Estimation device, estimation method, computer program, and thermoplastic resin composition

Abstract

This will enable greater convenience in techniques for estimating unknown information. [Solution] An estimation device comprising a trained model obtained by a learning process using multiple training data sets, in which configuration information, which is information about the composition of multiple materials, and information about the transmittance of electromagnetic waves in each material are associated, and a control unit that estimates information about the transmittance of electromagnetic waves in a target material by using the configuration information of the target material.

Description

Technical Field

[0004] ,

[0006] , , , ,

[0005] , , , , , ,

[0001] The present invention relates to an estimation device, an estimation method, a computer program, and a thermoplastic resin composition.

Background Art

[0002] Conventionally, techniques for estimating unknown information have been proposed. As one specific example, a technique for estimating the physical properties of a substance when the substance is made in a specific manner has been proposed. In this case, the physical properties of the substance made in a specific manner correspond to unknown information. For example, Patent Document 1 describes a technique for estimating the physical properties of a polymer composite material based on the mass ratio of the constituent components contained in the polymer composite material.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, the conventional technology may not be sufficiently convenient in some cases. The present invention has been made in view of the above circumstances, and provides a technology that realizes higher convenience in a technology for estimating unknown information.

Means for Solving the Problems

[0005] One aspect of the present invention is an estimation device including a control unit that estimates information regarding the transmittance of electromagnetic waves in a target substance by using a learned model obtained by a learning process using a plurality of teacher data in which configuration information regarding the configuration of a plurality of substances and information regarding the transmittance of electromagnetic waves in each substance are associated, and the configuration information of the target substance.

[0006] One aspect of the present invention is the estimation device described above, wherein the configuration information includes the constituent components and mass ratios of the substance.

[0007] One aspect of the present invention is the estimation device described above, wherein the information relating to the transmittance of the training data includes a preliminary estimation error that represents the difference between information relating to the transmittance obtained by performing a simulation process on the configuration information and information representing an actual measured value relating to the transmittance of the substance indicated by the configuration information, and the device estimates information relating to the transmittance of the target substance using the results of the simulation process and the information relating to the transmittance obtained by processing using the trained model.

[0008] One aspect of the present invention is an estimation method for estimating information regarding the electromagnetic wave transmittance in a target substance by using a trained model obtained through a learning process using multiple training data sets, in which information regarding the composition of multiple substances is associated with information regarding the transmittance of electromagnetic waves in each substance, and the composition information of the target substance.

[0009] One aspect of the present invention is a computer program for causing a computer to function as an estimation device, which includes a trained model obtained by a learning process using multiple training data sets, each of which is associated with configuration information, which is information regarding the composition of multiple materials, and information regarding the transmittance of electromagnetic waves in each material, and a control unit that estimates information regarding the transmittance of electromagnetic waves in a target material by using the configuration information of the target material.

[0010] One aspect of the present invention is a thermoplastic resin composition comprising raw materials with formulation conditions obtained from estimated information regarding the transmittance of electromagnetic waves in the target substance set by the computer program described above. [Effects of the Invention]

[0011] This invention makes it possible to achieve greater convenience in techniques for estimating unknown information. [Brief explanation of the drawing]

[0012] [Figure 1] This is a schematic block diagram showing the system configuration of the estimation system 100 of the present invention. [Figure 2] This section provides specific examples of spectral information that shows the transmittance of electromagnetic waves at different wavelengths. [Figure 3] This is a schematic block diagram showing a specific example of the functional configuration of terminal device 10. [Figure 4] This is a schematic block diagram showing a specific example of the functional configuration of the learning device 20. [Figure 5] This flowchart shows a specific example of the processing performed by the learning device 20. [Figure 6] This is a schematic block diagram showing a specific example of the functional configuration of the estimation device 30. [Figure 7] This flowchart shows a specific example of the processing performed by the estimation device 30. [Figure 8] This is a schematic block diagram showing a specific example of the functional configuration of the estimation device 30 in the second embodiment of the estimation system 100. [Figure 9] This figure shows the system configuration of the third embodiment of the estimated system 100. [Figure 10] This is a schematic block diagram showing a specific example of the functional configuration of the preliminary estimation device 40. [Figure 11] This is a schematic block diagram showing a specific example of the functional configuration of the estimation device 30 in the third embodiment of the estimation system 100. [Figure 12] This graph shows experimental examples of each estimation result when existing simulation techniques are applied as a preliminary estimation process. [Figure 13] This is a schematic block diagram showing a specific example of the functional configuration of the estimation device 30 in the fourth embodiment of the estimation system 100. [Figure 14] This figure shows a schematic example of the hardware configuration of the information processing device 90 applied to this embodiment. [Figure 15] This figure shows a modified example of the estimation device 30. [Figure 16] This figure shows a modified example of the estimation device 30. [Figure 17]This is a diagram showing a modified example of the estimation device 30. [Figure 18] This is a diagram showing a modified example of the estimation device 30. [Figure 19] This is a diagram showing a modified example of the estimation device 30. [Figure 20] This is a diagram showing a modified example of the estimation device 30.

Embodiments for Carrying out the Invention

[0013] FIG. 1 is a schematic block diagram showing the system configuration of the estimation system 100 of the present invention. The estimation system 100 is used when estimating unknown information (hereinafter referred to as "target unknown information") regarding an estimation target based on known information regarding the estimation target (hereinafter referred to as "target known information"). For example, when the estimation target is a substance, known information regarding the substance (hereinafter referred to as the "target substance") may be used as the target known information, and unknown information regarding the target substance may be estimated as the target unknown information. A more specific example of the target known information is information regarding the composition of the target substance (hereinafter referred to as "target composition information"). A more specific example of the target unknown information is information indicating the physical properties of the target substance (hereinafter referred to as "target substance property information").

[0014] A specific example of the target substance is a resin composition. Specific examples of the target composition information include information indicating the constituent components of the resin composition and the mass ratio of each constituent component. The target composition information may further include information regarding the thickness of the target substance.

[0015] One specific example of target material property information is information indicating the electromagnetic wave transmission properties of the target material. As a specific example of electromagnetic wave transmission properties, spectral information showing the transmittance for each wavelength of electromagnetic waves (e.g., light) (hereinafter referred to as "transmittance spectral information") may be defined as target unknown information. Figure 2 shows a specific example of spectral information showing the transmittance for each wavelength of electromagnetic waves. In Figure 2, the target material is composed of polycarbonate (PC). In polycarbonate produced using a specific recipe indicated by the target composition information, the electromagnetic waves transmitted and blocked change depending on the wavelength. For example, there are target materials that block electromagnetic waves with wavelengths shorter than 380 nm and transmit electromagnetic waves with wavelengths longer than 380 nm. In addition, there are target materials in which the blocking or transmission of electromagnetic waves changes at wavelengths of 700 nm or 850 nm.

