Information Processing Apparatus, Information Processing Method, and Information Processing Program

Abstract

To provide an information processing apparatus, an information processing method, and an information processing program that can generate spectral data on a material for which spectral data is not measured.SOLUTION: A server 14 sets each of pieces of spectral data that are measured from each of a plurality of materials as vector data. The server 14 generates two-dimensional map data having each of a plurality of pieces of vector data projected to two dimensions as each of a plurality of plot points by applying a dimension reduction technique for the plurality of pieces of vector data. The server 14 identifies unknown data representing a plot point being different from a plot point already existing on two-dimensional map data. The server 14 converts the unknown data to spectral data. The server 14 outputs the converted spectral data.SELECTED DRAWING: Figure 1

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses an electronic device and a control method thereof for achieving both accuracy and efficiency in analysis when analyzing a target using a plurality of spectral components. This electronic device selects any one of a plurality of parameters generated by machine learning, and uses the selected parameter to receive light reflected from a food to be analyzed and analyze spectral data indicating the spectral intensity of the plurality of spectral components (for example, [Summary]).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Generally, when performing an analysis on a certain material, it is necessary to measure the spectral data of the material. When performing an analysis on a material, various analyses on the material are performed using the measured spectral data.

[0005] On the other hand, the user may sometimes want to know, for example, what spectral data corresponds to a material having the performance they desire. In this case, if the material having the performance desired by the user is unknown and its spectral data has not been measured, it is necessary to obtain the spectral data of the material by some method.

[0006] The electronic device of Patent Document 1 selects any one of a plurality of parameters generated by machine learning, and uses the selected parameter to analyze spectral data indicating the spectral intensities of a plurality of spectral components by receiving light reflected from a food to be analyzed.

[0007] However, the electronic device of Patent Document 1 does not acquire the spectral data of a material for which spectral data has not been measured.

[0008] An object of the present disclosure is to provide an information processing apparatus, an information processing method, and an information processing program capable of generating spectral data of a material for which spectral data has not been measured.

Means for Solving the Problems

[0009] The information processing apparatus according to the first aspect includes a setting unit that sets each of the spectral data measured from each of a plurality of materials as vector data, and applies a dimensionality reduction method to the plurality of vector data, thereby generating two-dimensional map data in which each of the plurality of vector data is projected into two dimensions as each of a plurality of plot points. A generation unit, a specification unit that specifies unknown data representing a plot point different from the plot points already existing on the two-dimensional map data, a conversion unit that converts the unknown data into spectral data, and an output unit that outputs the converted spectral data. According to the information processing apparatus according to the first aspect, spectral data of a material for which spectral data has not been measured can be generated. Specifically, when a material having a performance value desired by the user is assumed, the spectral data of an unknown material expected to have that performance value can be obtained without actually measuring it. The spectral data of the unknown material can be obtained.

[0010] The spectral data of the information processing apparatus according to the second aspect is data generated by performing frequency analysis on an image of a material. The conversion unit converts the unknown data into the spectral data, generates an image of an unknown material from the converted spectral data, and the output unit outputs the converted spectral data and the generated image of the material. According to the information processing apparatus according to the second aspect, when a material having a performance value desired by the user is assumed, an image of an unknown material expected to have that performance value can be obtained without actually imaging the image of the unknown material. In addition, the user can recognize what kind of image is an image of a material having a performance value desired by the user himself / herself. In the second embodiment, a plurality of pieces of teacher data in which spectral data and images are associated may be prepared, a learned model may be generated based on the plurality of pieces of teacher data, and an image may be generated using the learned model. In this case, a known machine learning model for image generation is used as the learned model. The learned model is generated, for example, by training a machine learning model using a deep learning algorithm.

[0011] The unknown data of the information processing apparatus according to the third aspect is data on the two-dimensional map data specified by the user. The conversion unit converts the unknown data specified by the user into spectral data, and the output unit causes the converted spectral data to be displayed on the display unit. According to the information processing apparatus according to the third aspect, spectral data of an unknown material corresponding to a plot point specified by a user operation can be obtained.

[0012] The information processing method according to the fourth aspect sets each of the spectral data measured from each of a plurality of materials as vector data, and by applying a dimensionality reduction method to the plurality of vector data, each of the plurality of vector data is projected into two dimensions as each of a plurality of plot points to generate two-dimensional map data. It identifies unknown data representing plot points different from the plot points already existing on the two-dimensional map data, converts the unknown data into spectral data, and outputs the converted spectral data. It is an information processing method executed by a computer. According to the information processing method according to the fourth aspect, it is possible to generate spectral data of a material for which spectral data has not been measured.

