Information processing system, information processing method and program

Abstract

To provide a method for reducing a learning time in a qualitative analysis using machine learning of an X-ray diffraction pattern.SOLUTION: An information processing system includes a data group acquisition part 310, a subclass setting unit 320, a crystal phase selection unit 330, and a profile generation unit 340. The data group acquisition unit acquires a data group including a plurality of pieces of crystal phase information. The subclass setting unit sets the crystal phase information included in the data group into either subclass of a first subclass and a second subclass. The crystal phase selection unit selects the crystal phase information from the first subclass or both the first subclass and the second subclass and defines the selected crystal phase information as selected data. When there are a plurality of first subclasses, the selection data includes at least one piece of crystal phase information in each first subclass. The profile generation unit generates an X-ray diffraction profile on the basis of the selected data.SELECTED DRAWING: Figure 3

Description

[Technical field]

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

[0002] X-ray diffraction is an example of a method for analyzing the crystalline phases contained in a powder sample (hereafter referred to as qualitative analysis). In conventional qualitative analysis using X-ray diffraction, the crystalline phases contained in a powder sample are identified by comparing the diffraction pattern generated from the powder sample with diffraction patterns previously recorded in a database. However, the conventional method had problems such as a large number of crystalline phase data recorded in the database, which required a lot of time to compare the diffraction pattern with the information recorded in the database, and a low accuracy rate for complex diffraction patterns.

[0003] In recent years, qualitative analysis using machine learning has been considered as a method for improving conventional qualitative analysis. In qualitative analysis using machine learning, a neural network is created using training data in which a diffraction pattern is used as input data and the crystal phase contained in the diffraction pattern is used as output data. By inputting the measurement results of a test sample to the neural network, the crystal phase contained in the test sample can be obtained.

[0004] Non-Patent Document 1 teaches a method for creating training data. It describes how a diffraction pattern of a mixture can be simulated by creating multiple types of single-phase profiles based on crystal phase information recorded in a database and adding up the single-phase profiles, and how machine learning is performed using the obtained diffraction pattern. [Prior art documents] [Non-patent literature]

[0005] [Non-Patent Document 1] Jan Schuetzke et al., Enhancing deep-learning training for phase identification in powder X-ray diffractograms, IUCrJ 8 (2021) 408-420. Summary of the Invention [Problem to be solved by the invention]

[0006] In qualitative analysis using machine learning, a problem is that a huge amount of training data must be learned to create a neural network, which takes time. For example, the cement database contains information on approximately 70 types of crystal phase. There are a huge number of ways to combine this crystal phase information, approximately 10 billion, so it was necessary to train a huge amount of training data. Furthermore, if the amount of crystal phase information stored in the database increases, the number of combination methods will also increase dramatically, which is expected to require even more time. Therefore, a method to reduce the training time was required. [Means for solving the problem]

[0007] According to one aspect of the present invention, there is provided an information processing system for generating an X-ray diffraction profile. The information processing system includes a data group acquisition unit, a subclass setting unit, a crystal phase selection unit, and a profile generation unit. The data group acquisition unit acquires a data group including a plurality of pieces of crystal phase information. The subclass setting unit sets the crystal phase information included in the data group to any one of a first subclass and a second subclass. The number of first subclasses is 1 or more, the number of second subclasses is 0 or more, and the total number of the first subclasses and the second subclasses is 2 or more. The crystal phase selection unit selects crystal phase information from the first subclass or both the first subclass and the second subclass, and sets the selected data as selected data. When there are a plurality of first subclasses, the selected data includes at least one piece of crystal phase information for each first subclass. The profile generation unit generates an X-ray diffraction profile based on the selected data. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of a system configuration of an information processing system. [Diagram 2] FIG. 2 is a diagram illustrating an example of a hardware configuration of an information processing device. [Diagram 3] FIG. 3 is a diagram illustrating an example of a functional configuration of the information processing device. [Figure 4] FIG. 4 is a flowchart showing an example of information processing during learning in the information processing device. [Diagram 5] FIG. 5 is a diagram showing an example of the setting screen. [Figure 6] FIG. 6 is a diagram showing a modified example of the setting screen. [Figure 7] FIG. 7 is a flowchart showing an example of information processing during inference in the information processing device. [Figure 8] FIG. 8 is a conceptual diagram showing an example of a process for determining a crystal phase. [Figure 9] FIG. 9 is a diagram showing the difference in learning data patterns depending on whether or not there is a subclass. [Figure 10] FIG. 10 is a diagram showing an example of a comparison of performance depending on whether or not a subclass is included. [Figure 11] FIG. 11 is a diagram showing an example of a comparison of learning times depending on whether or not a subclass is included. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described with reference to the drawings. Various characteristic features shown in the following embodiments can be combined with each other.

