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

Abstract

To provide an information processing apparatus, an information processing method, and an information processing program that facilitate interpreting a result of principal component analysis on measurement data of a material.SOLUTION: A server 14 acquires multiple pieces of measurement data and executes principal component analysis on the acquired measurement data, to generate principal components of the multiple pieces of measurement data and principal component values of the multiple pieces of measurement data. In displaying the generated principal component values of the multiple pieces of measurement data on a display screen, the server 14 displays images representing the principal components of the measurement data, in a row obliquely to a horizontal direction or a vertical direction on the display surface. The server 14 displays a graph in which the principal component values of the measurement data are plotted, in a position representing an intersection of a line extending in the virtual direction from a first image and a line extending in the horizontal direction from a second image, for each of pairs of the first image and the second image, out of images representing the principal components of the measurement data.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] Patent Document 1 discloses a data analysis system that improves the analytical accuracy of measurement data while suppressing variations in the analytical results of the measurement data. This data analysis system acquires measurement data obtained by analyzing a material, processes the measurement data using a trained machine learning model, and outputs the analytical results of the measurement data. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-092467 Summary of the Invention [Problem to be solved by the invention]

[0004] Principal component analysis is known as an example of an analytical method for measurement data. When principal component analysis is performed on a plurality of measurement data, a user can interpret the trends, meanings, etc. of the plurality of measurement data by checking the results of the principal component analysis.

[0005] The data analysis system disclosed in Patent Document 1 processes measurement data using a trained machine learning model and outputs the analysis results of the measurement data. However, the data analysis system disclosed in Patent Document 1 is not a technology for facilitating the interpretation of the results of principal component analysis.

[0006] An object of the present disclosure is to provide an information processing device, an information processing method, and an information processing program that can facilitate interpretation of the results of principal component analysis of measurement data of materials. [Means for solving the problem]

[0007] An information processing device according to a first aspect includes an acquisition unit that acquires multiple pieces of measurement data; an analysis unit that performs principal component analysis on the multiple pieces of measurement data acquired by the acquisition unit to generate principal components of the multiple pieces of measurement data and principal component values ​​for each piece of measurement data; and an output unit that, when displaying the principal component values ​​of the multiple pieces of measurement data generated by the analysis unit on a display screen, displays each of the images representing the principal components of the multiple pieces of measurement data diagonally arranged with respect to the horizontal or vertical direction of the display screen, and for each pair of a first image and a second image among the images representing the principal components of the multiple pieces of measurement data, displays a graph with axes representing the principal components represented by the first image and the principal components represented by the second image, and plots the principal component values ​​of the multiple pieces of measurement data at a position representing the intersection of a line extending vertically from the first image and a line extending horizontally from the second image. The information processing device according to the first aspect facilitates interpretation of the results of principal component analysis of material measurement data. The principal component values ​​of the multiple pieces of measurement data obtained by performing principal component analysis can be used, for example, as input data for a machine learning model.

[0008] When the output unit of the information processing device according to the second aspect receives a user operation indicating that one of the plurality of graphs is to be designated, the output unit enlarges and displays the graph designated by the user. According to the information processing device according to the second aspect, it is possible to enlarge and display only the graph desired by the user from the graphs displayed in a list.

[0009] When the output unit of the information processing device according to the third aspect receives a user operation for switching the display of the enlarged graph, the output unit switches the enlarged graph to another graph. According to the information processing device according to the third aspect, a user can easily switch from one graph to another.

[0010] The output unit of the information processing device according to the fourth aspect displays the plotted points in the enlarged graph in a color according to a numerical value related to the measurement data represented by the plotted points. According to the information processing device according to the fourth aspect, for example, by coloring the plotted points according to the performance of the material represented by the plotted points, a user can intuitively understand which main component is related to the performance of the material.

[0011] The output unit of the information processing device according to the fifth aspect changes the horizontal axis or vertical axis of the enlarged graph and switches to another graph, thereby causing the plot points in the graph to appear to be moving continuously. The information processing device according to the fifth aspect can give the user the impression that they are viewing the same thing from different perspectives.

