Information processing device, information processing method, and program

Abstract

This information processing device comprises: an acquiring means for acquiring monomer information, which is information relating to a monomer; a generating means for generating sequence group information relating to a plurality of polymers which contain structural units derived from the monomer and in which the sequences of the structural units differ from one other, by referring to the monomer information; and a learning means for performing machine learning, with reference to the sequence group information, of a prediction model that takes information relating to a polymer material containing at least some of the plurality of polymers as an input and that outputs a prediction result relating to the polymer material.

Description

Information processing device, information processing method, and program

[0001] The present disclosure relates to an information processing device, an information processing method, and a program.

[0002] As a technique for making predictions regarding polymeric materials containing polymers, for example, predicting the physical properties of the polymeric materials, there is known a technique for constructing a regression model that predicts the physical properties of the polymeric material based on information about the structural units that constitute the polymer (see, for example, Patent Document 1).

[0003] International Publication No. 2019 / 172280

[0004] The technology described in Patent Document 1 performs predictions regarding polymer materials by assuming that the polymer structure is a uniquely determined model structure. However, polymers contained in actual polymer materials have various structures. For example, in the case of a polymer material containing a copolymer composed of a first monomer and a second monomer, even if the composition ratio of the two types of monomers in the entire polymer material is uniquely determined, the composition ratio and structure of each copolymer molecule will vary.

[0005] The technique described in Patent Document 1 does not take such variations into consideration, and there is room for improvement in terms of prediction accuracy.

[0006] The present disclosure has been made in view of the above problems, and an exemplary purpose thereof is to provide a technique for performing predictions regarding polymer materials with high accuracy.

[0007] An information processing device according to an exemplary aspect of the present disclosure includes an acquisition means for acquiring monomer information, which is information relating to a monomer; a generation means for generating, by referring to the monomer information, sequence group information relating to a plurality of polymers which contain structural units derived from the monomer and in which the sequences of the structural units differ from one another; and a learning means for performing machine learning by referring to the sequence group information to create a prediction model which receives as input information relating to a polymer material containing at least a portion of the plurality of polymers and outputs a prediction result relating to the polymer material.

[0008] An information processing device according to an exemplary aspect of the present disclosure includes an acquisition means for acquiring polymer material information related to a polymer material, and a prediction means for executing a prediction regarding the polymer material using a prediction model that receives information related to the polymer material as an input and outputs a prediction result related to the polymer material, the prediction model being machine-learned by referring to sequence group information related to a plurality of polymers contained in the polymer material and having different sequences of structural units.

[0009] An information processing method according to an exemplary aspect of the present disclosure includes: acquiring monomer information, which is information about a monomer; generating, by referring to the monomer information, sequence group information about a plurality of polymers that contain structural units derived from the monomer and in which the sequences of the structural units differ from one another; and performing machine learning on a prediction model, by referring to the sequence group information, that takes as input information about a polymer material that contains at least some of the plurality of polymers and outputs a prediction result about the polymer material.

[0010] An information processing method according to an exemplary aspect of the present disclosure includes acquiring polymer material information about a polymer material, and performing a prediction about the polymer material using a prediction model that takes the information about the polymer material as an input and outputs a prediction result about the polymer material, the prediction model being machine-learned by referring to sequence group information about a plurality of polymers contained in the polymer material and having different sequences of structural units.

[0011] A program according to an exemplary aspect of the present disclosure causes a computer to execute an acquisition process for acquiring monomer information, which is information about monomers; a generation process for generating, by referring to the monomer information, sequence group information about a plurality of polymers that contain structural units derived from the monomers and in which the sequences of the structural units differ from one another; and a learning process for using machine learning to develop a prediction model that takes information about a polymer material that contains at least some of the plurality of polymers as input and outputs a prediction result about the polymer material by referring to the sequence group information.

[0012] A program according to an exemplary aspect of the present disclosure causes a computer to execute an acquisition process for acquiring polymer material information about a polymer material, and a prediction process for making predictions about the polymer material using a prediction model that takes information about the polymer material as input and outputs a prediction result about the polymer material, the prediction model being machine-learned by referring to sequence group information about a plurality of polymers contained in the polymer material and having different sequences of structural units.

[0013] According to an exemplary aspect of the present disclosure, an exemplary effect can be achieved in that a technology for performing predictions regarding polymer materials with high accuracy can be provided.

[0014] FIG. 1 is a block diagram showing a configuration of an information processing device according to the present disclosure. FIG. 2 is a flow diagram showing a flow of an information processing method according to the present disclosure. FIG. 3 is a block diagram showing a configuration of an information processing device according to the present disclosure. FIG. 4 is a flow diagram showing a flow of an information processing method according to the present disclosure. FIG. 5 is a block diagram showing a configuration of an information processing device according to the present disclosure. FIG. 6 is a diagram for explaining processing by an information processing device according to the present disclosure. FIG. 7 is a diagram for explaining a display example by an information processing device according to the present disclosure. FIG. 8 is a block diagram showing a configuration of a computer functioning as an information processing device according to the present disclosure.

[0015] The following are examples of embodiments of the present invention. However, the present invention is not limited to the exemplary embodiments shown below, and various modifications are possible within the scope of the claims. For example, embodiments obtained by appropriately combining the technologies (part or all of the products or methods) employed in the exemplary embodiments shown below may also be included in the scope of the present invention. Furthermore, embodiments obtained by appropriately omitting some of the technologies employed in the exemplary embodiments shown below may also be included in the scope of the present invention. Furthermore, the effects mentioned in the exemplary embodiments shown below are examples of effects expected in the exemplary embodiments, and do not define the scope of the present invention. In other words, embodiments that do not exhibit the effects mentioned in the exemplary embodiments shown below may also be included in the scope of the present invention.

[0016] [First Exemplary Embodiment] A first exemplary embodiment, which is an example of an embodiment of the present invention, will be described in detail with reference to the drawings. This exemplary embodiment is a basic form for each of the exemplary embodiments described below. Note that the scope of application of each technique employed in this exemplary embodiment is not limited to this exemplary embodiment. That is, each technique employed in this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical obstacles arise. Furthermore, each technique shown in the drawings referenced to explain this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical obstacles arise.

[0017] (Configuration of information processing device 1) The configuration of the information processing device 1 according to this exemplary embodiment will be described with reference to Fig. 1. Fig. 1 is a block diagram showing the configuration of the information processing device 1. As shown in Fig. 1, the information processing device 1 includes an acquisition unit 11, a generation unit 12, and a learning unit 13.

[0018] (Acquisition Unit 11) The acquisition unit 11 acquires monomer information, which is information related to a monomer. Here, the monomer information is, for example, information indicating the molecular structure of a monomer and may be expressed in the form of 3D data, but this configuration does not limit the present exemplary embodiment. For example, the monomer information is information determined according to the molecular structure of the monomer and may include information such as the chemical structural formula of the monomer, the chemical composition of the monomer, the molecular weight of the monomer, functional groups contained in the monomer, the electron density distribution in the molecular structure of the monomer, and structural units derived from the monomer, but this does not limit the present exemplary embodiment.

