Information processing device, information processing method, and information processing program

Abstract

To provide an information processing device, an information processing method, and an information processing program by which analysis processing which is necessary to analyze a material can be set for each user.SOLUTION: A server 14 receives a user ID transmitted from a user terminal 12, and a combination of learning material data about a material and correct result data which is data obtained by executing prescribed analysis processing on the learning material data. By executing a plurality of pieces of analysis processing on the learning material data in the received combination, the server 14 generates result data for each of the plurality of pieces of analysis processing. Then, the server 14 calculates a difference between the result data and the correct result data for each of the plurality of result data, and stores identification information on analysis processing having the minimum difference and the user ID in association with each other, into a user information storage unit 145.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Non-Patent Document 1 discloses a technique for quantitative analysis of mineral phases in sintered ore by the XRD-Rietveld method. The technique disclosed in Non-Patent Document 1 quantitatively analyzes sintered ore using the Rietveld method, which fits the entire X-ray diffraction pattern by the least squares method. [Prior art documents] [Non-patent literature]

[0003] [Non-Patent Document 1] Toru Takayama, Reiko Murao, "Quantitative Analysis of Mineral Phases in Sintered Ore by XRD-Rietveld Method", [Nippon Steel & Sumitomo Metal Technical Report No. 408] (2017) Summary of the Invention [Problem to be solved by the invention]

[0004] Incidentally, when performing an analytical method for a material such as that disclosed in the above-mentioned Non-Patent Document 1, it is necessary to perform a predetermined process for each analytical method. For example, when performing the XRD method, it is necessary to perform each process of noise removal, background removal, peak search, phase identification, peak fitting, and crystallite size derivation on the material data obtained by measuring the material.

[0005] The content of each of the above processes may differ for each user, each measurement method, or each measurement device. For example, regarding "noise removal" in the XRD method, a user U A prefers that the parameters of the noise removal method are set to predetermined values, and adopts noise removal with the parameters set to predetermined values ​​when analyzing material data using the XRD method. Bprefers special noise reduction methods and employs them when analyzing materials data using XRD techniques.

[0006] In this regard, the technology disclosed in the above-mentioned Non-Patent Document 1 discloses the Rietveld method for fitting the entire X-ray diffraction pattern by the least squares method, but does not take into consideration the differences in processing for each user. Therefore, the conventional technology of the above-mentioned Patent Document 1 has a problem that the processing required for material analysis cannot be selected for each user.

[0007] In consideration of the above, an object of the present disclosure is to provide an information processing device, an information processing method, and an information processing program that enable analysis processing required for material analysis to be set for each user. [Means for solving the problem]

[0008] The information processing device according to the first aspect is an information processing device including: a receiving unit that receives a combination of a user ID, learning material data related to a material, and correct result data, which is data obtained by executing a predetermined analysis process on the learning material data, transmitted from a user terminal; a generating unit that generates result data for each of the multiple analysis processes by executing multiple analysis processes on the learning material data of the combination received by the receiving unit; and an analysis process identification unit that calculates the difference between the result data and the correct result data for each of the multiple result data generated by the generating unit, and associates the identification information of the analysis process in which the difference is smallest with the user ID and stores them in a memory unit.

[0009] The information processing device receives a combination of a user ID, learning material data related to materials, and correct result data obtained by executing a predetermined analysis process on the learning material data, transmitted from a user terminal. The information processing device then executes multiple analysis processes on the received combination of learning material data to generate result data for each of the multiple analysis processes. The information processing device calculates the difference between the result data and the correct result data for each of the multiple generated result data, and stores the identification information of the analysis process with the smallest difference in association with the user ID in a storage unit. This makes it possible to set the analysis process required for material analysis for each user.

[0010] The generating unit of the information processing device according to the second aspect projects the supervised result data and the result data into a latent space, and the analysis process identifying unit calculates the difference between the supervised result data in the latent space and the result data in the latent space, and stores the identification information of the analysis process in which the difference is the smallest in association with the user ID in the storage unit. This makes it possible to evaluate the difference between the supervised result data and the result data in the latent space even when it is difficult to numerically evaluate the difference between the supervised result data and the result data.

