Prediction system, program, and prediction method

Abstract

A prediction system, program, and method for generating a predictive model for predicting the performance of a composition are provided. [Solution] A prediction system that generates a prediction model that predicts the performance of a composition, comprising: a model acquisition unit that acquires first composition group data, including multiple pairs of composition information and performance values ​​of the composition, from a database and learns the first prediction model that predicts performance values ​​from composition information; a data acquisition unit that acquires second composition group data, including multiple pairs of composition information and performance values ​​of compositions different from the first composition group data, from the database; and a calculation unit that calculates parameters of the second prediction model based on the first prediction model and the second composition group data.

Description

[Technical Field]

[0001] The present invention relates to a prediction system, a program, and a prediction method. [Background technology]

[0002] Patent Document 1 describes an apparatus comprising: "a composition acquisition unit that acquires composition data indicating the composition of a photosensitive resin composition; a characteristic acquisition unit that acquires characteristic data indicating the characteristics of the photosensitive resin composition; and a learning processing unit that executes a model learning process that uses the acquired composition data and learning data including the characteristic data to output recommended composition data indicating the composition of a photosensitive resin composition to be recommended in response to input of target characteristic data indicating the characteristics of a target photosensitive resin composition" (Claim 1). [Prior art document] [Patent documents] [Patent Document 1] JP 2020-77346 A Summary of the Invention

[0003] A first aspect of the present invention provides a prediction system for generating a prediction model for predicting the performance of a composition. The prediction system includes a model acquisition unit, a data acquisition unit, and a calculation unit. The model acquisition unit may acquire a first prediction model that predicts a performance value from composition information, the first prediction model being trained based on first composition group data including a plurality of pairs of composition information and performance values ​​of the compositions. The data acquisition unit may acquire second composition group data including a plurality of pairs of composition information and performance values ​​of compositions different from the first composition group data. The calculation unit may calculate parameters of the second prediction model based on the first prediction model and the second composition group data.

[0004] In the above, the calculation unit may calculate the parameters of the second prediction model by correcting the first prediction model based on the second composition group data.

[0005] In the above, the model acquisition unit may acquire a first parameter constituting the first prediction model. The calculation unit may include a prior distribution generation unit and a statistics calculation unit. The prior distribution generation unit may generate a first probability distribution of the first parameter. The statistics calculation unit may use the first probability distribution as a prior probability based on the first probability distribution and the second composition group data, and calculate statistical values ​​of a second probability distribution, which is a posterior probability distribution of observed data, as parameters of the second prediction model.

[0006] In the above, the prior distribution generation unit may change the degree to which the first probability distribution is transferred to the second probability distribution by changing the variance of the first probability distribution.

[0007] In the above, the prior distribution generation unit may change the degree to which the first probability distribution is transferred to the second probability distribution so as to improve the accuracy of the second prediction model by performing cross-validation using the second composition group data.

[0008] In the above, the statistical value of the second probability distribution may be the mean value of the second probability distribution.

[0009] In the above, the statistics calculation unit may calculate the average value of the second probability distribution by performing sampling.

[0010] In the above, the statistical calculation unit may perform sampling using a Markov Chain Monte Carlo method (MCMC).

[0011] In the above, the data acquisition unit may acquire third composition group data including a plurality of pairs of composition information and performance values ​​of compositions different from the first composition group data and the second composition group data. The statistics calculation unit may use the second probability distribution as a new prior distribution and calculate statistical values ​​of a third probability distribution, which is a posterior probability distribution of the observed data of the third composition group data, as parameters of a third prediction model obtained by updating the second prediction model.

[0012] In the above, the first prediction model and the second prediction model may be regression models, and the parameters may be regression coefficients.

[0013] In the above, the number of pairs contained in the first composition group data may be three times or more the number of pairs contained in the second composition group data.

[0014] In the above, the data acquisition unit may acquire target composition data, which is composition information of the target composition to be predicted. The prediction system may include a prediction unit that inputs the composition information of the target composition into a second prediction model to predict a performance value of the target composition.

[0015] In the above, the performance value may be a range of products that can be produced with the composition.

[0016] In the above, the performance value may be the minimum size of a product that can be manufactured from the composition.

[0017] In the above, the composition may be a resin composition, and the composition information may include information on polymers, monomers, and other components in the resin composition.

[0018] A second aspect of the present invention provides a prediction method including a model acquisition step, a data acquisition step, and a calculation step. In the model acquisition step, a first prediction model may be acquired by regressing performance values ​​from composition information based on first composition group data including a plurality of pairs of composition information and performance values ​​of compositions. In the data acquisition step, second composition group data may be acquired including a plurality of pairs of composition information and performance values ​​of compositions different from the first composition group data. In the calculation step, parameters of the second prediction model may be calculated based on the first prediction model and the second composition group data.

[0019] In a third aspect, the present invention provides a program that, when executed by a computer, causes the computer to function as the above-described prediction system.

[0020] The above summary of the invention does not list all of the features of the present invention, and subcombinations of these features may also be inventions. [Brief explanation of the drawings]

[0021] [Figure 1] 1 shows the configuration of a prediction system 100 according to this embodiment. [Figure 2] 1 shows an example of the configuration of a calculation unit 150 according to this embodiment. [Figure 3] 1 shows an example of a manufacturing apparatus 200 according to this embodiment. [Figure 4] 1 shows a flow of a prediction method according to the present embodiment. [Figure 5] An example of a subflow of S10 in FIG. 4 is shown below. [Figure 6] An example of composition group data is shown below. [Figure 7] An example of a subflow of S400 in FIG. 5 is shown below. [Figure 8] 10 shows another example of the sub-flow of S20 according to a modified example of the present embodiment. [Figure 9] 22 illustrates an example computer 2200 in which aspects of the present invention may be embodied, in whole or in part. DETAILED DESCRIPTION OF THE INVENTION

[0022] The present invention will be described below through embodiments of the invention, but the following embodiments do not limit the scope of the invention according to the claims. Furthermore, not all of the combinations of features described in the embodiments are necessarily essential to the solution of the invention.