[0019] (Generation Unit 12) The generation unit 12 generates sequence group information for multiple polymers containing structural units derived from monomers and having different structural unit arrangements, with reference to the monomer information. Here, the generation unit 12 can, for example, be configured as follows: Determine structural units derived from the monomer that constitute the polymer, with reference to the molecular structure of the monomer indicated in the monomer information; Determine possible structural unit arrangements for the polymer structure with reference to the determined structural units; and Generate information indicating the possible structural unit arrangements as sequence group information. Polymers containing structural units derived from monomers may vary in various factors, such as the degree of polymerization of the polymer, the order of structural units, and the number of branches in the polymer. The arrangement of the structural units in the polymer will vary depending on these factors. Therefore, the possible structural unit arrangements form a sequence group, and the group includes multiple variations in the structural unit arrangements that differ from one another. Each of the included variations corresponds to a polymer with a uniquely defined structure. In other words, the information indicating the possible structural unit arrangements is information about multiple polymers that are different from one another. In other words, the process executed by the generating unit 12 can be expressed as data expansion related to the arrangement of structural units.

[0020] An example of a polymer with a unique structure is a linear polymer with zero branches, but is not limited to this and may be a non-linear polymer. An example of a non-linear polymer may be a branched polymer, a cyclic polymer, or a cross-linked polymer. Examples of branched polymers include, but are not limited to, graft polymers, comb polymers, star polymers, and dendritic polymers. Examples of cyclic polymers include, but are not limited to, polyrotaxanes. Examples of cross-linked polymers include, but are not limited to, network polymers.

[0021] For example, the generation unit 12 may refer to the structural unit sequences and monomer information to further determine information such as the chemical composition of each of the plurality of polymers having different sequences, the molecular weight of the polymer, the functional groups contained in the polymer, and the electron density distribution in the polymer, and include the information in the sequence group information. That is, for example, the sequence group information may include information such as the structural unit sequence, chemical composition, molecular weight, functional groups contained in the polymer, and the electron density in the polymer of each of the plurality of polymers having different sequences, but this does not limit the present exemplary embodiment.

[0022] For example, the generating unit 12 may refer to a predetermined upper limit value of the degree of polymerization and determine an arrangement of structural units that can fall within a range of degrees of polymerization equal to or less than the upper limit value.

[0023] As a specific example that does not limit the present exemplary embodiment, a process executed by the generation unit 12 will be described in a case where the monomer information is information about two or more monomers, and indicates ethylene as a first monomer and propylene as a second monomer. ２ =CH ２ With reference to the above, the structural unit derived from ethylene is [—CH ２ -CH ２ The generating unit 12 determines that the molecular structure of propylene is CH ２ =CH-CH ３ In consideration of the bond direction, the structural unit derived from propylene is [—CH ２ -CH(CH ３ )-] or [-CH(CH ３ )-CH ２ - The structural unit derived from ethylene is represented as "A", and the structural unit derived from propylene is represented as "B" or "B" depending on the direction of the bond. ＊ ", the generator 12 determines possible sequences of structural units as follows: "AA", "AB", "AB ＊ ”, “B-A”, “B ＊ -A”, “BB”, “BB” ＊ "," "B ＊ -B," "B ＊ -B ＊”, “A-A-A”, “A-A-B”, “A-A-B ＊ ", ... Here, the generation unit 12 generates, as an example, a set of sequences that have structural symmetry with each other, for example, "A-B" and "B ＊ -A" may be treated as the same sequence. The generating unit 12 generates information indicating the sequence of the determined structural unit as sequence group information.

[0024] As another specific example, the monomer information may be information about a single monomer. In this case, since the structural unit derived from the monomer is also single, the generation unit 12 generates sequence group information about multiple polymers that differ in factors such as the degree of polymerization of the polymer and the number of branches in the polymer, without taking into consideration the alignment order of the structural units.

[0025] (Learning Unit 13) The learning unit 13 receives information about a polymer material containing at least some of the multiple polymers as input, and performs machine learning on a prediction model that outputs a prediction result about the polymer material, by referring to the sequence group information. Here, the learning unit 13 can, as an example, be configured to: perform mapping in a latent space by referring to the sequences of the structural units of each of the multiple polymers indicated by the sequence group information; and update one or more parameters included in the prediction model by referring to the feature quantities in the mapped latent space.

[0026] (Effects of Information Processing Device 1) As described above, the information processing device 1 employs the following configuration: acquires monomer information, which is information about monomers; generates sequence group information about multiple polymers containing structural units derived from the monomers and in which the structural units have different sequences, by referring to the monomer information; and performs machine learning on a prediction model that inputs information about a polymer material containing at least some of the multiple polymers and outputs prediction results about the polymer material, by referring to the sequence group information. According to the information processing device 1, the generation unit 12 performs data expansion on the sequences of the structural units and generates sequence group information about multiple polymers whose sequences are different from each other. The sequence group information represents variation in the composition ratio and structure of polymers and can represent variation in actual polymer materials. Therefore, the information processing device 1, which performs machine learning on a prediction model using the sequence group information, can generate a prediction model that makes predictions about polymer materials with high accuracy.

[0027] (Additional Notes Regarding the Information Processing Device 1) For example, the generation unit 12 may generate sequence group information by determining, from the molecular structure of a monomer, a portion that constitutes a main chain in a polymer and a portion that constitutes a side chain in the polymer. In this case, the generation unit 12 may perform the following processes: - by referring to the monomer information, determine, from the molecular structure of the monomer, a portion that constitutes a main chain in a polymer and a portion that constitutes a side chain in the polymer; - by referring to the portion that constitutes the main chain, determine possible main chain structures in the polymer; and - by referring to the portion that constitutes the side chain, determine combined structures of the main chain and the side chain, in which possible side chains are bonded to the possible main chain structures.

[0028] As a specific example that does not limit the present exemplary embodiment, when the monomer information is information about two or more monomers, and indicates ethylene as a first monomer and propylene as a second monomer, the generation unit 12 may execute the following process. ２ =CH ２ With reference to the above, the moiety constituting the main chain derived from ethylene is [—CH ２ -CH２ -] and determines that there is no part that constitutes a side chain. ２ =CH-CH ３ With reference to the above, the portion constituting the main chain derived from propylene is [—CH ２ -CH ２ -], and the moiety constituting the side chain is -CH ３ The method determines whether the polymer is a polymer with a possible main chain structure. The method determines whether the polymer has a possible main chain structure and a possible side chain bonded to the possible main chain structure by referring to the portion constituting the main chain. In this specific example, the portion constituting the main chain derived from ethylene and the portion constituting the main chain derived from propylene have the same structure. Therefore, the order of arrangement of the structural units derived from ethylene and propylene in the polymer does not affect the structure of the main chain of the polymer, and therefore, there is no need to consider the order of arrangement. Therefore, the processing of this specific example is advantageous in terms of the amount of computational processing. This processing is suitable for predictions of polymer materials including copolymers containing two or more types of monomers whose main chains have the same structure, such as phosphorylated carboxymethyl cellulose, which consistently has α-glucose as the main chain and has phosphate groups, carboxymethyl groups, and hydroxy groups as side chains at various bonding positions.

[0029] For example, the acquisition unit 11 may acquire, as the monomer information, information separately indicating the portion of the molecular structure of the monomer that constitutes the main chain in the polymer and the portion that constitutes the side chain in the polymer. In this case, the generation unit 12 may execute the remaining processes described above without determining the portion that constitutes the main chain in the polymer and the portion that constitutes the side chain in the polymer.

[0030] (Flow of Information Processing Method S1) Next, the flow of information processing method S1 according to this exemplary embodiment will be described with reference to FIG. 2. FIG. 2 is a flow chart showing the flow of information processing method S1. As shown in FIG. 2, information processing method S1 includes a step (process) S11 of acquiring monomer information, a step (process) S12 of generating sequence group information, and a step (process) S13 of performing machine learning on a prediction model. As an example, information processing method S1 is executed by an information processing device 1, but this does not limit this exemplary embodiment.