[0016] In these cases, the target constituent information (recipe) of the target substance may be used as the target known information, and the transmittance spectral information of the target substance may be defined as the target unknown information. In this case, for example, by inputting a recipe for the target substance assumed by the user into the estimation system 100, the transmittance spectral information of a substance produced by such a recipe is estimated. This estimation process is referred to as "forward analysis" in the following explanation. Alternatively, the transmittance spectral information of the target substance (a specific example of target physical property information) may be used as the target known information, and the recipe for the target substance (a specific example of target constituent information) may be defined as the target unknown information. In this case, for example, by inputting a transmittance spectral information assumed by the user into the estimation system 100, a recipe for a target substance that can obtain the characteristics of such transmittance spectral information is estimated. This estimation process is referred to as "inverse analysis" in the following explanation. In inverse analysis, the target physical property information used as the target known information indicates the target values ​​of the physical property information for a hypothetical target substance.

[0017] [First Embodiment] The first embodiment of the estimation system 100 is a system that performs forward analysis. The first embodiment of the estimation system 100 will be described below. The estimation system 100 includes a terminal device 10, a learning device 20, and an estimation device 30. The terminal device 10 and the estimation device 30 are connected communicatively via a network 70. The learning device 20 and the estimation device 30 may also be connected communicatively via the network 70. The network 70 may be a network using wireless communication or a network using wired communication. The network 70 may be configured using, for example, the Internet or a local area network (LAN). The network 70 may be configured by combining multiple networks.

[0018] Figure 3 is a schematic block diagram showing a specific example of the functional configuration of the terminal device 10. The terminal device 10 is configured using information devices such as a smartphone, tablet, personal computer, or dedicated device. The terminal device 10 comprises a communication unit 11, an input unit 12, an output unit 13, a storage unit 14, and a control unit 15. The terminal device 10 may be used when a user inputs known target information to the estimation system 100. The terminal device 10 may also be used when a user receives output of unknown target information from the estimation system 100.

[0019] The communication unit 11 is a communication device. The communication unit 11 may be configured, for example, as a network interface. The communication unit 11 communicates data with other devices via the network 70 in accordance with the control of the control unit 15. The communication unit 11 may be a wireless communication device or a wired communication device.

[0020] The input unit 12 is configured using existing input devices such as a keyboard, pointing device (mouse, tablet, etc.), buttons, or touch panel. The input unit 12 is operated by the user when inputting user instructions to the terminal device 10. The input unit 12 may also be an interface for connecting the input device to the terminal device 10. In this case, the input unit 12 inputs the input signal generated in the input device in response to the user's input to the terminal device 10. The input unit 12 may also be configured using a microphone and a speech recognition device. In this case, the input unit 12 acquires the acoustic signal generated by the user's speech, performs speech recognition on the words spoken by the user, and inputs the recognized string information to the terminal device 10. The speech recognition process may be performed by the control unit 15. The input unit 12 may be configured in any way that allows user instructions to be input to the terminal device 10.

[0021] The output unit 13 outputs information in a format that the user can recognize. The output unit 13 may be an image display device such as a liquid crystal display or an organic EL (Electro-Luminescence) display. The output unit 13 may also be an interface for connecting an image display device to the terminal device 10. In this case, the output unit 13 generates a video signal for displaying image data and outputs the video signal to the image display device connected to it. The output unit 13 may also be a device that outputs sound, such as a speaker. The output unit 13 may also be an interface for connecting an audio output device such as a speaker or headphones to the terminal device 10. In this case, the output unit 13 generates an audio signal for playing audio data and outputs the audio signal to the audio output device connected to it. The output unit 13 may also be configured as a touch panel integrated with the input unit 12.

[0022] The storage unit 14 is configured using a storage device such as a magnetic hard disk drive or a semiconductor storage device. The storage unit 14 stores data used by the control unit 15. The storage unit 14 stores data necessary when the control unit 15 performs processing.

[0023] The control unit 15 is composed of a processor such as a CPU (Central Processing Unit) and memory (main memory). The control unit 15 functions when the processor executes a program. Note that all or part of the functions of the control unit 15 may be implemented using hardware such as an ASIC (Application Specific Integrated Circuit), PLD (Programmable Logic Device), or FPGA (Field Programmable Gate Array). The above program may be recorded on a computer-readable recording medium. Computer-readable recording media include, for example, portable media such as flexible disks, magneto-optical disks, ROMs, CD-ROMs, and semiconductor memory devices (e.g., SSDs: Solid State Drives), as well as storage devices such as hard disks and semiconductor memory devices built into computer systems. The above program may be transmitted via a telecommunications line.

[0024] The control unit 15 may, for example, execute an application installed on its own device (terminal device 10). A specific example of such an application is an application provided to the terminal device 10 as a dedicated application for the estimation system 100. Another specific example of such an application is a web browser application. Such an application may be pre-installed on the terminal device 10, or it may be downloaded each time estimation processing using known target information is performed. For example, if it is implemented as a web browser application, the terminal device 10 may download and execute the application from a device specified by the web server (for example, the web server itself or another server) when the terminal device 10 connects to a specific web server. The control unit 15 operates according to the program of the application being executed.

[0025] The control unit 15 controls the terminal device 10 according to user operations and information received from the estimation device 30. For example, the control unit 15 transmits information (e.g., known target information) input by the target person or user operating the input unit 12 to the estimation device 30 using the communication unit 11. For example, when the control unit 15 receives information (e.g., unknown target information) transmitted from the estimation device 30 via the network 70 to the communication unit 11, it generates screen data based on the received information and displays the screen data on the output unit 13. Such screen data includes images and characters that represent the information transmitted from the estimation device 30. For example, when the control unit 15 receives information transmitted from the estimation device 30 via the network 70 to the communication unit 11, it generates audio data based on the received information and outputs the audio data from the output unit 13.

[0026] Figure 4 is a schematic block diagram showing a specific example of the functional configuration of the learning device 20. The learning device 20 is configured using information processing equipment such as a personal computer or a server. The learning device 20 includes a communication unit 21, a storage unit 22, and a control unit 23.

[0027] The communication unit 21 is a communication device. The communication unit 21 may be configured, for example, as a network interface. The communication unit 21 communicates data with other devices via the network 70 in accordance with the control of the control unit 23. The communication unit 21 may be a wireless communication device or a wired communication device.