[0023] FIG. 1 shows the configuration of a prediction system 100 according to this embodiment. The prediction system 100 generates a prediction model for predicting the performance of a composition. The prediction system 100 predicts the performance value of a target composition using the prediction model. The prediction system 100 searches for a composition that satisfies a target performance value using the prediction model.

[0024] The composition is not particularly limited, and may be a resin composition, for example, a photosensitive resin composition. The photosensitive resin composition may be a photocurable negative type or a photodissolvable positive type. The photosensitive resin composition may be in a liquid state, or may be provisionally cured and / or dried. The provisionally cured and / or dried photosensitive resin composition may be in the form of a film formed on a support layer. In this case, it is also referred to as a photosensitive resin laminate.

[0025] In this embodiment, as an example, the photosensitive resin composition may be formed into a roll by being laminated with a support layer and a protective layer and wound up for the purpose of facilitating storage and transportation, and in this case, the roll-shaped laminate is also referred to as a photosensitive resin roll.

[0026] The prediction system 100 includes a learning unit 120, a model acquisition unit 130, a data acquisition unit 140, a calculation unit 150, a prediction unit 160, and a search unit 180. The prediction system 100 may include modules having other functions as necessary.

[0027] The prediction system 100 may be a computer such as a PC (personal computer), a tablet computer, a smartphone, a workstation, a server computer, or a general-purpose computer, or may be a computer system in which a plurality of computers are connected.

[0028] Alternatively, the prediction system 100 may be a dedicated computer designed for purposes such as generating a prediction model, or may be dedicated hardware implemented using dedicated circuits. The prediction system 100 may be implemented by a single device (computer), or may be implemented by multiple devices with different roles. Although not specifically described below, the prediction system 100 is equipped with a memory / hard disk, etc., which stores information necessary for processing as appropriate and transmits information between processing modules such as the learning unit 120 and the model acquisition unit 130.

[0029] The learning unit 120 learns a first prediction model that predicts a performance value from composition information. The learning unit 120 acquires, from the database 110, first composition group data that includes a plurality of pairs of composition information and performance values ​​of compositions.

[0030] The learning unit 120 may learn a first prediction model based on the first composition group data. The learning unit 120 may acquire first parameters constituting the first prediction model through learning.

[0031] The model acquisition unit 130 acquires the first prediction model from the learning unit 120. The prediction system 100 may not include the learning unit 120. In this case, the model acquisition unit 130 may acquire the first prediction model that has been trained or generated in advance from the database 110 or from an external source. The model acquisition unit 130 may acquire the first parameters from the learning unit 120.

[0032] The data acquisition unit 140 may acquire data required for the prediction system 100 from the database 110 and provide it to each module of the prediction system 100. For example, the data acquisition unit 140 may acquire second composition group data that includes multiple pairs of composition information and performance values ​​of compositions different from the first composition group data.

[0033] The second composition group data is smaller in size than the first composition group data. That is, the number of pairs included in the second composition group data is smaller than the number of pairs included in the first composition group data. The second composition group data may be equal to or larger in size than the first composition group data.

[0034] The data acquiring unit 140 may further acquire third composition group data including a plurality of pairs of composition information and performance values ​​of compositions different from the first composition group data and the second composition group data. The data acquiring unit 140 may acquire target composition data, which is composition information of the target composition to be predicted.

[0035] The calculation unit 150 generates a second prediction model. The calculation unit 150 may acquire the first prediction model from the model acquisition unit 130 and acquire the first composition group data from the data acquisition unit 140. The calculation unit 150 may calculate parameters of the second prediction model based on the first prediction model and the second composition group data. The calculation unit 150 may calculate parameters of the second prediction model by modifying the first prediction model based on the second composition group data.

[0036] 2 shows an example of the configuration of the calculation section 150 according to this embodiment. The calculation section 150 may include a prior distribution generation section 152 and a statistics calculation section 154.

[0037] The prior distribution generation unit 152 generates a first probability distribution of the first parameter of the first prediction model. The prior distribution generation unit 152 supplies the first probability distribution to the statistics calculation unit 154.

[0038] Based on the first probability distribution and the second composition group data, the statistics calculation unit 154 calculates, as a second parameter of the second prediction model, the statistical value of the second probability distribution, which is a posterior probability distribution with the first probability distribution as the prior probability and the second composition group data as the observed data. That is, the statistics calculation unit 154 generates the second prediction model by updating the first prediction model represented by the first probability distribution with the second composition group data, which is the observed data. The operations of the prior distribution generation unit 152 and the statistics calculation unit 154 will be described in detail below.

[0039] The prediction unit 160 predicts the performance value of the composition based on the second prediction model. For example, the prediction unit 160 inputs composition information (hereinafter also referred to as "target composition information") of the composition to be predicted (hereinafter also referred to as "target composition") into the second prediction model and predicts the performance value of the target composition. The prediction unit 160 acquires the performance value output from the second prediction model as the predicted result of the performance value of the target composition.

[0040] The search unit 170 searches for a composition having a performance value that satisfies the target performance value. The search unit 170 receives the target performance value as an input, supplies target composition information to the prediction unit 160, and acquires a predicted performance value from the prediction unit 160. The search unit 170 outputs, as recommended composition information, target composition information whose predicted performance value satisfies the target performance value.

[0041] 3 shows an example of a manufacturing apparatus 200 according to this embodiment. The manufacturing apparatus 200 manufactures a composition. For example, the manufacturing apparatus 200 manufactures a photosensitive resin composition. The manufacturing apparatus 200 may include a mixing section 210 that mixes raw materials for the composition, and a production section 220 that produces the composition from the mixed raw materials.

[0042] The mixing unit 210 may perform mixing based on the recommended composition information output from the searching unit 170. For example, the mixing unit 210 may receive the recommended composition information from the prediction system 100 and mix the ingredients according to the recommended composition information.