[0012] An information processing method according to a sixth aspect is an information processing method executed by a computer, which acquires a plurality of measurement data, performs principal component analysis on the acquired plurality of measurement data to generate principal components of the plurality of measurement data and principal component values ​​for each of the plurality of measurement data, and displays the generated principal component values ​​of the plurality of measurement data on a display screen by displaying images representing the principal components of the plurality of measurement data diagonally side by side with respect to the horizontal or vertical direction of the display screen, and for each pair of first and second images among the images representing the principal components of the plurality of measurement data, display a graph with axes representing the principal components represented by the first image and the principal components represented by the second image, and plotting the principal component values ​​of the plurality of measurement data at a position representing the intersection of a line extending vertically from the first image and a line extending horizontally from the second image.The information processing method according to the sixth aspect makes it possible to easily interpret the results of principal component analysis of material measurement data.

[0013] A seventh aspect of the present invention provides an information processing program for causing a computer to execute a process of acquiring a plurality of measurement data, performing principal component analysis on the acquired plurality of measurement data to generate principal components of the plurality of measurement data and principal component values ​​of the plurality of measurement data, and displaying the generated principal component values ​​of each of the plurality of measurement data on a display screen, by displaying images representing the principal components of the plurality of measurement data diagonally side by side with respect to a horizontal or vertical direction on the display screen, and for each pair of a first image and a second image among the images representing the principal components of the plurality of measurement data, displaying a graph with axes representing the principal components represented by the first image and the principal components represented by the second image, and plotting the principal component values ​​of the plurality of measurement data, at a position representing an intersection of a line extending vertically from the first image and a line extending horizontally from the second image. The information processing program of the seventh aspect of the present invention facilitates interpretation of the results of principal component analysis of material measurement data. [Effects of the Invention]

[0014] As described above, the present disclosure has the effect of making it easier to interpret the results of principal component analysis of material measurement data. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a block diagram illustrating an example of a functional configuration of an information processing system according to an embodiment. [Figure 2] FIG. 10 is a diagram for explaining a method for displaying principal component values ​​of a plurality of spectral data. [Figure 3] FIG. 10 is a diagram for explaining a method for displaying principal component values ​​of a plurality of spectral data. [Figure 4] FIG. 10 is a diagram for explaining a method for displaying principal component values ​​of a plurality of spectral data. [Figure 5] FIG. 2 is a diagram illustrating an example of the configuration of a server and a computer of a user terminal according to the embodiment. [Figure 6]10 is a flowchart illustrating an example of processing performed by a server according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

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

[0017] Fig. 1 is a block diagram showing an example of the functional configuration of an information processing system 10 according to an embodiment. As shown in Fig. 1, the information processing system 10 includes a user terminal 12 and a server 14, which is an example of an information processing device. The user terminal 12 and the server 14 are connected to each other so as to be able to communicate with each other via a network 16 such as the Internet.

[0018] (user terminal) The user terminal 12 is operated by a user. Functionally, the user terminal 12 includes a control unit 120 and a display unit 122, as shown in FIG.

[0019] The control unit 120 controls the operation of the user terminal 12. The display unit 122 displays various types of information in accordance with the control of the control unit 120.

[0020] (server) As shown in FIG. 1, the server 14 functionally includes an acquisition unit 140, a data storage unit 141, an analysis unit 142, and an output unit 144.

[0021] The acquisition unit 140 acquires a data set representing a combination of material measurement data and material performance data transmitted from the user terminal 12. Material measurement data is data obtained by performing some kind of measurement on the target material. For example, spectral data is an example of measurement data. In this embodiment, a case will be described where the material measurement data is spectral data. Furthermore, material performance data is data representing the performance of the material, such as the mechanical strength, surface reflectance, or transparency of the material. The acquisition unit 140 stores the data set in the data storage unit 141.

[0022] Data sets are stored in the data storage unit 141. For example, one data set stores spectrum data, which is an example of measurement data, and mechanical strength, which is an example of performance data, in association with each other.

[0023] The analysis unit 142 reads a data set from the data storage unit 141 and performs principal component analysis on a plurality of spectral data in the data set to generate principal components of the plurality of spectral data and principal component values ​​for each of the plurality of spectral data. The analysis unit 142 also converts each of the plurality of spectral data into vector data and performs principal component analysis on each of the vector data.

[0024] The principal components of the multiple spectral data are principal component axes obtained by principal component analysis. The principal component values ​​of each of the multiple spectral data are projected onto a graph formed by the principal component axes, thereby generating a scatter plot of the principal component values ​​of each of the multiple spectral data.

[0025] Then, the analysis unit 142 stores the principal component values ​​for each of the plurality of spectral data in the data storage unit 141. For example, a plurality of principal component values ​​are associated with one spectral data and stored in the data storage unit 141. A vector having a plurality of principal component values ​​as its components corresponds to a principal component vector for one spectral data.