[0010] In this specification, the term "unit" may include, for example, a combination of hardware resources implemented by a circuit in the broad sense and software information processing that can be specifically realized by these hardware resources. In addition, while various information is handled in the first embodiment, this information is represented by high and low signal values ​​as a binary bit collection consisting of 0 or 1, and communication and calculation can be performed on the circuit in the broad sense.

[0011] In addition, a circuit in the broad sense is a circuit realized by at least appropriately combining a circuit, circuitry, a processor, a memory, etc. In other words, it includes an application specific integrated circuit (ASIC), a programmable logic device (e.g., a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)), etc.

[0012] <Embodiment 1> 1. System configuration diagram FIG. 1 is a diagram showing an example of a system configuration of an information processing system 1000. As shown in FIG. 1, the information processing system 1000 includes, as a system configuration, an information processing device 100 and an X-ray diffraction device 110. The information processing device 100 and the X-ray diffraction device 110 are communicably connected via a network 150. The information processing device 100 is a device that generates an X-ray diffraction profile, and executes processing according to the first embodiment including a modified example described later. The X-ray diffraction device 110 is a device that performs measurement by analyzing diffraction that occurs as a result of X-rays being scattered and interfered with by electrons around atoms of the sample when X-rays are irradiated onto the sample.

[0013] Here, the information processing system described in the claims may be composed of multiple devices or may be composed of one device. When the information processing system described in the claims is composed of one device, an example of the device is the information processing device 100. When the information processing system described in the claims is composed of multiple devices, an example of the multiple devices is the information processing device 100 and the X-ray diffraction device 110, or a cloud system that provides the functions of the information processing device 100, etc.

[0014] 2. Hardware Configuration Fig. 2 is a diagram showing an example of a hardware configuration of the information processing device 100. As shown in Fig. 2, the information processing device 100 includes, as the hardware configuration, a control unit 210, a storage unit 220, an input interface (hereinafter referred to as an input I / F) 230, an output interface (hereinafter referred to as an output I / F) 240, and a communication unit 250.

[0015] The control unit 210 is a CPU (Central Processing Unit) or the like, and controls the entire information processing device 100. The control unit 210 executes processing based on a program stored in the storage unit 220, thereby realizing the functional configuration of the information processing device 100 shown in Fig. 3 described later, the processing of the flowcharts shown in Fig. 4 and Fig. 7 described later, and the like.

[0016] The storage unit 220 is any one of a hard disk drive (HDD), a read only memory (ROM), a random access memory (RAM), and a solid state drive (SSD), or any combination thereof, and stores a program and data used when the control unit 210 executes a process based on the program. The storage unit 220 is an example of a storage medium. Note that, in this specification, the data used when the control unit 210 executes a process based on the program is described as being stored in the storage unit 220, but the data may be stored in a storage unit of another device that can communicate with the information processing device 100. In other words, the data may be stored in a storage unit of any device as long as the control unit 210 can refer to the data.

[0017] The input I / F 230 is an interface that connects an input device to the information processing device 100. Examples of the input device include a keyboard and a mouse. Information input from the input device is passed to the control unit 210 via the input I / F 230.

