Information processing device, information processing method, and computer program

Abstract

To provide an information processing device, an information processing method, and a computer program that allow appropriate acquisition of a desired physical amount by machine learning from part of waveform data relating to heat characteristics.SOLUTION: An information processing device 1 that performs data analysis based on waveform data relating to heat characteristics by machine learning includes: a processor that executes a computer program; and a storage device that stores the computer program. The storage device further stores parameter used for the data analysis, which is derived based on teacher data including a plurality of pieces of waveform data to each of which an annotation indicating a peak is attached. The processor receives the waveform data relating to heat characteristics; determines a peak of a waveform based on a curvature or variation value of the waveform data and a threshold included in the parameter; and updates the threshold based on both the determined peak of the waveform data and the peak of the teacher data.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] In materials development or product testing, it is important to know how a material behaves with respect to temperature changes. To do this, there is a technique called thermal analysis, in which a controlled temperature change is imposed on a material and the physical quantities of the material change under that temperature change. In general, values ​​such as heat flow, mass, and elastic modulus are measured as functions of temperature and time, which can be considered as essentially continuous values, and are recorded in the form of waveform data, which is a type of non-structured data.

[0003] To obtain physical quantities related to the thermal properties of a material from the waveform data obtained in this way, it is usually necessary to process the waveform data. For example, in one type of signal processing, when the first or higher derivatives of the waveform data are discontinuous, the temperature at that time is obtained as the transition temperature at which the material undergoes a phase transition. In another type of signal processing, when the heat flow has a peak shape near the transition temperature, the area enclosed by the peak is obtained as the enthalpy change of the material before and after the phase transition. However, this signal processing often depends on the user's knowledge of materials and thermal analysis, and the difficulty of technology transfer due to its high degree of personalization has often been an issue.

[0004] There are attempts to automate this signal processing using machine learning to reduce dependency on individual skills and at the same time improve throughput. However, this signal processing may differ depending on the purpose of the thermal analysis. For example, should one peak be the subject of the enthalpy change acquisition process? It is usually difficult to collect the necessary learning data for machine learning to have sufficient accuracy for each use case and purpose.

[0005] Patent Document 1 discloses a thermal analysis data processing device capable of detecting inflection point temperatures with high accuracy from thermal analysis data of various substances. The device is a thermal analysis data processing device that processes thermal analysis data of a sample, and includes a condition setting unit that sets detection conditions for the inflection point temperature by machine learning teacher data including known data, which is known thermal analysis data, and correct temperatures, which are inflection point temperatures previously specified in the known data, and a temperature detection unit that detects the inflection point temperature from the thermal analysis data of the sample in accordance with the detection conditions. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] JP 2023-80556 A Summary of the Invention [Problem to be solved by the invention]

[0007] In the technology disclosed in Patent Document 1, the detection of the inflection point temperature, which is one of the physical quantities to be obtained by thermal analysis, can be automated by machine learning. However, in Patent Document 1, physical quantities other than the inflection point temperature cannot be obtained. In particular, the inflection point temperature can be determined in principle based on the first derivative value of the waveform, regardless of the difference in use case or analysis purpose, and can be obtained relatively easily as a physical quantity. For this reason, it is also applicable to physical quantities that are more difficult to obtain, such as the amount of enthalpy change near the transition point, and there is a need for an apparatus that can accurately obtain physical quantities according to the difference in use case or analysis purpose by machine learning using a small amount of learning data.

[0008] One objective of the present disclosure is to provide an information processing device, an information processing method, and a computer program that enable a desired physical quantity to be appropriately acquired from a portion of waveform data related to thermal characteristics through machine learning. [Means for solving the problem]

[0009] In order to solve the above problem, an information processing device according to one aspect of the present invention is an information processing device that performs data analysis based on waveform data related to thermal characteristics through machine learning, and includes a processor that executes a computer program and a storage device that stores the computer program, and the storage device further stores parameters used in the data analysis derived based on teacher data including a plurality of waveform data each of which is annotated to indicate a peak, and the processor receives the waveform data related to thermal characteristics, identifies a peak in the waveform based on a curvature or variation value of the waveform data and a threshold value included in the parameters, and updates the threshold based on the identified peak of the waveform data and the peak of the teacher data. Effect of the Invention

