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

Abstract

To provide an information processing device, an information processing method and an information processing program capable of easily determining a measuring time or the number of measuring times of measurement processing to a material while executing the measurement processing to the material.SOLUTION: A server 14 acquires measurement data acquired by executing prescribed measurement processing to a material. The server 14 calculates an improvement rate representing improvement of measurement data between measurement data measured by a time n and measurement data measured by a time n+1 on the basis of a first statistic representing variation of the measurement data measured by the time n and a second statistic representing variation of the measurement data measured by the time n+1. The server 14 determines the number of measurement times or a measurement time of the measurement data such that the improvement rate becomes a prescribed threshold or below. The server 14 outputs the determined number of measurement times or measurement time 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 surface analysis device capable of analyzing trace elements in a short time, and Patent Document 2 discloses a method for automatically setting the number of data accumulations appropriate for identifying a target peptide, neither too many nor too few. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2020-85565 [Patent Document 2] Japanese Patent Application Laid-Open No. 2016-50866 Summary of the Invention [Problem to be solved by the invention]

[0004] As disclosed in Patent Documents 1 and 2, there exists data in which the final data for a material is obtained by accumulating data obtained when multiple measurement processes are performed on the material. In this case, when performing measurement processes on the material, the user must determine the measurement time or number of measurements. In this case, the longer the measurement time or number of measurements in the measurement process, the more accurate the data obtained.

[0005] The technology of Patent Document 1 calculates the statistical error of the noise component of the spectrum and calculates the number of times the spectrum is accumulated based on the statistical error. In addition, the technology of Patent Document 2 increases the number of times data accumulation is performed and performs additional analysis of the standard peptide by the increased number of times when identification fails or when identification is successful but the score or expected value indicating the reliability of identification does not reach a predetermined threshold.

[0006] Although the techniques of Patent Documents 1 and 2 calculate a score representing the statistical error or reliability of noise separately from the measured data, it would be preferable to be able to more easily determine the measurement time or number of measurements for the measurement process on the material.

[0007] The present disclosure aims to provide an information processing device, an information processing method, and an information processing program that can easily determine the measurement time or number of measurements for a measurement process on a material while performing the measurement process on the material. [Means for solving the problem]

[0008] An information processing device according to a first aspect includes: an acquisition unit that acquires measurement data obtained by performing a predetermined measurement process on a material; a calculation unit that calculates an improvement rate that represents an improvement in the measurement data between the measurement data measured up to the number of times or time n and the measurement data measured up to the number of times or time n+1 based on a first statistic that represents a variance in the measurement data measured up to the number of times or time n and a second statistic that represents a variance in the measurement data measured up to the number of times or time n+1, both acquired by the acquisition unit; a determination unit that determines the number of measurements or the measurement times of the measurement data such that the improvement rate calculated by the calculation unit is equal to or less than a predetermined threshold; and an output unit that outputs the number of measurements or the measurement times of the measurement data determined by the determination unit. The information processing device according to the first aspect allows the measurement time or the number of measurements of the material to be easily determined while performing the measurement process on the material.

[0009] The calculation unit of the information processing device according to the second aspect calculates the improvement rate for a plurality of different target counts or target times, and the determination unit generates a regression curve representing the relationship between the improvement rate and the number of measurements or measurement times of the measurement data based on the plurality of improvement rates, and predicts the number of measurements or measurement times of the measurement data based on the regression curve so that the improvement rate will be equal to or less than a predetermined threshold. According to the information processing device according to the second aspect, the measurement time or number of measurements in the measurement process for the material can be easily predicted by generating a regression curve using several pieces of measurement data obtained by an initial measurement process.

[0010] The output unit of the information processing device according to the third aspect also outputs examples of the measurement data at the measurement count or measurement time of the measurement data that makes the improvement rate equal to or less than a predetermined threshold. According to the information processing device according to the third aspect, by providing examples of measurement data at the measurement time or measurement count that are expected to be optimal, it is possible to support a user in making a decision on the measurement time or measurement count.

[0011] An information processing method according to a fourth aspect is an information processing method in which a computer executes the following processing: acquires measurement data obtained by performing a predetermined measurement process on a material, calculates an improvement rate representing an improvement in the measurement data between the measurement data measured up to the number of times or time n and the measurement data measured up to the number of times or time n+1 based on a first statistic representing the variability of the measurement data measured up to the number of times or time n and a second statistic representing the variability of the measurement data measured up to the number of times or time n+1, determines the number of measurements or measurement times of the measurement data such that the calculated improvement rate is equal to or less than a predetermined threshold, and outputs the determined number of measurements or measurement times of the measurement data. The information processing method according to the fourth aspect makes it possible to easily determine the measurement time or number of measurements for the measurement process on the material while performing the measurement process on the material.

