candidate upstream materials by performing an optimization method using the search target and the physical properties of each of the two or more candidate upstream materials, A search method that includes this.

12. A step of obtaining search criteria related to candidate downstream material properties, which are the properties of candidate downstream materials, which are materials obtained in the downstream processes of manufacturing, The steps include extracting one or more data records corresponding to the search criteria from a database that stores multiple data records showing combinations of candidate downstream material properties and related physical properties which are physical properties related to the candidate downstream material properties, The steps include setting the relevant physical property indicated by one data record selected from the one or more extracted data records as the search target, A step of obtaining the physical properties of the candidate upstream material for each of the two or more candidate upstream materials used in the upstream process of the aforementioned manufacturing, The steps include: determining the blending ratio between the two or more candidate upstream materials by performing an optimization method using the search target and the physical properties of each of the two or more candidate upstream materials, A search program that causes a computer to execute a command.

Images