[0010] According to the present invention, a waveform peak can be identified based on the curvature or variation value of waveform data related to thermal characteristics and a threshold value included in the parameters, and the threshold value can be updated based on the identified peak of the waveform data and the peak of the teacher data. [Brief description of the drawings]

[0011] [Figure 1] FIG. 1 is a block diagram of an information processing apparatus according to a first embodiment. [Diagram 2] FIG. 2 is a block diagram showing an example of a hardware configuration of a computer. [Diagram 3] FIG. 3 is a diagram illustrating an example of input waveform data according to the first embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of peak data according to the first embodiment. [Diagram 5] FIG. 5 is an explanatory diagram of an example of a setting screen for learning information according to the first embodiment. [Figure 6] FIG. 6 is a flowchart of an example of a procedure for calculating curvatures, etc., performed by the curvature, etc., calculation unit according to the first embodiment. [Figure 7] FIG. 7 is a flowchart of an example of a peak determination procedure performed by the peak determination unit according to the first embodiment. [Figure 8] FIG. 8 is a flowchart of an example of a parameter update procedure performed by the parameter update unit according to the first embodiment. [Figure 9] FIG. 9 is an explanatory diagram illustrating an example of the parameter data. [Figure 10] FIG. 10 is an explanatory diagram illustrating an example of the difference data. [Figure 11] FIG. 11 is a block diagram of an information processing apparatus according to the second embodiment. [Figure 12] FIG. 12 is a diagram illustrating an example of peak boundary data according to the second embodiment. [Figure 13] FIG. 13 is a flowchart of an example of a boundary determination procedure performed by the boundary determining unit according to the second embodiment. [Figure 14] FIG. 14 is a flowchart of an example of a parameter update procedure performed by the parameter update unit according to the second embodiment. [Figure 15] FIG. 15 is a block diagram of an information processing apparatus according to the third embodiment. [Figure 16] FIG. 16 is an explanatory diagram showing an example of material physical quantity data. [Figure 17] FIG. 17 is a flowchart of an example of a parameter update procedure performed by the parameter update unit according to the third embodiment. [Figure 18] FIG. 18 is a block diagram of an information processing apparatus according to a fourth embodiment. [Figure 19] FIG. 19 is a flowchart of an example of a robustness information calculation procedure performed by the robustness information calculation unit according to the fourth embodiment. [Figure 20A] FIG. 20A is an explanatory diagram illustrating an example of a robustness information display screen according to the fourth embodiment. [Figure 20B] FIG. 20B is an explanatory diagram showing another example of the robustness information display screen according to the fourth embodiment. [Figure 20C] FIG. 20C is an explanatory diagram illustrating another example of the robustness information display screen according to the fourth embodiment. [Figure 21] FIG. 21 is a block diagram of an information processing apparatus according to a fifth embodiment. [Figure 22]FIG. 22 is a flowchart of an example of a robustness information calculation procedure performed by the robustness information calculation unit according to the fifth embodiment. [Figure 23A] FIG. 23A is an explanatory diagram illustrating an example of a robustness information display screen according to the fifth embodiment. [Figure 23B] FIG. 23B is an explanatory diagram showing another example of the robustness information display screen according to the fifth embodiment. [Figure 23C] FIG. 23C is an explanatory diagram illustrating another example of the robustness information display screen according to the fifth embodiment. [Figure 24] FIG. 24 is a block diagram of an information processing apparatus according to a sixth embodiment. [Diagram 25] FIG. 25 is a diagram illustrating an example of input waveform data according to the sixth embodiment. [Figure 26] FIG. 26 is a flowchart of an example of a parameter update procedure performed by the parameter update unit according to the sixth embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. In this embodiment, parameters used in machine learning for thermal analysis are optimized with a small amount of waveform data. As a result, in this embodiment, machine learning is realized for acquiring physical quantities according to differences in use cases or analysis purposes from waveform data related to thermal characteristics. In this embodiment, as described later, a basic algorithm is defined and only important parameters are adjusted, so that physical quantities according to differences in use cases or analysis purposes can be acquired from a small amount of data.