[0028] The storage unit 22 is configured using a storage device such as a magnetic hard disk drive or a semiconductor storage device. The storage unit 22 stores data used by the control unit 23. The storage unit 22 may also function as, for example, a training data storage unit 221 and a trained model storage unit 222.

[0029] The training data storage unit 221 stores training data used in the learning process performed in the learning device 20. In the estimation system 100 in which forward analysis is performed on the explanatory variables and target variable of the training data, known target information (e.g., target configuration information) may be defined as explanatory variables, and unknown target information (e.g., target physical property information) may be defined as the target variable.

[0030] In the following explanation, we will use target constituent information as an example of explanatory variables and target physical property information as an example of the dependent variable. More specifically, the following information may be used as an example of explanatory variables. Note that the absorbance information below will be used as an explanatory variable for at least each dye (e.g., specific wavelength absorber) used in the target substance.

[0031] • Information indicating the absorbance at each wavelength (for example, each wavelength at predetermined intervals between 300 nm and 1500 nm) obtained when a predetermined amount of a dye having a specific absorption wavelength with respect to electromagnetic waves (for example, a wavelength-selective dye or dye that selectively absorbs light in a specific wavelength range in the near-ultraviolet, visible light, and near-infrared light ranges (350-1100 nm)) is added to a specific substrate (for example, a thermoplastic resin such as polycarbonate) (hereinafter referred to as "absorbance information"). • Information indicating the type and amount of dye used in the target substance. • Information indicating the type and amount of substances other than dyes (e.g., stabilizers) used in the target substance. • Information regarding the shape of the target material (e.g., thickness: the thickness of the path through which electromagnetic waves pass)

[0032] Furthermore, the following information may be used as a concrete example of the dependent variable. • Transmittance spectral information when the target substance is of a specified thickness Individual training data, composed of such combinations of explanatory and dependent variables, may be obtained, for example, by actually generating the target substance and measuring its transmittance spectrum information.

[0033] The trained model storage unit 222 stores the trained model obtained by a training process using the training data stored in the training data storage unit 221.

[0034] The control unit 23 is composed of a processor such as a CPU and memory. The control unit 23 functions as an information control unit 231 and a learning control unit 232 when the processor executes a program. Note that all or part of the functions of the control unit 23 may be implemented using hardware such as an ASIC, PLD, or FPGA. The above program may be recorded on a computer-readable recording medium. Computer-readable recording media include, for example, portable media such as flexible disks, magneto-optical disks, ROMs, CD-ROMs, and semiconductor storage devices (e.g., SSDs), as well as storage devices such as hard disks and semiconductor storage devices built into computer systems. The above program may be transmitted via a telecommunications line.

[0035] The information control unit 231 controls the input and output of information. For example, the information control unit 231 acquires training data from other devices (information processing devices and storage media) and records it in the training data storage unit 221. For example, the information control unit 231 transmits the trained model stored in the trained model storage unit 222 to another device (for example, the estimation device 30).

[0036] The learning control unit 232 executes a learning process using the training data stored in the training data storage unit 221. Specific examples of such learning processes include supervised learning methods such as support vector machines, decision trees, random forests, and neural networks. The learning control unit 232 generates a trained model for outputting a type based on the input information, for example, by performing supervised learning. The learning control unit 232 records the generated trained model in the trained model storage unit 222. The trained model obtained by the learning control unit 232 may be transmitted to the estimation device 30 and recorded in the estimation model storage unit 321 of the estimation device 30.

[0037] Figure 5 is a flowchart illustrating a specific example of the processing performed by the learning device 20. First, the information control unit 231 acquires training data (step S101). The training data may be input by a user, acquired by communication from another information device, or acquired from a recording medium connected to the learning device 20. The learning control unit 232 uses the training data to perform a learning process and records the trained model in the trained model storage unit 222 (step S102).

[0038] Figure 6 is a schematic block diagram showing a specific example of the functional configuration of the estimation device 30. The estimation device 30 is configured using an information processing device such as a personal computer or a server device. The estimation device 30 comprises a communication unit 31, a storage unit 32, and a control unit 33.

[0039] The communication unit 31 is a communication device. The communication unit 31 may be configured, for example, as a network interface. The communication unit 31 communicates data with other devices via the network 70 in accordance with the control of the control unit 33. The communication unit 31 may be a device that performs wireless communication or a device that performs wired communication.

[0040] The storage unit 32 is configured using a storage device such as a magnetic hard disk drive or a semiconductor storage device. The storage unit 32 stores data used by the control unit 33. The storage unit 32 may also function as, for example, an estimation model storage unit 321.

[0041] The estimation model storage unit 321 stores the estimation model used by the estimation unit 332 when performing estimation processing. The estimation model may be configured, for example, using information from a pre-trained model generated by a training process. Such training processing may be performed, for example, by another device (e.g., training device 20) or by the device itself (estimation device 30). The estimation model does not necessarily have to be generated by a training process. The estimation model may be configured, for example, using a lookup table that associates target configuration information with target physical property information, or it may be configured in other ways.

[0042] The control unit 33 is configured using a processor such as a CPU and memory. The control unit 33 functions as an information control unit 331 and an estimation unit 332 when the processor executes a program. Note that all or part of the functions of the control unit 33 may be implemented using hardware such as an ASIC, PLD, or FPGA. The above program may be recorded on a computer-readable recording medium. Computer-readable recording media include, for example, portable media such as flexible disks, magneto-optical disks, ROMs, CD-ROMs, and semiconductor storage devices (e.g., SSDs), as well as storage devices such as hard disks and semiconductor storage devices built into computer systems. The above program may be transmitted via a telecommunications line.

[0043] The information control unit 331 acquires information corresponding to the explanatory variables in the estimation model (e.g., target configuration information) from other devices such as the terminal device 10. The information control unit 331 transmits information indicating the estimation results obtained by the estimation unit 332 (information corresponding to the target variable, e.g., target physical property information) to other devices such as the terminal device 10. Such information exchange between the information control unit 331 and other devices may be performed, for example, by communication via the communication unit 31.

[0044] The estimation unit 332 performs estimation processing using the estimation model stored in the estimation model storage unit 321 and the target configuration information. The target physical property information is estimated through the estimation processing. For example, the information described as a specific example of the target variable may be estimated by using the estimation model and the information described as a specific example of the explanatory variable in the above-mentioned explanation of the training data.

[0045] Figure 7 is a flowchart illustrating a specific example of the processing performed by the estimation device 30. First, the information control unit 331 acquires target configuration information from the terminal device 10 (step S201). The estimation unit 332 performs estimation processing using at least the target configuration information and the estimation model (step S202). The estimation unit 332 transmits target physical property information indicating the estimation result to the terminal device 10 (step S203).