[0031] (Step S11) In step S11, the acquisition unit 11 acquires monomer information, which is information about monomers. The monomer information has been described above, so the description will not be repeated here.

[0032] (Step S12) In step S12, the generation unit 12 refers to the monomer information to generate sequence group information for a plurality of polymers that contain structural units derived from monomers and have different structural unit sequences. The processing by the generation unit 12 has been described above, and therefore will not be described again here.

[0033] (Step S13) In step S13, the learning unit 13 receives information about a polymer material containing at least some of the multiple polymers as input, and performs machine learning on a prediction model that outputs a prediction result about the polymer material by referring to the sequence group information. The processing by the learning unit 13 has been described above, and therefore will not be described again here.

[0034] (Effects of Information Processing Method S1) As described above, the information processing method S1 employs the following configurations: acquire monomer information, which is information about monomers; generate sequence group information about a plurality of polymers containing structural units derived from the monomers and in which the structural units have different sequences, by referring to the monomer information; and perform machine learning on a prediction model that uses information about a polymer material containing at least some of the plurality of polymers as input and outputs prediction results about the polymer material, by referring to the sequence group information. According to the information processing method S1, data expansion is performed on the sequences of the structural units, and sequence group information about a plurality of polymers having different sequences is generated. The sequence group information is information that represents variations in the composition ratio and structure of polymers, and can represent variations in actual polymer materials. Therefore, according to the information processing method S1, which performs machine learning on a prediction model using the sequence group information, it is possible to generate a prediction model that makes predictions about polymer materials with high accuracy.

[0035] (Configuration of information processing device 2) Next, the configuration of the information processing device 2 according to this exemplary embodiment will be described with reference to Fig. 3. Fig. 3 is a block diagram showing the configuration of the information processing device 2. As shown in Fig. 3, the information processing device 2 includes an acquisition unit 21 and a prediction unit 22.

[0036] (Acquisition Unit 21) The acquisition unit 21 acquires polymer material information related to a polymer material. Here, the polymer material information is, for example, information indicating the characteristics of a polymer material containing a polymer. The characteristics may be, for example, characteristics determined based on information about the polymers that constitute the polymer material. For example, the characteristics may be: - the type and composition ratio of the monomers constituting the polymer material, and the composition ratio of the monomers constituting the polymer material, which is determined by the blending ratio of the respective polymers; - the average molecular weight of each polymer contained in the polymer material, and the average molecular weight of the polymer material, which is determined by the blending ratio of the respective polymers, etc., but this does not limit the present exemplary embodiment.

[0037] (Prediction unit 22) The prediction unit 22 is a prediction model that receives information about a polymer material as input and outputs a prediction result about the polymer material, and performs predictions about the polymer material using a prediction model that has been machine-learned by referring to sequence group information about a plurality of polymers that are contained in the polymer material and have different sequences of structural units. As an example, the prediction model may be a prediction model that has been machine-learned by the above-mentioned information processing device 1. As an example, the prediction unit 22 inputs polymer material information into the prediction model and performs predictions about the polymer material.

[0038] The target of prediction regarding a polymer material may be arbitrarily selected from the properties of the polymer material, and may be, for example, at least one of the physical properties and chemical properties of the polymer material. For example, the predicted physical properties may be those commonly used in the technical field of polymer materials, such as the melting point, viscosity, elasticity, and hardness of the polymer material. For example, the predicted chemical properties may be chemical reactivity, pH, and the amount of volatile organic compounds (VOCs) emitted. The prediction may be a prediction of a value, for example, a prediction of a physical property value, or may be clustering, for example, allocating polymer materials having similar physical properties to a group.

[0039] (Effects of Information Processing Device 2) As described above, the information processing device 2 employs the following configuration: - acquires polymer material information related to a polymer material; - performs predictions on the polymer material using a prediction model that takes the information on the polymer material as input and outputs prediction results on the polymer material, the prediction model being machine-learned with reference to sequence group information on a plurality of polymers contained in the polymer material and having different sequences of structural units. In this way, the information processing device 2 generates prediction results using a prediction model generated by machine learning with reference to sequence group information on a plurality of polymers having different sequences of structural units, thereby enabling predictions on the polymer material to be made with high accuracy.

[0040] (Flow of Information Processing Method S2) Next, the flow of information processing method S2 according to this exemplary embodiment will be described with reference to Fig. 4. Fig. 4 is a flow diagram showing the flow of information processing method S2. As shown in Fig. 4, information processing method S2 includes step (process) S21 of acquiring polymer material information and step (process) S22 of executing prediction regarding the polymer material. As an example, information processing method S2 is executed by information processing device 2, but this is not intended to limit this exemplary embodiment.

[0041] (Step S21) In step S21, the acquisition unit 21 acquires polymer material information related to the polymer material. The polymer material information has been described above, and therefore will not be described again here.

[0042] (Step S22) In step S22, the prediction unit 22 executes a prediction for the polymer material using a prediction model that receives information about the polymer material as input and outputs a prediction result for the polymer material, the prediction model being machine-learned by referring to sequence group information for a plurality of polymers that are contained in the polymer material and have different sequences of structural units. The polymer material information has been described above, and therefore will not be described again here.

[0043] (Effects of Information Processing Method S2) As described above, information processing method S2 employs the following configuration: - acquiring polymer material information related to a polymer material; - making a prediction related to the polymer material using a prediction model that takes the information related to the polymer material as input and outputs a prediction result related to the polymer material, the prediction model having been machine-learned with reference to sequence group information related to a plurality of polymers contained in the polymer material and having different sequences of structural units. In this way, information processing method S2 generates a prediction result using a prediction model generated by machine learning with reference to sequence group information related to a plurality of polymers having different sequences of structural units, thereby enabling predictions related to the polymer material to be made with high accuracy.

[0044] Second Exemplary Embodiment A second exemplary embodiment, which is an example of an embodiment of the present invention, will be described in detail with reference to the drawings. Components having the same functions as those described in the above exemplary embodiment will be denoted by the same reference numerals, and their description will be omitted as appropriate. The scope of application of each technique employed in this exemplary embodiment is not limited to this exemplary embodiment. That is, each technique employed in this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical hindrance occurs. Furthermore, each technique shown in each drawing referenced to describe this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical hindrance occurs.

[0045] (Configuration of Information Processing Device 1A) The configuration of the information processing device 1A according to this exemplary embodiment will be described with reference to Fig. 5. Fig. 5 is a block diagram showing the configuration of the information processing device 1A. As shown in Fig. 5, the information processing device 1A includes a control unit 10A, a storage unit 20A, a communication unit 30A, and an input / output unit 40A.

[0046] (Communication unit 30A) The communication unit 30A communicates with devices external to the information processing device 1A. As an example, the communication unit 30A communicates with one or more terminal devices located outside the information processing device 1A. The communication unit 30A transmits data supplied from the control unit 10A to the terminal devices, and supplies data received from the terminal devices to the control unit 10A.

[0047] (Input / Output Unit 40A) The input / output unit 40A is configured to include at least one of input / output devices such as a keyboard, mouse, display, printer, and touch panel. Alternatively, the input / output unit 40A may be configured to have input / output devices such as a keyboard, mouse, display, printer, and touch panel connected to it. In this configuration, the input / output unit 40A accepts various types of information input to the information processing device 1A from the connected input devices. Furthermore, the input / output unit 40A outputs various types of information to the connected output devices under the control of the control unit 10A. An example of the input / output unit 40A is an interface such as a USB (Universal Serial Bus).