[0011] In the information processing device according to the third aspect, the receiving unit further includes an analyzing unit that receives a combination of the user ID and material data for analysis of a material, identifies identification information of an analysis process stored in the storage unit that corresponds to the user ID, and executes the analysis process corresponding to the identified identification information on the material data for analysis, thereby making it possible to analyze the material data using the analysis process set for each user.

[0012] An information processing method according to a fourth aspect is an information processing method in which a computer executes a process to receive a combination of a user ID, learning material data related to a material, and correct result data, which is data obtained by executing a predetermined analysis process on the learning material data, transmitted from a user terminal, execute a plurality of analysis processes on the learning material data of the received combination to generate result data for each of the plurality of analysis processes, calculate the difference between the result data and the correct result data for each of the generated plurality of result data, and associate the identification information of the analysis process in which the difference is smallest with the user ID and store them in a memory unit.

[0013] The information processing program of the fifth aspect is an information processing program for causing a computer to execute a process of receiving a combination of a user ID, learning material data related to a material, and correct result data, which is data obtained by executing a predetermined analysis process on the learning material data, transmitted from a user terminal, executing a plurality of analysis processes on the learning material data of the received combination to generate result data for each of the plurality of analysis processes, calculating the difference between the result data and the correct result data for each of the generated plurality of result data, and storing in a memory unit an identification information of the analysis process in which the difference is smallest in association with the user ID. Effect of the Invention

[0014] As described above, according to the present disclosure, there is an advantage that analysis processing required for material analysis can be set for each user. [Brief description of the drawings]

[0015] [Figure 1] 1 is a schematic block diagram of an information processing device according to a first embodiment. [Diagram 2] FIG. 1 is a diagram for explaining an overview of a first embodiment. [Diagram 3] FIG. 1 is a diagram for explaining an overview of a first embodiment. [Figure 4]4 is a diagram showing an example of data stored in a processing program storage unit; FIG. [Diagram 5] FIG. 4 is a diagram illustrating an example of data stored in a user information storage unit. [Figure 6] FIG. 2 is a diagram illustrating an example of the configuration of a server and a computer of a user terminal according to the first embodiment. [Figure 7] 5 is a flowchart showing an example of processing performed in the information processing device according to the first embodiment. [Figure 8] 5 is a flowchart showing an example of processing performed in the information processing device according to the first embodiment. [Figure 9] FIG. 11 is a diagram for explaining a process according to a second embodiment. [Figure 10] FIG. 13 is a diagram for explaining data projected into a latent space. [Figure 11] FIG. 11 is a diagram illustrating a modified example of the information processing system according to the second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0016] Hereinafter, an information processing system according to an embodiment will be described with reference to the drawings.

[0017] First Embodiment Fig. 1 is a block diagram showing an example of a functional configuration of an information processing system 10 according to a first embodiment. As shown in Fig. 1, the information processing system 10 includes a plurality of user terminals 12A, 12B, ..., 12Z and a server 14 which is an example of an information processing device. The plurality of user terminals 12A, 12B, ..., 12Z and the server 14 are connected via a network 13 such as the Internet. In the following, when referring to one user terminal, it is simply referred to as a user terminal 12.

[0018] The information processing system 10 of the first embodiment customizes the analysis process of material data for each user. There are various measurement methods for measuring material data. By analyzing the material data obtained by the measurement method, an analysis result related to the material data is obtained. Note that, in order to obtain the analysis result of the material data, multiple analysis processes are often executed on the material data.

[0019] For example, for material data obtained by the XRD (X-ray diffraction) method, analysis results are obtained by performing analysis processes such as noise removal, background removal, peak search, phase identification, peak fitting, and crystallite size derivation. For material data obtained by the IR (Infrared spectroscopy) method, analysis processes such as noise removal, background removal, peak search, and phase identification are performed. For material data obtained by the WAXD (Wide Angle X-ray Diffraction) method, analysis processes such as noise removal, background removal, peak search, and crystal fraction derivation are performed. For material data that is image data, analysis processes such as background removal, grain boundary extraction, and grain size histogram derivation are performed. For material data obtained by the SAXS (Small Angle X-ray Scattering) method, analysis processes such as noise removal, background removal, and grain size derivation are performed.