[0043] The generating section 220 may include a filtering section that filters the raw materials, an application section that applies the raw materials onto a support layer to form a film-like composition, and a roller section that attaches a protective layer to the composition and winds up the laminate.

[0044] In this manner, according to this embodiment, a first prediction model based on the first composition group data is modified based on the second composition group data to generate a second prediction model. Even if the scale of the second composition group data is small, the second prediction model can be generated with high accuracy.

[0045] This allows for higher accuracy of the second prediction model compared to when the second composition group data is used alone. Furthermore, compared to when re-learning is performed using both the first composition group data and the second composition group data, it is possible to reduce the computational and storage resources used while still improving the accuracy of the prediction model. This is because a model can be constructed using the second composition group data while adjusting the weight of the first composition group data.

[0046] 4 shows a flow of the prediction method according to this embodiment. The prediction system 100 executes, for example, steps S10 to S50 to use the second prediction model to produce a composition having recommended composition information that satisfies the target performance value. The order of steps S10 to S50 may be changed, and some steps may be omitted.

[0047] In S10, the prediction system 100 generates a second prediction model.

[0048] Figure 5 shows an example of a subflow of S10 in Figure 4. The prediction system 100 may perform S10 by executing the flow of S100 to S400 in Figure 5. S100 to S400 may be performed in a different order than stated above, or some of them may be omitted.

[0049] First, in S100, the learning unit 120 acquires first composition group data. The first composition group data includes a plurality of pairs of composition information and performance values ​​of the compositions.

[0050] The composition information is information about the components contained in the composition and / or the raw materials that can produce the composition (hereinafter, the components and raw materials are collectively referred to as "components, etc.").

[0051] The composition information may be, for example, the presence or absence of a component, etc. in the composition, the amount of the component, etc., and / or the content ratio of the component, etc. The component, etc. may be represented by information that can at least partially identify its chemical structure, and may be represented by, for example, a common name, a common name, an IUPAC name, a trade name, a model number, a chemical formula, a structural formula, a composition formula, a CAS number, a three-dimensional structure, a molecular fingerprint, a molecular weight, an average molecular weight, a molecular weight distribution, a manufacturer, a place of production, and / or a production lot.

[0052] The composition may be, for example, a resin composition, for example, a photosensitive resin composition. However, the composition is not limited thereto. The composition information may include, as components, information on polymers, monomers, and other components in the resin composition.

[0053] More specifically, the components may include at least one of an alkali-soluble polymer, an ethylenically unsaturated bond-containing compound, a photopolymerization initiator, a resin having a repeating unit containing an acid-decomposable group (for example, a group that is deprotected by an acid), a phenolic resin, a photoacid generator, a dissolution inhibitor, a sensitizer, a polymerization inhibitor, an adhesion agent, a plasticizer, and a solvent.

[0054] Among these, the alkali-soluble polymer may be a polymer in a photocurable resin composition, such as a polymer containing a carboxyl group. The ethylenically unsaturated bond-containing compound may be a monomer in a photocurable resin composition. The photopolymerization initiator may bond monomers together in a photocurable resin composition upon exposure to light. Resins having repeating units containing acid-decomposable groups and phenolic resins may be polymers in a photosoluble resin composition and may be dissolved and decomposed by acid. The photoacid generator generates acid in a photosoluble resin composition upon exposure to light. The dissolution inhibitor, also known as a dissolution inhibitor, inhibits the dissolution of components in an alkaline aqueous solution. The sensitizer may be, for example, a photosensitizer, but other types of sensitizers such as N-phenylglycine may also be used. The polymerization inhibitor may inhibit polymerization reactions due to the influence of light or heat. The adhesion agent enhances the adhesion of the photosensitive resin composition to the substrate surface. The plasticizer is added to the photosensitive resin composition to impart flexibility and facilitate processing.

[0055] The performance value may be a numerical representation of the performance of the composition itself, the performance of the composition after processing by a predetermined method, or the performance of a product produced from the composition. For example, the performance value may be one or more of the minimum development time of the photosensitive resin composition, sensitivity to light, transparency, resolution, the range of products that can be produced from the composition, adhesion to the substrate, foaming property of the developer, cohesive property of the developer, edge fuse characteristics, flexibility of the cured film, color stability, peeling time, size of the peeled piece, film thickness, tackiness with the support layer or protective layer, and tentability.

[0056] Development of a photosensitive resin composition may involve exposing the photosensitive resin composition to light to cure or solubilize the photosensitive resin composition in the exposed regions, and then removing the photosensitive resin composition in the exposed or unexposed regions to reveal a negative or positive image corresponding to the exposed region. When the photosensitive resin composition is photocurable (also referred to as negative), the minimum development time, also referred to as the breakpoint, indicates the minimum time required for the photosensitive resin composition to be developed. For example, the minimum development time may be the time required for all of the photosensitive resin composition to be removed by developing the photosensitive resin composition laminated on a substrate by spraying an alkaline solution without exposure to light. The minimum development time may be the time required when parameters that may affect the development time, such as the number of spray nozzles and spray pressure, are fixed.

[0057] When the photosensitive resin composition is photocurable, the sensitivity to light is also referred to as the minimum curing exposure amount, and indicates the minimum exposure amount capable of forming an image corresponding to the exposed area. For example, when the photosensitive resin composition is photocurable, the sensitivity to light is the minimum exposure amount (mJ / cm) at which the photosensitive resin composition that is applied or laminated to a substrate is cured and remains on the substrate when exposed and developed. 2 As an example, the sensitivity to light may be calculated from the lowest transmittance at which the photosensitive resin composition is cured by exposing the photosensitive resin composition to light using a mask having gradually different transmittances.

[0058] The transmittance, also referred to as the transmittance, indicates the transmittance of light. The wavelength of the transmitted light may be a wavelength that cures or solubilizes the photosensitive resin composition.