[0013] In this embodiment, for example, in data analysis in thermal analysis, a point where the curvature (or variation value) exceeds a threshold is identified as a waveform peak, and the identified threshold is updated based on a comparison between the peak of the waveform data to be analyzed and the peak of the teacher data (waveform). As a result, in this embodiment, for example, for a material that undergoes a slow phase transition such as a polymer material, a parameter (threshold) to be used in thermal analysis can be identified from a small amount of teacher data, and accurate thermal analysis can be performed.

[0014] The information processing device disclosed in this embodiment has a processor that executes a computer program and a storage device that stores the computer program, and is an information processing device that performs data analysis based on waveform data related to thermal characteristics, in which the storage device stores parameters used for data analysis derived based on teacher data including multiple waveform data, each of which is annotated to indicate a peak (the apex of the peak waveform), and the processor receives the waveform data related to thermal characteristics, identifies a peak of the waveform based on a curvature or variation value of the waveform data and a threshold value included in the parameters, and updates the threshold based on the identified peak of the waveform data and the peak of the teacher data. EXAMPLES

[0015] A first embodiment will be described with reference to Figures 1 to 10. Figure 1 is a block diagram of an information processing device according to the first embodiment. Figure 2 is a block diagram showing the hardware configuration of a computer included in the information processing device.

[0016] 1, an information processing device 1 includes, for example, computers 100-1 and 100-2 and a terminal 101. The computers 100-1 and 100-2 and the control terminal 101 are connected to a communication network 102. The communication network 102 is a facility that enables data transmission and reception via wired or wireless lines.

[0017] The computer 100-1 is a computer that can access teacher waveform data 110. The teacher waveform data 110 stores, for example, input waveform data 111 related to thermal characteristics and peak data 112 that designates a peak that is a target for acquiring a corresponding physical quantity.

[0018] The computer 100-2 includes, for example, a learning information input receiving unit 120, a curvature etc. calculating unit 121, a peak determining unit 122, and a parameter updating unit 123. The computer 100-2 is a computer that outputs the results of machine learning using teacher waveform data 110 as input, and is a computer that can access parameter data 124 and difference data 125. Hereinafter, when there is no need to distinguish between the computers 100-1 and 100-2, they may be collectively referred to as the computers 100. The terminal 101 is a computer terminal for control that can access the computers 100-1 and 100-2.

[0019] With reference to FIG. 2, the computer 100 includes, for example, a processor 201, a main memory device 202, a secondary memory device 203, a network interface 204, an input device 205, and an output device 206.

[0020] The secondary storage device 203 is a device for storing data in a writable and readable manner. Data to be used in calculation processing and the results of calculation processing are stored in the secondary storage device 203.

[0021] Processor 201 is a device that reads data stored in secondary storage device 203 into primary storage device 202 and executes a software computer program (not shown). Curvature etc. calculation unit 121, peak determination unit 122, and parameter update unit 123 in computer 100-2 are realized by processor 201 executing the software computer program.

[0022] The network interface 204 is a device that transmits and receives data to and from other devices via the communication network 102. The network interface 204 can transmit data resulting from processing by the processor 201 to other devices via the communication network 102. The network interface 204 can receive data to be used for processing by the processor 201 from other devices via the communication network 102.

[0023] The input device 205 is a device such as a keyboard or a mouse that accepts user operations and acquires information input by user operations. The output device 206 is a device that outputs information to a monitor display or a printer, and presents information to the user by displaying it on a screen, for example.

[0024] Returning to Fig. 1, the computer 100-1 is able to access teacher waveform data 110. The teacher waveform data 110 stores input waveform data 111 and peak data 112.

[0025] 3 is an explanatory diagram illustrating an example of the input waveform data 111 according to the first embodiment. The input waveform data 111 includes, for the input waveform data 111 related to thermal characteristics, an attribute 310 that describes the attribute of the waveform, and a waveform descriptor 320 that describes a measurement value for each time and temperature.

[0026] The feature 310 is assigned an input waveform data ID 311 that is an individual identification number for the input waveform data 111. The feature 310 can include information used in analyzing the input waveform data, such as a temperature change computer program for performing unit conversion related to the numerical value stored in the waveform descriptor 320, limiting the measurement target, and the like, and the amount of sample.