[0020] For example, there are various noise removal methods. A prefers to use noise removal technique X to perform analysis, whereas another user U B In some cases, user U may prefer to use noise removal technique Y to perform analysis processing. In addition, even if the same type of noise removal technique is used, different analysis results may be obtained by adjusting the parameters. A prefers to set the parameters of noise removal method X to param1 and execute the analysis process, whereas user U Bmay prefer to run the analysis process with the parameters of noise removal method X set to param2.

[0021] In this way, in order to obtain the analysis results of the material data, it is necessary to execute an analysis process according to the type of material data, and further, it is preferable that the analysis process be set for each user.

[0022] Therefore, the information processing system 10 of the first embodiment customizes the analysis process of material data for each user. Specifically, the information processing system 10 compares the analysis result obtained by the user analyzing the material data by operating the user terminal 12 with the analysis result obtained by the server 14 analyzing the same material data, and identifies the analysis process preferred by the user according to the comparison result.

[0023] 2 and 3 are diagrams for explaining an overview of the processing of the information processing system 10 of the first embodiment. As shown in FIG. 2, the information processing system 10 of the first embodiment executes a plurality of analysis processes A, B, and C on certain material data, and compares each of the plurality of analysis results with correct answer result data, which is an analysis result obtained by a user analyzing the material data himself. For example, the graph G shown in the upper left of FIG. 2 shows material data D obtained by the XRD method. By executing a predetermined analysis process on this material data D, normalized data "normalized", background "bg", and baseline "Baseline" in the graph G are obtained. Note that the horizontal axis "2theta (deg)" of the graph G represents the diffraction angle, and the vertical axis "intensity" represents the intensity.

[0024] For example, consider the case where the crystallinity is derived from a diffraction pattern, which is material data obtained by a certain method, as shown in Figure 3. In this case, it is necessary to perform each of the analytical processes of removing the baseline, determining the number of peaks, and fitting the peaks on the diffraction pattern, which is material data.

[0025] In this embodiment, for example, as shown in FIG. 3, a plurality of analysis processes B A ,B B ,B C , , ,multiple analysis processes P A ,P B ,P C , and multiple analysis processes F that perform peak fitting. A ,F B ,F C ,... are prepared in advance. Each of the processing programs that realizes a plurality of analysis processes is also a module for obtaining analysis results from material data.

[0026] The server 14 of the information processing system 10 of the first embodiment first performs a plurality of baseline removal analysis processes B on the diffraction pattern. A ,B B ,B C Next, the server 14 executes a plurality of analysis processes B A ,B B ,B C The server 14 compares each of the analysis results obtained using each of the baseline removal analysis processes B with correct answer data obtained by the user himself / herself operating the user terminal 12 to execute the baseline removal analysis process on the material data. A ,B B ,B C From each of the analysis results obtained using each of the above, the analysis result with the smallest difference from the correct result data, which is the analysis result obtained by the user himself, is identified. For example, the baseline removal analysis process B C If the analysis result obtained by is identified, analysis process B C is identified as corresponding to the user's preferred analysis process.

[0027] Similarly, for each of the analysis process of determining the number of peaks and the analysis process of peak fitting, the server 14 identifies the analysis result that has the smallest difference from the analysis result obtained by the user himself. As a result, for example, the analysis process preferred by a certain user is the analysis process B of baseline removal. C , peak number determination analysis process P A , and peak fitting analysis process F C This allows the processing required for material analysis to be set for each user.

[0028] The specific details will be explained below.

[0029] (User terminal)

[0030] Each of the multiple user terminals 12A, 12B, . . . , 12Z is ​​operated by multiple different users.

[0031] As shown in FIG. 1, one user terminal 12 includes a terminal control unit 120, a terminal storage unit 122, a terminal transmission unit 124, and a terminal reception unit 126.