[0046] The estimation system 100 configured in this way makes it possible to achieve greater convenience in the technique of estimating unknown information. Specifically, this is as follows: The estimation system 100 makes it possible to estimate the physical properties of a target substance with greater accuracy by using the target constituent information. For example, if information indicating the type and amount of dyes used in the target substance is used as a specific example of the target constituent information, and transmittance spectral information is obtained as a specific example of the physical properties information, it becomes possible to estimate the transmittance spectral information of the thermoplastic resin composition containing the target substance with greater accuracy by estimating based on the type and amount of each dye. In particular, if a trained model is used as the estimation model, it becomes possible to achieve even higher accuracy.

[0047] [Second Embodiment] The second embodiment of the estimation system 100 is a system that performs inverse analysis. Below, the second embodiment of the estimation system 100 will be described, focusing on the differences from the first embodiment. First, the learning device 20 in the second embodiment of the estimation system 100 will be described. Regarding the explanatory variables and target variable of the training data in the second embodiment, unknown target information (e.g., target configuration information) may be defined as explanatory variables, and known target information (e.g., target physical property information) may be defined as the target variable. In the learning device 20 of the second embodiment, other configurations may be the same as in the first embodiment.

[0048] Figure 8 is a schematic block diagram showing a specific example of the functional configuration of the estimation device 30 in the second embodiment of the estimation system 100. The estimation device 30 of the second embodiment differs from that of the first embodiment in that it further includes an estimation result storage unit 322 and an optimization unit 333. The estimation device 30 will be described below.

[0049] The communication unit 31 has the same configuration as in the first embodiment, so its description is omitted. The storage unit 32 functions as an estimation model storage unit 321 and an estimation result storage unit 322. The estimation model storage unit 321 is the same as in the first embodiment. The estimation result storage unit 322 stores the estimation results by the estimation unit 332. The estimation result storage unit 322 stores, for example, the explanatory variables (especially target configuration information) used in the estimation process in the estimation unit 332 and the target variable (especially target physical property information) obtained from the estimation result in association with each other. In the second embodiment, the estimation process is performed for multiple pieces of target configuration information. Therefore, the estimation result storage unit 322 stores multiple combinations of explanatory variables and target variables.

[0050] The information control unit 331 acquires information corresponding to the known target information in the inverse analysis (target physical property information) from other devices such as the terminal device 10. The information control unit 331 transmits information indicating the estimation results obtained by the optimization unit 333 to other devices such as the terminal device 10. Such information exchange between the information control unit 331 and other devices may be performed, for example, by communication via the communication unit 31.

[0051] The estimation unit 332 and the optimization unit 333 work together to perform processing. There are at least two modes of processing by the estimation unit 332 and the optimization unit 333. The first mode and the second mode will be described below.

[0052] First, a first mode of processing by the estimation unit 332 and the optimization unit 333 will be described. The estimation unit 332 obtains target physical property information corresponding to each target configuration information by performing estimation processing based on an estimation model using one or more target configuration information as explanatory variables. The estimation unit 332 records the target configuration information used as explanatory variables and the target physical property information obtained in the estimation processing in the estimation result storage unit 322 in association. The contents of the one or more target configuration information that the estimation unit 332 uses in the initial estimation processing may be predetermined, or they may be determined based on target physical property information given as known target information. For example, a combination of target physical property information and one or more target configuration information that would be the target of estimation processing if that target physical property information were given as known target information may be stored in the storage unit 32 in advance. In this case, the estimation unit 332 may estimate target physical property information for each of the one or more target configuration information associated with the target physical property information given as known target information.

[0053] The optimization unit 333 selects from the target physical property information stored in the estimation result storage unit 322 that satisfies the optimal condition for the target physical property information given as known target physical property information. The optimal condition is a condition for presenting target configuration information that is estimated to yield the target physical property information closest to the target physical property information obtained as known target physical property information. The optimal condition may be, for example, the smallest difference between the values ​​of the target physical property information. More specifically, for example, if the target physical property information given as known target information is transmittance spectrum information, the optimal condition may be the smallest difference in the wavelengths being blocked.

[0054] The optimal condition may be, for example, that it satisfies the given object physical property information as known object information and minimizes the difference between them. Specifically, for example, if the given object physical property information as known object information is transmittance spectrum information, the optimal condition may be that the blocked wavelength is longer and the difference between the blocked wavelengths is minimized. Conversely, the optimal condition may be that the blocked wavelength is shorter and the difference between the blocked wavelengths is minimized. The optimization unit 333 reads the object configuration information stored in the estimation result storage unit 322 in association with the selected object physical property information.

[0055] The optimization unit 333 generates one or more new object configuration information based on the obtained object configuration information so that the object physical property information estimated based on the obtained object configuration information approaches the object known information (target value). Such processing may be achieved, for example, by performing mathematical optimization processing. More specifically, the optimization unit 333 generates new object configuration information by using a solution method such as simulated annealing or a genetic algorithm with respect to the obtained object configuration information.

[0056] The estimation unit 332 estimates the target physical property information by performing estimation processing on each of the new target configuration information generated by the optimization unit 333. Based on the estimation results from the estimation unit 332, the optimization unit 333 generates new target configuration information. This process is repeated until a predetermined termination condition is met. The predetermined termination condition may be defined, for example, by the number of repetitions, or by a predetermined condition indicating that the difference between the known target information (target value) and the estimated target physical property information is small. Such a predetermined condition may be defined, for example, by a threshold value for the difference in the value of the wavelength to be blocked, or by other values. The estimation results obtained in this way are transmitted to another device (for example, terminal device 10) by the information control unit 331. The above is a description of the first aspect of the processing of the estimation unit 332 and the optimization unit 333.

[0057] Next, a second aspect of the processing of the estimation unit 332 and the optimization unit 333 will be described. The estimation unit 332 obtains object property information corresponding to each of the predetermined object configuration information by performing estimation processing based on the estimation model for each of the predetermined object configuration information. It is desirable that the predetermined object configuration information be defined so that various object property information can be obtained as estimation results. The estimation unit 332 records the object configuration information used as explanatory variables and the object property information obtained in the estimation processing in the estimation result storage unit 322 in association with each other.

[0058] The optimization unit 333 selects from the target physical property information stored in the estimation result storage unit 322 that satisfies the optimal conditions for the target physical property information given as known target information. The optimal conditions are the same as the optimal conditions in the first embodiment described above. The target configuration information corresponding to the target physical property information selected by the optimization unit 333 is determined as the estimation result. The estimation result obtained in this way is transmitted to another device (for example, terminal device 10) by the information control unit 331. The above describes the second embodiment of the processing of the estimation unit 332 and the optimization unit 333.

