Analysis system and analysis method

Abstract

To provide an analysis system and method that allows users to easily verify measurement data of a simulated sample and a sample similar to it. [Solution] The analysis system 1 according to this disclosure comprises an actual score acquisition unit 111, a simulated score acquisition unit 112, a similarity evaluation unit 113, and a presentation unit 114. The actual score acquisition unit 111 acquires the characteristic quantities of measurement data obtained by actually measuring a sample as an actual score. The simulated score acquisition unit 112 acquires the characteristic quantities of a simulated sample defined by the user as a simulated score. The similarity evaluation unit 113 evaluates the similarity between multiple actual scores and the simulated score. The presentation unit 114 presents the sample having the actual score with the highest similarity to the simulated score.

Description

Technical Field

[0001] The present disclosure relates to an analysis system and an analysis method.

Background Art

[0002] In Patent Document 1, by applying principal component analysis, two-dimensional map data is generated in which each of a plurality of spectral data is projected into two dimensions as each of a plurality of plot points, and unknown data representing a plot point different from the plot points already existing on the two-dimensional map data is identified, and an information processing apparatus that executes an operation of converting the unknown data into spectral data is described.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] By the way, when a user defines unknown data as in the technique described in Patent Document 1, it may be necessary to check the spectral data of a sample similar to the defined unknown data. In other words, when a user defines a simulated sample, it may be necessary to check the measurement data of a sample similar to the simulated sample.

[0005] However, it is difficult to find a sample similar to a simulated sample from a plurality of samples, and the user may feel bothered when checking. Patent Document 1 does not disclose a technique capable of solving such a problem.

[0006] The present disclosure has been made to solve such problems, and an object thereof is to provide an analysis system and an analysis method that enable a user to easily check a sample similar to a simulated sample. [Means for solving the problem]

[0007] The analysis system described herein comprises a measured score acquisition unit, a simulated score acquisition unit, a similarity evaluation unit, and a presentation unit. The measured score acquisition unit acquires the characteristic quantities of measurement data obtained by actually measuring a sample as the measured score. The simulated score acquisition unit acquires the characteristic quantities of a simulated sample defined by the user as the simulated score. The similarity evaluation unit evaluates the similarity between multiple measured scores and the simulated score. The presentation unit presents the sample having the measured score with the highest similarity to the simulated score.

[0008] The analysis system relating to this disclosure may further include a simulated data output unit that simulates measurement data of a simulated sample based on a simulated score and outputs it as simulated data. The display unit may also display the measurement data of the sample with the highest similarity to the simulated score, along with the simulated data, in parallel.

[0009] In the analysis system relating to this disclosure, the feature quantities may be principal component scores obtained as a result of principal component analysis of multiple measurement data.

[0010] In the analysis system relating to this disclosure, the similarity evaluation unit may determine whether a simulated score corresponds to an outlier in a data set consisting of multiple measured scores obtained. Furthermore, if the similarity evaluation unit determines that the simulated score corresponds to an outlier, the presentation unit may choose not to present the sample.

[0011] The analysis method relating to this disclosure comprises the following steps. The characteristic features of the measurement data obtained from the sample are acquired as the measured score. The features of the simulated samples defined by the user are obtained as a simulated score. The similarity between multiple measured scores and simulated scores is evaluated. We present the sample with the most similar measured score to the simulated score. [Effects of the Invention]

[0012] This disclosure provides an analysis system and method that allows users to easily verify samples similar to simulated samples. [Brief explanation of the drawing]

[0013] [Figure 1] This is a block diagram showing the configuration of the analysis system according to the first embodiment. [Figure 2] This is a block diagram showing the server configuration according to the first embodiment. [Figure 3] This is a block diagram showing the server configuration according to the first embodiment. [Figure 4] This is a schematic screen diagram illustrating the server configuration according to the first embodiment. [Figure 5] This is a schematic screen diagram illustrating the server configuration according to the first embodiment. [Figure 6] This is a flowchart illustrating the operation of the analysis system according to the first embodiment. [Modes for carrying out the invention]

[0014] <First Embodiment> (Configuration of the display control system) Hereinafter, a first embodiment of the present disclosure will be described in detail with reference to the drawings. First, the configuration of the display control system according to this embodiment will be described in detail.