[0027] The waveform descriptor 320 stores the time 330-1, the temperature 330-2, and the measurement values ​​340 such as heat flow at each time point. The time 330-1 and the temperature 330-2 are recorded at intervals that can be considered as substantially continuous values, and when the corresponding measurement values ​​340 are plotted, a continuous waveform-shaped graph is obtained. In the following, the time 330-1 and the temperature 330-2 may both be referred to as time. In the following, a heating program that performs analysis while applying a heat flow to a substance is used as an example, and the low and high temperatures are explained in correspondence with each other before and after the time. However, the present invention can also be applied to the observation of thermal characteristics during cooling of a substance by appropriately interpreting the high and low temperatures. The first-order differentials and higher-order differentials of the measurement values ​​340 with respect to the time 330-1 and the temperature 330-2 can be substantially obtained from the difference values ​​with respect to the time 330-1 and the temperature 330-2, and therefore, in the following, the terms differential and difference are used without distinction. The points where the absolute values ​​of the waveform, first derivative, and higher derivatives are extremely large correspond to the phase transition points of the substance. Obtaining the peak areas of the waveform around the phase transition points corresponds to the "calculation of physical quantities" as the purpose of thermal analysis.

[0028] FIG. 4 is an explanatory diagram showing an example of the peak data 112 according to the first embodiment. For the input waveform data 111 identified by the input waveform data ID 311, the measured values ​​340 corresponding to the time 330-1 and the temperature 330-2 are plotted to obtain a waveform 400. In this waveform 400, a peak location 410 to be extracted is identified by values ​​such as the time 330-1 and the temperature 330-2. It is also possible to include identification of a phase transition point 420 to be extracted, not limited to a peak. Even if a peak-shaped location 430 in the waveform is not included in the peak data 112 as an extraction target according to knowledge about the target material or the purpose of the analysis, the purpose of the analysis can be reflected.

[0029] Returning to Fig. 1, the computer 100-2 has a learning information input accepting unit 120 that accepts input of learning information. The learning information input accepting unit 120 displays necessary information on the terminal 101 in order to accept input from a user regarding machine learning setting information. The learning information input accepting unit 120 applies the setting information regarding machine learning input from the terminal 101 to processing of the curvature etc. calculation unit 121 and the like.

[0030] 5 shows an example of a screen 500 for accepting input of settings related to machine learning. This screen 500 is generated by the learning information input accepting unit 120 and provided to the user from the terminal 101. The screen 500 may be called a learning information input screen, or a setting screen. The screen 500 is displayed on the terminal 101, accepts input from the user related to machine learning settings, and transmits the input to the curvature etc. calculation unit 121, etc.

[0031] As an example, screen 500 may include a learning data specification field 510, a learning parameter search method specification field 520, an initial parameter determination method setting field 530, a learning parameter search range setting field 540, a loss function specification field 550, a behavior setting field 560 when peaks are excessively detected, a behavior setting field 570 when peaks are underdetected, and a preprocessing information setting field 580.

[0032] The learning data specification field 510 is a field for selecting teacher waveform data 110. An extraction target according to the purpose of each analysis is specified by peak data 112, and machine learning is performed using the peak data 112, so that the purpose of the analysis can be appropriately reflected.

[0033] The learning parameter search method specification field 520 is a field for selecting a parameter search method related to parameter update by machine learning. The parameter update unit 123 calculates the difference between the peak candidate information calculated for the parameters specified based on the method and the peak data 112, and machine learning is performed so that the optimal parameters for peak extraction can be selected based on the calculated value. The user can specify that the learning parameter search range set in the learning parameter search range setting field 540 is searched by grid search, or can specify that the parameters are searched by Bayesian optimization such as GP-UCB (Gaussian Process Upper Confidence Bound).

[0034] The initial parameter determination method setting field 530 is a field for selecting a method for determining the initial values ​​of the learning parameters. The parameter update unit 123 calculates the difference between the peak candidate information calculated for the parameters specified based on the method and the peak data 112, and machine learning is performed so that the optimal parameters for extracting the peak can be selected based on the calculated value. The user can specify that the initial values ​​are to be determined randomly from the learning parameter search range set in the learning parameter search range setting field 540, or can specify a file including past machine learning results to adopt the parameters that were optimized in the past machine learning results as the initial values.