[0026] The output unit 144 displays the principal component values ​​of the plurality of spectral data on a display screen based on the result of the principal component analysis obtained by the analysis unit 142. The principal component values ​​of the plurality of spectral data are displayed on the display screen of the display unit 122 of the user terminal 12.

[0027] Specifically, when the output unit 144 displays the principal component values ​​of a plurality of pieces of spectral data on the display screen, the output unit 144 displays information such as that shown in FIG. 2 on the display screen of the display unit 122 of the user terminal 12.

[0028] In Fig. 2, images Im_PC1, Im_PC2, Im_PC3, ... representing the principal components of multiple spectral data are displayed diagonally aligned with respect to the horizontal or vertical direction on the display screen. Note that in Fig. 2, the principal components of multiple spectral data are displayed as waveform data.

[0029] Then, for each pair of a first image and a second image among the images Im_PC1, Im_PC2, Im_PC3, ... representing the principal components of the multiple spectral data, the output unit 144 displays a graph representing a scatter plot of the principal component values ​​at a position representing the intersection of a line extending vertically from the first image and a line extending horizontally from the second image.

[0030] The enlarged view shown on the right side of Fig. 2 illustrates an example in which the first image is image Im_PC1 and the second image is image Im_PC2. As shown in the enlarged view of Fig. 2, the output unit 144 displays a graph MAP12 at a position representing the intersection of a virtual line L1 extending vertically from image Im_PC1 and a virtual line L2 extending horizontally from the second image. The horizontal axis of graph MAP12 represents the principal component represented by image Im_PC1, and the vertical axis of graph MAP12 represents the principal component represented by image Im_PC2. Principal component values ​​PC1 and PC2 of multiple spectral data are plotted on this graph MAP12.

[0031] As shown in FIG. 2, a pair of a first image and a second image is set for each combination of multiple principal components, and graphs corresponding to the pair of the first image and the second image are displayed in a matrix.

[0032] For example, if the first image is image Im_PC1 and the second image is image Im_PC3, graph MAP13 is displayed at the position shown in Fig. 2. The horizontal axis of this graph MAP13 is the axis of the principal component represented by image Im_PC1, and the vertical axis is the axis of the principal component represented by image Im_PC3. Principal component values ​​PC1 and PC3 of multiple spectral data are plotted on graph MAP13.

[0033] If the first image is image Im_PC2 and the second image is image Im_PC3, graph MAP23 is displayed at the position shown in Fig. 2. The horizontal axis of graph MAP23 is the axis of the principal component represented by image Im_PC2, and the vertical axis is the axis of the principal component represented by image Im_PC3. Principal component values ​​PC2 and PC3 of multiple spectral data are plotted on graph MAP23.

[0034] In this way, a pair of a first image and a second image is set for each combination of a plurality of principal components, and a graph corresponding to the pair of the first image and the second image is displayed on the display screen of the display unit 122 of the user terminal 12. This makes it easy for the user to analyze the spectral data.

[0035] 2, the images Im_PC1, Im_PC2, Im_PC3,... representing the principal components of multiple spectral data are displayed diagonally, allowing the user to immediately understand the relationship between the waveforms represented by the principal components and the spectral data. For example, the waveform represented by image Im_PC1 can be recognized as data having a peak on the left side. The waveform represented by image Im_PC2 can also be recognized as data having a peak on the right side.

[0036] Furthermore, as shown in FIG. 2, the horizontal axis of the graph represents the principal component of the image located above the graph, and the vertical axis of the graph represents the principal component of the image located to the right of the graph, so that the user can easily recognize the principal component represented by the horizontal axis and the principal component represented by the vertical axis of each graph.

[0037] The output unit 144 transmits the information shown in FIG.

[0038] The user terminal 12 receives the information transmitted from the server 14 and displays the information on its own display unit 122 .

[0039] The user operating the user terminal 12 checks the information output from the server 14. The user also operates his / her own user terminal 12 to input operation information to the user terminal 12 to specify one graph from among the multiple graphs. For example, the user inputs operation information to the user terminal 12 to click one graph from among the multiple graphs.

[0040] Then, the acquisition unit 140 of the server 14 acquires the operation information transmitted from the user terminal 12 operated by the user. The output unit 144 of the server 14 enlarges and displays one graph specified by the user in accordance with the user's operation information.