[0048] (Storage Unit 20A) The storage unit 20A stores various types of data referenced by the control unit 10A and various types of data generated by the control unit 10A. As an example, the storage unit 20A stores the following: Monomer information MI, Polymer physical property information PPI, Polymer material information PMI, Sequence group information SGI, and Prediction model PM.

[0049] The monomer information MI is information acquired by the acquisition unit 11 (21) described below and referenced by the generation unit 12. The polymer physical property information PPI is information acquired by the acquisition unit 11 (21) described below and referenced by the learning unit 13. The polymer material information PMI is information acquired by the acquisition unit 11 (21) described below and referenced by the generation unit 12 or the learning unit 13. Specific examples of the monomer information MI, polymer physical property information PPI, and polymer material information PMI will be described later.

[0050] The sequence group information SGI is information generated by the generating unit 12 (described later) and referenced by the learning unit 13. Specific examples of the sequence group information SGI will be described later.

[0051] The prediction model PM is a prediction model that is the target of the learning process executed by the learning unit 13. Here, the prediction model PM is, for example, a model that makes predictions by taking information about a polymer material as input and outputting a prediction result about the polymer material. For example, the prediction model PM includes one or more parameters that the prediction model PM includes.

[0052] Here, the prediction model PM is information representing the relationship between explanatory variables and a target variable. The prediction model PM is, for example, a component for estimating the outcome of an estimation target by calculating a target variable based on the explanatory variables.

[0053] The prediction model PM may be represented by, for example, a function c that maps an input x to a correct answer y. The prediction model PM may estimate a numerical value of an estimation target, or may estimate a label of an estimation target. The prediction model PM may output a variable that describes the probability distribution of a target variable. The prediction model PM may also be referred to as a "learning model," "analysis model," "AI model," "trained model," "inference model," or "prediction formula."

[0054] The explanatory variables are variables used as inputs in the prediction model PM. The explanatory variables may also be referred to as "features" or "features."

[0055] Furthermore, the learning algorithm for generating the prediction model PM is not particularly limited and may be an existing learning algorithm, such as a random forest, a support vector machine, a naive Bayesian model, a neural network, a piecewise linear model using factorized asymptotic Bayesian inference (FAB), or a neural network.

[0056] (Control Unit 10A) As shown in FIG. 5 , the control unit 10A includes the acquisition unit 11, generation unit 12, learning unit 13, and prediction unit 22 described in the first exemplary embodiment. Here, the acquisition unit 11 can be expressed as having the same configuration as the acquisition unit 21 described in the first exemplary embodiment, and therefore the acquisition unit 11 may also be referred to as the acquisition unit 11 (21). The processing performed by each unit included in the control unit 10A is classified into a learning phase for machine learning the prediction model PM and a prediction phase for making predictions using the prediction model PM. The learning phase is mainly involved with the acquisition unit 11 (21), the generation unit 12, and the learning unit 13, while the prediction phase is mainly involved with the acquisition unit 11 (21) and the prediction unit 22.

[0057] (Acquisition Unit 11 (21)) In the learning phase, the acquisition unit 11 (21) acquires monomer information, which is information about monomers. Here, the monomer information MI is, for example, information indicating the molecular structure of a monomer. For example, the monomer information MI is information determined according to the molecular structure of a monomer, and may include information such as the chemical structural formula of the monomer, the chemical composition of the monomer, the molecular weight of the monomer, functional groups contained in the monomer, the electron density distribution in the molecular structure of the monomer, and structural units derived from the monomer, but this does not limit the present exemplary embodiment. Furthermore, the monomer information MI may be, for example, information about two or more monomers.

[0058] Furthermore, the acquisition unit 11 (21) further acquires polymer physical property information PPI during the learning phase. Here, the polymer physical property information PPI is information about a polymer containing structural units derived from monomers and is information indicating the physical properties of the polymer. Here, the polymer physical property information may be information indicating the arrangement of structural units in a polymer in association with the physical properties of the polymer.

[0059] The polymer physical property information PPI may include, for example, information such as the melting point, viscosity, elasticity, and hardness of the polymer, but this does not limit the present exemplary embodiment. The polymer physical property information PPI may be a correct label related to the physical properties of the polymer, and the correct label may indicate an experimentally measured physical property or a theoretically predicted physical property. The physical property indicated by the polymer physical property information PPI may be a physical property measured or predicted for a polymer material made of a polymer with a uniquely defined structure, or may be a physical property measured or predicted for a polymer material containing a polymer with variations in composition and structure. In the latter case, the polymer physical property information may indicate the physical property of the polymer in association with the variations.

[0060] Furthermore, the acquisition unit 11 (21) further acquires polymer material information PMI during the learning phase. Here, the polymer material information PMI is, for example, information about a polymer material. For example, the polymer material information PMI is information indicating the characteristics of a polymer material containing a polymer. For example, the characteristics may be determined based on information about the polymers that constitute the polymer material. For example, the characteristics may be: the types of monomers that constitute the polymer material; the average molecular weight of the polymer material, which is determined by the molecular weight of each polymer contained in the polymer material and the blending ratio of each polymer; and the composition ratio of the monomers that constitute the polymer material, which is determined by the composition ratio of each polymer. However, this does not limit the present exemplary embodiment.

[0061] The acquisition unit 11 (21) acquires polymer material information PMI in the prediction phase. Here, the polymer material information PMI is, for example, information about the polymer material. Specific examples of the polymer material information PMI have been described above, so the description will not be repeated.

[0062] (Generation Unit 12) The generation unit 12 generates sequence group information SGI for multiple polymers containing structural units derived from monomers and having different sequences of the structural units, with reference to the monomer information MI. Here, the generation unit 12 generates the sequence group information SGI with reference to the molecular structures of at least the monomers in the monomer information MI. The generation unit 12 also generates sequence group information for copolymers containing structural units derived from each of the two or more monomers indicated by the monomer information MI.

[0063] For example, the generation unit 12 may be configured to: determine two or more structural units that constitute a polymer and are derived from each of the two or more monomers by referring to the molecular structures of two or more monomers indicated by the monomer information MI; determine possible structural unit sequences for the structure of a copolymer containing the two or more structural units; and generate information indicating the possible structural unit sequences as sequence group information SGI. For example, the sequence group information SGI may indicate the sequence of the structural units of each of multiple polymers whose sequences are different from each other. For example, the generation unit 12 may further determine information such as the chemical composition of a polymer having each sequence, the molecular weight of the polymer, and the electron density distribution of the polymer by referring to the structural unit sequences and the monomer information, and generate the information as sequence group information SGI.

[0064] The sequence group information SGI, for example, is information indicating the abundance ratio of each of a plurality of polymers. In this case, the generation unit 12 determines the abundance ratio of each polymer by referring to the reference information, and generates information including the abundance ratio of each polymer as the sequence group information SGI. Here, the reference information is information acquired by the acquisition unit 11, and is information indicating the composition ratio of the monomers constituting the polymer and the bonding reactivity between the monomers. The reference information may be determined based on a statistical distribution, or may be determined by a user according to a predetermined purpose. Here, the statistical distribution is, for example, a probability distribution determined according to: the amount of monomer used in producing the polymer; the affinity between the monomers determined by reaction kinetics and structural stability; and, for two or more monomers having the same main chain structure but different side chain structures, the abundance ratio of each monomer determined according to the bonding ability of the side chain to the main chain.