[0013] The information processing program according to the fifth aspect sets each of the spectral data measured from each of a plurality of materials as vector data, and by applying a dimensionality reduction method to the plurality of vector data, each of the plurality of vector data is projected into two dimensions as each of a plurality of plot points to generate two-dimensional map data. It identifies unknown data representing plot points different from the plot points already existing on the two-dimensional map data, converts the unknown data into spectral data, and outputs the converted spectral data. It is an information processing program for causing a computer to execute the processing. According to the information processing program according to the fifth aspect, it is possible to generate spectral data of a material for which spectral data has not been measured.

Advantages of the Invention

[0014] As described above, according to the present disclosure, there is an effect that spectral data of a material for which spectral data has not been measured can be generated.

Brief Description of the Drawings

[0015]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Embodiments for Carrying Out 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 apparatus. The user terminal 12 and the server 14 are communicably connected via a network 16 such as the Internet, for example.

[0018] The information processing system 10 of the present embodiment projects each of the spectral data measured from each of a plurality of materials onto two-dimensional map data. Note that one plot point on the two-dimensional map data corresponds to one spectral data, and one spectral data corresponds to one material. The spectral data is data measured by various methods, for example.

[0019] Then, the information processing system 10 of the present embodiment converts unknown data, which is a plot point different from the plot points already existing on the two-dimensional map data and is specified by the user, into spectral data. Thereby, spectral data of a material for which spectral data has not been measured can be generated. This will be specifically described below.

[0020] (User Terminal)

[0021] The user terminal 12 is operated by the user. Functionally, as shown in FIG. 1, the user terminal 12 includes a control unit 120 and a display unit 122.

[0022] The control unit 120 controls the operation of the user terminal 12. The display unit 122 displays various information according to the control by the control unit 120.

[0023] (Server)

[0024] Functionally, as shown in FIG. 1, the server 14 includes an acquisition unit 140, a data storage unit 141, a setting unit 142, a generation unit 144, a specifying unit 146, a conversion unit 148, and an output unit 150.

[0025] The acquisition unit 140 acquires a plurality of spectral data transmitted from the user terminal 12. Then, the acquisition unit 140 stores the plurality of spectral data in the data storage unit 141.

[0026] In the data storage unit 141, each of the spectral data measured from each of the plurality of materials is stored.

[0027] The setting unit 142 sets each of the plurality of spectral data as vector data. For example, when the spectral data is illustrated in a graph in which the horizontal axis represents frequency and the vertical axis represents spectral value, vector data having each of the spectral values corresponding to each frequency as a component is set.

[0028] The generation unit 144 applies principal component analysis, which is an example of a dimensionality reduction method, to the plurality of vector data. Then, based on the result of applying the principal component analysis, the generation unit 144 generates two-dimensional map data in which each of the plurality of vector data is projected into two dimensions as each of a plurality of plot points. The generation unit 144 transmits the two-dimensional map data and related information to the user terminal 12.

[0029] FIG. 2 is a diagram showing an example of two-dimensional map data and related information. As the related information in FIG. 2, the principal component values displayed as bars (hereinafter, also simply referred to as "PC values") and the spectral data corresponding to the principal component values are shown. The user operates his / her user terminal 12 to display the two-dimensional map data and related information as shown in FIG. 2 on the display unit 122 of the user terminal 12.

[0030] In FIG. 2(A), "pc1" on the horizontal axis of the two-dimensional map data represents the value of the first principal component, and "pc2" on the vertical axis represents the value of the second principal component. One plotted point shown in FIG. 2(A) corresponds to one spectral data. Also, as shown in FIG. 2(A), the darkness of the color of the plotted point represents the quality of the performance of the material corresponding to the plotted point. Specifically, when the color of the plotted point is white, it indicates that the performance of the material is poor, and when the color of the plotted point is black, it indicates that the performance of the material is good. Therefore, the plotted points located further to the right in FIG. 2(A) correspond to higher-performance materials. When the "Back" button in FIG. 2(A) is pressed, the screen transitions to another screen.