[0015] Figure 1 is a block diagram showing the configuration of the analysis system according to the first embodiment. As shown in Figure 1, the analysis system 1 according to this embodiment has a server 100 and a user terminal 200 connected via a network N such as the Internet.

[0016] The analysis system 1 is a system for analyzing measurement data obtained by actually measuring a sample. The analysis system 1 according to this embodiment is typically provided as part of a data cloud type service used in material development and research and development, and is used as a system for promoting research and development using so-called materials informatics (MI) and data science.

[0017] In the analysis system 1, the user terminal 200 transmits measurement data to the server 100, and the server 100 analyzes the received measurement data. Then, the server 100 transmits the analysis result to the user terminal 200, and the user terminal 200 displays the received analysis result.

[0018] Examples of the measurement data analyzed by the analysis system 1 include spectrum data, waveform data, graph data, secondary image data, three-dimensional image data, and the like. Examples of the spectrum data include spectrum data measured using nuclear magnetic resonance spectroscopy (NMR), infrared spectroscopy (IR), ultraviolet-visible spectroscopy (UV-vis), X-ray absorption spectroscopy (XAS), Raman spectroscopy, X-ray diffraction (XRD), small angle X-ray scattering (SAXS), mass spectrometry (MS), and the like. Furthermore, examples of two-dimensional image data include image data acquired using optical microscopes, scanning electron microscopes (SEM), transmission electron microscopes (TEM), and computed tomography (CT). Furthermore, examples of 3D image data include imaging data created by stacking tomographic images taken by computed tomography (CT), and model data created using CAD (Computer-Aided Design), etc. Wave-related data can include, for example, time-series data and displacement data. Time-series data can include, for example, acoustic data and vibration data, but any data in which the numerical value changes with time can be used. Displacement data can include, for example, the surface height and surface profile of a sample, but any data in which the numerical value changes with changes in coordinates and other parameters can be used. Other data sources include, for example, cyclic voltammograms and gas chromatography (GC) charts. Furthermore, measurement data can also include, for example, coordinate data such as CIF (Crystallographic Information) files, or numerical data such as ingredient lists of compositions.

[0019] The user terminal 200 according to this embodiment is a terminal operated by a user, and is typically a computer device having a display device. The user terminal 200 transmits measurement data to the server 100 via the network N. The user terminal 200 then receives the analysis results of the measurement data from the server 100 via the network N.

[0020] In this embodiment, the server 100 receives measurement data from the user terminal 200 and analyzes the received measurement data. The server 100 then transmits the analysis results to the user terminal 200 via the network N.

[0021] Figure 2 is a block diagram showing the hardware configuration of the server according to the first embodiment. As shown in Figure 2, the server 100 includes a processor 110, memory 120, storage device 130, input / output interface 140, network interface 150, and internal bus 160.

[0022] The internal bus 160 is a data transmission path for the processor 110, memory 120, storage device 130, input / output interface 140, and network interface 150 to send and receive data to and from each other. However, the method of connecting the processor 110 and the other components to each other is not limited to bus connection.

[0023] Memory 120 is the main memory, implemented using RAM (Random Access Memory), etc. Furthermore, the storage device 130 is an auxiliary storage device implemented using a hard disk, SSD (Solid State Drive), memory card, or ROM (Read Only Memory), etc. The storage device 130 stores a program for realizing a desired function.

[0024] The processor 110 is a variety of processor, such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or an FPGA (field-programmable gate array). The processor 110 reads the program stored in the storage device 130 into the memory 120 and executes it, thereby performing the functions of each functional block as shown in Figures 3 and 4, which will be described later.

[0025] The input / output interface 140 is an interface for connecting the server 100 with input / output devices. For example, input devices such as keyboards and output devices such as display devices may be connected to the input / output interface 140. The network interface 150 is an interface for connecting the server 100 to the network.