[0018] The output I / F 240 is an interface that connects an output device to the information processing device 100. An example of the output device is a display. Information output via the output I / F 240 based on the control of the control unit 210 is output to the output device.

[0019] The communication unit 250 is a NIC (Network Interface Card) or the like, and connects the information processing device 100 to the network 150 and controls communication with other devices.

[0020] 3. Functional configuration Fig. 3 is a diagram showing an example of a functional configuration of the information processing device 100. As shown in Fig. 3, the information processing device 100 includes, as its functional configuration, a data group acquiring unit 310, a subclass setting unit 320, a crystal phase selecting unit 330, a profile generating unit 340, a neural network generating unit 350, a measurement data acquiring unit 360, and a measurement data analyzing unit 370.

[0021] The data group acquisition unit 310 acquires a data group including multiple pieces of crystal phase information from the storage unit 220 or the like. Here, the crystal phase information means information from which a diffraction pattern can be calculated, such as crystal structure information and intensity information at a certain angle (2θ). The data group is preferably a structured collection of information such as a database, but does not have to be this. The data group is not limited to the one provided, and a user may collect multiple pieces of crystal phase information and record the collected information as the data group.

[0022] The subclass setting unit 320 sets the crystal phase information included in the data group to either the first subclass or the second subclass. Here, the number of the first subclasses is 1 or more, the number of the second subclasses is 0 or more, and the total number of the first subclasses and the second subclasses is 2 or more. Here, the crystal phase information included in the data group is necessarily classified into either the first subclass or the second subclass. If there is crystal phase information that is not classified into either, it is considered to be classified into the second subclass. The subclass setting unit 320 may set based on a user's input, or the subclass setting unit 320 may set automatically. In addition, it is preferable that the subclass is determined based on the type of analysis target or the purpose of the analysis. Examples of the type of analysis target include cement and battery materials, and examples of the purpose of the analysis include analysis of impurity components and determination of crystal polymorphism.

[0023] The crystalline phase selection unit 330 selects crystalline phase information from the first subclass or from both the first subclass and the second subclass, and sets the selected data as the selected data. Here, when there are a plurality of first subclasses, the selected data includes at least one crystalline phase information for each first subclass. By selecting crystalline phase information in this manner, the types of combinations of crystalline phase information included in the selected data can be reduced. For example, by setting crystalline phase information considered to be a main component as the first subclass and setting crystalline phase information considered to be an impurity as the second subclass, it is possible to create selected data that always includes the main component. The above description does not prevent crystalline phase information considered to be an impurity from being set as the first subclass, and when it is known that an impurity is always included, it may be set as the first subclass. Note that, regardless of how the subclasses are set, the types of combinations of crystalline phase information included in the selected data can be reduced by setting one or more first subclasses, and the effect of the first embodiment can be enjoyed.

[0024] The profile generating unit 340 generates an X-ray diffraction profile based on the selection data selected by the crystal phase selecting unit 330. More specifically, the profile generating unit 340 preferably generates a plurality of single phase profiles from the selection data and combines the generated plurality of single phase profiles to generate an X-ray diffraction profile. Here, the combination of profiles means adding intensity information using a plurality of crystal phase information and their mixture ratios, and the generated X-ray diffraction profile becomes an X-ray diffraction profile of the mixture. Note that the above description shows an efficient method for generating an X-ray diffraction profile of the mixture, and does not prevent the X-ray diffraction profile of the mixture from being generated directly from the selection data.

[0025] The neural network generating unit 350 generates a neural network by machine learning the teacher data in which the X-ray diffraction profile generated by the profile generating unit 340 is used as input data and the selected data is used as output data. The machine-learned trained neural network (hereinafter also simply referred to as neural network) is stored in the storage unit 220 or the like.

[0026] The measurement data acquisition unit 360 acquires an X-ray diffraction profile, which is measurement data. The measurement data is generated by the X-ray diffraction device 110, transmitted to the information processing device 100, and stored in the storage unit 220, etc. The measurement data acquisition unit 360 acquires the measurement data from the storage unit 220, etc.