[0031] FIGS. 2(B), (C), and (D) are diagrams showing an example of the principal component values displayed as bars and the spectral data corresponding to the principal component values. On the left side of FIGS. 2(B), (C), and (D), 10 PC values from pc1 to pc10 are displayed as bars. Also, on the right side of FIGS. 2(B), (C), and (D), the spectral data corresponding to the PC values on the left side is shown. The conversion from the PC values to the spectral data is uniquely determined. Note that the "0SET" button shown in FIGS. 2(B), (C), and (D) is a button for setting the 10 PC values from pc1 to pc10 to zero. Also, the "RESET" button shown in FIGS. 2(B), (C), and (D) is a button for restoring the 10 PC values from pc1 to pc10 that have been changed to their original values.

[0032] On the two-dimensional map data of Fig. 2(A), the positions of the respective plots are configured to be adjustable. For this reason, for example, the user can move the plot point P of the two-dimensional map data shown in Fig. 2(A) on the two-dimensional map data by operating his or her user terminal 12. The user operates his or her user terminal 12 and moves a plot point already existing on the two-dimensional map data to specify a plot point different from the already existing plot point. A plot point different from the already existing plot point is unknown data where spectral data does not exist. Also, the unknown data is data on the two-dimensional map data specified by the user.

[0033] For example, the user moves the plot point P shown in Fig. 2(A) to a plot point PU1 corresponding to unknown spectral data that has not been measured. When the plot point P on the two-dimensional map data is moved to the plot point PU1, the value of pc1 shown in Fig. 2(B) ("1.75" in Fig. 2(B)) changes to the value of pc1 shown in Fig. 2(D) ("2.16" in Fig. 2(D)).

[0034] Also, for example, the user moves the plot point P shown in Fig. 2 to an unknown plot point PU2. When the plot point P on the two-dimensional map data is moved to the plot point PU2, the value of pc1 shown in Fig. 2(A) ("1.75" in Fig. 2(A)) changes to the value of pc1 shown in Fig. 2(C) ("0.41" in Fig. 2(C)).

[0035] Due to the change in the PC value, the waveform of the spectral data shown on the right side of Fig. 2 also changes. Note that the horizontal axis of the graph of the spectral data represents, for example, frequency, and the vertical axis represents the spectral value. For example, the spectral data WA changes to the spectral data WB shown in Fig. 2(C) due to the change in the value of pc1. Also, the spectral data WA changes to the spectral data WC shown in Fig. 2(D) due to the change in the value of pc1.

[0036] In this way, the server 14 of the present embodiment converts unknown data corresponding to plot points different from the plot points already existing on the two-dimensional map data (specifically, the points designated by the user as described above) into spectral data. Then, as shown on the right side of FIGS. 2(B), (C), and (D), the server 14 outputs the converted spectral data. Thereby, spectral data of an unknown material for which spectral data has not been measured can be generated.

[0037] For example, as shown in FIG. 2(A), when the higher the value of pc1 of the spectral data, the higher the performance of the material, the user can confirm the pseudo spectral data of the high-performance material by designating the plot point PU1. Therefore, if the user designates a plot point expected to be a high-performance material, spectral data corresponding to that plot point is generated, and the user can know what kind of spectrum realizes high performance.

[0038] Note that the PC values indicated by the bar shown in FIG. 2 may be configured to be adjustable. For example, by changing the PC values as shown by the arrows D1 and D2 in FIG. 2, the waveform of the spectral data may be changed. In this case, since the waveform of the spectral data changes in response to changing and adjusting the principal component values (PC values) indicated by the bar display, the user can also understand the meaning of the principal component values (PC values).

[0039] The specifying unit 146 specifies unknown data representing plot points different from the plot points already existing on the two-dimensional map data generated by the generating unit 144. Specifically, the specifying unit 146 specifies unknown data (for example, the PC value corresponding to the plot point) representing the plot point designated by the user as described above.

[0040] The conversion unit 148 converts the unknown data specified by the specifying unit 146 into spectral data. Note that the conversion from unknown data to spectral data can be realized by a known method.

[0041] The output unit 150 outputs the spectral data and each PC value converted by the conversion unit 148. The data output from the output unit 150 is transmitted to the user terminal 12.

[0042] 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 two-dimensional map data and related information as shown in FIG. 2, and checks what shape the spectral data (for example, pseudo-spectral data corresponding to a material with high performance) corresponding to the unknown data specified by the user is.