[0026] The program, when loaded into a computer, includes a set of instructions (or software code) for causing the computer to perform one or more of the functions described in the embodiments. The program may be stored in a non-temporary computer-readable medium or a physical storage medium. Examples, but not limited to, include RAM, ROM, flash memory, SSD or other memory technologies, CD-ROM, DVD (digital versatile disc), Blu-ray® disc or other optical disc storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices. The program may be transmitted over a temporary computer-readable medium or a communication medium. Examples, but not limited to, include, a temporary computer-readable medium or a communication medium that includes electrically, optically, acoustically, or otherwise propagating signals.

[0027] Figure 3 is a block diagram showing the functions of the server 100 according to the first embodiment. As shown in Figure 3, the server 100 according to this embodiment includes a measured score acquisition unit 111, a simulated score acquisition unit 112, a similarity evaluation unit 113, a presentation unit 114, and a simulated data output unit 115 as functional blocks.

[0028] The measured score acquisition unit 111 acquires the feature quantities of the measurement data obtained from the sample as the measured score. The measured score acquisition unit 111 outputs the acquired measured score to the similarity evaluation unit 113.

[0029] For example, the measured score acquisition unit 111 in this embodiment may acquire measured scores by performing principal component analysis (PCA) on multiple measurement data. In other words, in this embodiment, the feature quantities may be principal component scores obtained as a result of performing principal component analysis on multiple measurement data.

[0030] Therefore, the measured score acquisition unit 111 according to this embodiment outputs multiple principal component scores to the similarity evaluation unit 113. In addition, the measured score acquisition unit 111 according to this embodiment outputs the principal components obtained as a result of principal component analysis to the simulated data output unit 115.

[0031] However, the configuration of the measured score acquisition unit 111 relating to this disclosure is not limited to the above. For example, the measured score acquisition unit 111 does not need to extract features from the measurement data. In this case, the measured score acquisition unit 111 may acquire features that have been previously recorded in association with the measurement data. In other words, the measured score acquisition unit 111 may acquire the measured score from a database that records the measurement data and features in association. Furthermore, the measured score acquired by the measured score acquisition unit 111 is not limited to the principal components. Any feature can be used as the measured score, as long as it is a feature extracted by a known analysis method.

[0032] The simulated score acquisition unit 112 acquires the feature quantities of the simulated sample defined by the user as a simulated score. The simulated score acquisition unit 112 outputs the acquired simulated score to the similarity evaluation unit 113 and the simulated data output unit 115.

[0033] In this context, a simulated sample refers to a virtual sample defined by the user setting the features. The simulated sample does not need to be strictly defined in every detail; it is sufficient that at least the features used as the simulated score are defined. Alternatively, a simulated sample may be defined by the simulated score acquisition unit 112 acquiring a simulated score.

[0034] The simulated score acquisition unit 112 acquires the same type of feature quantities as the measured score as the simulated score. Therefore, in this embodiment, the principal component score defined by the user is acquired as the simulated score.

[0035] In this embodiment, the simulated score acquisition unit 112 acquires a simulated score by receiving feature quantities of a simulated sample from the user. More specifically, in this embodiment, the simulated score acquisition unit 112 controls the user terminal 200 to display a control screen on the user terminal 200 for receiving the simulated score.

[0036] Figure 4 is a schematic screen diagram illustrating the configuration of the simulated score acquisition unit 112 according to the first embodiment. More specifically, Figure 4 is an example of a control screen that the simulated score acquisition unit 112 displays on the user terminal 200 in order to receive the simulated score.

[0037] As shown in Figure 4, the simulated score acquisition unit 112 may display a control screen P1 on the user terminal 200 that shows the feature identification image P11, the feature magnitude bar P12, and the feature value P13 side by side.

[0038] The feature identification image P11 is an image assigned to the user for identifying features, and typically displays the feature name as text. For example, as shown in Figure 4, the identification image P11 according to this embodiment is a text image inscribed with "PC1", "PC2", and "PC3", which are names representing the first principal component, the second principal component, and the third principal component, respectively.

[0039] Bar P12 visually represents the magnitude of the feature corresponding to the adjacent identified image P11. Here, bar P2 is configured so that the size of the feature can be changed by dragging it by the user.