[0065] The generation unit 12 outputs the sequence group information SGI. Here, the generation unit 12 may output the sequence group information SGI to the storage unit 20A and store the sequence group information SGI in the storage unit 20A, or may output the sequence group information SGI to the input / output unit 40A and output or display the sequence group information SGI on the input / output unit 40A. Examples of displays by the input / output unit 40A will be described later with reference to different drawings.

[0066] The generation unit 12 may further refer to the polymer material information PMI. In this case, the generation unit 12 generates the sequence group information SGI so that each of the multiple polymers has properties that match the properties of the polymer material indicated by the polymer material information PMI. As an example, if the polymer material information PMI indicates the molecular weight of a polymer, the generation unit 12 generates the sequence group information SGI so that the sequence group information SGI includes only sequences of structural units of polymers having the same molecular weight as the molecular weight of the polymer.

[0067] (Learning Unit 13) The learning unit 13 receives information about a polymer material containing at least some of the multiple polymers as input, and performs machine learning on a prediction model PM that outputs a prediction result about the polymer material, by referring to the sequence group information SGI. Here, the learning unit 13 can, as an example, be configured to: perform mapping in a latent space by referring to the sequences of the structural units of each of the multiple polymers indicated by the sequence group information; and update one or more parameters included in the prediction model by referring to the feature quantities in the mapped latent space.

[0068] The learning unit 13 may train the prediction model PM by further referring to the polymer property information PPI. Here, the learning unit 13 refers to the polymer property information PPI as a correct label of the training data. As an example, the learning unit 13 may be configured to: search for a sequence that matches the sequence of the structural units contained in the polymer property information PPI from among the group of structural unit sequences indicated by the sequence group information SGI; assign a correct label related to the physical properties of the polymer contained in the polymer property information PPI, for example, the physical property value of a polymer having the structural unit sequence, to the structural unit sequence extracted by the search; and perform semi-supervised learning on the prediction model PM using both sequences in the sequence group information SGI that have been assigned a correct label and sequences that have not been assigned a correct label. Alternatively, the learning unit 13 may perform supervised learning on the prediction model PM using only sequences in the sequence group information SGI that have been assigned a correct label.

[0069] The learning unit 13 may train the prediction model PM by referring to at least the sequences and abundance ratios of the structural units in the sequence group information SGI. Here, the learning unit 13 refers to the abundance ratio of the polymer corresponding to each sequence of the structural units and assigns importance weighting in machine learning to each sequence. For example, the learning unit 13 assigns a greater weight to each sequence as the abundance ratio increases.

[0070] The learning unit 13 may perform machine learning on the prediction model PM by further referring to the polymer material information PMI. As an example, when the polymer material information PMI indicates the molecular weight of a polymer, the learning unit 13 may extract, from the sequence group information SGI, the sequence of a structural unit of a polymer having the same molecular weight as the molecular weight of the polymer, and perform machine learning on the prediction model PM using the extracted sequence.

[0071] (Prediction unit 22) The prediction unit 22 is a prediction model that receives information about a polymer material as input and outputs a prediction result about the polymer material, and performs predictions about the polymer material using a prediction model PM that has been machine-learned by referring to sequence group information about a plurality of polymers that are contained in the polymer material and have different sequences of structural units. As an example, the prediction model may be the prediction model PM that has been machine-learned by the learning unit 13 described above. As an example, the prediction unit 22 inputs the polymer material information PMI acquired by the acquisition unit 11 (21) in the prediction phase into the prediction model PM to perform predictions about the polymer material.

[0072] (Specific Example (1) of Processing in the Learning Phase) The flow of processing by information processing device 1A in the learning phase will be described below with reference to Fig. 6. Fig. 6 is a diagram for explaining a specific example of processing by information processing device 1A.

[0073] In the specific example shown in Figure 6, the acquisition unit 11 (21) acquires monomer information MI, polymer material information PMI, and polymer physical property information PPI. As shown in Figure 6, the monomer information MI indicates information about monomer A and monomer B, specifically, "molecular structure of monomer A" and "molecular weight of monomer A: 130", as well as "molecular structure of monomer B" and "molecular weight of monomer B: 70". Furthermore, the polymer material information PMI indicates information about a polymer material including a polymer containing structural units derived from monomer A and monomer B, specifically, "average molecular weight: 460" and "composition ratio of monomer A to monomer B: 3:1" as properties of the polymer material. The polymer physical property information PPI indicates the physical properties of a polymer having the structural unit sequences "B-A" and "A-A-B-A", specifically indicating "melting point of polymer B-A: 30°C" and "viscosity of polymer B-A: 1.0", as well as "melting point of polymer A-A-B-A: 60°C" and "viscosity of polymer B-A: 1.5".

[0074] As shown in FIG. 6 , in this specific example, the generation unit 12 generates sequence group information SGI with reference to monomer information MI. The sequence group information SGI indicates the sequence of structural units in a polymer containing structural units derived from monomer A and monomer B, as well as the molecular weight and composition ratio determined from the structural units. As an example, for a polymer having a structural unit sequence "A-B," the sequence group information SGI indicates "molecular weight: 200" and "composition ratio of monomer A to monomer B: 1:1." The generation unit 12 also determines the abundance ratio of each polymer with reference to the reference information and includes the abundance ratio in the sequence group information SGI. As an example, for a polymer having a structural unit sequence "A-B," the sequence group information SGI indicates "abundance ratio: 2."

[0075] As shown in FIG. 6 , in this specific example, the learning unit 13 performs machine learning on the prediction model PM by referring to the sequence group information SGI, polymer material information PMI, and polymer material information PPI. The learning unit 13 assigns correct labels of the physical properties (melting point and viscosity) indicated by the polymer physical property information PPI to the polymers "B-A" and "A-A-B-A" indicated by the sequence group information SGI, whose structural unit sequences match those of the polymer indicated by the polymer physical property information PPI. The learning unit 13 extracts polymers such as "A-A-A-B" and "A-A-B-A" indicated by the sequence group information SGI, whose properties match those of the information indicated by the polymer material information PMI, and subjects only the extracted polymers to machine learning. Therefore, in this specific example, the process performed by the learning unit 13 is semi-supervised learning, in which, among the polymers "A-A-A-B" and "A-A-B-A" and the like that are subjected to machine learning, only the polymer "A-A-B-A" is labeled as the correct answer. Furthermore, the learning unit 13 refers to the abundance ratios of the polymers "A-A-A-B" and "A-A-B-A" and the like that are subjected to machine learning, and performs importance weighting in the machine learning according to the abundance ratios.

[0076] (Specific Example (2) of Processing in the Learning Phase) Hereinafter, with reference to Fig. 7, a processing flow by information processing device 1A in the learning phase, which differs from the flow shown in Fig. 6, will be described. Fig. 7 is a diagram for explaining a specific example of processing by information processing device 1A.

[0077] 7, the acquisition unit 11 (21) acquires monomer information MI, polymer material information PMI, and polymer physical property information PPI. The content of each piece of information is the same as in the example shown in FIG. 6, and therefore the description thereof will not be repeated.