[0059] The range of products producible by the composition may be the dimensions that can be formed without defects by the photosensitive resin composition, etc. For example, the range of products producible by the composition may be the minimum dimensions of products that can be produced by the composition.

[0060] The developer foaming property indicates the foaming property when a photosensitive resin composition is developed using a developer. As the developer foaming property, values ​​measured by various known methods may be used.

[0061] The developer coagulation property indicates the coagulation property when the photosensitive resin composition is developed using a developer. As the developer coagulation property, a value measured by various known methods may be used.

[0062] The edge fuse characteristic indicates the amount of photosensitive resin composition that protrudes from the end face of a photosensitive resin laminate roll due to winding pressure during storage of the photosensitive resin laminate roll. The smaller the edge fuse characteristic, the longer the usable life of the photosensitive resin laminate, which is preferable. Values ​​measured by various known methods may be used as the edge fuse characteristic.

[0063] The flexibility of the cured film indicates the flexibility of the developed photocurable photosensitive resin composition. For example, the flexibility of the cured film may be the smallest diameter at which the resist does not crack when a photosensitive resin laminate of the photosensitive resin composition laminated on a flexible substrate is exposed to light and developed, and then wrapped around multiple cylinders of different diameters. As an example, the flexibility of the cured film may be measured using a mandrel bending tester.

[0064] The tackiness with the support layer or protective layer indicates the adhesiveness between the photosensitive resin laminate and the support layer or protective layer. For example, the tackiness may be the force required to peel the photosensitive resin laminate from the support layer or protective layer using a Tensilon device. If the tackiness is too high or too low, the usability of the photosensitive resin laminate roll will be reduced, so it is preferable that the tackiness be within an appropriate range.

[0065] The peeling time indicates the releasability when peeling the photosensitive resin composition from the substrate. For example, the peeling time may be the time it takes for the photosensitive resin composition to peel from the substrate when a photosensitive resin laminate laminated on a substrate and exposed to light is immersed in an alkaline stripping solution for development. A shorter peeling time is preferred.

[0066] The color stability indicates the stability of the color tone of the photosensitive resin composition. As the color stability, values ​​measured by various known methods may be used.

[0067] The peeled piece size indicates the size of the photosensitive resin composition (also referred to as peeled piece) peeled from the substrate. The peeled piece size may be the size of the peeled piece peeled from the substrate and broken into small pieces by a water spray. Smaller peeled pieces are preferred.

[0068] The tentability indicates the rate of breakage when tenting tent holes in a substrate with a photosensitive resin laminate. For example, the tentability may be the number of broken tent holes when a photosensitive resin laminate is laminated onto a substrate having tent holes with a diameter of 1 to 10 mm, exposed to light, and developed. The smaller the tentability, the better.

[0069] Next, the learning unit 120 learns a first prediction model. By learning the first prediction model, the learning unit 120 acquires first parameters of the first prediction model that constitute the prediction model. The first prediction model may input composition information and output a performance value.

[0070] For example, the learning unit 120 may learn a regression model as the first prediction model. In this case, the first parameter of the first prediction model may include a regression coefficient and / or an intercept. The regression model is not particularly limited and may be, for example, a linear regression model such as simple regression, multiple regression, or logistic regression, or a nonlinear regression model. The learning unit 120 may perform learning using a known algorithm.

[0071] The learning unit 120 may learn a model other than a regression model as the first prediction model. For example, the learning unit 120 may learn a recurrent or time-delay neural network, a random forest, gradient boosting, logistic regression, or a support vector machine (SVM). The learning unit 120 may acquire parameters constituting these prediction models (e.g., weights of each node of a neural network) as first parameters of the first prediction model.

[0072] Instead of the learning unit 120 acquiring the first composition group data, the data acquiring unit 140 may acquire the first composition group data and provide it to the learning unit 120.

[0073] An example of composition group data is shown in Fig. 6. The learning unit 120 may use the data shown in Fig. 6 as first composition group data to learn the first prediction model.

[0074] In Figure 6, "Polymer 1," "Polymer 2," "Monomer 1," and "Monomer 2" correspond to components, etc., of the composition information. Polymer 1 and Polymer 2 represent specific types of polymers. Monomer 1 and Monomer 2 represent specific types of monomers. For example, Figure 6 shows that the composition with ID=1 contains 0.5 parts by weight of a polymer of the type "Polymer 1," 0.1 parts by weight of a polymer of the type "Polymer 2," 0.4 parts by weight of a monomer of the type "Monomer 1," and 0.1 parts by weight of a monomer of the type "Monomer 2," and as a result, the performance value was 4.2.

[0075] Next, in S300, the data acquisition unit 140 acquires second composition group data. The second composition group data may be in the same format as the first composition group data (e.g., the same format as that shown in FIG. 6). The number of pairs included in the second composition group data may be fewer than the number of pairs included in the first composition group data. For example, the number of pairs included in the first composition group data may be three times or more, five times or more, or ten times or more the number of pairs included in the second composition group data.

[0076] The composition information of the second composition group data may be included in the range of the composition information of the first composition group data. For example, the composition information of the second composition group data may include no components that are not included in the composition information of the first composition group data (i.e., the second composition group data includes only the components already mentioned).

[0077] Alternatively, the composition information of the second composition group data may include components outside the scope of the composition information of the first composition group data, i.e., the second composition group data may include new components (hereinafter referred to as "new components") that are not included in the components (hereinafter referred to as "previous components") included in the first composition group data.

[0078] In this case, the data acquisition unit 140 may replace information on the new component, etc. with information on the previously mentioned component, etc., based on a predetermined rule. For example, the content of the new component, etc. may be replaced with the content of a previously mentioned component, etc., having similar chemical properties. The content may remain the same before and after the replacement, or the content may be corrected based on a predetermined rule. The replacement rule may be registered by the user in advance, or the user may perform the replacement on the spot. In addition to or instead of the above, the non-informative distribution described below or transition suppression may be applied to the new component, etc.