[0040] The feature value P13 indicates the feature value corresponding to the adjacent identified image P11 and bar P12. If the size of the feature is changed by dragging bar P12, the value P13 will display the size of the changed feature. Furthermore, the value P13 may be configured to allow the user to input a specific numerical value. In this case, the simulated score acquisition unit 112 changes the display of bar P12 according to the specific numerical value entered for value P13.

[0041] The simulated score acquisition unit 112 according to this embodiment displays a control screen as shown in Figure 4 on the user terminal 200 and receives a simulated score from the user by having the user operate the control screen. More specifically, the simulated score acquisition unit 112 allows the user to manipulate at least one of the bar P12 and the value P13. The simulated score acquisition unit 112 accepts the value of the feature changed by manipulating at least one of the bar P12 and the value P13 as a simulated score.

[0042] The simulated data output unit 115 acquires a simulated score from the simulated score acquisition unit 112. Based on the simulated score, the simulated data output unit 115 simulates the measurement data of the simulated sample and outputs it as simulated data.

[0043] For example, the simulated data output unit 115 according to this embodiment may acquire principal components from the measured score acquisition unit 111 and acquire principal component scores defined by the user as simulated scores from the simulated score acquisition unit 112. Then, simulated data may be output based on the acquired principal components and the simulated scores.

[0044] JPEG2026122618000002.jpg40166

[0045] The similarity evaluation unit 113 obtains multiple measured scores from the measured score acquisition unit 111 and a simulated score from the simulated score acquisition unit 112. The similarity evaluation unit 113 evaluates the similarity between the multiple measured scores and the simulated score. The similarity evaluation unit 113 outputs the evaluation result of the similarity between the multiple measured scores and the simulated score to the presentation unit 114.

[0046] The method used by the similarity evaluation unit 113 to evaluate similarity is not particularly limited, but may be, for example, an evaluation method using a distance function or an evaluation method using a similarity function. Furthermore, the similarity evaluation unit 113 may, for example, use artificial intelligence to evaluate similarity. Furthermore, the method for evaluating similarity may be appropriately selected depending on the features being evaluated, or it may be appropriately selected by the user. In other words, the similarity evaluation unit 113 may use any method to perform the similarity evaluation, as long as it is a method that can appropriately evaluate the similarity between the measured score and the simulated score.

[0047] Furthermore, the similarity evaluation unit 113 according to this embodiment determines whether the simulated score is an outlier in the data set consisting of multiple acquired measured scores. If the similarity evaluation unit 113 determines that the simulated score is an outlier, it notifies the presentation unit 114 accordingly. The method used to determine whether a simulated score is an outlier is not particularly limited, but for example, it may be a determination method using the Isolation Forest method, a determination method using the LOF (Local Outlier Factor) method, or a determination method using the OCSVM (One Class Support Vector Machine) method. The similarity evaluation unit 113 may, for example, use artificial intelligence to determine whether a simulated score is an outlier. Furthermore, the method for determining whether a simulated score is an outlier may be appropriately selected depending on the feature being evaluated, or it may be appropriately selected by the user. In other words, the similarity evaluation unit 113 may use any method to perform the similarity evaluation, as long as it is a method that can appropriately evaluate the similarity between the measured score and the simulated score.

[0048] The presentation unit 114 obtains the similarity evaluation results between multiple measured scores and simulated scores from the similarity evaluation unit 113. The presentation unit 114 then presents the sample with the measured score that has the highest similarity to the simulated score. With this configuration, the analysis system 1 according to this embodiment allows the user to easily confirm measurement data similar to simulated data.

[0049] More specifically, the display unit 114 according to this embodiment presents the sample having the most similar measured score to the simulated score by displaying the corresponding measurement data. However, the configuration of the presentation unit 114 relating to this disclosure is not limited thereto; for example, it may be configured to present sample identification information to the user. In other words, the presentation unit 114 relating to this disclosure may have any configuration as long as it can present the sample that is most similar to the simulated score.

[0050] Furthermore, the display unit 114 according to this embodiment acquires simulated data from the simulated data output unit 115. The display unit 114 according to this embodiment then displays the measurement data of the sample having the highest similarity to the simulated score, and the simulated data, side by side.