[0078] As shown in FIG. 7 , in this specific example, the generation unit 12 generates sequence group information SGI with reference to the monomer information MI and polymer material information PMI. Here, the generation unit 12 determines the sequences of structural units derived from each of monomers A and B so that the properties match the information indicated by the polymer material information PMI, and includes the sequences in the sequence group information SGI. Specifically, the generation unit 12 determines polymers such as "A-A-A-B" and "A-A-B-A" having an "average molecular weight: 460" and a "composition ratio of monomer A to monomer B: 3:1." Furthermore, the generation unit 12 determines the abundance ratio of each polymer with reference to the reference information, and includes the abundance ratio in the sequence group information SGI.

[0079] As shown in FIG. 7 , in this specific example, the learning unit 13 performs machine learning on the prediction model PM by referring to the sequence group information SGI and the polymer material information PPI. The learning unit 13 assigns correct labels for the physical properties (melting point and viscosity) indicated by the polymer physical property information PPI to the polymer "A-A-B-A" indicated by the sequence group information SGI, whose structural unit sequence matches that of the polymer indicated by the polymer physical property information PPI. The learning unit 13 subjects the entire sequence group information SGI to machine learning. Therefore, in this specific example, the process performed by the learning unit 13 is semi-supervised learning, in which only the polymer "A-A-B-A" is assigned a correct label among the sequence group information SGI subjected to machine learning. Furthermore, the learning unit 13 performs machine learning by assigning importance weights according to the abundance ratios of the polymers "A-A-A-B" and "A-A-B-A" subjected to machine learning.

[0080] (Display Example) Fig. 8 shows a display example of the input / output unit 40A included in the information processing device 1A. As shown in Fig. 9, the display included in the input / output unit 40A may be configured as follows: in a display region RR1, to display the monomer information MI referenced by the learning unit 13; in a display region RR2, to display the polymer material information PMI referenced by the learning unit 13 in the learning phase or the polymer material information PMI referenced by the prediction unit 22 in the prediction phase; in a display region RR3, to display the polymer physical property information PPI referenced by the learning unit 13 in the learning phase or the prediction result generated by the prediction model PM in the prediction phase; and in a display region RR4, to display the sequence group information SGI generated by the generation unit 12. This configuration allows the user to conveniently check the generated sequence group information SGI.

[0081] Here, the display region RR1 may function as a reception area for the user to input monomer information MI, the display region RR2 may function as a reception area for the user to input polymer material information PMI, and the display region RR3 may function as a reception area for the user to input polymer physical property information PPI.

[0082] (Effects of Information Processing Device 1A) As described above, the information processing device 1A employs the following configuration in the learning phase: the acquisition unit 11 (21) further acquires polymer property information PPI, which is information about a polymer containing structural units derived from a monomer and indicates the physical properties of the polymer; and the learning unit 13 performs machine learning on the prediction model PM by further referencing the polymer property information PPI. According to the information processing device 1A, the learning unit 13 can perform semi-supervised learning or supervised learning using the physical properties of the polymer indicated by the polymer property information PPI as correct labels. Therefore, the information processing device 1A can generate a prediction model that makes predictions about the physical properties of polymer materials with higher accuracy.

[0083] Furthermore, the information processing device 1A employs the following configuration in the learning phase: the sequence group information SGI indicates the abundance ratio of each of the multiple polymers; and the learning unit 13 performs machine learning on the prediction model PM by referring to at least the sequences and abundance ratios of the structural units in the sequence group information SGI. According to the information processing device 1A, the learning unit 13 can weight the importance of each sequence by referring to the abundance ratio of each sequence of the structural units. Therefore, the learning unit 13 can perform machine learning on the prediction model PM that reflects the variation in polymer structure in actual polymer materials. Therefore, according to the information processing device 1A, a prediction model that makes predictions about polymer materials with higher accuracy can be generated.

[0084] Furthermore, the information processing device 1A employs the following configuration during the learning phase: the acquisition unit 11 (21) further acquires polymer material information PMI related to the polymer material; and (1) the learning unit 13 performs machine learning on the prediction model PM by further referencing the polymer material information PMI, or (2) the generation unit 12 generates sequence group information SGI such that each of the multiple polymers has properties that match the properties of the polymer material indicated by the polymer material information PMI. According to the information processing device 1A, in both processes (1) and (2), the learning unit 13 can use only polymers from the sequence group information SGI that have properties that match the properties of the polymer material indicated by the polymer material information PMI for machine learning. Therefore, the learning unit 13 can perform machine learning on the prediction model PM that reflects the properties of the polymer material desired by the user. Therefore, the information processing device 1A can generate a prediction model that performs predictions on polymer materials with higher accuracy.

[0085] Furthermore, the information processing device 1A employs the following configuration in the learning phase: the monomer information MI indicates the molecular structure of a monomer; and the generation unit 12 generates the sequence group information SGI by referring to at least the molecular structure of the monomer in the monomer information MI. According to the information processing device 1A, the generation unit 12 can determine possible structural unit sequences according to the molecular structure of the monomer and generate the sequence group information SGI. Therefore, the generated sequence group information SGI preferably indicates polymers that may be contained in an actual polymer material. Therefore, according to the information processing device 1A, a prediction model that performs predictions regarding polymer materials with higher accuracy can be generated.

[0086] Furthermore, the information processing device 1A employs the following configuration during the learning phase: the monomer information MI is information about two or more monomers; and the generation unit 12 generates sequence group information SGI about a copolymer containing structural units derived from each of the two or more monomers. Generally, in polymer materials containing copolymers, variations in copolymer structure have a significant impact on the properties of the polymer material, such as its physical properties. However, the information processing device 1A can generate a prediction model that can make predictions about polymer materials with higher accuracy, even for polymer materials containing copolymers.

[0087] Furthermore, the information processing device 1A employs the following configuration in the learning phase: the generation unit 12 outputs sequence group information SGI. According to the information processing device 1A, the user can conveniently check the generated sequence group information SGI.

[0088] [Software Implementation Example] Some or all of the functions of the information processing devices 1, 2, 1A (hereinafter also referred to as "each of the above devices") may be implemented by hardware such as an integrated circuit (IC chip), or by software.

[0089] In the latter case, each of the above devices is realized by, for example, a computer that executes instructions of a program, which is software that realizes each function. An example of such a computer (hereinafter referred to as computer C) is shown in Figure 9. Figure 9 is a block diagram showing the hardware configuration of computer C that functions as each of the above devices.

[0090] The computer C includes at least one processor C1 and at least one memory C2. The memory C2 stores a program P for causing the computer C to function as each of the above-mentioned devices. In the computer C, the processor C1 reads and executes the program P from the memory C2, thereby realizing the functions of each of the above-mentioned devices.

[0091] The processor C1 may be, for example, a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processor (DSP), a micro processing unit (MPU), a floating point number processing unit (FPU), a physics processing unit (PPU), a tensor processing unit (TPU), a quantum processor, a microcontroller, or a combination thereof. The memory C2 may be, for example, a flash memory, a hard disk drive (HDD), a solid state drive (SSD), or a combination thereof.

[0092] The computer C may further include a RAM (Random Access Memory) for expanding the program P during execution and for temporarily storing various data. The computer C may also include a communication interface for transmitting and receiving data to and from other devices. The computer C may also include an input / output interface for connecting input / output devices such as a keyboard, a mouse, a display, and a printer.

[0093] The program P can also be recorded on a non-transitory, tangible recording medium M that can be read by the computer C. Such a recording medium M can be, for example, a tape, a disk, a card, a semiconductor memory, or a programmable logic circuit. The computer C can acquire the program P via such a recording medium M. The program P can also be transmitted via a transmission medium. Such a transmission medium can be, for example, a communication network or broadcast waves. The computer C can also acquire the program P via such a transmission medium.