[0079] As an example, if the first composition group data includes methyl acrylate as a component, etc., but does not include methyl methacrylate, and the second composition group data includes methyl methacrylate as a component, etc., the data acquisition unit 140 may replace the content of methyl methacrylate in the second composition group data (e.g., 0.2 parts by weight of methyl methacrylate) with the same content of methyl acrylate (e.g., 0.2 parts by weight of methyl acrylate).

[0080] The performance values ​​of the second composition group data may be obtained by the same method as the performance values ​​of the first composition group data. For example, the performance values ​​of the first composition group data may represent the performance of the composition after processing under predetermined conditions (e.g., exposure, development, and heating under certain conditions), and the performance values ​​of the second composition group data may represent the performance of the composition after processing under the same conditions.

[0081] Alternatively, the performance values ​​of the second composition group data may be obtained by a method different from that of the first composition group data. For example, the performance values ​​of the first composition group data may represent the performance of the composition after processing under predetermined conditions (e.g., exposure, development, and heating under certain conditions), and the performance values ​​of the second composition group data may represent the performance of the composition after processing under different conditions.

[0082] In the second composition group data, the conditions of the treatments performed on the compositions in the first composition group data (e.g., temperature, treatment time, atmospheric pressure, pressure and / or voltage, etc.) may be changed. In the second composition group data, some of the treatments performed on the compositions in the first composition group data may be omitted. In the second composition group data, in addition to the treatments performed on the compositions in the first composition group data, additional treatments may be performed. As an example, the performance values ​​of the first composition group data may be the performance values ​​when the compositions are heated after exposure and before development, and the performance values ​​of the second composition group data may be the performance values ​​when heating after exposure is not performed.

[0083] Next, in S400, the calculation unit 150 generates a second prediction model.

[0084] Fig. 7 shows an example of a sub-flow of S400 in Fig. 5. The calculation section 150 may perform S400 by executing the flow of S410 to S440 in Fig. 7.

[0085] First, in S410, the prior distribution generation unit 152 generates a first probability distribution of the first parameter of the first prediction model trained in S200. For example, the prior distribution generation unit 152 generates the first probability distribution by setting a degree of dispersion specified by the user or determined in advance for a distribution whose mean value is the regression coefficient of the first prediction model. The prior distribution generation unit 152 may generate a distribution of a predetermined shape (for example, a Gaussian distribution) as the first probability distribution.

[0086] The prior distribution generation unit 152 changes the degree of variance of the first probability distribution to change the degree to which the first probability distribution will later be transitioned to the second probability distribution. As the variance increases, the first probability distribution becomes closer to a uniform distribution, and the degree of transition decreases. As the variance decreases, the peak of the first probability distribution becomes sharper, and the degree of transition increases. The variance may be, for example, the variance or standard deviation of the distribution. For new components, etc., the prior distribution generation unit 152 may generate a non-informative distribution (i.e., a uniform distribution) as the first probability distribution, or may not perform transition.

[0087] The prior distribution generating unit 152 may set the degree of transition of a plurality of parameters to be the same. For example, the prior distribution generating unit 152 may set the degree of transition (e.g., dispersity) for a parameter (e.g., regression coefficient) related to polymer 1 to be the same as the degree of transition (e.g., dispersity) for a parameter (e.g., regression coefficient) related to polymer 2.

[0088] The prior distribution generating unit 152 may vary the degree of transition of a plurality of parameters. For example, the second composition group data may vary the degree of transition (e.g., dispersity) for a parameter (e.g., regression coefficient) related to polymer 1 and the degree of transition (e.g., dispersity) for a parameter (e.g., regression coefficient) related to polymer 2.

[0089] In the first S410, the prior distribution generating unit 152 may randomly determine the degree of transfer, or may receive input of the degree of transfer from the user.

[0090] Next, in S420, the statistics calculation unit 154 calculates second parameters of the second prediction model. Based on the first probability distribution generated in S410 and the second composition group data acquired in S300, the statistics calculation unit 154 may calculate, as the second parameters of the second prediction model, statistical values ​​of the second probability distribution, which is a posterior probability distribution in which the first probability distribution is the prior probability and the second composition group data is the observed data.

[0091] The statistics calculation unit 154 may calculate the statistics of the second probability distribution by performing sampling on the parameters of the prediction model. For example, the statistics calculation unit 154 may perform sampling using a Markov Chain Monte Carlo method (MCMC). The statistics may be, for example, a mean, a median, or an expected value. For example, the statistics calculation unit 154 acquires the mean value of the second probability distribution obtained as a result of the sampling as the second parameter of the second prediction model.

[0092] The second prediction model may be a model similar to the first prediction model. For example, if the first prediction model is a regression model, the second prediction model may be a regression model of the same type as the first prediction model. In this case, the second parameter may be a regression coefficient and / or an intercept. In this way, the statistical calculation unit 154 uses the first prediction model as a prior distribution, modifies the prior distribution using the second composition group data as observations to obtain a posterior distribution, and obtains the second parameter by analyzing the posterior distribution.

[0093] Next, in S430, the prior distribution generation unit 152 obtains the prediction accuracy of the second prediction model. The prior distribution generation unit 152 may obtain the prediction accuracy by cross-validation.

[0094] For example, the prior distribution generating unit 152 may input the composition information of the second composition group data into the second prediction model and compare the output value with the performance value of the second composition group data to evaluate the accuracy of the current second prediction model. As an example, the prior distribution generating unit 152 may calculate the degree of deviation between the output value and the performance value using a known loss function and calculate the accuracy of the second prediction model based on the degree of deviation.

[0095] Next, in S440, the prior distribution generation unit 152 determines whether or not to end the process of S400. The prior distribution generation unit 152 may end the process of S400 when the accuracy of the second prediction model is equal to or greater than a threshold. The prior distribution generation unit 152 may end the process of S400 when the loop of S410 to S440 has been executed a predetermined number of times and / or for a predetermined time.