[0032] The user inputs material data to be analyzed to the user terminal 12 that the user operates. The material data to be analyzed is material data for learning about materials, and is data that is used when identifying the user's preferred analysis processing in the server 14, which will be described later.

[0033] When the terminal control unit 120 receives the learning material data, it executes an analysis process on the learning material data in response to a user operation. The analysis process executed by the terminal control unit 120 is an analysis process selected and parameters adjusted by the user, and is an analysis process preferred by the user. The terminal control unit 120 temporarily stores the correct answer result data, which is the analysis process obtained by executing the analysis process on the learning material data, in the terminal storage unit 122. When multiple analysis processes are executed on one learning material data, a series of multiple analysis results obtained by the multiple analysis processes becomes the correct answer result data.

[0034] The terminal storage unit 122 stores the correct answer result data obtained by the terminal control unit 120.

[0035] The terminal transmitting unit 124 and the terminal receiving unit 126 exchange data with the server 14 .

[0036] In accordance with the control of the terminal control unit 120, the terminal transmission unit 124 transmits to the server 14 data representing a combination of the correct answer result data stored in the terminal memory unit 122, a user ID representing the identification information of the user terminal 12, and learning material data.

[0037] The above-mentioned processes executed in the user terminal 12 may be executed under the control of the server 14. For example, the server 14 may output a control signal to the user terminal 12 to cause a predetermined screen to be displayed on a display unit (not shown) of the user terminal 12, and the user may operate the user terminal 12 according to instructions displayed on the screen to execute various processes.

[0038] (server) As shown in FIG. 1, the server 14 includes a receiving unit 140, a processing program storage unit 141, a generating unit 142, an analysis processing identifying unit 144, a user information storage unit 145, an analyzing unit 146, and a transmitting unit 148.

[0039] The receiving unit 140 receives data transmitted from the user terminal 12, which represents a combination of the correct answer data, the user ID, and the learning material data.

[0040] The processing program storage unit 141 stores a processing program for executing each of a plurality of analysis processes. FIG. 4 shows an example of data stored in the processing program storage unit 141. In the example of FIG. 4, processing programs for each of the analysis processes of noise removal, background removal, and peak search are shown. For example, a plurality of noise removal programs 1, 2, ... are stored in the processing program storage unit 141 as a program for performing noise removal. Also, for example, a plurality of background removal programs 1, 2, ... are stored in the processing program storage unit 141 as a program for performing background removal. Also, for example, a plurality of peak search programs 1, 2, ... are stored in the processing program storage unit 141 as a program for performing peak search. Note that the processing program storage unit 141 also stores a program for performing other analysis processes. Each of these plurality of processing programs is also a module for obtaining an analysis result from material data. By executing these plurality of modules on material data, an analysis result is obtained.

[0041] The generating unit 142 executes a plurality of analysis processes on the learning material data received by the receiving unit 140, thereby generating result data for each of the plurality of analysis processes.

[0042] Specifically, when noise removal processing is required to obtain the analysis results of the learning material data, the generation unit 142 performs multiple noise removal processes on the learning material data, thereby generating result data for each of the multiple noise removal processes.

[0043] The analysis process identification unit 144 calculates the difference between each of the multiple result data generated by the generation unit 142 and the correct result data received by the receiving unit 140, and stores the identification information of the analysis process with the smallest difference in association with the user ID in the user information storage unit 145.

[0044] For example, for each of the multiple noise removal processing result data 1, 2, and 3 generated by the generation unit 142, the analysis processing identification unit 144 calculates the difference between the result data and the correct result data of the noise removal processing among the correct result data received by the reception unit 140. The result data 1 is the analysis result obtained by the noise removal program 1 stored in the processing program storage unit 141. The result data 2 is the analysis result obtained by the noise removal program 2 stored in the processing program storage unit 141. The result data 3 is the analysis result obtained by the noise removal program 3 stored in the processing program storage unit 141.