[0041] Fig. 3(A) is a diagram showing an enlarged graph MAP 12. In the example shown in Fig. 3(A), together with the enlarged graph MAP 12, a selection field 20 for selecting the type of analysis, a selection field 22 for selecting the type of performance data, a selection field 23 for selecting the data display format, a list of files 24 in which spectral data is recorded, and a horizontal bar 25 indicating the level of the performance value represented by the performance data are displayed.

[0042] The output unit 144 displays the plot points in the enlarged graph in different colors according to the numerical values ​​associated with the spectral data represented by the plot points. For example, if "mechanical strength" is selected in the selection field 22 for selecting the type of performance data, the color of the plot points representing the principal component values ​​changes according to the value of the mechanical strength, which is the performance data. In this case, for example, the horizontal bar 25 represents the level of mechanical strength, and the darker the color within the horizontal bar 24, the lower the mechanical strength. In this way, changing the color of the plot points representing the principal component values ​​according to the performance value makes it easier to understand the relationship between the principal components, which are the axes of the graph onto which each plot point is projected, and performance. Furthermore, adding color to each plot point allows the user to intuitively understand which principal components are related to the performance of the material.

[0043] Also, in (A) of FIG. 3, "Back," "Previous," and "Next" buttons are shown. When the "Back," "Previous," or "Next" button is pressed by a user operation, a transition to another screen occurs. When the "Back" button is pressed, for example, a transition to the screen shown in FIG. 2 occurs. Pressing the "Previous" or "Next" button is an example of a user operation that represents switching the display of an enlarged graph. Here, the output unit 144 changes the horizontal or vertical axis of the enlarged graph and switches to another graph, thereby displaying the plot points in the graph as if they are moving continuously.

[0044] For example, when the "Next" button in FIG. 3A is pressed by the user, the enlarged graph MAP12 is switched to another graph MAP13 shown in FIG. 3B. Also, when the "Next" button is pressed by the user while the enlarged graph MAP13 is being displayed, it is switched to another graph MAP23. In this way, when the "Next" button is pressed repeatedly by the user, the graphs are switched in the order of graphs MAP12, MAP13, MAP23, MAP14, MAP24, ... shown in FIG. 2. When switching from graph MAP12 in FIG. 3A to graph MAP13 in FIG. 3B, each plot point is displayed at the coordinates (x A ,y A ) to the coordinates (x B ,y B At this time, the plot point (x A ,y A ) to the plot point (x B ,y B ), which gives the user the impression that the graph MAP12 in Figure 3(A) and the graph MAP13 in Figure 3(B) are not two different things, but that they are the same thing viewed from different perspectives, allowing the user to imagine a 10-dimensional space, PC1 to PC10.

[0045] Furthermore, for example, when a plot point in a graph is selected by a user operation, a predetermined process can be performed on the selected plot point. For example, as shown in FIG. 4, when a plot point in a predetermined region 26 is selected by a user operation, the file selected by the user is displayed in a list of files 24 in which spectral data is recorded, as indicated by a check mark 27 on the left side. For example, a process to display only the plot points selected in this way and a re-execution of principal component analysis can be performed.

[0046] The user operates the user terminal 12 and checks the information displayed on the display unit 122 of the user terminal 12. For example, the user refers to the information shown in FIGS. 2 to 4 and checks each graph in which the spectral data is plotted as the principal component values. The user also checks the color assigned to each plot point to check the relationship between the principal component values ​​and the performance data.

[0047] The user terminal 12 and the server 14 can be realized, for example, by a computer 50 as shown in Fig. 5. The computer 50 that realizes 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 50 also includes an input / output interface (I / F) 54 to which input / output devices (not shown) are 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, memory 52, storage unit 53, input / output I / F 54, R / W unit 55, and network I / F 56 are connected to one another via a bus 57.

[0048] 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, loads it into the memory 52, and sequentially executes the processes contained in the program.

[0049] Next, the operation of the information processing system 10 according to the embodiment will be described.

[0050] The user inputs a data set, which is a combination of spectral data and performance data for each of a plurality of materials, into the user terminal 12 that the user operates.

[0051] The control unit 120 of the user terminal 12 accepts the data set in response to an operation by the user, and then transmits the data set to the server 14 in response to the operation by the user.