[0035] The learning parameter search range setting field 540 is a field for setting the upper and lower limits of the search range when searching for learning parameters. By appropriately specifying the range, the user can set it so that efficient machine learning is performed without unnecessary parameter searches. By setting the search range for the variation value or curvature to different ranges for positive values ​​and negative values, it is also possible to set it so that it has different sensitivities for upward peaks and downward peaks (not shown).

[0036] The loss function designation field 550 is a field for selecting a loss function to be used as an evaluation method when the parameter update unit 123 evaluates the difference between the calculated peak candidate information and the peak data 112. By designating the loss function, the user can easily reflect the purpose of the analysis by controlling the weights of the multiple differences, particularly when multiple peaks are included in one input waveform data.

[0037] The peak overdetection behavior setting field 560 and the peak underdetection behavior setting field 570 are fields for setting behavior when the number of peaks included in the peak candidate information calculated using the specified parameters differs from the number of peaks included in the peak data 112, and the difference information between them cannot be simply calculated. By specifying the setting fields, the user can search for parameters that do not cause overdetection or underdetection by applying a large penalty value to overdetection or underdetection. Furthermore, the user can control the detection sensitivity by setting the value of the loss function related to overdetection or underdetection to zero, making it easier to reflect the analysis purpose.

[0038] The preprocessing information setting field 580 is a field for setting preprocessing that is applied to the input waveform data 111 before the curvature etc. calculation unit 121 calculates the curvature etc. The user can set, for example, to perform smoothing of the waveform 400. The user can set information such as the range of time 330-1 and temperature 330-2 to be referenced by the smoothing, or can set the information to be the subject of machine learning in this information processing device and input setting information related to the machine learning.

[0039] The user sets some or all of the learning data specification field 510, learning parameter search method specification field 520, initial parameter determination method setting field 530, learning parameter search range setting field 540, loss function specification field 550, peak excessive detection behavior setting field 560, peak underdetection behavior setting field 570, and preprocessing information setting field 580, and presses the save button 501. As a result, the information set in each unit 510-580 is applied to processing by the curvature etc. calculation unit 121 etc. These setting information can also be stored in the secondary storage device 203.

[0040] The GUI (Graphical User Interface) shown in the screen 500 in Fig. 5 is an example and is not limited to this. The user does not necessarily need to set all the setting items, and there is no prevention of the settings being automatically determined by an appropriate method.

[0041] 1, the computer 100-2 has a curvature etc. calculation unit 121. The curvature etc. calculation unit 121 calculates the curvature etc. of the waveform 400 related to the input waveform data 111 that has been input.

[0042] 6 is a flowchart showing an example of a procedure for calculating curvatures, etc., by the curvature, etc., calculation unit 121. The curvature, etc., calculation unit 121 acquires setting information I specified by a user operating the terminal 101, and further acquires input waveform data 111 specified by the setting information I (S601).

[0043] The curvature etc. calculation unit 121 performs pre-processing on the input waveform data 111 based on the acquired setting information I (S602). The pre-processing is smoothing of the waveform 400, etc., specified in the pre-processing information setting field 580.

[0044] The curvature etc. calculation unit 121 calculates the variation value and curvature of the waveform 400 at each time specified by the time 330-1 and temperature 330-2 of the input waveform data 111 as the curvature etc. information (S603). As described above, the variation value and curvature can be calculated using the difference between the values ​​at each time and the values ​​at adjacent points. The curvature etc. information calculated here does not preclude the inclusion of values ​​related to third or higher order differentials. The curvature etc. information may be calculated from values ​​at a certain moment, or may be information based on the change in value within a certain time range (value range in multiple steps).

[0045] The curvature etc. calculation unit 121 transmits the curvature etc. information calculated in step S603 to the peak determination unit 122 and ends the process (S604).

[0046] Returning to Fig. 1, the computer 100-2 has a peak determination unit 122. The peak determination unit 122 calculates peak candidates based on specific parameters from the received information on curvature, etc.