[0096] The prior distribution generation unit 152 may output the last generated second parameter and / or the second parameter with the highest accuracy as the second parameter of the final second prediction model. If the termination condition is not satisfied, the prior distribution generation unit 152 returns the process to S410 and generates the first probability distribution again.

[0097] In S410 from the second time onwards, the prior distribution generation unit 152 may decrease or increase the degree of transfer (e.g., the degree of distribution). For example, the prior distribution generation unit 152 may increase the degree of dispersion while maintaining the mean value of the first probability distribution. Based on the accuracy evaluated in S430, the prior distribution generation unit 152 may adjust the degree of transfer so as to increase the accuracy. For example, the prior distribution generation unit 152 may adjust the degree of transfer using a gradient method or the like.

[0098] Thus, in S400, the prior distribution generation unit 152 may change the degree to which the first probability distribution is transferred to the second probability distribution by performing cross-validation using the second composition group data, so as to improve the accuracy of the second prediction model.

[0099] The processes performed by the prior distribution generating unit 152 and the statistics calculating unit 154 may be performed by known software. For example, programs such as pyMC, stan, and pyro may be used.

[0100] As described above, in S10, the calculation unit 150 generates a second prediction model that predicts a performance value from the composition information. The calculation unit 150 supplies the second prediction model to the prediction unit 160. The prediction unit 160 inputs the target composition information of the target composition into the second prediction model, thereby obtaining a predicted value of the performance value of the target composition.

[0101] In S20, a target performance value is input from the user to the search unit 170. The target performance value is a performance value that the composition should satisfy.

[0102] In S30, the search unit 170 searches for composition information of a composition that satisfies the target performance value. The search unit 170 generates target composition information for the search and supplies it to the prediction unit 160. The prediction unit 160 inputs the target composition information into a second prediction model and obtains a performance value corresponding to the target composition information.

[0103] The search unit 170 may generate composition information so that the composition satisfies the target performance value. The search unit 170 may generate composition information using a known search algorithm. For example, the search unit 170 may initially generate composition information randomly, and then generate composition information using a gradient method or the like so that the performance value approaches the target performance value.

[0104] The search unit 170 identifies composition information that satisfies the target performance value as recommended composition information. If composition information that satisfies the target performance value cannot be found, the search unit 170 identifies one or more pieces of composition information that have achieved performance close to the target performance value as recommended composition information.

[0105] In S40, the search section 170 outputs the generated recommended composition information. The search section 170 may output the recommended composition information to the manufacturing apparatus 200.

[0106] In S50, the manufacturing apparatus 20 may manufacture a composition based on the recommended composition information. For example, the mixing unit 210 mixes raw materials based on the recommended composition information. This allows the manufacturing apparatus 20 to manufacture a composition that is likely to achieve target performance. Thereafter, the performance value of the manufactured composition may be measured, and additional learning may be performed using the pair of composition information and performance value of the manufactured composition.

[0107] The manufacturing apparatus 20 may manufacture a product using the composition. For example, the manufacturing apparatus 20 may apply a fluid of a composition that is a photosensitive resin composition onto a support layer. After applying the photosensitive resin composition, the manufacturing apparatus 20 may remove the solvent and dispersion medium by drying. This produces a laminate of the support layer and the film-like photosensitive resin composition. The manufacturing apparatus 20 may manufacture a photosensitive resin laminate by providing a protective layer on the photosensitive resin composition to protect the photosensitive resin composition.

[0108] According to this embodiment, the prediction system 100 can utilize the first prediction model to generate a second prediction model using a relatively small amount of second composition group data. This method can save computational and / or storage resources compared to merging the first and second composition group data and re-learning. Furthermore, according to this embodiment, even if the composition information, processing conditions, etc. of the second composition group data differ from those of the first composition group data, the second prediction model can be generated with high accuracy by referring to the first prediction model.

[0109] 8 shows another example of the subflow of S20 according to a modification of the present embodiment. In this modification, S20 may be executed by S100 to S600. S100 to S400 may be executed in the same manner as the processing described in FIG. 5. In this modification, the prediction system 100 may execute S500 to S600 in addition to S100 to S400.

[0110] In S500, the data acquisition unit 140 acquires third composition group data. The third composition group data may be in the same format as the first composition group data and / or the second composition group data (e.g., the same format as that shown in FIG. 6). The number of pairs included in the third composition group data may be fewer than the number of pairs included in the first composition group data. For example, the number of pairs included in the first composition group data may be three times or more, five times or more, or ten times or more the number of pairs included in the third composition group data.

[0111] The composition information of the third composition group data may be included in the range of the composition information of the first composition group data. Alternatively, the composition information of the third composition group data may include information outside the range of the composition information of the first composition group data. The data acquisition unit 140 may perform the same processing on the third composition group data as on the second composition group data in S300.

[0112] In S600, the calculation unit 150 generates a third prediction model. The calculation unit 150 may generate the third prediction model using a method similar to that used to generate the second prediction model in S400. For example, the statistics calculation unit 154 may use the second probability distribution obtained as the posterior probability distribution in S420 as a new prior distribution, and calculate the statistical values ​​of the third probability distribution, which is the posterior probability distribution of the observed data, for the third composition group data as parameters of the third prediction model, which is an updated version of the second prediction model. The calculation unit 150 may provide the third prediction model to the prediction unit 160, and the prediction unit 160 may use the third prediction model for prediction.

[0113] The prediction system 100 may execute the processes of S500 to S600 at any time after S20, instead of S10. For example, if a composition is produced in S50 and then the performance value of the composition is measured, the prediction system 100 may acquire third composition group data including composition information and performance value of the composition, and generate a third prediction model.

[0114] The prediction system 100 may further acquire the third and subsequent composition group data and further update the prediction model. For example, the prediction system 100 may acquire fourth composition group data in the same manner as in S500 to S600 and generate a fourth prediction model.

[0115] In this way, according to this modification, the calculation unit 150 can update the prediction model every time new composition group data is acquired, thereby enabling the prediction system 100 to improve the accuracy of prediction using fewer computational and / or storage resources.