[0027] The measurement data analysis unit 370 may input the measurement data into a trained neural network, and output an inference result obtained by inferring crystalline phase information contained in the measurement data. The measurement data analysis unit 370 may output the inference result by displaying the inference result on an output device via the output I / F 240 or the like, or may output the inference result by writing the inference result to a file or the like and storing it in the storage unit 220. Here, the inference result is a result of inferring crystalline phase information contained in the measurement data, and is a continuous value from 0 to 1 related to the probability that a certain crystalline phase is included.

[0028] The measurement data analysis unit 370 may input the measurement data into a neural network to obtain an inference result for inferring crystalline phase information contained in the measurement data, and output the crystalline phase information contained in the measurement data based on the inference result. As a method for determining the crystalline phase information contained in the measurement data, for example, a certain threshold value may be used for the inference result. The measurement data analysis unit 370 outputs at least one of the inference result or the crystalline phase information contained in the measurement data.

[0029] 4. Information Processing (1) During study FIG. 4 is a flowchart showing an example of information processing during learning in the information processing device 100. In step S401, the data group acquiring unit 310 acquires a data group including a plurality of pieces of crystalline phase information from the storage unit 220 or the like. In step S402, the subclass setting unit 320 controls the output device to display a setting screen for setting the multiple crystal phase information included in the data group to either the first subclass or the second subclass, based on the multiple crystal phase information included in the data group.

[0030] FIG. 5 is a diagram showing an example of a setting screen 500. The setting screen 500 includes a subclass setting window 510, a subclass type setting window 520, and a register button 530. The subclass setting window 510 includes a crystal phase information display field 511 and a subclass setting field 512, and the subclass type setting window 520 includes a subclass display field 521 and a subclass type setting field 522. As described above, either the first subclass or the second subclass can be set in the subclass type setting field 522, and it is set whether each subclass set in the subclass setting field 512 corresponds to the first subclass or the second subclass. Setting the crystal phase information included in the data group to the first subclass and the second subclass means setting both the subclass and the subclass type for the crystal phase information.

[0031] Crystal phase information included in the data group is displayed in a crystal phase information display field 511. For each crystal phase, the user may input a subclass name in a subclass setting field 512 or may select it from a list box. Also, subclasses may be automatically assigned based on information included in the data group without user input.

[0032] Subclasses set in subclass setting field 512 are displayed in subclass display field 521. Either the first subclass or the second subclass is selected and set in subclass type setting field 522 for each subclass displayed in subclass display field 521. In this case, too, selection may be made from a list box, or a method of selecting either the first subclass or the second subclass using a check box may be used. In FIG. 5, subclass name setting window 510 and subclass type setting window 520 are shown side by side on the same screen, but they may be present on different screens. Information regarding the subclass settings is updated by pressing register button 530.

[0033] Note that the list box is an example of a GUI component, and any GUI component may be used as long as a subclass can be set in the crystal phase information. Also, although the subclass setting field 512 and the subclass type setting field 522 are separate in Fig. 5, both the subclass and the subclass type may be set at the same time, such as the nth first subclass.

[0034] Fig. 6 is a diagram showing a modified example of the setting screen 500. The explanation overlapping with Fig. 5 will be omitted. The setting screen 600 comprises a subclass setting window 610 and a registration button 630, and the subclass setting window 610 comprises a crystal phase information display field 611 and a subclass setting field 612. In the subclass setting field 612, the subclass name may be entered only for crystal phases that correspond to the first subclass. In this case, crystal phases for which no subclass name is entered may be treated as the second subclass.

[0035] The subclass setting unit 320 sets the crystal phase information included in the data group to either the first subclass or the second subclass based on an operation via the setting screen. As shown in Fig. 6, if the data does not fall into either subclass, it is treated as the second subclass, and subclassification is performed so as not to include crystal phase information that does not belong to either subclass.