[0047] 7 is a flowchart showing an example of a procedure for determining a peak candidate by the peak determining unit 122. The peak determining unit 122 acquires setting information I designated by the user operating the terminal 101, curvature information etc. transmitted from the curvature etc. calculating unit 121, and parameter data 124 and difference data 125 described later (S701). The parameter data 124 is information on a small number of parameter sets that control the behavior of information processing for determining a peak, and is data related to the history of parameter sets that were targets in past trials. The difference data 125 is data storing a difference value evaluated by the parameter updating unit 123 described later regarding the difference between the peak candidate information calculated for the parameter set that was targets in the past trial and the peak data 112.

[0048] The peak determination unit 122 creates a learning parameter set P to be tried this time from the history contained in the parameter data 124 and the difference data 125 based on the setting information I set in the learning parameter search method specification field 520, the initial parameter determination method setting field 530, the learning parameter search range setting field 540, etc. (S702).

[0049] The peak determination unit 122 calculates threshold information such as curvature thresholds for the variation and curvature of the waveform 400, which are used to identify peak candidates, from the setting information I and the created training parameter set P (S703). The parameter data 124 and training parameter set P may include the variation and curvature thresholds themselves. The variation and curvature thresholds may be ratios of the variation and curvature thresholds to the maximum variation and curvature of the waveform 400 for each input waveform data 111.

[0050] The peak determination unit 122 compares the curvature etc. information with the curvature etc. threshold information, and extracts the time 330-1 or temperature 330-2 of the input waveform data 111 relating to the time having the variation value or curvature exceeding the threshold as peak candidate information (S704). When multiple times belonging to the same vicinity are simultaneously extracted as peak candidates, the peak determination unit 122 may include processing such as extracting only the time having the maximum value as a representative value as a peak candidate and deleting the other times from the peak candidates.

[0051] The peak determining unit 122 transmits the extracted peak candidate information to the parameter updating unit 123 and ends the process (S705).

[0052] Returning to Fig. 1, the computer 100-2 has a parameter update unit 123. The parameter update unit 123 compares the received peak candidate information with the peak data 112 to calculate a difference, stores the difference in difference data 125 as an evaluation of the learning parameter set P, and updates the parameter data 124 based on the evaluation.

[0053] 8 is a flowchart showing an example of a parameter updating procedure by the parameter updating unit 123. The parameter updating unit 123 acquires setting information I specified by a user operating the terminal 101, peak candidate information transmitted from the peak determining unit 122, the input waveform data 111, the peak data 112, and the parameter data 124 (S801).

[0054] The parameter update unit 123 evaluates the difference between the time specifying the peak included in the peak candidate information and the time specifying the peak stored in the peak data 112 based on the setting information I specified in the loss function specification field 550, the behavior setting field 560 at the time of peak overdetection, the behavior setting field 570 at the time of peak underdetection, and the preprocessing information setting field 580, and calculates the difference information (S802).

[0055] The parameter update unit 123 stores the currently tried learning parameter set P in the parameter data 124, and correspondingly stores the difference information together with the input waveform data ID 311 related to the input waveform data 111 in the difference data 125 (S803).

[0056] The parameter update unit 123 refers to the difference data 125 and updates the parameter data 124 as necessary (S804). That is, the parameter update unit 123 refers to the difference data 125 related to the parameter data 124 tried in the past for the same or similar input waveform, and if it is determined that the difference data related to the learning parameter set P has a smaller value than the difference data 125 and is suitable for actual peak candidate extraction, the parameter update unit 123 performs an update process such as setting a flag to that effect for the learning parameter set P stored in the parameter data 124, and ends the process (S804). The parameter update unit 123 can refer to the feature 310 when determining the identity or similarity of the input waveforms.

[0057] Returning to FIG. 1, the computer 100 - 2 can access the parameter data 124 and the difference data 125 .

[0058] 9 is an explanatory diagram showing an example of the parameter data 124 according to the embodiment 1. Each parameter set stored in the parameter data 124 is assigned a parameter set ID 910 which is an individual identification number.

[0059] For the parameter sets stored in the parameter data 124, the parameter update unit 123 refers to the difference data 125, and for those parameter sets that are determined to be suitable for actual peak candidate extraction based on the past trial history, this is recorded in the optimum flag 920 together with information on what waveform, what substance, and what experimental conditions the parameter set is suitable for.