[0051] Figure 5 is a schematic screen diagram illustrating the configuration of the presentation unit 114 according to the first embodiment. More specifically, Figure 5 is an example of a control screen that the presentation unit 114 displays on the user terminal 200 to present a sample having the measured score that is most similar to the simulated score.

[0052] As shown in Figure 5, the display unit 114 may display a control screen P2 on the user terminal 200, which displays a simulated data display area P21 for displaying simulated data and a measurement data display area P22 for displaying measurement data side by side. Furthermore, as shown in Figure 5, the display unit 114 may display the control screen P2 adjacent to the aforementioned control screen P1.

[0053] In other words, the server 100 displays, side by side, a control screen P1 for receiving simulated scores from the user, a simulated data display area P21 for displaying simulated data output based on the received simulated scores, and a measurement data display area P22 for displaying measurement data of a sample with an actual measurement score that is most similar to the simulated score.

[0054] Note that the arrangement of the control screen P1, simulated data display area P21, and measurement data display area P22 on the screen is not limited to the arrangement shown in Figure 5, and may be set as appropriate considering design and other factors. For example, the server 100 according to this disclosure may be configured such that the control screen P1 and the simulated data display area P21 are arranged horizontally, and the simulated data display area P21 and the measurement data display area P22 are arranged vertically. Furthermore, the server 100 relating to this disclosure may be configured such that the control screen P1 and the simulated data display area P21 are arranged horizontally, and the measurement data display area P22 is displayed in a separate window.

[0055] By arranging the control screen P1 and the simulated data display area P21 side by side, the analysis system 1 according to this embodiment allows the user to intuitively understand the influence that the features have on the measured data. Furthermore, by arranging the simulated data display area P21 and the measurement data display area P22 side by side, the analysis system 1 according to this embodiment allows the user to easily determine the validity of the simulated data. Furthermore, by arranging the control screen P1 and the measurement data display area P22 side by side, the analysis system 1 according to this embodiment allows the user to easily grasp measurement data that has the characteristics desired by the user.

[0056] In this embodiment, the presentation unit 114 may choose not to present a sample if the similarity evaluation unit 113 determines that the simulated score is an outlier. In this case, the presentation unit 114 may also notify the user that the simulated score is an outlier. With this configuration, the analysis system 1 according to this embodiment allows the user to easily determine the validity of the simulated data.

[0057] As described above, the analysis system according to this embodiment evaluates the similarity between multiple measured scores and simulated scores, and presents the sample having the measured score with the highest similarity to the simulated score. With this configuration, the analysis system according to this embodiment allows the user to easily verify measurement data that is similar to simulated data.

[0058] (Operation of the analysis system) Next, the operation of the analysis system, that is, the analysis method according to the first embodiment, will be described in detail. Figure 6 is a flowchart showing the operation of the analysis system according to the first embodiment. In the following description, Figures 1 to 5 will be referred to as appropriate.

[0059] In the processing procedure shown in Figure 6, the processor 110 of the server 100 functions as a measured score acquisition unit 111, a simulated score acquisition unit 112, a similarity evaluation unit 113, a presentation unit 114, and a simulated data output unit 115 by reading the program stored in the storage device 130 into the memory 120 and executing it.

[0060] In the analysis method according to this embodiment, first, the processor 110 acquires an actual measured score (step ST1). More specifically, in step ST1, the processor 110 according to this embodiment acquires the characteristic quantities of the measurement data obtained by actually measuring the sample as an actual measured score. In other words, in step ST1, the processor 110 functions as an actual measured score acquisition unit 111.

[0061] Step ST1 may also be a step in which the processor 110 obtains an actual score by extracting features from multiple measurement data. Alternatively, step ST1 may be a step in which the processor 110 obtains an actual score from a database stored in a storage device 130 or the like. Furthermore, step ST1 may be a step that is performed after step ST3.