[0036] In step S403, the crystal phase selection unit 330 selects crystal phase information from the first subclass or from both the first subclass and the second subclass, and sets the selected data as selection data. Here, when there are a plurality of first subclasses, the selection data includes at least one piece of crystal phase information for each first subclass.

[0037] In step S404, the profile generating unit 340 generates an X-ray diffraction profile (mixture profile) based on the selection data selected by the crystal phase selecting unit 330.

[0038] In step S405, the neural network generating unit 350 generates a neural network by machine learning the teacher data, in which the X-ray diffraction profile generated by the profile generating unit 340 is used as input data and the selected data is used as output data.

[0039] (2) At the time of inference FIG. 7 is a flowchart showing an example of information processing during inference in the information processing device 100. In step S701, the measurement data acquisition unit 360 acquires measurement data. The measurement data acquisition unit 360 acquires the measurement data measured by the X-ray diffraction apparatus 110 from the storage unit 220 or the like.

[0040] In step S702, the measurement data analysis unit 370 inputs the measurement data to the trained neural network, and obtains an inference result of inferring crystalline phase information contained in the measurement data from the trained neural network. Also, the measurement data analysis unit 370 may obtain crystalline phase information contained in the measurement data based on the inference result.

[0041] Fig. 8 is a conceptual diagram showing an example of a process for acquiring crystalline phase information. The likelihood that each crystalline phase is included in the measurement data is output as a continuous value between 0 and 1, so for convenience, it is written as probability in Fig. 8. A threshold is set for the inference result to acquire the crystalline phase information included in the measurement data.

[0042] In step S703, the measurement data analysis unit 370 outputs at least one of the inference result and the crystalline phase information calculated based on the inference result. The measurement data analysis unit 370 may output the inference result by displaying the inference result on an output device via the output I / F 240 or the like, or may output the inference result by writing the inference result to a file or the like and storing it in the storage unit 220.

[0043] 5. Embodiment In the embodiment, the number of pieces of crystal phase information included in each of the first subclass and the second subclass is assumed to be 2 or more. In the embodiment, the description will be given taking as an example a case where the type of analysis target is cement.

[0044] When the type of the analysis target is cement, the subclass setting unit 320 may set a first subclass to include C3S (alite), C2S (belite), C3A (aluminate), and C4AF (ferrite).

[0045] In the cement manufacturing process, C3S, C2S, C3A, and C4AF are used as raw materials. C3S, C2S, C3A, and C4AF each have multiple types of crystal phases, but at least one type of crystal phase information is selected from each of C3S, C2S, C3A, and C4AF. Therefore, it is believed that efficient creation of training data is possible by setting C3S, C2S, C3A, and C4AF as the first subclass and impurity phases as the second subclass.

[0046] The crystal phase information contained in C3S, C2S, C3A, and C4AF includes, for example, the following: · C3S The chemical formula is the same, Ca3(SiO4)O, but there are different crystal systems, such as monoclinic, rhombohedral, and hexagonal. ·C2S The chemical formula is the same, Ca2(SiO4), but there are different crystal systems, such as monoclinic, orthorhombic, tetragonal, rhombohedral, and hexagonal. · C3A The chemical formula is based on Ca3(Al2O6), with Na, Fe, and Si added, and there are also ones with different composition ratios. Different crystal systems include the orthorhombic system and the cubic system. ·C4AF The chemical formula is Ca2FeAlO5, but there are also ones with added Ca. The crystal system includes the rectangular system.

[0047] FIG. 9 is a diagram showing the difference in the combination patterns of mixtures depending on whether or not subclasses are present. In the following diagram, the verification results of the effect of setting subclasses for data groups of cement containing 72 and 124 types of crystal phases are shown. Generally, cement is composed of four types of main components (C3S, C2S, C3A, C4AF) and minor components. Each main component has multiple types of crystal phases. In the example of FIG. 9, the information processing device 100 shows an example in which a total of five subclasses are set for each of the main components and the minor components. In FIG. 9, the difference in the combination patterns of mixtures (8 phases) depending on whether or not subclasses are present is shown. In this way, the increase in the number of data groups causes a dramatic increase in the combination patterns of mixtures.