[0012] An information processing program according to a fifth aspect is an information processing program for causing a computer to execute processing to acquire measurement data obtained by performing a predetermined measurement process on a material, calculate an improvement rate representing an improvement in the measurement data between the measurement data measured up to the number of times or time n and the measurement data measured up to the number of times or time n+1 based on a first statistic representing the variability of the measurement data measured up to the number of times or time n and a second statistic representing the variability of the measurement data measured up to the number of times or time n+1, determine the number of measurements or measurement times of the measurement data such that the calculated improvement rate is equal to or less than a predetermined threshold, and output the determined number of measurements or measurement times of the measurement data. The information processing program according to the fifth aspect makes it possible to easily determine the measurement time or number of measurements for the measurement process on the material while performing the measurement process on the material.

[0013] In each of the above aspects, the improvement rate may be calculated using a trained model that has been trained in advance by machine learning. In this case, for example, when the first statistic and the second statistic are input to the trained model, the trained model is configured to output the improvement rate.

[0014] Alternatively, in each of the above aspects, a trained model that has been trained in advance by machine learning may be used to determine the number of measurements or the measurement time of the measurement data such that the improvement rate is equal to or less than a predetermined threshold. In this case, for example, when the first statistic and the second statistic are input to the trained model, the trained model is configured to output the number of measurements or the measurement time of the measurement data such that the improvement rate is equal to or less than the predetermined threshold. [Effects of the Invention]

[0015] As described above, the present disclosure has the advantage of being able to easily determine the measurement time or number of measurements for the measurement process on a material while the measurement process on the material is being performed. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a block diagram showing an example of a functional configuration of an information processing system 10 according to an embodiment. [Figure 2] FIG. 10 is a diagram for explaining an improvement rate according to an embodiment. [Figure 3] FIG. 10 is a diagram showing the relationship between the number of measurements and the improvement rate. [Figure 4] FIG. 10 is a diagram for explaining an example of measurement 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

[0017] Hereinafter, an information processing system according to an embodiment will be described with reference to the drawings.

[0018] 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.

[0019] As disclosed in the above Patent Documents 1 and 2, there exists data of such a nature that the final data for a material can be obtained by accumulating data obtained when measurement processing is performed multiple times on the material.

[0020] In this case, when obtaining final data on the material, the user must decide the number of measurements or the measurement time, but there is a problem in that the user does not know how much measurement time or number of measurements will be required to obtain measurement data with what accuracy.

[0021] Therefore, the server 14 of this embodiment outputs data on the number of measurements or the measurement time of the measurement process for the material and recommends the conditions for the material measurement process. This allows the user to easily determine the measurement time or the number of measurements for the material measurement process while performing the measurement process for the material.

[0022] The specific details will be explained below.

[0023] (user terminal) The user terminal 12 is operated by a user.

[0024] A user inputs measurement data, which is data obtained by performing a predetermined measurement process on a material, into the user terminal 12 that the user operates. The measurement data is, for example, data measured by various methods, such as spectral data or image data. The user terminal 12 transmits the measurement data to the server 14 in response to an operation by the user.

[0025] (server)

[0026] As shown in FIG. 1, the server 14 includes an acquisition unit 140, a data storage unit 141, a calculation unit 142, a determination unit 144, and an output unit 146.

[0027] The acquiring unit 140 successively acquires the measurement data transmitted from the user terminal 12. Then, the acquiring unit 140 stores the measurement data in the data storage unit 141.

[0028] The calculation unit 142 calculates a first statistic σ representing the variance of the measurement data measured up to the number n (or time n) based on the measurement data for each measurement or each time stored in the data storage unit 141. n and the second statistic σ, which represents the variance of the measurement data measured up to the number n+1 (or time n+1). n+1 Calculate the following.

[0029] Then, the calculation unit 142 calculates the first statistic σ n and the second statistic σn+1 Based on this, an improvement rate is calculated that represents the improvement in the measurement data between the measurement data measured up to the nth number of times (or time n) and the measurement data measured up to the n+1th number of times (or time n+1).

[0030] 2 is a diagram for explaining the improvement rate of this embodiment. An example of a method for calculating the improvement rate will be described below with reference to FIG.