[0094] Furthermore, the functions of each of the devices may be realized by a single processor provided in a single computer, by multiple processors provided in a single computer working in cooperation, or by multiple processors provided in each of multiple computers working in cooperation. Furthermore, the programs for causing each of the devices to realize the functions may be stored in a single memory provided in a single computer, or may be distributed and stored in multiple memories provided in a single computer, or may be distributed and stored in multiple memories provided in each of multiple computers.

[0095] [Appendix A] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0096] (Appendix A1) An information processing device comprising: an acquisition means for acquiring monomer information, which is information about a monomer; a generation means for generating sequence group information about a plurality of polymers containing structural units derived from the monomer, the polymers having different sequences of the structural units, by referring to the monomer information; and a learning means for performing machine learning on a prediction model, by referring to the sequence group information, which receives as input information about a polymer material containing at least a portion of the plurality of polymers and outputs a prediction result about the polymer material.

[0097] (Appendix A2) The information processing device according to Appendix A1, wherein the acquisition means further acquires polymer property information that is information about a polymer containing a structural unit derived from the monomer and indicates physical properties of the polymer, and the learning means performs machine learning on the prediction model by further referring to the polymer property information.

[0098] (Appendix A3) The information processing device according to Appendix A1 or A2, wherein the sequence group information indicates an abundance ratio of each of the plurality of polymers, and the learning means performs machine learning on the prediction model by referring to at least the sequences and the abundance ratios of the structural units in the sequence group information.

[0099] (Appendix A4) The information processing device according to any one of Appendices A1 to A3, wherein the acquisition means further acquires polymer material information relating to a polymer material, and (1) the learning means performs machine learning on the prediction model by further referring to the polymer material information, or (2) the generation means generates the sequence group information so that each of the plurality of polymers has properties that match the properties of the polymer material indicated by the polymer material information.

[0100] (Appendix A5) The information processing device according to any one of Appendices A1 to A4, wherein the monomer information indicates a molecular structure of the monomer, and the generating means generates the sequence group information by referring to at least the molecular structure of the monomer in the monomer information.

[0101] (Appendix A6) The information processing device according to any one of Appendices A1 to A5, wherein the monomer information is information relating to two or more monomers, and the generating means generates the sequence group information relating to a copolymer containing structural units derived from each of the two or more monomers.

[0102] (Appendix A7) The information processing device according to any one of Appendices A1 to A6, wherein the generating means outputs the sequence group information.

[0103] (Appendix A8) An information processing device comprising: an acquisition means for acquiring polymer material information about a polymer material; and a prediction means for executing a prediction about the polymer material using a prediction model that receives information about the polymer material as an input and outputs a prediction result about the polymer material, the prediction model being machine-learned by referring to sequence group information about a plurality of polymers that are contained in the polymer material and have different sequences of structural units.

[0104] [Appendix B] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0105] (Appendix B1) An information processing method including: an acquisition process in which at least one processor acquires monomer information, which is information about a monomer; a generation process in which the at least one processor refers to the monomer information and generates sequence group information about a plurality of polymers that contain structural units derived from the monomer and whose sequences of the structural units differ from one another; and a learning process in which the at least one processor uses information about a polymer material that contains at least some of the plurality of polymers as input and machine-learns a prediction model that outputs a prediction result about the polymer material by referring to the sequence group information.

[0106] (Appendix B2) The information processing method described in Appendix B1, wherein, in the acquisition process, the at least one processor further acquires polymer property information, which is information about a polymer containing a structural unit derived from the monomer and indicates the physical properties of the polymer; and, in the learning process, the at least one processor performs machine learning on the prediction model by further referring to the polymer property information.

[0107] (Appendix B3) The information processing method according to Appendix B1 or B2, wherein the sequence group information indicates the abundance ratio of each of the plurality of polymers, and in the learning process, the at least one processor performs machine learning on the prediction model by referring to at least the sequences and the abundance ratios of the structural units in the sequence group information.

[0108] (Appendix B4) The information processing method according to any one of Appendices B1 to B3, wherein in the acquisition process, the at least one processor further acquires polymer material information related to a polymer material; (1) in the learning process, the at least one processor performs machine learning on the prediction model by further referring to the polymer material information; or (2) in the generation process, the at least one processor generates the sequence group information so that each of the plurality of polymers has properties that match the properties of the polymer material indicated by the polymer material information.

[0109] (Appendix B5) The information processing method according to any one of Appendices B1 to B4, wherein the monomer information indicates a molecular structure of the monomer, and in the generation process, the at least one processor generates the sequence group information by referring to at least the molecular structure of the monomer in the monomer information.

[0110] (Appendix B6) The information processing method according to any one of Appendices B1 to B5, wherein the monomer information is information relating to two or more monomers, and in the generation process, the at least one processor generates the sequence group information relating to a copolymer containing structural units derived from each of the two or more monomers.

[0111] (Supplementary Note B7) The information processing method according to any one of Supplementary Notes B1 to B6, wherein in the generation process, the at least one processor outputs the sequence group information.

[0112] (Appendix B8) An information processing method including: an acquisition process in which at least one processor acquires polymer material information about a polymer material; and a prediction process in which the at least one processor executes a prediction about the polymer material using a prediction model that takes information about the polymer material as input and outputs a prediction result about the polymer material, the prediction model being machine-learned by referring to sequence group information about a plurality of polymers contained in the polymer material and having different sequences of structural units.

[0113] [Appendix C] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0114] (Appendix C1) An information processing program that causes a computer to function as an information processing device, the information processing program causing the computer to function as: an acquisition means that acquires monomer information, which is information about monomers; a generation means that refers to the monomer information and generates sequence group information about a plurality of polymers that contain structural units derived from the monomers and whose sequences of the structural units differ from one another; and a learning means that refers to the sequence group information and performs machine learning to create a prediction model that receives information about a polymer material containing at least a portion of the plurality of polymers as input and outputs a prediction result about the polymer material.

[0115] (Appendix C2) The information processing program according to Appendix C1, wherein the acquisition means further acquires polymer property information that is information about a polymer containing a structural unit derived from the monomer and indicates physical properties of the polymer, and the learning means performs machine learning on the prediction model by further referring to the polymer property information.

[0116] (Appendix C3) The information processing program according to Appendix C1 or C2, wherein the sequence group information indicates an abundance ratio of each of the plurality of polymers, and the learning means performs machine learning on the prediction model by referring to at least the sequences and the abundance ratios of the structural units in the sequence group information.

[0117] (Appendix C4) The information processing program according to any one of Appendices C1 to C3, wherein the acquisition means further acquires polymer material information relating to a polymer material; and (1) the learning means performs machine learning on the prediction model by further referring to the polymer material information, or (2) the generation means generates the sequence group information so that each of the plurality of polymers has properties that match the properties of the polymer material indicated by the polymer material information.

[0118] (Appendix C5) The information processing program according to any one of Appendices C1 to C4, wherein the monomer information indicates a molecular structure of the monomer, and the generating means generates the sequence group information by referring to at least the molecular structure of the monomer in the monomer information.

[0119] (Appendix C6) The information processing program according to any one of Appendices C1 to C5, wherein the monomer information is information about two or more monomers, and the generating means generates the sequence group information about a copolymer containing structural units derived from each of the two or more monomers.

[0120] (Appendix C7) The information processing program according to any one of Appendices C1 to C6, wherein the generating means outputs the sequence group information.