[0059] In the second embodiment, instead of performing the estimation process described above each time known information about the target to be estimated is provided, estimation processing may be performed in advance for all predetermined target configuration information, and the results (target physical property information) may be recorded in the estimation result storage unit 322 in association with the target configuration information. This configuration makes it possible to reduce processing time and computational costs when processing a new target to be estimated.

[0060] The estimation system 100 configured in this way makes it possible to achieve greater convenience in the technology of estimating unknown information. Specifically, this is as follows: The estimation system 100 uses target physical property information to obtain information about the composition of a material from which such physical properties can be obtained (target composition information). Therefore, users can more easily obtain information about the composition of a material from which the desired physical properties can be obtained. As a result, users can more easily obtain a material from which the desired physical properties can be obtained.

[0061] [Third Embodiment] The third embodiment of the estimation system 100 is a system that performs forward analysis. Below, the third embodiment of the estimation system 100 will be described, focusing on the differences from the first embodiment. First, the system configuration of the third embodiment of the estimation system 100 will be described. Figure 9 is a diagram showing the system configuration of the third embodiment of the estimation system 100. In the third embodiment, the estimation system 100 includes a terminal device 10, a learning device 20, an estimation device 30, and a further auxiliary estimation device 40. The auxiliary estimation device 40 is connected to the terminal device 10 and the estimation device 30 so as to be able to communicate via the network 70.

[0062] Figure 10 is a schematic block diagram showing a specific example of the functional configuration of the preliminary estimation device 40. The preliminary estimation device 40 estimates the physical properties of an object from the object's configuration information using a predetermined preliminary estimation model. A specific example of such a preliminary estimation model is a so-called simulation algorithm. For example, a technique for estimating the physical properties of an object by virtually reproducing physical behavior and chemical changes based on the object's configuration information may be used as the preliminary estimation model. For example, a technique for estimating transmittance spectral information by performing a simulation using the information of explanatory variables described in the section describing the training data of the first embodiment may be applied as the preliminary estimation model.

[0063] The communication unit 41 is a communication device. The communication unit 41 may be configured, for example, as a network interface. The communication unit 41 communicates data with other devices via the network 70 in accordance with the control of the control unit 43. The communication unit 41 may be a wireless communication device or a wired communication device.

[0064] The storage unit 42 is configured using a storage device such as a magnetic hard disk drive or a semiconductor storage device. The storage unit 42 stores data used by the control unit 43. The storage unit 42 may also function as, for example, a preliminary estimation model storage unit 421.

[0065] The preliminary estimation model storage unit 421 stores the preliminary estimation model. The preliminary estimation model storage unit 421 may also store the processing and parameters necessary for performing estimation processing (e.g., simulation) using the preliminary estimation model.

[0066] The control unit 43 is configured using a processor such as a CPU and memory. The control unit 43 functions as an information control unit 431 and a preliminary estimation unit 432 when the processor executes a program. Note that all or part of the functions of the control unit 23 may be implemented using hardware such as an ASIC, PLD, or FPGA. The above program may be recorded on a computer-readable recording medium. Computer-readable recording media include, for example, portable media such as flexible disks, magneto-optical disks, ROMs, CD-ROMs, and semiconductor storage devices (e.g., SSDs), as well as storage devices such as hard disks and semiconductor storage devices built into computer systems. The above program may be transmitted via a telecommunications line.

[0067] The information control unit 431 controls the input and output of information. For example, the information control unit 431 acquires target configuration information used for preliminary estimation processing from other devices (information processing devices and storage media). For example, the information control unit 431 transmits the preliminary estimation results (e.g., simulation results) obtained by the preliminary estimation unit 432 to other devices (e.g., terminal device 10 and estimation device 30).

[0068] The preliminary estimation unit 432 estimates the physical properties of the target material based on the target configuration information by performing preliminary estimation processing using a preliminary estimation model. The preliminary estimation unit 432 estimates the physical properties of the target material based on the target configuration information by, for example, performing simulation processing. A specific example of the preliminary estimation processing will be described. For example, in the preliminary estimation processing of a thermoplastic resin composition, a database of measured absorbances in the 300-2000 nm wavelength range for a specific wavelength absorbent (dye) alone at a concentration of 50 ppm may be used. The measured absorbance may be, for example, the difference between the absorbance of a transparent resin without additives and the absorbance of a resin that differs only in that a specific wavelength absorbent has been added. From such a database, preliminary estimation results may be obtained by combining each specific wavelength absorbent at an arbitrary concentration (for example, a combination of Lambert-Beer absorbances) and converting the absorbance spectrum calculated with the material thickness indicated by the target configuration information into a transmittance spectrum.

[0069] Next, the learning device 20 in the third embodiment of the estimation system 100 will be described. In the third embodiment, the learning device 20 uses information as the target variable of the training data, which differs from that of the first embodiment. The information used as the target variable of the training data in the third embodiment is the difference (hereinafter referred to as "preliminary estimation error") between the preliminary estimation result obtained as a result of the preliminary estimation process of the preliminary estimation device 40 based on the target configuration information used as the explanatory variables of the training data, and the measured value of the target physical property information of the target substance generated based on the same target configuration information. The learning control unit 232 of the third embodiment acquires a trained model by performing a learning process using such training data. This trained model outputs the preliminary estimation error as the target variable in response to inputting the target configuration information as an explanatory variable.

[0070] Figure 11 is a schematic block diagram showing a specific example of the functional configuration of the estimation device 30 in the third embodiment of the estimation system 100. The estimation device 30 of the third embodiment differs from that of the first embodiment in that it further includes a final estimation unit 334. The estimation device 30 will be described below.

[0071] The communication unit 31 has the same configuration as in the first embodiment, so its description is omitted. The storage unit 32 functions as an estimation model storage unit 321. The estimation model stored in the estimation model storage unit 321 in the third embodiment is different from the estimation model in the first embodiment. The estimation model in the third embodiment is an estimation model for obtaining the difference (preliminary estimation error) between the preliminary estimation result obtained as a result of the preliminary estimation processing of the preliminary estimation device 40 and the measured value, with the target configuration information as the explanatory variable. The estimation model may be, for example, a trained model obtained by the learning processing of the learning device 20, or it may be a lookup table.

[0072] The information control unit 331 acquires information (target configuration information) corresponding to the known target information in the sequential analysis from other devices such as the terminal device 10. The information control unit 331 acquires preliminary estimation results from the preliminary estimation device 40. The information control unit 331 transmits information indicating the estimation results obtained by the final estimation unit 334 to other devices such as the terminal device 10. Such information exchange between the information control unit 331 and other devices may be performed, for example, by communication via the communication unit 31.