[0031] For example, as shown in Fig. 2, assume that certain spectrum data D is obtained by accumulating measurement data obtained from the first to nth measurement processes (or time 1 to time n) for a material. As shown on the right side of Fig. 2, the y value of this spectrum data D is obtained by averaging the y values obtained at each point p1, p2, p3, p4, and p5 in the x-axis direction.

[0032] For example, when n=2, as shown on the right side of Figure 2, the average values μ1 to μ5 of the y values at each of the points p1 to p5 obtained by the measurement process up to the second time are calculated. Also, the standard deviations s1 to s5 of the y values at each of the points p1 to p5 up to the second time are calculated. Then, the coefficient of variation σ, which represents the variation of the y values at each of the points p1 to p5 up to the second time, is calculated. n 1~σ n 5 is calculated. As shown in Figure 2, the coefficient of variation (standard deviation normalized by the mean value) σ n = s / μ. Also, "ave" shown in Figure 2 represents the average value from p1 to p5.

[0033] As shown on the right side of Figure 2, the coefficient of variation σ1 represents the variation in the y values at each point p1 to p5 obtained by the measurement process up to the n+1=3 times. n+1 ~σ5 n+1 is calculated similarly.

[0034] The coefficient of variation σ1 obtained by the first two measurements n ~σ5 n and the coefficient of variation σ1 obtained by the first three measurementsn+1 ~σ5 n+1 Based on this, the improvement rate of each point from p1 to p5 is 1-(σ n+1 / σ n ) is calculated. In FIG. 2, the improvement rates of the points p1 to p5 are represented by imp1 to imp5.

[0035] For this reason, the calculation unit 142 calculates a coefficient of variation σ n and the coefficient of variation σ, which is an example of the second statistic n+1 Based on this, 1-(σ n+1 / σ n ) is calculated as the improvement rate.

[0036] Figure 3 shows the relationship between the number of measurements and the improvement rate. As shown in Figure 3(A), the improvement rate decreases as the number of measurements increases. Figure 3(A) also shows that as the number of measurements increases, the difference in quality between the data obtained by the measurement process up to the nth time and the data obtained by the measurement process up to the n+1th time becomes smaller.

[0037] Usually, to determine the number of measurements, a predetermined threshold for the improvement rate is determined based on criteria such as when the data analysis results no longer change or when the difference in data becomes indistinguishable from human appearance, and the optimal number of measurements N is determined. opt Determine.

[0038] The determination unit 144 determines the improvement rate 1-(σ n+1 / σ n The number of measurements or the measurement time of the measurement data is determined so that the difference (i.e., the difference) is equal to or less than a predetermined threshold.

[0039] For example, the calculation unit 142 calculates the improvement rate 1-(σ n+1 / σ n ) is calculated.

[0040] Then, the determination unit 144 determines the plurality of improvement rates 1-(σ n+1 / σ n), a regression curve is generated that shows the relationship between the number of measurements (or measurement time) of the measurement data and the improvement rate, as shown in Figure 3(B). The horizontal axis of the regression curve graph shown in Figure 3(B) (# of scans) represents the number of measurements, and the vertical axis (Improvement ratio) represents the improvement rate. "Original" in Figure 3(B) represents multiple improvement rates, and "Estimated" represents the regression curve. Also, the "1% line" in Figure 3(B) represents the point where the improvement rate is 1%, and "N=51154" represents the number of measurements where the improvement rate is 1%.

[0041] The determination unit 144 determines the improvement rate 1-(σ n+1 / σ n The number of measurements of the measurement data (for example, "N=51154" in FIG. 3B) is predicted so that the difference (for example, "1% line" in FIG. 3B) is equal to or less than a predetermined threshold (for example, "1% line" in FIG. 3B).

[0042] The output unit 146 outputs the number of measurements (or measurement time) of the measurement data output by the determination unit 144. The output unit 146 also outputs the improvement rate 1-(σ n+1 / σ n ) is equal to or less than the predetermined threshold value, an example of the measurement data at the measurement count (or measurement time) of the measurement data is also output. FIG. 4 is a diagram for explaining an example of the measurement data.

[0043] For example, the output unit 146 outputs information as shown in Fig. 4. Fig. 4 is an example of other measurement data. Fig. 4 shows image data and regression curves obtained from measurement data up to measurement counts N=3, N=42, and N=100. The data output from the output unit 146 is transmitted to the user terminal 12.