[0121] (Appendix C8) An information processing program that causes a computer to function as an information processing device, the information processing program causing the computer to function as: an acquisition means that acquires polymer material information related to a polymer material; and a prediction means that executes predictions related to the polymer material using a prediction model that receives information related to the polymer material as input and outputs a prediction result related to the polymer material, the prediction model being machine-learned by referring to sequence group information related to a plurality of polymers that are contained in the polymer material and have different sequences of structural units.

[0122] [Appendix D] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0123] (Appendix D1) An information processing device comprising at least one processor, the at least one processor executing: an acquisition process for acquiring monomer information that is information about a monomer; a generation process for generating, by referring to the monomer information, sequence group information about a plurality of polymers that contain structural units derived from the monomer and whose sequences of the structural units differ from one another; and a learning process for machine learning a prediction model that receives information about a polymer material that contains at least a portion of the plurality of polymers as input and outputs a prediction result about the polymer material by referring to the sequence group information.

[0124] The information processing device may further include a memory, and the memory may store a program for causing the at least one processor to execute each of the processes.

[0125] (Appendix D2) The information processing device described in Appendix D1, wherein in the acquisition process, the at least one processor further acquires polymer property information, which is information about a polymer containing a structural unit derived from the monomer and indicates the physical properties of the polymer; and in the learning process, the at least one processor trains the prediction model by machine learning, further referring to the polymer property information.

[0126] (Appendix D3) The information processing device according to Appendix D1 or D2, wherein the sequence group information indicates the abundance ratio of each of the plurality of polymers, and in the learning process, the at least one processor performs machine learning on the prediction model by referring to at least the sequences and the abundance ratios of the structural units in the sequence group information.

[0127] (Appendix D4) The information processing device according to any one of Appendices D1 to D3, wherein in the acquisition process, the at least one processor further acquires polymer material information relating to a polymer material; (1) in the learning process, the at least one processor performs machine learning on the prediction model by further referring to the polymer material information; or (2) in the generation process, the at least one processor generates the sequence group information so that each of the plurality of polymers has properties that match the properties of the polymer material indicated by the polymer material information.

[0128] (Appendix D5) The information processing device according to any one of Appendices D1 to D4, wherein the monomer information indicates a molecular structure of the monomer, and in the generation process, the at least one processor generates the sequence group information by referring to at least the molecular structure of the monomer in the monomer information.

[0129] (Appendix D6) The information processing device according to any one of Appendices D1 to D5, wherein the monomer information is information relating to two or more monomers, and in the generation process, the at least one processor generates the sequence group information relating to a copolymer containing structural units derived from each of the two or more monomers.

[0130] (Supplementary Note D7) The information processing device according to any one of Supplementary Notes D1 to D6, wherein in the generation process, the at least one processor outputs the sequence group information.

[0131] (Appendix D8) An information processing device comprising at least one processor, the at least one processor executing: an acquisition process for acquiring polymer material information about a polymer material; and a prediction process for making a prediction about the polymer material using a prediction model that takes information about the polymer material as input and outputs a prediction result about the polymer material, the prediction model being machine-learned by referring to sequence group information about a plurality of polymers that are included in the polymer material and have different sequences of structural units.

[0132] [Appendix E] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0133] (Appendix E1) A non-transitory recording medium having recorded thereon an information processing program that causes a computer to function as an information processing device, the information processing program causing the computer to execute: an acquisition process that acquires monomer information, which is information about monomers; a generation process that refers to the monomer information and generates sequence group information about a plurality of polymers that contain structural units derived from the monomers and whose sequences of the structural units differ from one another; and a learning process that uses information about a polymer material that contains at least a portion of the plurality of polymers as input and machine-learns, by referring to the sequence group information, a prediction model that outputs a prediction result about the polymer material.

[0134] REFERENCE SIGNS LIST 1, 1A, 2... Information processing device 11, 21... Acquisition unit 12... Generation unit 13... Learning unit 22... Prediction unit

Claims

1. An information processing device comprising: an acquisition means for acquiring monomer information, which is information relating to monomers; a generation means for generating sequence group information relating to a plurality of polymers containing structural units derived from the monomers and in which the sequences of the structural units differ from one another, by referring to the monomer information; and a learning means for performing machine learning on a prediction model, by referring to the sequence group information, which receives as input information about a polymer material containing at least some of the plurality of polymers and outputs a prediction result relating to the polymer material.

2. The information processing device according to claim 1, wherein the acquisition means further acquires polymer property information that indicates the physical properties of the polymer, the polymer containing structural units derived from the monomer, and the learning means performs machine learning on the prediction model by further referring to the polymer property information.

3. The information processing device according to claim 1 or 2, wherein the sequence group information indicates the abundance ratio of each of the plurality of polymers, and the learning means performs machine learning on the prediction model by referring to at least the sequence and the abundance ratio of the structural units in the sequence group information.

4. The information processing device according to any one of claims 1 to 3, wherein the acquisition means further acquires polymer material information relating to polymer materials, and (1) the learning means performs machine learning on the prediction model by further referring to the polymer material information, or (2) the generation means generates the sequence group information so that each of the plurality of polymers has properties that match the properties of the polymer material indicated by the polymer material information.

5. An information processing device according to any one of claims 1 to 4, wherein the monomer information indicates the molecular structure of the monomer, and the generating means generates the sequence group information by referring to at least the molecular structure of the monomer in the monomer information.

6. An information processing device according to any one of claims 1 to 5, wherein the monomer information is information relating to two or more monomers, and the generating means generates the sequence group information relating to a copolymer containing structural units derived from each of the two or more monomers.

7. The information processing device according to any one of claims 1 to 6, wherein the generating means outputs the sequence group information.

8. An information processing device comprising: an acquisition means for acquiring polymer material information about a polymer material; and a prediction means for executing a prediction about the polymer material using a prediction model that receives information about the polymer material as an input and outputs a prediction result about the polymer material, the prediction model being machine-learned by referring to sequence group information about a plurality of polymers contained in the polymer material and having different sequences of structural units.

9. An information processing method comprising: acquiring monomer information, which is information about a monomer; generating sequence group information about a plurality of polymers containing structural units derived from the monomer and in which the sequences of the structural units differ from one another, by referring to the monomer information; and performing machine learning on a prediction model, by referring to the sequence group information, which inputs information about a polymer material containing at least some of the plurality of polymers and outputs a prediction result about the polymer material.

10. An information processing method comprising: acquiring polymer material information about a polymer material; and performing a prediction about the polymer material using a prediction model that takes the information about the polymer material as input and outputs a prediction result about the polymer material, the prediction model being machine-learned by referring to sequence group information about a plurality of polymers contained in the polymer material and having different sequences of structural units.

11. A program that causes a computer to execute the following steps: an acquisition process that acquires monomer information, which is information about monomers; a generation process that references the monomer information and generates sequence group information about a plurality of polymers that contain structural units derived from the monomers and whose sequences of the structural units differ from one another; and a learning process that uses information about a polymer material that contains at least some of the plurality of polymers as input and machine-learns a prediction model that outputs prediction results about the polymer material by reference to the sequence group information.

12. A program that causes a computer to execute: an acquisition process that acquires polymer material information related to a polymer material; and a prediction process that makes predictions about the polymer material using a prediction model that takes information about the polymer material as input and outputs a prediction result about the polymer material, the prediction model being machine-learned by referring to sequence group information about a plurality of polymers that are contained in the polymer material and have different sequences of structural units.

Images