[0045] Then, the analysis processing specification unit 144 associates the identification information of the analysis processing with the smallest difference with the user ID and stores them in the user information storage unit 145. For example, if the result data with the smallest difference is result data 2, the identification information of the noise removal program 2 is associated with the user ID and stores them in the user information storage unit 145.

[0046] This identifies that the noise removal process that the user prefers to use is the one by the noise removal program 2. If it is necessary to set certain parameters when executing the noise removal program, for example, the parameters are changed and the difference is calculated, and parameters that minimize the difference are identified. In this case, the parameters are also stored in the user information storage unit 145. As the difference, for example, the difference between the numerical value represented by the correct result data and the numerical value represented by the result data is used.

[0047] In the user information storage unit 145, a user ID, identification information of the analysis process in which the difference is the smallest, and parameters of the processing program in which the difference is the smallest are stored in association with each other. FIG. 5 shows an example of data stored in the user information storage unit 145. In the example of FIG. 5, for example, for user ID "U00001", "noise removal program 2" as the processing program for noise removal processing and its parameters "P A " is stored in association with the user ID "U00001". For example, "background removal program 1" and its parameters are stored in association with the user ID "U00001" as a processing program for background removal processing. In this way, by storing the user ID in association with the identification information of the processing program that executes the analysis processing, the processing required for material analysis is set for each user. Therefore, from the next time onwards, when the user operates his / her user terminal 12 to transmit material data for analysis to the server 14, the server 14 will be able to analyze the material data using the analysis processing preferred by each user.

[0048] After the content of the analysis process preferred by the user is stored in the user information storage unit 145, the receiving unit 140 receives a combination of the user ID and material data for analysis of the material.

[0049] The analysis unit 146 identifies the identification information of the analysis process stored in the user information storage unit 145, which corresponds to the user ID received by the receiving unit 140. For example, when the user ID is "U00001", the analysis unit 146 refers to the user information storage unit 145 and identifies identification information such as "noise removal program 2" and "background removal program 1" as the identification information of the analysis process. The analysis unit 146 then reads out the processing program corresponding to the identified identification information from the processing program storage unit 141. At this time, if parameters are necessary for the processing program, the parameters are also read out from the user information storage unit 145.

[0050] Then, the analysis unit 146 executes an analysis process corresponding to the specified identification information on the material data for analysis. Specifically, the analysis unit 146 executes each processing program, such as the noise removal program 2 and the background removal program 1, on the material data for analysis to obtain an analysis result of the material data for analysis.

[0051] The transmitting unit 148 transmits the analysis results of the material data for analysis obtained by the analyzing unit 146 to the user terminal 12 .

[0052] In this way, the server 14 of the information processing system 10 of the first embodiment receives a combination of the user ID, the learning material data, and the correct answer result data for the learning material data transmitted from the user terminal 12, and executes various analysis processes on the learning material data. The server 14 then compares a plurality of analysis results obtained by executing various analysis processes on the learning material data with the correct answer result data, and stores identification information of the processing program that has output the analysis result in which the difference between the analysis result and the correct answer result data is the smallest, in association with the user ID, in the user information storage unit 145. This allows the processing required for material analysis to be set for each user.

[0053] The user terminal 12 and the server 14 can be realized by, for example, a computer 50 as shown in Fig. 6. The computer 50 realizing the user terminal 12 and the server 14 includes a CPU 51, a memory 52 as a temporary storage area, and a non-volatile storage unit 53. The computer also includes an input / output interface (I / F) 54 to which an input / output device or the like (not shown) is connected, and a read / write (R / W) unit 55 that controls reading and writing of data from and to a recording medium 59. The computer also includes a network I / F 56 that is connected to a network such as the Internet. The CPU 51, the memory 52, the storage unit 53, the input / output I / F 54, the R / W unit 55, and the network I / F 56 are connected to one another via a bus 57.

[0054] The storage unit 53 can be realized by a hard disk drive (HDD), a solid state drive (SSD), a flash memory, etc. The storage unit 53 as a storage medium stores a program for causing the computer to function. The CPU 51 reads the program from the storage unit 53, expands it in the memory 52, and sequentially executes the processes contained in the program.