[0048] Figure 10 shows an example of a comparison of performance with and without subclasses. The same number of training data were created for both cases, one with subclasses and one without, and neural network training was performed. After that, 1,000 low-strength cement simulation profiles were input to the trained neural network, and crystalline phase information contained in the simulation profiles was inferred.

[0049] Here, the F1 value is defined by the following formula.

number

[0050] The score with subclasses was higher than without subclasses, both when the number of data groups was 72 and when it was 124. Furthermore, in the case without subclasses, the F1 value decreased significantly as the number of data groups increased, whereas in the case with subclasses, the F1 value remained almost constant even when the number of data groups increased. This is thought to be due to the fact that the use of subclasses made it possible to reduce the number of mixture combination patterns, and indicates that the method is less susceptible to the effects of an increase in the number of data groups.

[0051] FIG. 11 shows an example of a comparison of learning time with and without subclasses. The same number of training data was created for both cases where subclasses were used and where subclasses were not used, and neural network learning was performed. After that, 1,000 high-strength cement simulation profiles were input to the trained neural network, and the crystal phase information contained in the simulation profile was inferred. FIG. 11 shows the transition of the F1 value during the learning process. The case with subclasses reached a high score at an earlier stage than the case without subclasses. This means that high performance can be achieved even in a short time. Note that an epoch in FIG. 11 is a unit of learning division. In the example in FIG. 11, 500,000 pieces of data are learned per epoch. The number of epochs is proportional to the learning time.

[0052] According to the process of the embodiment, it is possible to restrict the combination patterns of mixtures in the training data by setting subclasses for the target data group. As a result, the performance of the neural network can be improved compared to when subclasses are not set. We also showed that subclass settings are useful when there are a large number of data sets or when training is required in a short time.

[0053] (Variation 1) A modification of the embodiment will now be described. In the embodiment, cement has been used as an example of the type of analysis target. However, the analysis target is not limited to cement. Another example of the analysis target is battery material. In the first modification, when the type of analysis target is battery material, the subclass setting unit 320 sets a subclass to include at least one of anode material, cathode material, solid electrolyte, and current collector as a first subclass.

[0054] Batteries are made by combining multiple types of materials, such as positive and negative electrode materials, solid electrolytes, and current collectors. In addition, various types of materials are used for the positive and negative electrode materials, solid electrolytes, and current collectors. Therefore, by setting the positive and negative electrode materials, solid electrolytes, and current collectors as the first subclass, it becomes possible to create training data efficiently.

[0055] The crystal phase information contained in the positive electrode material, the negative electrode material, the solid electrolyte, and the current collector includes, for example, the following: Cathode material Layered rock salt type LiCoO2 (LCO) and LiNiCoAlO2 (NCA), spinel type LiMn2O4 (LMO), olivine type LiFePO4 (LFP), sulfur-based sulfur Anode materials Carbon-based graphite, metallic Sn and Si, oxide-based SiO, metallic Li ·Solid electrolyte Sulfide-based solid electrolyte, oxide-based solid electrolyte Current collector Cu foil, Al foil The positive electrode material and the negative electrode material may partly contain a binder such as polyvinylidene fluoride (PVDF) or styrene-butadiene rubber (SBR).

[0056] According to the first modification, battery materials can also be analyzed. Also, the first modification can achieve the same effects as the embodiment.

[0057] (Variation 2) In the embodiment and variant 1, an example is shown in which the number of crystal phase information included in the first subclass and the second subclass is two or more, respectively, whereas variant 2 shows an example in which the number of crystal phase information included in the first subclass is one.

[0058] In chemical synthesis, pharmaceutical synthesis, etc., there are cases where the target crystal phase is known. In such cases, by setting the target crystal phase as the first subclass and other compounds as the second subclass, it becomes possible to identify impurity components contained in compounds other than the target crystal phase.