[0043] The user terminal 12 and the server 14 can be realized by, for example, a computer 50 as shown in FIG. 3. 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. Further, the computer 50 includes an input / output interface (I / F) 54 to which an input / output device etc. (not shown) is connected, and a read / write (R / W) unit 55 that controls reading and writing of data to and from the recording medium 59. Further, the computer includes a network I / F 56 connected to a network such as the Internet. The CPU 51, the memory 52, the storage unit 5 3, the input / output I / F 54, the R / W unit 55, and the network I / F 56 are connected to each other via a bus 57.

[0044] The storage unit 53 can be realized by a Hard Disk Drive (HDD), a Solid state drive (SSD), a flash memory, etc. A program for operating the computer is stored in the storage unit 53 as a storage medium. The CPU 51 reads the program from the storage unit 53 and expands it in the memory 52, and sequentially executes the processes included in the program.

[0045] Next, the operation of the information processing system 10 of the embodiment will be described.

[0046] For example, a user inputs a plurality of spectral data, which are data obtained by performing predetermined measurement processing on a plurality of materials, into a user terminal 12 that the user operates.

[0047] The control unit 120 of the user terminal 12 receives a plurality of spectral data according to an operation by the user. Then, the control unit 120 transmits the plurality of spectral data to the server 14 according to an operation by the user.

[0048] When a plurality of spectral data are transmitted from the user terminal 12 to the server 14, the acquisition unit 140 of the server 14 acquires the plurality of spectral data transmitted from the user terminal 12. Then, the acquisition unit 140 stores the plurality of spectral data in the data storage unit 141.

[0049] When the server 14 receives a predetermined instruction signal transmitted from the user terminal 12, it executes the information processing routine shown in FIG. 4.

[0050] In step S100, the setting unit 142 of the server 14 reads out each of the plurality of spectral data stored in the data storage unit 141, and sets each of the plurality of spectral data as vector data.

[0051] In step S102, the generation unit 144 of the server 14 applies principal component analysis, which is an example of a dimensionality reduction method, to the plurality of vector data. Then, the generation unit 144 of the server 14 generates two-dimensional map data in which each of the plurality of vector data is projected into two dimensions as each of a plurality of plot points based on the result of applying the principal component analysis. The generation unit 144 of the server 14 transmits the two-dimensional map data and related information as shown in FIG. 2 to the user terminal 12.

[0052] The control unit 120 of the user terminal 12 receives the two-dimensional map data and related information transmitted from the user terminal 12 in step S102. The user operates their own user terminal 12 to display the two-dimensional map data and related information shown in FIG. 2 on the display unit 122. Then, the user operates their own user terminal 12 to move the plot points already existing on the two-dimensional map data, thereby specifying plot points different from the already existing plot points. The plot points different from the already existing plot points are unknown data where spectral data does not exist. The unknown data specified by the user is transmitted from the user terminal 12 to the server 14.

[0053] In step S104, the specifying unit 146 of the server 14 specifies the unknown data transmitted from the user terminal 12. Specifically, the specifying unit 146 specifies the unknown data (for example, the PC value corresponding to that plot point) representing the plot points specified by the user as described above.

[0054] In step S106, the conversion unit 148 of the server 14 converts the unknown data specified in step S104 into spectral data. into spectral data.

[0055] In step S108, the output unit 150 of the server 14 transmits the spectral data of the unknown data obtained in step S106 and other information (for example, the two-dimensional map data shown in FIG. 2(A) and the PC values in the bar format on the left side of FIGS. 2(B), (C), and (D)) to the user terminal 12.

[0056] The user operating the user terminal 12 checks the data output from the server 14 to check what the spectral data of the material they desire is like.

[0057] As described above, the server of the information processing system according to the embodiment sets each of the spectral data measured from each of the plurality of materials as vector data. The server applies a dimensionality reduction method to the plurality of vector data to generate two-dimensional map data in which each of the plurality of vector data is projected into two dimensions as each of a plurality of plot points. The server identifies unknown data representing a plot point different from the plot points already existing on the two-dimensional map data. The server converts the unknown data into spectral data. Then, the server outputs the converted spectral data. Thereby, it is possible to generate spectral data of a material for which spectral data has not been measured. Specifically, when a material having a performance value desired by the user is assumed, it is possible to obtain the spectral data of the unknown material expected to have the performance value without actually measuring the spectral data of the unknown material. Also, the user can recognize what kind of data the spectral data of the material having the performance value desired by the user itself is. Also, it is possible to obtain the spectral data of an unknown material corresponding to the plot point specified by the operation of the user.