[0055] Next, the operation of the information processing system 10 of the first embodiment will be described.

[0056] When learning material data is input to the user terminal 12, a predetermined analysis process is performed on the learning material data to obtain correct answer result data under the control of the terminal control unit 120. The terminal transmission unit 124 of the user terminal 12 transmits a combination of the learning material data, correct answer result data, and the user ID to the server 14. When the combination of the above data is transmitted from the user terminal 12 to the server 14, the server 14 executes the information processing routine shown in FIG.

[0057] In step S100, the receiving unit 140 of the server 14 receives a combination of study material data, correct answer data, and a user ID transmitted from the user terminal 12.

[0058] In step S102, the generation unit 142 executes a plurality of analysis processes on the learning material data received in step S100, thereby generating result data for each of the plurality of analysis processes.

[0059] In step S104, for each of the multiple pieces of result data generated in step S102, the analysis processing identification unit 144 calculates the difference between the result data and the correct answer data received in step S100.

[0060] In step S106, the analysis processing identifying unit 144 stores in the user information storage unit 145 the identification information of the analysis processing for which the difference calculated in step S104 is the smallest, in association with the user ID.

[0061] By executing the information processing routine shown in FIG. 7, a processing program for executing an analysis process of the preferences of the user operating the user terminal 12 is stored in the user information storage unit 145 together with the user ID.

[0062] Next, when the material data for analysis is input to the user terminal 12, the terminal transmission unit 124 of the user terminal 12 transmits the material data for analysis and the user ID to the server 14. When the combination of the above data is transmitted from the user terminal 12 to the server 14, the server 14 executes the information processing routine shown in FIG.

[0063] In step S200, the receiving unit 140 of the server 14 receives the material data for analysis and the user ID transmitted from the user terminal 12.

[0064] In step S202, the analysis unit 146 refers to the information stored in the user information storage unit 145 and identifies the identification information of the analysis process corresponding to the user ID received by the reception unit 140.

[0065] In step S204, the analysis unit 146 reads out from the processing program storage unit 141 a processing program corresponding to the identification information specified in step S202.

[0066] In step S206, the analysis unit 146 executes an analysis process on the material data for analysis using the processing program read in step S204. When multiple processing programs are read, each of the multiple processing programs is executed in a predetermined order to obtain an analysis result of the material data for analysis.

[0067] In step S208, the transmission unit 148 transmits the analysis result obtained in step S206 to the user terminal 12.

[0068] The user terminal 12 obtains the analysis results sent from the server 14. Then, the terminal control unit 120 of the user terminal 12 displays the analysis results on a display unit (not shown). The user operating the user terminal 12 checks the analysis results. The analysis results of the material data for analysis obtained by the server 14 are analysis results obtained by the analysis processing desired by the user. Therefore, the user can obtain analysis results obtained by the analysis processing that suits his or her preferences. By examining the analysis results,

[0069] As described above, the server of the information processing system 10 according to the first embodiment receives a combination of a user ID, learning material data related to materials, and correct result data obtained by executing a predetermined analysis process on the learning material data, transmitted from a user terminal. The server then executes multiple analysis processes on the received combination of learning material data to generate result data for each of the multiple analysis processes. For each of the multiple generated result data, the server calculates the difference between the result data and the correct result data, and associates the identification information of the analysis process with the smallest difference with the user ID and stores them in the user information storage unit. This allows the analysis process required for material analysis to be set for each user.

[0070] Furthermore, the server of the information processing system 10 according to the first embodiment receives a combination of a user ID and material data for analysis related to materials after an analysis process is set for each user. The server then identifies the identification information of the analysis process stored in the user information storage unit corresponding to the user ID, and executes the analysis process corresponding to the identified identification information on the material data for analysis. This allows the analysis process desired by the user to be executed on the material data for analysis. Furthermore, it is possible to automatically determine an analysis process that meets the needs of the user, and it is possible to achieve both customization of the analysis process and accuracy of the analysis process.