[0073] The estimation unit 332 estimates a preliminary estimation error according to the target configuration information by using the estimation model stored in the estimation model storage unit 321.

[0074] The final estimation unit 334 obtains the final estimation result based on the preliminary estimation error obtained as an estimation result by the estimation unit 332 and the preliminary estimation result obtained by the preliminary estimation device 40. That is, the final estimation unit 334 estimates the measured value of the target substance by performing calculations using the preliminary estimation result and the preliminary estimation error.

[0075] Figure 12 is a graph showing experimental examples of each estimation result when existing simulation techniques are applied as a preliminary estimation process. The estimation in Figure 12 is a process that estimates transmittance spectral information using specific examples of the explanatory variables of the training data described above. In Figure 12, the horizontal axis shows the wavelength of electromagnetic waves, and the vertical axis shows the transmittance of electromagnetic waves at each wavelength. 'ref' indicates the result of the preliminary estimation process. Direct prediction shows the estimation result of the estimation device 30 in the first embodiment. That is, direct prediction is the estimation result obtained by an estimation process using a trained model in which transmittance spectral information is defined as the target variable. Corrected prediction shows the estimation result of the estimation device 30 in the third embodiment. That is, corrected prediction shows the final estimation result obtained using the estimation result obtained by an estimation process using a trained model in which a preliminary correction error is defined as the target variable, and the preliminary estimation result. Measured values ​​show the measured values ​​of the transmittance spectral information of the target substance that were actually generated according to the target configuration information.

[0076] As shown in Figure 12, the corrected prediction reproduces the value that is closest to the measured value. In particular, it can be seen that the corrected prediction reproduces the steepness of the rise of the graph around the wavelength of 800 nm more appropriately than the direct prediction. Furthermore, it can be seen that the corrected prediction reproduces the convergence of the graph between 850 nm and 900 nm more accurately than the ref and direct predictions.

[0077] Thus, the third embodiment of the estimation system 100 makes it possible to achieve greater convenience in the technique of estimating unknown information. Specifically, it is as follows: In the third embodiment, a preliminary estimation error is estimated, and the final estimation result is obtained using the preliminary estimation process and the preliminary estimation error, thereby achieving more accurate estimation of the object's physical properties. By making it possible to obtain information with higher accuracy in this way, greater convenience is achieved.

[0078] [Fourth Embodiment] The fourth embodiment of the estimation system 100 is a system that performs inverse analysis using preliminary estimation errors. Below, the fourth embodiment of the estimation system 100 will be described, focusing on the differences from the third embodiment. First, the learning device 20 in the fourth embodiment of the estimation system 100 will be described. Regarding the explanatory variables and target variable of the training data in the fourth embodiment, unknown target information (e.g., target configuration information) may be defined as explanatory variables, and preliminary estimation errors corresponding to the target configuration information used as explanatory variables may be defined as the target variable. This differs only in that the target configuration information is defined as unknown target information rather than known target information, and is substantially the same as the third embodiment in that the target configuration information is an explanatory variable and the preliminary estimation error is the target variable. Therefore, the configuration of the learning device 20 in the fourth embodiment may be the same as that of the third embodiment.

[0079] Figure 13 is a schematic block diagram showing a specific example of the functional configuration of the estimation device 30 in the fourth embodiment of the estimation system 100. The estimation device 30 of the fourth embodiment differs from the third embodiment in that it further includes an estimation result storage unit 322 and an optimization unit 333.

[0080] The communication unit 31 has the same configuration as in the third embodiment, so its description is omitted. The storage unit 32 functions as an estimation model storage unit 321 and an estimation result storage unit 322. The estimation model storage unit 321 is the same as in the third embodiment. The estimation result storage unit 322 stores the estimation results from the final estimation unit 334. The estimation result storage unit 322 stores, for example, the explanatory variables (especially the target configuration information) used in the estimation process in the final estimation unit 334, and the target physical property information obtained from the estimation results by the final estimation unit 334, in association with each other. In the fourth embodiment, estimation processing and acquisition of the final estimation result are performed for multiple target configuration information. Therefore, the estimation result storage unit 322 stores multiple combinations of target configuration information and the final estimation result.

[0081] The information control unit 331 acquires information corresponding to the known target information in the inverse analysis (target physical property information) from other devices such as the terminal device 10. The information control unit 331 transmits information indicating the estimation results obtained by the optimization unit 333 to other devices such as the terminal device 10. Such information exchange between the information control unit 331 and other devices may be performed, for example, by communication via the communication unit 31.

[0082] The estimation unit 332, the optimization unit 333, and the final estimation unit 334 work together to perform processing. There are at least two modes of processing by the estimation unit 332, the optimization unit 333, and the final estimation unit 334. The first mode and the second mode will be described below.

[0083] First, a first mode of processing of the estimation unit 332, the optimization unit 333, and the final estimation unit 334 will be described. The estimation unit 332 obtains a preliminary estimation error corresponding to each target configuration information by performing estimation processing based on an estimation model using one or more target configuration information as explanatory variables. The estimation unit 332 records the target configuration information used as explanatory variables and the preliminary estimation error obtained in the estimation processing in the estimation result storage unit 322, associating them. The content of the one or more target configuration information that the estimation unit 332 uses in the initial estimation processing may be predetermined, or it may be determined based on the target physical property information given as known target information. For example, a combination of target physical property information and one or more target configuration information that would be the subject of estimation processing if that target physical property information were given as known target information may be stored in the storage unit 32 in advance. In this case, the estimation unit 332 may estimate a preliminary estimation error for each of the one or more target configuration information associated with the target physical property information given as known target information.

[0084] The final estimation unit 334 obtains the final estimation result based on the preliminary estimation error obtained as an estimation result by the estimation unit 332 and the preliminary estimation result obtained by the preliminary estimation device 40. That is, the final estimation unit 334 estimates the measured value of the target substance by performing calculations using the preliminary estimation result and the preliminary estimation error. The final estimation unit 334 records the estimated measured value in the estimation result storage unit 322 in association with the target configuration information.

[0085] The optimization unit 333 selects from the estimated results of measured values ​​(estimated results of target physical property information) stored in the estimation result storage unit 322 that the target physical property information given as known target information satisfies the optimal conditions. The optimal conditions are as described in the description of the second embodiment. The optimization unit 333 generates one or more new target configuration information based on the obtained target configuration information so that the target physical property information estimated based on the obtained target configuration information approaches the known target information (target value). Such processing may be achieved, for example, by performing mathematical optimization processing. More specifically, the optimization unit 333 generates new target configuration information by using a solution method such as simulated annealing or a genetic algorithm with respect to the obtained target configuration information.