[0044] The user operates the user terminal 12 and checks the information displayed on the display unit (not shown) of the user terminal 12. The user then checks the number of measurements (or measurement time) of the measurement data for which the improvement rate is equal to or less than a predetermined threshold, and the information shown in FIG. 4. In this case, by checking other examples of measurement data such as those shown in FIG. 4, the user can understand the level of quality of the data obtained by the number of measurements of the measurement data for which the improvement rate is equal to or less than a predetermined threshold (for example, 1%). For example, as shown in FIG. 4, if the user feels that there is not much difference in quality between an image with a measurement count of N=42 that is recommended as optimal and an image with a measurement count of N=100, N=42 may be adopted as the measurement count.

[0045] 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.

[0046] 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.

[0047] Next, the operation of the information processing system 10 according to the embodiment will be described.

[0048] When the execution of a measurement process for a certain material is started and measurement data is input to the user terminal 12, the measurement data for each measurement is sequentially transmitted to the server 14. When the measurement data is transmitted from the user terminal 12 to the server 14, the acquisition unit 140 of the server 14 acquires the measurement data transmitted from the user terminal 12. The acquisition unit 140 then stores the measurement data in the data storage unit 141. The server 14 then executes the information processing routine shown in FIG. 6.

[0049] In step S100, the calculation unit 142 of the server 14 acquires, from the data storage unit 141, the measurement data measured up to the number n (or time n) and the measurement data measured up to the number n+1 (or time n+1).

[0050] In step S102, the calculation unit 142 of the server 14 calculates a first statistic σ n and the second statistic σ, which represents the variance of the measurement data measured up to the number n+1 (or time n+1). n+1 Calculate the following.

[0051] In step S104, the calculation unit 142 of the server 14 calculates the first statistic σ n and the second statistic σ n+1 Based on this, the improvement rate is 1-(σ n+1 / σ n ) is calculated.

[0052] In step S106, the calculation unit 142 of the server 14 calculates the improvement rate 1-(σ n+1 / σ n The number of measurements of the measurement data (for example, "N=51154" in FIG. 3B) is determined so that the difference (for example, "1% line" in FIG. 3B) is equal to or less than a predetermined threshold (for example, "1% line" in FIG. 3B).

[0053] In step S108, the output unit 146 of the server 14 outputs the number of measurements (or measurement time) of the measurement data determined in step S106. The output unit 146 of the server 14 also outputs the improvement rate 1-(σn+1 / σ n ) is equal to or less than the predetermined threshold, an example of the measurement data (for example, FIG. 4 above) at the measurement count (or measurement time) of the measurement data is also output.

[0054] The data output from the output unit 146 of the server 14 is transmitted to the user terminal 12 .

[0055] The user operating the user terminal 12 checks the data output from the server 14. Then, for example, the user operating the user terminal 12 checks the improvement rate 1-(σ n+1 / σ n The number of measurements (or measurement time) of measurement data at which the difference (%) is equal to or less than a predetermined threshold is adopted, and the measurement process is repeated until the number of measurements (or measurement time) is reached.

[0056] As described above, the server of the information processing system according to the embodiment acquires measurement data obtained by performing a predetermined measurement process on a material. The server calculates an improvement rate representing the improvement in the measurement data between the measurement data measured up to the nth count (or time n) and the measurement data measured up to the nth count (or time n+1) based on a first statistic representing the variability in the measurement data measured up to the nth count (or time n) and a second statistic representing the variability in the measurement data measured up to the nth count (or time n+1). The server determines the number of measurements or the measurement time of the measurement data such that the calculated improvement rate is equal to or less than a predetermined threshold. The server outputs the determined number of measurements or the measurement time of the measurement data. This makes it possible to easily determine the measurement time or the number of measurements for the measurement process on the material while performing the measurement process on the material.

[0057] Furthermore, the server of the information processing system according to the embodiment generates a regression curve that represents the relationship between the number of measurements or the measurement time of the measurement data and the improvement rate, and predicts the number of measurements or the measurement time of the measurement data that will make the improvement rate equal to or less than a predetermined threshold, based on the regression curve. This allows for easy prediction of the measurement time or the number of measurements in the measurement process for the material by generating a regression curve using several pieces of measurement data obtained by the initial measurement process.

[0058] Furthermore, the server of the information processing system according to the embodiment also outputs examples of measurement data at the number of measurements or measurement times at which the improvement rate is equal to or less than a predetermined threshold. This provides examples of measurement data at the measurement time or number of measurements that are expected to be optimal, thereby assisting the user in making a decision about the measurement time or number of measurements.