[0059] Furthermore, it may be provided in the following aspects:

[0060] (1) An information processing system for generating an X-ray diffraction profile, comprising: a data group acquisition unit, a subclass setting unit, a crystalline phase selection unit, and a profile generation unit, wherein the data group acquisition unit acquires a data group including a plurality of pieces of crystalline phase information; the subclass setting unit sets the crystalline phase information included in the data group to either a first subclass or a second subclass; the number of the first subclasses is 1 or more; the number of the second subclasses is 0 or more; and a total number of the first subclasses and the second subclasses is 2 or more; the crystalline phase selection unit selects crystalline phase information from the first subclass or both the first subclass and the second subclass to set the selected data; and when there are a plurality of first subclasses, the selected data includes at least one piece of crystalline phase information for each of the first subclasses; and the profile generation unit generates an X-ray diffraction profile based on the selected data.

[0061] (2) In the information processing system described above in (1), the number of pieces of crystal phase information included in the first subclass and the second subclass is two or more.

[0062] (3) In the information processing system according to (1) or (2) above, the type of object to be analyzed is cement, and the first subclass includes C3S (alite), C2S (belite), C3A (aluminate), and C4AF (ferrite).

[0063] (4) In the information processing system according to (1) or (2) above, the type of the analysis target is a battery material, and the first subclass includes at least one of an anode material, a cathode material, a solid electrolyte, and a current collector.

[0064] (5) In the information processing system according to any one of (1) to (4) above, the subclass setting unit displays a setting screen and sets the crystal phase information included in the data group to either a first subclass or a second subclass based on an operation via the setting screen.

[0065] (6) In the information processing system according to any one of (1) to (5) above, the profile generating unit generates a plurality of single-phase profiles from the selected data, and combines the generated single-phase profiles to generate the X-ray diffraction profile.

[0066] (7) The information processing system according to any one of (1) to (6) above, further comprising a neural network generation unit, wherein the neural network generation unit generates a neural network by machine learning training data in which the generated X-ray diffraction profile is used as input data and the selected data is used as output data.

[0067] (8) The information processing system described in (7) above, further comprising a measurement data acquisition unit and a measurement data analysis unit, wherein the measurement data acquisition unit acquires an X-ray diffraction profile as measurement data, and the measurement data analysis unit inputs the measurement data to the neural network to output an inference result obtained by inferring crystal phase information contained in the measurement data.

[0068] (9) The information processing system described in (7) above further includes a measurement data acquisition unit and a measurement data analysis unit, wherein the measurement data acquisition unit acquires an X-ray diffraction profile as measurement data, and the measurement data analysis unit inputs the measurement data to the neural network to acquire an inference result for inferring crystalline phase information contained in the measurement data, and outputs the crystalline phase information contained in the measurement data based on the inference result.

[0069] (10) An information processing method executed by an information processing system for generating an X-ray diffraction profile, comprising: acquiring a data group including a plurality of pieces of crystalline phase information; setting the crystalline phase information included in the data group to any one of a first subclass and a second subclass; the number of the first subclasses is 1 or more; the number of the second subclasses is 0 or more; and a total number of the first subclasses and the second subclasses is 2 or more; selecting crystalline phase information from the first subclass or both the first subclass and the second subclass to obtain selected data; and when there are a plurality of first subclasses, the selected data includes at least one piece of crystalline phase information for each of the first subclasses; and generating an X-ray diffraction profile based on the selected data.

[0070] (11) A program for causing a computer to function as the information processing system described in any one of (1) to (9) above. Of course, this is not the case.