[0086] The estimation unit 332 estimates a preliminary estimation error by performing estimation processing on each of the new target configuration information generated by the optimization unit 333. Based on the estimation results from the estimation unit 332, the final estimation unit 334 calculates the estimated results of the measured values. Based on the new estimation results, the optimization unit 333 generates new target configuration information. This process is repeated until a predetermined termination condition is met. The predetermined termination condition may be defined, for example, by the number of repetitions, or by a predetermined condition indicating that the difference between the known target information (target value) and the estimated target physical property information is small. Such a predetermined condition may be defined, for example, by a threshold value for the difference in the value of the wavelength to be blocked, or by other values. The estimation results obtained in this way are transmitted to another device (for example, terminal device 10) by the information control unit 331. The above is a description of the first aspect of the processing of the estimation unit 332, the optimization unit 333, and the final estimation unit 334.

[0087] Next, a second aspect of the processing of the estimation unit 332, the optimization unit 333, and the final estimation unit 334 will be described. The estimation unit 332 obtains a preliminary estimation error corresponding to each of the predetermined target configuration information by performing estimation processing based on the estimation model for each of the predetermined target configuration information. It is desirable that the predetermined target configuration information be defined so that various target physical property information can be obtained as the final estimation result. The estimation unit 332 records the target configuration information used as explanatory variables and the preliminary estimation error obtained in the estimation processing in the estimation result storage unit 322, associating them with each other.

[0088] The final estimation unit 334 obtains a final estimation result for each target configuration information based on the preliminary estimation error obtained as an estimation result by the estimation unit 332 and the preliminary estimation result obtained by the preliminary estimation device 40 for the target configuration information used in the estimation process. That is, the final estimation unit 334 estimates the measured value of the target substance by performing calculations using the preliminary estimation result and the preliminary estimation error. The final estimation unit 334 records the estimated measured value in the estimation result storage unit 322 in association with each target configuration information.

[0089] The optimization unit 333 selects from the target physical property information stored in the estimation result storage unit 322 that satisfies the optimal conditions for the target physical property information given as known target information. The optimal conditions are the same as the optimal conditions in the first embodiment described above. The target configuration information corresponding to the target physical property information selected by the optimization unit 333 is determined as the estimation result. The estimation result obtained in this way is transmitted to another device (for example, terminal device 10) by the information control unit 331. The above describes the second embodiment of the processing of the estimation unit 332, the optimization unit 333, and the final estimation unit 334.

[0090] In the second embodiment, instead of performing the estimation process described above each time known information about the target to be estimated is provided, estimation and final estimation processes may be performed in advance for all predetermined target configuration information, and the results (target physical property information) may be recorded in the estimation result storage unit 322 in association with the target configuration information. This configuration makes it possible to reduce processing time and computation costs when processing a new target to be estimated.

[0091] The estimation system 100 configured in this way makes it possible to achieve greater convenience in the technique of estimating unknown information. Specifically, this is as follows: The estimation system 100 uses target physical property information to obtain information about the composition of a material from which such physical properties can be obtained (target composition information). Therefore, users can more easily obtain information about the composition of a material from which the desired physical properties can be obtained. As a result, users can more easily obtain a material from which the desired physical properties can be obtained. Furthermore, in the fourth embodiment, processing using a preliminary estimation error is performed, similar to the third embodiment, which enables more accurate estimation. In this respect as well, greater convenience is achieved.

[0092] Figure 14 is a schematic diagram of an example hardware configuration of an information processing device 90 applied to this embodiment. The information processing device 90 comprises a processor 91, main memory 92, communication interface 93, auxiliary storage device 94, input / output interface 95, and internal bus 96. The processor 91, main memory 92, communication interface 93, auxiliary storage device 94, and input / output interface 95 are connected to each other so as to be able to communicate via the internal bus 96. The information processing device 90 may be applied to, for example, a learning device 20, an estimation device 30, and a preliminary estimation device 40. In this case, for example, the communication unit 21, communication unit 31, and communication unit 41 may be configured using the communication interface 93. For example, the storage unit 22, storage unit 32, and storage unit 42 may be configured using the auxiliary storage device 94. Also, the control unit 23, control unit 33, and control unit 43 may be configured using the processor 91 and main memory 92.

[0093] (modified version) In the first embodiment described above, the terminal device 10 and the estimation device 30 are configured as separate devices. However, these devices may be configured as a single integrated device. Figure 15 shows a modified example of the estimation device 30 configured in this way. The estimation device 30 shown in Figure 15 further includes an input unit 34 and an output unit 35 in addition to the configuration of the estimation device 30 in the first embodiment. The input unit 34 and output unit 35 of the estimation device 30 shown in Figure 15 function similarly to the input unit 12 and output unit 13 of the terminal device 10, respectively. The control unit 33 operates in response to operations on the input unit 34, performs estimation processing using the input known target information (target configuration information), and outputs unknown target information (target physical property information) using the output unit 35.

[0094] In the second embodiment described above, the terminal device 10 and the estimation device 30 are configured as separate devices. However, these devices may be configured as a single integrated device. Figure 16 shows a modified example of the estimation device 30 configured in this way. The estimation device 30 shown in Figure 16 further includes an input unit 34 and an output unit 35 in addition to the configuration of the estimation device 30 in the second embodiment. The input unit 34 and output unit 35 of the estimation device 30 shown in Figure 16 function similarly to the input unit 12 and output unit 13 of the terminal device 10, respectively. The control unit 33 operates in response to operations on the input unit 34, performs estimation processing using the input known target information (target physical property information), and outputs unknown target information (target configuration information) using the output unit 35.

[0095] In the first embodiment described above, the learning device 20 and the estimation device 30 are configured as separate devices. However, these devices may be configured as an integrated device. Figure 17 shows a modified example of the estimation device 30 configured in this way. The storage unit 32 of the estimation device 30 shown in Figure 17 also functions as a training data storage unit 323. The control unit 33 of the estimation device 30 shown in Figure 17 also functions as a learning control unit 335. The training data storage unit 323 functions similarly to the training data storage unit 221 of the learning device 20. The learning control unit 335 functions similarly to the learning control unit 232 of the learning device 20.