[0116] In the above example, the method of transferring the first prediction model to the second prediction model using a prior probability distribution in S400 has been described, but the present invention is not limited to this. For example, an error function of the first parameter of the first prediction model and the second parameter of the second prediction model may be defined, and the degree of transfer to the second prediction model may be adjusted by adjusting the magnitude of the error.

[0117] Various embodiments of the present invention may be described with reference to flowcharts and block diagrams, where the blocks may represent (1) stages of a process in which operations are performed or (2) sections of an apparatus responsible for performing the operations. Particular stages and sections may be implemented by dedicated circuitry, programmable circuitry provided with computer-readable instructions stored on a computer-readable medium, and / or a processor provided with computer-readable instructions stored on a computer-readable medium. Dedicated circuitry may include digital and / or analog hardware circuitry, and may include integrated circuits (ICs) and / or discrete circuits. Programmable circuitry may include reconfigurable hardware circuitry, including logical AND, OR, XOR, NAND, NOR, and other logical operations, flip-flops, registers, memory elements such as field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), and the like.

[0118] A computer-readable medium may include any tangible device capable of storing instructions that are executed by an appropriate device, such that the computer-readable medium having instructions stored thereon comprises an article of manufacture containing instructions that can be executed to create means for performing the operations specified in the flowcharts or block diagrams. Examples of computer-readable media may include electronic, magnetic, optical, electromagnetic, and semiconductor storage media. More specific examples of computer-readable media may include floppy disks, diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), electrically erasable programmable read-only memory (EEPROM), static random access memory (SRAM), compact disc read-only memory (CD-ROM), digital versatile disc (DVD), Blu-ray disc, memory stick, integrated circuit card, and the like.

[0119] The computer readable instructions may include either assembler instructions, Instruction Set Architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state-setting data, or source or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk®, JAVA®, C++, etc., and conventional procedural programming languages ​​such as the “C” programming language or similar programming languages.

[0120] The computer-readable instructions may be provided to a processor or programmable circuitry of a programmable data processing apparatus, such as a general-purpose computer, special-purpose computer, or other computer, either locally or over a wide-area network (WAN) such as a local area network (LAN), the Internet, etc., which executes the computer-readable instructions to create means for performing the operations specified in the flowcharts or block diagrams. Examples of processors include computer processors, processing units, microprocessors, digital signal processors, controllers, microcontrollers, etc.

[0121] 9 illustrates an example of a computer 2200 in which aspects of the present invention may be embodied, in whole or in part. Programs installed on the computer 2200 may cause the computer 2200 to function as or perform operations associated with an apparatus or one or more sections of the apparatus according to embodiments of the present invention, and / or to perform a process or steps of a process according to embodiments of the present invention. Such programs may be executed by the CPU 2212 to cause the computer 2200 to perform specific operations associated with some or all of the blocks of the flowcharts and block diagrams described herein.

[0122] A computer 2200 according to this embodiment includes a CPU 2212, a RAM 2214, a graphics controller 2216, and a display device 2218, which are interconnected by a host controller 2210. The computer 2200 also includes input / output units such as a communication interface 2222, a hard disk drive 2224, a DVD-ROM drive 2226, and an IC card drive, which are connected to the host controller 2210 via an input / output controller 2220. The computer also includes legacy input / output units such as a ROM 2230 and a keyboard 2242, which are connected to the input / output controller 2220 via an input / output chip 2240.

[0123] The CPU 2212 operates according to programs stored in the ROM 2230 and RAM 2214, thereby controlling each unit. The graphics controller 2216 acquires image data generated by the CPU 2212 into a frame buffer or the like provided in the RAM 2214 or into the graphics controller 2216 itself, and causes the image data to be displayed on the display device 2218.

[0124] The communications interface 2222 communicates with other electronic devices via a network. The hard disk drive 2224 stores programs and data used by the CPU 2212 in the computer 2200. The DVD-ROM drive 2226 reads programs or data from the DVD-ROM 2201 and provides the programs or data to the hard disk drive 2224 via the RAM 2214. The IC card drive reads programs and data from an IC card and / or writes programs and data to an IC card.

[0125] The ROM 2230 stores therein a boot program or the like that is executed by the computer 2200 upon activation, and / or programs that depend on the hardware of the computer 2200. The input / output chip 2240 may also connect various input / output units to the input / output controller 2220 via a parallel port, a serial port, a keyboard port, a mouse port, etc.

[0126] The programs are provided by a computer-readable medium such as a DVD-ROM 2201 or an IC card. The programs are read from the computer-readable medium, installed in the hard disk drive 2224, RAM 2214, or ROM 2230, which are also examples of computer-readable media, and executed by the CPU 2212. Information processing described in these programs is read by the computer 2200, and brings about cooperation between the programs and the various types of hardware resources described above. An apparatus or method may be configured by realizing information manipulation or processing in accordance with the use of the computer 2200.

[0127] For example, when communication is performed between the computer 2200 and an external device, the CPU 2212 may execute a communication program loaded into the RAM 2214 and instruct the communication interface 2222 to perform communication processing based on the processing described in the communication program. Under the control of the CPU 2212, the communication interface 2222 reads transmission data stored in a transmission buffer processing area provided in the RAM 2214, the hard disk drive 2224, the DVD-ROM 2201, or a recording medium such as an IC card, and transmits the read transmission data to the network, or writes reception data received from the network to a reception buffer processing area or the like provided on the recording medium.

[0128] The CPU 2212 may cause all or a necessary portion of a file or database stored on an external recording medium such as the hard disk drive 2224, the DVD-ROM drive 2226 (DVD-ROM 2201), an IC card, etc. to be read into the RAM 2214, and may perform various types of processing on the data on the RAM 2214. The CPU 2212 then writes back the processed data to the external recording medium.