[0058] Also, although the processing performed by the computer 50 in each of the above embodiments has been described as software processing performed by executing a program, it is not limited thereto. For example, it may be processing performed by hardware such as a GPU (Graphics Processing Unit), an ASIC (Application Specific Integrated Circuit), and an FPGA (Field-Programmable Gate Array). Alternatively, it may be processing that combines both software and hardware. Also, when it is software processing, the program may be stored in various storage media and distributed.

[0059] Furthermore, the present invention is not limited to the above, and it goes without saying that various modifications can be made and implemented within the scope not departing from the gist thereof other than the above.

[0060] For example, the spectral data of the above embodiment may be spectral data generated from an image of a material. For example, the spectral data may be data generated by performing frequency analysis on an image obtained by imaging a material with an electron microscope or the like. In this case, the conversion unit 148 of the server 14 of the information processing system 10 converts the unknown data into spectral data and generates an image of an unknown material from the converted spectral data. Then, the output unit 150 outputs the converted spectral data and the generated image of the material.

[0061] FIG. 5 is a diagram for explaining an example of generating an image of an unknown material from the converted spectral data. As shown in the upper part of FIG. 5, consider the case where the user moves a plot point P already existing on the two-dimensional map data to a plot point PU corresponding to the unknown data. In this case, the spectral data generated from the actually captured image IM1 of the material corresponds to the plot point P, and the unknown data for which no image has been captured corresponds to the plot point PU. The image IM1 shown in the middle part of FIG. 5 is an image of the actually captured material, and the image IM2 is an image of the unknown material. The image IM2 is an example of an image generated by the conversion unit 148 of the server 14 of the information processing system 10.

[0062] Also, a bar-form PC value is shown on the left side of the lower part of FIG. 5, and the spectral data (solid line in FIG. 5) generated from the actual image IM and the spectral data corresponding to the unknown data (dashed line in FIG. 5) are shown on the right side of the lower part of FIG. 5. The horizontal axis of the graph of the spectral data represents, for example, frequency, and the vertical axis represents the spectral value.

[0063] In this case, the server 14 of the information processing system 10 identifies the plot point PU corresponding to the unknown data and calculates the spectral data (dashed line in FIG. 5) corresponding to the unknown data. As described above, the conversion from the PC value corresponding to the unknown data to the spectral data can be uniquely determined. On the other hand, the conversion from the spectral data to the unknown image IM2 is not uniquely determined.

[0064] Therefore, when the server 14 of the information processing system 10 executes the conversion process from spectral data to an image, for example, when generating a plurality of image candidates randomly based on the image IM1, the server 14 selects an image candidate close to the spectral data from those image candidates. For example, the server 14 generates a plurality of image candidates by randomly changing the pixel values that make up the image IM1 corresponding to the plot point P specified by the user. Then, the server 14 generates spectral data for each of the plurality of image candidates by performing frequency analysis on each of the plurality of image candidates. Then, the server 14 selects, as the image IM2 corresponding to the unknown data, an image candidate with a small difference (or equal to or less than the threshold value) between the spectral data for each of the plurality of image candidates and the spectral data corresponding to the plot point PU corresponding to the unknown data.

[0065] Alternatively, for example, the server 14 of the information processing system 10 may prepare a plurality of teacher data in which spectral data and images are associated, generate a learned model based on the plurality of teacher data, and use the learned model to generate an image. In this case, the solid-line spectral data and the image IM1 shown in FIG. 5 are preset as teacher data. Also, for example, a known machine learning model for image generation is used as the learned model. The learned model is generated, for example, by training a machine learning model using a deep learning algorithm. For example, the server 14 of the information processing system 10 inputs the broken-line spectral data shown in FIG. 5 into the learned model to generate the image IM2 corresponding to the unknown spectral data.

[0066] As a result, when a material having the performance value desired by the user is assumed, the image of the unknown material expected to have that performance value can be obtained without actually imaging the image of the unknown material. Also, the user can recognize what kind of image is the image of the material having the performance value desired by the user himself / herself. Also, by generating an image from the spectral data, the user can also understand the relationship between the PC value of the spectral data and the image.