[0060] Here, assuming that extraction should be performed using a single parameter set for all substances and all experimental conditions, it does not preclude a data format in which only a single parameter set ID is recorded separately and the optimal flag 920 is not attached to each record of the parameter data 124.

[0061] The parameter data 124 stores the values ​​of parameters 930, which are a small number of parameters that control the behavior of peak candidates and are the subject of search. As described above for the learning parameter P, the parameters 930 can be a threshold value 930-1 for the variation value and a threshold value 930-2 for the curvature. The parameters 930 can be the ratios of the threshold values ​​for the variation value and the curvature to the maximum values ​​of the variation value and the curvature for the waveform 400 associated with each piece of input waveform data 111. If set in the preprocessing information setting field 580, a parameter 930-3 relating to preprocessing can be included in the parameter data 124.

[0062] In addition, it may be possible that an optimal parameter set cannot be uniquely determined for one waveform or one substance. In this case, an optimal flag may be set for each of multiple parameter sets, and the results calculated using the multiple parameter sets may be provided to the user, who may then select one of the parameter sets.

[0063] 10 is an explanatory diagram showing an example of difference data 125 according to Example 1. The difference data 125 associates a parameter set ID 910 assigned when the learning parameter P is stored in the parameter data 124 with an input waveform data ID 311 assigned to the input waveform data targeted when the parameter update unit 123 evaluates the difference information, and stores the value of the difference information as a difference value 1010.

[0064] In this way, in the first embodiment, when extracting peaks from waveform data related to thermal properties obtained by thermal analysis, the learning target is limited to only a small number of parameters that control the behavior of extraction, such as a threshold value for curvature. Therefore, according to the first embodiment, the user can perform machine learning that enables extraction of peaks that reflect the analysis purpose for each use case by simply creating a relatively small number of peak data 112. The waveform data related to thermal properties may be any one or more of DSC (Differential Scanning Calorimetry) data of thermal analysis, thermogravimetry (TG: Thermogravimetry) data, thermomechanical analysis (TMA: Thermomechanical Analysis) data, dynamic mechanical analysis (DMA: Dynamic Mechanical Analysis) data, and differential thermal analysis (DTA: Differential Thermal Analysis) data. EXAMPLES

[0065] A second embodiment will be described with reference to Figs. 11 to 14. In each of the following embodiments including this embodiment, the differences from the previously described embodiments will be mainly described. In the second embodiment, an example of an information processing device 1A for performing machine learning that enables extraction of peaks reflecting the analysis purpose for each use case when determining the boundary of a peak related to the specification of a baseline for calculating the area swept by the extracted peak candidate is shown.

[0066] 11 is a block diagram of an information processing device 1A according to the second embodiment. In the second embodiment, the teacher waveform data 110 included in the computer 100-1 stores peak boundary data 1102 in addition to the input waveform data 111. The computer 100-2 includes a boundary determination unit 1122 and a parameter update unit 1123 in addition to the learning information input reception unit 120, the curvature etc. calculation unit 121, the peak determination unit 122, the parameter data 124, and the difference data 125.

[0067] FIG. 12 is an explanatory diagram showing an example of the peak boundary data 1102 according to the second embodiment. The peak boundary data 1102 can record a peak start time 1211, which indicates the start point of the peak to be analyzed, and a peak end time 1212, which indicates the end point of the peak to be analyzed, for each of the peak locations 410 to be extracted for the waveform 400 related to the peak data 112. A physical quantity related to the phase transition, such as a solidification start point or a solidification end point, can be calculated from the waveform 400, the peak location 410, the peak start time 1211, and the peak end time 1212. For example, an area surrounded by the baseline 1221, which connects the peak start time 1211 and the peak end time 1212 with a line segment or a smooth curve, and the waveform 400 is calculated as an enthalpy change related to the phase transition.

[0068] 11, the computer 100-2 includes a boundary determining unit 1122. Based on the peak candidate information determined by the peak determining unit 122, the boundary determining unit 1122 calculates a peak boundary candidate related to the peak candidate.