[0062] In the analysis method according to this embodiment, the processor 110 then acquires a simulated score (step ST2). More specifically, in step ST2, the processor 110 according to this embodiment acquires the feature quantities of a simulated sample defined by the user as a simulated score. In other words, in step ST2, the processor 110 functions as a simulated score acquisition unit 112.

[0063] In the analysis method according to this embodiment, the processor 110 then outputs simulated data (step ST3). More specifically, in step ST3, the processor 110 according to this embodiment simulates the measurement data of a simulated sample based on the simulated score and outputs it as simulated data. In other words, in step ST3, the processor 110 functions as a simulated data output unit 115. In step ST3, the processor 110 may present the outputted simulated data to the user. In other words, in step ST3, the processor 110 may display the simulated data on the user terminal 200.

[0064] In the analysis method of this implementation, the processor 110 then evaluates the similarity between the measured score and the simulated score (step ST4). In other words, in step ST4, the processor 110 functions as a similarity evaluation unit 113.

[0065] In the analysis method according to this embodiment, the processor 110 then determines whether the simulated score is an outlier (step ST5). More specifically, in step ST5, the processor 110 according to this embodiment determines whether the simulated score is an outlier in the data set consisting of a plurality of acquired actual scores. In other words, in step ST5, the processor 110 functions as a similarity evaluation unit 113.

[0066] If the simulated score does not fall under the category of an outlier (step ST5 NO), the processor 110 presents a sample with an actual score that is most similar to the simulated score (step ST6), and the analysis system 1 terminates its series of operations. With this configuration, the analysis system 1 according to this embodiment allows the user to easily confirm measurement data similar to simulated data.

[0067] If the simulated score is an outlier (step ST5 YES), the analysis system 1 terminates its series of operations. In other words, if the simulated score is an outlier, the processor 110 does not present a sample with an actual score that is most similar to the simulated score. With this configuration, the analysis system 1 according to this embodiment allows the user to easily determine the validity of the simulated data.

[0068] As described above, in the analysis method according to this embodiment, the similarity between multiple measured scores and simulated scores is evaluated, and the sample having the measured score with the highest similarity to the simulated score is presented. With this configuration, the analysis method according to this embodiment allows the user to easily confirm measurement data that is similar to simulated data.

[0069] Although the present invention has been described above in reference to the embodiments described above, the present invention is not limited to the configuration of the embodiments described above, and of course includes various modifications, alterations, and combinations that can be made by a person skilled in the art within the scope of the claims of the present patent application. [Explanation of Symbols]

[0070] 1. Analysis System 100 servers 200 user terminals 110 processors 120 memory 130 Storage Devices 140 Input / Output Interfaces 150 network interfaces 160 Internal Bus 111 Actual Score Acquisition Unit 112. Simulation Score Acquisition Section 113 Similarity Evaluation Unit 114 Presentation section 115 Simulated Data Output Unit

Claims

1. An actual measurement score acquisition unit that obtains the characteristic quantities of the measurement data obtained by actually measuring the sample as an actual measurement score, A simulated score acquisition unit that obtains the features of a simulated sample defined by the user as a simulated score, A similarity evaluation unit that evaluates the similarity between a plurality of the measured scores and the simulated scores, The system includes a display unit that presents the sample having the measured score that is most similar to the simulated score, Analysis system.

2. The system further includes a simulated data output unit that simulates the measurement data of the simulated sample based on the simulated score and outputs it as simulated data. The display unit displays the measurement data of the sample having the most similar measured score to the simulated score, and the simulated data in parallel. The analysis system according to claim 1.

3. The aforementioned feature is the principal component score obtained as a result of principal component analysis of multiple measurement data. The analysis system according to claim 1 or 2.

4. The similarity evaluation unit determines whether the simulated score corresponds to an outlier in the data set consisting of the multiple measured scores obtained. If the similarity evaluation unit determines that the simulated score is an outlier, the presentation unit will not present the sample. The analysis system according to claim 1 or 2.

5. The features of the measurement data obtained from the sample are acquired as the measured score. The features of the simulated samples defined by the user are obtained as a simulated score. The similarity between multiple measured scores and the simulated scores is evaluated. The sample having the measured score that is most similar to the simulated score is presented. Analysis method.

Images