[0067] Note that, for example, as shown in FIG. 6, only a portion of the spectral data that has a correlation with the performance of the material may be converted into an image. For example, consider a case where the PC value obtained by the principal component analysis in FIG. 6 has a positive correlation with a certain performance of the material. For example, only the partial region RX1 of the spectral data Sx corresponding to the portion having a high value among each PC value which is high-dimensional vector data may be converted into the image IMX. Or, only the partial region RY1 of the spectral data Sx corresponding to the portion having a low value among each PC value which is high-dimensional vector data may be converted into an image. By generating an image from a part of the spectral data, the user can also understand the relationship between a part of the spectral data and the image. Thereby, the user can also understand what kind of image can obtain the desired performance.

[0068] Further, the output unit 150 may bar-display the values of each dimension corresponding to the unknown data (for example, the PC value of the principal component analysis), and the conversion unit 148 may convert the PC value into spectral data according to the user's operation (for example, the operation of the bar) on the values of each dimension (for example, the PC value of the principal component analysis) bar-displayed. Thereby, according to the user's operation on the values of each dimension (for example, the PC value of the principal component analysis) of the dimension compression result displayed on the display unit 122 of the user terminal 12, the spectral data of the unknown material can be displayed. Also, the user can understand the meaning of the values of each dimension (for example, the PC value of the principal component analysis) of the dimension compression result.

[0069] Further, the conversion unit 148 may generate spectral data corresponding to the average of the plot points already existing in the two-dimensional map data according to the user's operation (for example, operating the bar), and the output unit 150 may output the spectral data corresponding to the average. Thereby, according to the user's operation, the average of a plurality of spectral data already displayed in the two-dimensional map data can be displayed.

[0070] Further, the conversion unit 148 may perform regression analysis between the performance values of the material (e.g., mechanical strength, surface reflectance, transparency, etc.) and the values of each dimension obtained by applying principal component analysis, which is an example of a dimensionality reduction method (e.g., the PC value of principal component analysis). In this case, the output unit 150 may further output the regression analysis result obtained by the conversion unit 148. Thereby, a regression analysis result between the performance value of the material and the values of each dimension of the dimensionality reduction result (e.g., the PC value of principal component analysis) can be obtained.

[0071] Also, each of the plot points on the two-dimensional map data may be added with a color (e.g., the higher the performance value, the redder the color, etc.) according to the performance value of the material (e.g., mechanical strength, surface reflectance, transparency, etc.). By adding a color according to the performance value of the material to the plot points, the user can obtain the spectral data of the material with the performance value he desires by specifying the plot points using the color as a clue.

Explanation of Signs

[0072] 10 Information processing system 12 User terminal 14 Server 50 Computer 53 Storage unit 140 Acquisition unit 141 Data storage unit 142 Setting unit 144 Generation unit 146 Identification unit 148 Conversion unit 150 Output unit

Claims

1. Each of the spectral data measured from each of the plurality of materials is set as vector data; Applying a dimensionality reduction technique to the plurality of vector data; Displaying the values ​​of each dimension resulting from the application of the dimension reduction technique and the spectral data corresponding to each of the values ​​of each dimension; The displayed value of each of the dimensions is configured to be adjustable; A change in the value of each of the dimensions displayed causes a change in the waveform of the displayed spectrum data. Information processing device.

2. the dimensionality reduction technique is principal component analysis, The values ​​of each dimension are principal component values. The information processing device according to claim 1 .

3. The values ​​of each dimension are displayed as bars, By changing the length of the bar, the value of each dimension changes.

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

4. Each of the spectral data measured from each of the plurality of materials is set as vector data; Applying a dimensionality reduction technique to the plurality of vector data; Displaying the values ​​of each dimension resulting from the application of the dimension reduction technique and the spectral data corresponding to each of the values ​​of each dimension; The displayed value of each of the dimensions is configured to be adjustable; A change in the value of each of the dimensions displayed causes a change in the waveform of the displayed spectrum data. An information processing method in which processing is performed by a computer.

5. Each of the spectral data measured from each of the plurality of materials is set as vector data; Applying a dimensionality reduction technique to the plurality of vector data; Displaying the values ​​of each dimension resulting from the application of the dimension reduction technique and the spectral data corresponding to each of the values ​​of each dimension; The displayed value of each of the dimensions is configured to be adjustable; A change in the value of each of the dimensions displayed causes a change in the waveform of the displayed spectrum data. An information processing program for causing a computer to execute processing.

Images