[0052] When a data set is transmitted from the user terminal 12 to the server 14, the acquisition unit 140 of the server 14 acquires the data set transmitted from the user terminal 12. Then, the acquisition unit 140 stores the data set in the data storage unit 141.

[0053] When the server 14 receives a predetermined instruction signal transmitted from the user terminal 12, it executes an information processing routine shown in FIG.

[0054] In step S100, the analysis unit 142 of the server 14 reads out a data set from the data storage unit 141 to obtain a plurality of spectral data.

[0055] In step S102, the analysis unit 142 of the server 14 performs principal component analysis on the plurality of spectral data acquired in step S100 to generate principal components of the plurality of spectral data and principal component values ​​of each of the plurality of spectral data. The principal components of the plurality of spectral data are used as axes of a graph.

[0056] In step S104, the output unit 144 of the server 14 outputs the result of the principal component analysis generated in step S102. Specifically, the output unit 144 of the server 14 transmits a control signal to the user terminal 12 to cause the display unit 122 of the user terminal 12 to display information such as that shown in Fig. 2, which includes each of the principal component values ​​of the plurality of spectral data generated in step S102.

[0057] The user operating the user terminal 12 checks the information output from the server 14 and understands the distribution of the spectral data when each principal component is used as an axis. The user also checks the information output from the server 14 and confirms the relationship between the distribution of the spectral data and the performance value represented by the performance data.

[0058] As described above, the server of the information processing system according to the embodiment acquires multiple pieces of measurement data and performs principal component analysis on the acquired pieces of measurement data to generate principal components of the multiple pieces of measurement data and principal component values ​​of the multiple pieces of measurement data. When displaying the principal component values ​​of each of the generated pieces of measurement data on a display screen, the server displays each of the images representing the principal components of the multiple pieces of measurement data diagonally aligned with respect to the horizontal or vertical direction of the display screen. Furthermore, for each pair of a first image and a second image among the images representing the principal components of the multiple pieces of measurement data, the server displays a graph with axes representing the principal components represented by the first image and the principal components represented by the second image, plotting the principal component values ​​of the multiple pieces of measurement data, at a position representing the intersection of a line extending vertically from the first image and a line extending horizontally from the second image. This facilitates interpretation of the results of principal component analysis of the material measurement data.

[0059] Furthermore, the processing performed by the computer 50 in each of the above embodiments has been described as software processing performed by executing a program, but this is not limited to this. For example, the processing may be performed by hardware such as a GPU (Graphics Processing Unit), an ASIC (Application Specific Integrated Circuit), or an FPGA (Field-Programmable Gate Array). Alternatively, the processing may be a combination of both software and hardware. Furthermore, if the processing is software, the program may be stored in various storage media and distributed.

[0060] 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 of the present invention.

[0061] For example, in the above embodiment, the measurement data is spectrum data, but the measurement data may be any data obtained by performing some kind of measurement process on a material.Furthermore, the performance data may be any data that represents the performance of a material. [Explanation of symbols]

[0062] 10 Information Processing Systems 12 User terminal 14 Servers 50 Computers 53 Memory section 140 Acquisition Department 141 Data storage unit 142 Analysis Department 144 Output section

Claims

1. an acquisition unit that acquires a plurality of measurement data; an analysis unit that performs principal component analysis on the plurality of measurement data acquired by the acquisition unit to generate principal components of the plurality of measurement data and principal component values ​​of each of the plurality of measurement data; When the principal component values ​​of the plurality of measurement data generated by the analysis unit are displayed on a display screen, displaying the images representing the principal components of the plurality of measurement data in a diagonal arrangement with respect to the horizontal or vertical direction on the display screen; an output unit that displays, for each pair of a first image and a second image among the images representing the principal components of the plurality of measurement data, a graph with axes representing the principal components represented by the first image and the principal components represented by the second image at a position representing an intersection of a line extending vertically from the first image and a line extending horizontally from the second image, and in which principal component values ​​of the plurality of measurement data are plotted; Equipped with The output unit When a user operation indicating that one of the plurality of graphs is to be designated is received, the graph designated by the user is enlarged and displayed; When a user operation indicating a change in display of the enlarged graph is received, the enlarged graph is changed to another graph; By changing the horizontal axis or vertical axis of the enlarged graph and switching to another graph, the plot points in the graph are displayed as if they are moving continuously. Information processing device.

2. The output unit displays the plotted points in the enlarged graph in a color according to a numerical value related to the measurement data represented by the plotted points. The information processing device according to claim 1 .

Images