[0129] Various types of information, such as various types of programs, data, tables, and databases, may be stored on the recording medium and may undergo information processing. The CPU 2212 may perform various types of processing on data read from the RAM 2214, including various types of operations, information processing, conditional judgment, conditional branching, unconditional branching, information search / replacement, etc., as described throughout this disclosure and specified by the instruction sequences of the programs, and write the results back to the RAM 2214. The CPU 2212 may also search for information in a file, database, etc. on the recording medium. For example, if multiple entries each having an attribute value of a first attribute associated with an attribute value of a second attribute are stored on the recording medium, the CPU 2212 may search for an entry that matches a condition specified by the attribute value of the first attribute from among the multiple entries, read the attribute value of the second attribute stored in the entry, and thereby obtain the attribute value of the second attribute associated with the first attribute that satisfies a predetermined condition.

[0130] The above-described programs or software modules may be stored in a computer-readable medium on or near the computer 2200. A recording medium such as a hard disk or RAM provided in a server system connected to a dedicated communication network or the Internet can also be used as a computer-readable medium, thereby providing the programs to the computer 2200 via the network.

[0131] Although the present invention has been described above using embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It will be apparent to those skilled in the art that various modifications and improvements can be made to the above embodiments. It is clear from the claims that such modifications and improvements can also be included within the technical scope of the present invention.

[0132] It should be noted that the execution order of each process, such as operations, procedures, steps, and stages, in the devices, systems, programs, and methods shown in the claims, specifications, and drawings is not specifically stated as "before" or "prior to," and that any order may be used unless the output of a previous process is used in a subsequent process. Even if the operational flow in the claims, specifications, and drawings is described using "first," "next," etc. for convenience, this does not mean that the process must be performed in that order. The expression "A and / or B" may mean "A, B, or A and C." The expression "A, B, and / or C" may mean "any one of A, B, and C, or any combination of two or more of these." [Explanation of symbols]

[0133] 100 Prediction System 110 databases 120 Learning Department 130 Model Acquisition Department 140 Data Acquisition Unit 150 Calculation Unit 152 Prior distribution generator 154 Calculation Unit 160 Prediction Department 170 Search Department 200 Manufacturing equipment 210 Mixing section 220 Generation part 2200 Computer 2201 DVD-ROM 2210 host controller 2212 CPU 2214 RAM 2216 Graphics Controller 2218 Display Device 2220 Input / Output Controller 2222 communication interface 2224 hard disk drive 2226 DVD-ROM drive 2230 ROM 2240 I / O chip 2242 keyboard

Claims

1. 1. A prediction system for generating a predictive model that predicts the performance of a composition, comprising: A model acquisition unit acquires a first prediction model that predicts performance values ​​from composition information, which is learned based on a first composition group data containing multiple pairs of composition information and performance values ​​of compositions. a data acquisition unit that acquires second composition group data including a plurality of pairs of composition information and performance values ​​of compositions different from the first composition group data; a calculation unit that calculates parameters of a second prediction model based on the first prediction model and the second composition group data; A prediction system equipped with the following features.

2. the calculation unit calculates parameters of the second prediction model by correcting the first prediction model based on the second composition group data. The prediction system according to claim 1.

3. the model acquisition unit acquires first parameters constituting the first prediction model; The calculation unit described above, a prior distribution generator that generates a first probability distribution of the first parameter; A statistical calculation unit calculates the statistical value of a second probability distribution, which is a posterior probability distribution using the first probability distribution as the prior probability and the second composition group data as the observed data, based on the first probability distribution and the second composition group data, as a parameter of the second prediction model. The prediction system of claim 2 , comprising:

4. the prior distribution generation unit changes the degree of transition of the first probability distribution to the second probability distribution by changing the variance of the first probability distribution; The prediction system according to claim 3.

5. The prior distribution generation unit performs cross-validation using the second composition group data to change the degree to which the first probability distribution is transferred to the second probability distribution in order to improve the accuracy of the second prediction model. The prediction system according to claim 4.

6. the statistical value of the second probability distribution is the mean value of the second probability distribution; The prediction system according to claim 3.

7. the statistics calculation unit calculates a mean value of the second probability distribution by performing sampling; The prediction system according to claim 6.

8. the statistical calculation unit performs the sampling by a Markov Chain Monte Carlo method (MCMC). The prediction system of claim 7 .

9. The data acquisition unit acquires a third composition group data set which includes multiple pairs of composition information and performance values ​​for compositions different from the first and second composition group data sets. The statistical calculation unit uses the second probability distribution as a new prior distribution and calculates the statistical value of the third probability distribution, which is the posterior probability distribution of the observed data for the third composition group data, as a parameter of the updated third prediction model. The prediction system according to claim 3.

10. the first prediction model and the second prediction model are regression models; The parameters are regression coefficients. The prediction system according to claim 1.

11. the number of pairs included in the first composition group data is three times or more the number of pairs included in the second composition group data; The prediction system according to claim 1.

12. the data acquisition unit acquires target composition data, which is composition information of a target composition to be predicted; a prediction unit that inputs composition information of the target composition into the second prediction model to predict a performance value of the target composition; The prediction system of claim 1 further comprising:

13. The performance values ​​are within the range of products that can be produced with the composition. The prediction system according to claim 1.

14. The performance value is the minimum size of a product that can be manufactured from the composition. The prediction system of claim 13.

15. the composition is a resin composition, The composition information includes information on polymers, monomers, and other components in the resin composition. The prediction system according to claim 1.

16. The prediction system according to any one of claims 1 to 15, A model acquisition step involves obtaining a first prediction model that predicts performance values ​​from composition information, which is trained based on a first group of composition data containing multiple pairs of composition information and performance values. a data acquisition step of acquiring second composition group data including a plurality of pairs of composition information and performance values ​​of compositions different from the first composition group data; a calculation step of calculating parameters of the second prediction model based on the first prediction model and the second composition group data; A prediction method comprising:

17. The method is executed by a computer, causing the computer to: The prediction system according to any one of claims 1 to 15 is operated as follows: program.

Images