[0071] <Second embodiment> Next, a second embodiment will be described. The configuration of the information processing system according to the second embodiment is the same as that of the first embodiment, so the same reference numerals are used and the description is omitted. The server of the information processing system according to the second embodiment is different from that of the first embodiment in that each data is plotted in a latent space to customize the analysis process for each user.

[0072] In the first embodiment, the difference between each of the plurality of result data and the correct result data is calculated, and the analysis process is customized for each user. However, there are cases where the difference between the correct result data obtained by the analysis process preferred by the user and each of the result data obtained by the plurality of analysis processes cannot be simply compared by numerical value.

[0073] For example, in the pre-processing of material data, a case is considered in which noise, a signal, and a background contained in the material data are separated. In this case, it is difficult to numerically calculate the difference between the noise removed by an analysis process desired by a user and the noise removed by each of a plurality of analysis processes.

[0074] Therefore, the information processing system of the second embodiment projects the correct result data obtained by the analysis process preferred by the user and each of the result data obtained by the multiple analysis processes into a latent space, and calculates the difference between the correct result data and the result data in the latent space.

[0075] Specifically, the generation unit 142 of the server 14 in the second embodiment projects the supervised result data and the multiple result data transmitted from the user terminal 12 into the latent space. For the projection into the latent space, for example, a method such as UMAP (Uniform Manifold Approximation and Projection) or t-SNE can be used.

[0076] FIG. 9 is a diagram for explaining the processing of the generating unit 142 of the second embodiment. As shown in FIG. 9, for example, consider a case where there are processing programs that realize each of the methods (a), (b), etc. It should be noted that parameters can be set for each of the methods (a) and (b), and by setting the parameters, an analysis result according to the parameters can be obtained. For example, as shown in FIG. 9, the generating unit 142 sets a parameter (1) for the method (a), and then executes the processing program that realizes the method (a) on the material data, thereby separating the signal, background (denoted as BG in the figure), and noise from the material data.

[0077] Next, the generation unit 142 sets parameters (2) for the method (a) and executes a processing program that realizes the method (a) on the material data, thereby separating the signal, background, and noise from the material data.

[0078] In this way, the generation unit 142 realizes combinations of a plurality of methods and a plurality of parameters by processing programs, and generates a plurality of analysis results by executing the processing programs on the material data.

[0079] Fig. 10 shows a diagram for explaining data projected into a latent space. Each plot in Fig. 10 is a plot point when the result data obtained by multiple processing programs is projected into a latent space.

[0080] The plot points marked with stars in FIG. 10 are the data corresponding to the correct answer data. A represents the signal separated from the training data, and BG A represents the background separated from the training data, and NS A represents noise separated from the training data. SG A , B.G. A , N.S. A corresponds to the correct answer result data.

[0081] The white squares in Fig. 10 represent the signals SG separated from the learning material data by a processing program R. R , Background BG R , and noise NS R Shows.

[0082] Then, the analysis process identification unit 144 of the server 14 of the second embodiment calculates the difference between the correct result data in the latent space and the result data in the latent space, and stores the identification information of the analysis process with the smallest difference in association with the user ID in the user information storage unit 145.

[0083] In the example shown in FIG. 10, the signal SG R and the correct result data, signal SG A The distance between is the shortest. Furthermore, the background BG R And the correct answer data, background BG A The distance between is also the shortest. Also, the noise NS R and the correct answer data, noise NS A The distance between is also the shortest.

[0084] Therefore, in the example shown in FIG. 10, the analysis processing identifying unit 144 stores in the user information storage unit 145 the identification information of the processing program R corresponding to the analysis processing with the smallest difference in association with the user ID.

[0085] Other configurations and operations of the information processing system according to the second embodiment are similar to those of the first embodiment, and therefore will not be described.

[0086] As described above, the server of the information processing system 10 according to the second embodiment projects the correct answer result data and the result data into the latent space, calculates the difference between the correct answer result data in the latent space and the result data in the latent space, and stores the identification information of the analysis process with the smallest difference in association with the user ID in the user information storage unit. This makes it possible to evaluate the difference between the correct answer result data and the result data in the latent space even when it is difficult to numerically evaluate the difference between the correct answer result data and the result data.