[0096] In the second embodiment described above, the learning device 20 and the estimation device 30 are configured as separate devices. However, these devices may be configured as an integrated device. Figure 18 shows a modified example of the estimation device 30 configured in this way. The storage unit 32 of the estimation device 30 shown in Figure 18 also functions as a training data storage unit 323. The control unit 33 of the estimation device 30 shown in Figure 18 also functions as a learning control unit 335. The training data storage unit 323 functions similarly to the training data storage unit 221 of the learning device 20. The learning control unit 335 functions similarly to the learning control unit 232 of the learning device 20.

[0097] In the third embodiment described above, the estimation device 30 and the preliminary estimation device 40 are configured as separate devices. However, these devices may be configured as a single integrated device. Figure 19 shows a modified example of the estimation device 30 configured in this way. The storage unit 32 of the estimation device 30 shown in Figure 19 also functions as a preliminary estimation model storage unit 324. The control unit 33 of the estimation device 30 shown in Figure 19 also functions as a preliminary estimation unit 336. The preliminary estimation model storage unit 324 functions similarly to the preliminary estimation model storage unit 421 of the preliminary estimation device 40. The preliminary estimation unit 336 functions similarly to the preliminary estimation unit 432 of the preliminary estimation device 40.

[0098] In the fourth embodiment described above, the estimation device 30 and the preliminary estimation device 40 are configured as separate devices. However, these devices may be configured as a single integrated device. Figure 20 shows a modified example of the estimation device 30 configured in this way. The storage unit 32 of the estimation device 30 shown in Figure 20 also functions as a preliminary estimation model storage unit 324. The control unit 33 of the estimation device 30 shown in Figure 20 also functions as a preliminary estimation unit 336. The preliminary estimation model storage unit 324 functions similarly to the preliminary estimation model storage unit 421 of the preliminary estimation device 40. The preliminary estimation unit 336 functions similarly to the preliminary estimation unit 432 of the preliminary estimation device 40.

[0099] Any other devices may be integrated into the system, even if they are not the modified examples described above. For example, the estimation device 30 in the third or fourth embodiment may be configured as an integrated device with the terminal device 10 or the learning device 20. Also, three or more devices may be configured as an integrated device.

[0100] In each of the embodiments described above, the learning device 20 may be implemented using multiple information processing devices. For example, the learning device 20 may be implemented using a device such as a cloud. For example, in the learning device 20, the storage unit 22 and the control unit 23 may be implemented in different information processing devices. For example, the storage unit 22 of the learning device 20 may be distributed and implemented across multiple information processing devices. For example, the control unit 23 of the learning device 20 may be distributed and implemented across multiple information processing devices.

[0101] In each of the embodiments described above, the estimation device 30 may be implemented using multiple information processing devices. For example, the estimation device 30 may be implemented using a device such as a cloud. For example, in the estimation device 30, the storage unit 32 and the control unit 33 may be implemented in different information processing devices. For example, the storage unit 32 of the estimation device 30 may be distributed and implemented across multiple information processing devices. For example, the control unit 33 of the estimation device 30 may be distributed and implemented across multiple information processing devices.

[0102] In each of the embodiments described above, the preliminary estimation device 40 may be implemented using multiple information processing devices. For example, the preliminary estimation device 40 may be implemented using a device such as a cloud. For example, in the preliminary estimation device 40, the storage unit 42 and the control unit 43 may be implemented in different information processing devices. For example, the storage unit 42 of the preliminary estimation device 40 may be distributed and implemented across multiple information processing devices. For example, the control unit 43 of the preliminary estimation device 40 may be distributed and implemented across multiple information processing devices.

[0103] In one embodiment of the present invention, the thermoplastic resin composition contains at least one thermoplastic resin. Examples of thermoplastic resins include aromatic polycarbonate resins, aliphatic polycarbonate resins, olefin resins, styrene resins, acrylic resins, polyphenylene ether resins, polyester resins (such as polybutylene terephthalate resins and polyethylene terephthalate resins), polyamide resins, and polyacetal resins, and the material may be composed of one or more of these resins. Furthermore, the resin composition of the embodiment of the present invention may contain other components in addition to those mentioned above, as long as it does not depart from the spirit of the present invention.

[0104] Although embodiments of this invention have been described in detail above with reference to the drawings, the specific configuration is not limited to these embodiments and includes designs and the like that do not depart from the spirit of this invention. [Explanation of symbols]

[0105] 100…Estimation System, 10…Terminal Device, 11…Communication Unit, 12…Input Unit, 13…Output Unit, 14…Storage Unit, 15…Control Unit, 20…Learning Device, 21…Communication Unit, 22…Storage Unit, 221…Training Data Storage Unit, 222…Trained Model Storage Unit, 23…Control Unit, 231…Information Control Unit, 232…Learning Control Unit, 30…Estimation Device, 31…Communication Unit, 32…Storage Unit, 321…Estimation Model Storage Unit, 322…Estimation Result Storage Unit, 33…Control Unit, 331…Information Control Unit, 332…Estimation Unit, 333…Optimization Unit, 334…Final Estimation Unit, 40…Preliminary Estimation Device, 41…Communication Unit, 42…Storage Unit, 421…Preliminary Estimation Model Storage Unit, 43…Control Unit, 431…Information Control Unit, 432…Preliminary Estimation Unit

Claims

1. An estimation device comprising a trained model obtained by a learning process using multiple training data sets, each of which is associated with configuration information, which is information about the composition of multiple materials, and information about the transmittance of electromagnetic waves in each material; and a control unit that estimates information about the transmittance of electromagnetic waves in a target material by using the configuration information of the target material.

2. The estimation apparatus according to claim 1, wherein the configuration information includes the constituent components and mass ratio of the substance.

3. The information regarding transmittance in the training data includes a preliminary estimation error that represents the difference between the information regarding transmittance obtained by performing a simulation process on the configuration information and the information representing the measured value of the transmittance of the substance indicated by the configuration information. The estimation apparatus according to claim 1, which estimates information regarding the transmittance of the target substance using the results of the simulation process and information regarding transmittance obtained by processing using the trained model.

4. An estimation method for estimating information regarding the electromagnetic wave transmittance of a target substance by using a trained model obtained through a learning process using multiple training data sets, in which information regarding the composition of multiple substances is associated with information regarding the transmittance of electromagnetic waves in each substance, and the composition information of the target substance.

5. A computer program for causing a computer to function as an estimation device, comprising a trained model obtained through a learning process using multiple training data sets, each of which associates configuration information (information about the composition of multiple materials) with information about the transmittance of electromagnetic waves in each material, and a control unit that estimates information about the transmittance of electromagnetic waves in a target material by using the configuration information of the target material.

6. A thermoplastic resin composition comprising raw materials for formulation conditions obtained from estimated information regarding the transmittance of electromagnetic waves in the target substance set by the computer program described in claim 5.

Images