[0059] Furthermore, 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, 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, a regression curve is generated and the number of measurements or the measurement time of the measurement data are predicted so that the improvement rate is equal to or less than a predetermined threshold. However, the present invention is not limited to this. For example, the server 14 may output an alert to the user terminal 12 when the number of measurements or the measurement time of the current measurement data exceeds the number of measurements or the measurement time of the determined measurement data (the number of measurements or the measurement time corresponding to the predetermined threshold). This allows the user to be notified in real time that the number of measurements or the measurement time of the current measurement data has exceeded the optimal measurement time or the number of measurements.

[0062] In the above embodiment, the coefficient of variation is used as the first and second statistics representing the variation when the measurement data is normally distributed. However, the present invention is not limited to this. Any statistics representing the variation of the measurement data may be used. For example, the first and second statistics may be parameters corresponding to the type of data distribution, such as a Poisson distribution.

[0063] In the above embodiment, the improvement rate is 1-(σ n+1 / σ n ) is used as an example, but the present invention is not limited to this, and any statistic that represents the improvement rate of measurement data may be used. For example, the improvement rate may be calculated using a trained model that has been trained in advance by machine learning. In this case, for example, when the first statistical quantity and the second statistical quantity are input to the trained model, the trained model may be configured to output the improvement rate. Alternatively, for example, a trained model that has been trained in advance by machine learning may be used to determine the number of measurements or the measurement time of measurement data that will result in the improvement rate being equal to or less than a predetermined threshold. In this case, for example, when the first statistical quantity and the second statistical quantity are input to the trained model, the trained model may be configured to output the number of measurements or the measurement time of measurement data that will result in the improvement rate being equal to or less than a predetermined threshold. [Explanation of symbols]

[0064] 10 Information Processing Systems 12 User terminal 14 Servers 50 Computers 53 Storage section 140 Acquisition Department 141 Data storage unit 142 Calculation section 144 Decision Section 146 Output section

Claims

1. an acquisition unit that acquires measurement data obtained by performing a predetermined measurement process on the material; a calculation unit that calculates an improvement rate that represents an improvement in the measurement data between the measurement data measured up to the nth number of times or the nth time and the measurement data measured up to the nth number of times or the nth time, based on a first statistic that represents a variance in the measurement data measured up to the nth number of times or the nth time, and a second statistic that represents a variance in the measurement data measured up to the nth number of times or the nth time, both acquired by the acquisition unit; a determination unit that determines the number of measurements or the measurement time of the measurement data so that the improvement rate calculated by the calculation unit is equal to or less than a predetermined threshold; an output unit that outputs the number of measurements or the measurement time of the measurement data determined by the determination unit; An information processing device comprising:

2. The calculation unit calculates the improvement rate for a plurality of different target counts or target times, the determination unit generates a regression curve representing a relationship between the improvement rate and the number of measurements or the measurement time of the measurement data, based on the plurality of improvement rates, and predicts, based on the regression curve, the number of measurements or the measurement time of the measurement data such that the improvement rate is equal to or less than a predetermined threshold. The information processing device according to claim 1 .

3. The output unit also outputs examples of the measurement data at the measurement count or measurement time of the measurement data where the improvement rate is equal to or less than a predetermined threshold.

3. The information processing device according to claim 1.

4. Acquiring measurement data obtained by performing a predetermined measurement process on the material; calculating an improvement rate representing an improvement in the measurement data between the measurement data measured up to the nth number of times or the nth time and the measurement data measured up to the nth number of times or the nth time, based on a first statistic representing a variance in the measurement data measured up to the nth number of times or the nth time, and a second statistic representing a variance in the measurement data measured up to the nth number of times or the nth time; determining the number of measurements or the measurement time of the measurement data such that the calculated improvement rate is equal to or less than a predetermined threshold; outputting the determined number of measurements or measurement time of the measurement data; An information processing method in which processing is performed by a computer.

5. Acquiring measurement data obtained by performing a predetermined measurement process on the material; calculating an improvement rate representing an improvement in the measurement data between the measurement data measured up to the nth number of times or the nth time and the measurement data measured up to the nth number of times or the nth time, based on a first statistic representing a variance in the measurement data measured up to the nth number of times or the nth time, and a second statistic representing a variance in the measurement data measured up to the nth number of times or the nth time; determining the number of measurements or the measurement time of the measurement data such that the calculated improvement rate is equal to or less than a predetermined threshold; outputting the determined number of measurements or measurement time of the measurement data; An information processing program that causes a computer to execute a process.

Images