[0071] Finally, although various embodiments of the present invention have been described, these are presented as examples and are not intended to limit the scope of the invention. The new embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. The embodiments and their modifications are within the scope and spirit of the invention, and are included in the scope of the invention and its equivalents described in the claims. [Explanation of symbols]

[0072] 100: Information processing device 110: X-ray diffraction equipment 150: Network 210: Control section 220: Storage section 230: Input I / F 240: Output I / F 250: Communications Department 310: Data group acquisition unit 320: Subclass setting section 330: Crystal phase selection section 340: Profile generation unit 350: Neural network generation section 360: Measurement data acquisition section 370: Measurement Data Analysis Department 500: Setting screen 510: Subclass Settings window 511: Crystal phase information display column 512: Subclass setting field 520: Subclass type setting window 521: Subclass display column 522: Type setting field 530: Registration button 600: Setting screen 610: Subclass Settings window 611: Crystal phase information display column 612: Subclass setting field 630: Registration button 1000: Information processing systems

Claims

1. An information processing system for generating an X-ray diffraction profile, comprising: The apparatus includes a data group acquisition unit, a subclass setting unit, a crystal phase selection unit, and a profile generation unit, The data group acquisition unit acquires a data group including a plurality of pieces of crystalline phase information; the subclass setting unit sets the crystal phase information included in the data group to either a first subclass or a second subclass; the number of the first subclasses is 1 or more, the number of the second subclasses is 0 or more, and the total number of the first subclasses and the second subclasses is 2 or more; the crystal phase selection unit selects crystal phase information from the first subclass or from both the first subclass and the second subclass as selected data; When there are a plurality of the first subclasses, the selection data includes at least one crystal phase information for each of the first subclasses; The profile generator generates an X-ray diffraction profile based on the selected data. Information processing system.

2. 2. The information processing system according to claim 1, The number of crystal phase information included in the first subclass and the second subclass is two or more, Information processing system.

3. 2. The information processing system according to claim 1, The type of material being analyzed is cement, The first subclass includes C3S (alite), C2S (belite), C3A (aluminate), and C4AF (ferrite). Information processing system.

4. 2. The information processing system according to claim 1, The type of analysis target is battery materials, The first subclass includes at least one of an anode material, a cathode material, a solid electrolyte, and a current collector; Information processing system.

5. 2. The information processing system according to claim 1, The subclass setting unit Display the setting screen, setting the crystal phase information included in the data group to either a first subclass or a second subclass based on an operation via the setting screen; Information processing system.

6. 2. The information processing system according to claim 1, The profile generator generates a plurality of single-phase profiles from the selected data, and combines the generated plurality of single-phase profiles to generate the X-ray diffraction profile. Information processing system.

7. 2. The information processing system according to claim 1, Further comprising a neural network generating unit, The neural network generation unit generates a neural network by machine learning teacher data in which the generated X-ray diffraction profile is used as input data and the selected data is used as output data. Information processing system.

8. 8. The information processing system according to claim 7, Further comprising a measurement data acquisition unit and a measurement data analysis unit, The measurement data acquisition unit acquires an X-ray diffraction profile as measurement data, The measurement data analysis unit inputs the measurement data to the neural network, and outputs an inference result obtained by inferring crystal phase information contained in the measurement data. Information processing system.

9. 8. The information processing system according to claim 7, Further comprising a measurement data acquisition unit and a measurement data analysis unit, The measurement data acquisition unit acquires an X-ray diffraction profile as measurement data, The measurement data analysis unit inputs the measurement data into the neural network to obtain an inference result for inferring crystalline phase information contained in the measurement data, and outputs the crystalline phase information contained in the measurement data based on the inference result. Information processing system.

10. An information processing method executed by an information processing system for generating an X-ray diffraction profile, comprising: Acquire a data set containing information on multiple crystal phases, Setting the crystal phase information included in the data group to either a first subclass or a second subclass; the number of the first subclasses is 1 or more, the number of the second subclasses is 0 or more, and the total number of the first subclasses and the second subclasses is 2 or more; Selecting crystalline phase information from the first subclass or from both the first subclass and the second subclass as selected data; When there are a plurality of the first subclasses, the selection data includes at least one crystal phase information for each of the first subclasses; generating an X-ray diffraction profile based on the selected data; Information processing methods.

11. A program, Computer, A program for causing the information processing system according to any one of claims 1 to 9 to function as such.

Images