[0087] In the above embodiment, the processes performed by each device have been described as software processes performed by executing a program, but they may be hardware processes. Alternatively, they may be a combination of both software and hardware processes. Furthermore, the programs stored in the ROM may be stored in various storage media and distributed.

[0088] Furthermore, the present invention is not limited to the above, and it goes without saying that various modifications can be made without departing from the spirit and scope of the present invention.

[0089] For example, the information processing system of the second embodiment is described above with reference to an example in which the correct answer result data and the result data are projected into the latent space, and the difference between the correct answer result data in the latent space and the result data in the latent space is calculated, but the present invention is not limited to this. For example, an analysis process that meets a preset condition may be associated with a user ID to identify the analysis process used by the user. For example, as shown in FIG. 11, an analysis process that generates plot points within an area surrounded by the plot points of the signal SG1, background BG1, and noise NS1 obtained by a certain analysis process A (parameter is param2) may be identified as the analysis process used by the user. In the example of FIG. 11, for example, the plot point marked with an x ​​exists outside the area surrounded by the plot points of the signal SG1, background BG1, and noise NS1, so the analysis process that generates the plot point marked with an x ​​is not the analysis process used by the user. Therefore, for example, in the example of Figure 11, the analysis process that generated the plot points SG2, BG2, and noise NS2 that exist in the area surrounded by the plot points of the signal SG1, background BG1, and noise NS1 is identified as the analysis process used by the user. [Explanation of symbols]

[0090] 10. Information Processing Systems 12 User terminal 14 Server 50 Computer 120 Terminal control unit 122 Terminal memory section 124 Terminal transmitter 126 Terminal receiving section 140 Receiving unit 141 Processing program storage unit 142 Generation part 144 Analysis and Processing Specific Unit 145 User information storage unit 146 Analysis Department 148 Transmitter

Claims

1. a receiving unit that receives a combination of a user ID, learning material data related to a material, and correct answer result data obtained by executing a predetermined analysis process on the learning material data, all of which are transmitted from a user terminal; a generation unit that generates result data for each of the plurality of analysis processes by executing a plurality of analysis processes on the combination of the learning material data received by the receiving unit; an analysis processing specification unit that calculates a difference between each of the plurality of result data generated by the generation unit and the correct answer result data, and stores in a storage unit an identification information of an analysis processing in which the difference is smallest in association with the user ID; An information processing device comprising:

2. The generation unit projects the correct answer data and the result data into a latent space, The analysis processing identification unit calculates a difference between the correct answer result data in the latent space and the result data in the latent space, and stores in a storage unit an identification information of the analysis processing in which the difference is smallest in association with the user ID. The information processing device according to claim 1 .

3. The receiving unit receives a combination of the user ID and material data for analysis related to a material, and an analysis unit that identifies identification information of an analysis process stored in the storage unit and that corresponds to the user ID, and executes the analysis process corresponding to the identified identification information on the material data for analysis.

3. The information processing device according to claim 1 or 2.

4. receiving a combination of a user ID, learning material data related to a material, and correct answer result data obtained by executing a predetermined analysis process on the learning material data, the combination being transmitted from the user terminal; executing a plurality of analysis processes on the received combination of learning material data to generate result data for each of the plurality of analysis processes; For each of the generated plurality of pieces of result data, a difference between the result data and the correct answer data is calculated, and identification information of an analysis process in which the difference is smallest is associated with the user ID and stored in a storage unit. An information processing method in which processing is performed by a computer.

5. receiving a combination of a user ID, learning material data related to a material, and correct answer result data obtained by executing a predetermined analysis process on the learning material data, the combination being transmitted from the user terminal; executing a plurality of analysis processes on the received combination of learning material data to generate result data for each of the plurality of analysis processes; For each of the generated plurality of pieces of result data, a difference between the result data and the correct answer data is calculated, and identification information of an analysis process in which the difference is smallest is associated with the user ID and stored in a storage unit. An information processing program for causing a computer to execute processing.

Images