[0069] 13 is a flowchart showing an example of a boundary determination procedure by the boundary determination unit 1122. The boundary determination unit 1122 acquires setting information I specified by a user operating the terminal 101, a learning target parameter set P, peak candidate information, and input waveform data 111 (S1301). The peak determination unit 122 of the second embodiment transmits the learning target parameter set P together with the peak candidate information. The boundary determination unit 1122 acquires the peak candidate information and the learning target parameter set P transmitted from the peak determination unit 122.

[0070] The boundary determining unit 1122 divides the waveform 400 related to the input waveform data 111 for each time of the peak candidate included in the peak candidate information, and creates segmented waveform data (S1302). The boundary determining unit 1122 may create multiple types of segmented waveform data by dividing the waveform 400 for each order of differentiation that the peak determining unit 122 refers to when calculating the peak candidates.

[0071] The boundary determination unit 1122 calculates a section feature characterizing each section for each of the divided section waveform data (S1303). The boundary determination unit 1122 does not prevent the parameters required for calculating the section feature from being included in the learning parameter set P, and from being subject to optimization by machine learning realized by the present information processing system under settings related to machine learning included in the setting information I. In one embodiment, the section feature is the slope of the waveform in the section. In another embodiment, the section feature is the slope of the waveform within a range further limited to an area in the section where the curvature is equal to or less than a certain value. In yet another embodiment, the threshold value of the curvature referred to when limiting the range within the section is included in the learning parameter set P, and is subject to optimization by machine learning realized by the present information processing system 1A.

[0072] The boundary determination unit 1122 calculates threshold information such as a partition curvature, which is a variation value or a curvature threshold value for each partition waveform data, from the calculated partition feature, the learning parameter set P, and the setting information I (S1304). In one embodiment, the partition curvature threshold information is set to a variation threshold value obtained by increasing or decreasing a certain value for the waveform slope within a range further limited to an area in the partition section where the curvature is equal to or less than a certain value. In another embodiment, the certain value to be increased or decreased is included in the learning parameter set P, and is subject to optimization by machine learning realized by the information processing system 1A.

[0073] The boundary determination unit 1122 extracts peak boundary candidates based on the results of comparing the calculated section curvature etc. threshold information with the variation value or curvature value at each time of the section waveform data, and creates peak boundary candidate information (S1305). The peak boundary candidate times are compared, and the later one is set as peak start time 1211 for the peak that divides the waveform at the end time of the section waveform data, and the earlier one is set as peak end time 1212 for the peak that divides the waveform at the start time of the section waveform data. The boundary determination unit 1122 may include a process of extracting only the time furthest or closest to the peak candidate time, or the average time of those, as the peak boundary, among the times at which the variation value or curvature value exceeds the section curvature etc. threshold value.

[0074] The boundary determining unit 1122 determines whether the peak start time and the peak end time have been identified for all the peak candidates (S1306). If it is determined that the peak start time and the peak end time have been identified for all the peak candidates, the boundary determining unit 1122 proceeds to step S1308.

[0075] If it is determined that the peak start time and the peak end time cannot be identified for all the peak candidates, the boundary determination unit 1122 corrects the threshold information for the piece curvature, etc. (S1307). The correction includes changing the values ​​of the parameters referenced when calculating the threshold information for the piece curvature, etc., and then calculating the threshold information for the piece curvature, etc. again. If it is determined that the peak start time and the peak end time cannot be identified for all the peak candidates, the boundary determination unit 1122 may provide a large value as the difference information 1010, transmit the information to the parameter update unit 1123, and end the process (not shown).

[0076] The boundary determining unit 1122 transmits the generated peak boundary candidate information to the parameter updating unit 1123 and ends the process (S1308).

[0077] 11, the computer 100-2 has a parameter update unit 1123. The parameter update unit 1123 compares the peak boundary candidate information with the peak boundary data 1102, calculates the difference, stores it in the difference data 125 as an evaluation of the learning target parameter set P, and updates the parameter data 124 based on the evaluation.

[0078] 14 is a flowchart showing an example of a parameter update procedure by the parameter update unit 1123. The parameter update unit 1123 acquires setting information I specified by a user operating the terminal 101, input waveform data 111, peak boundary data 1102, parameter data 124, difference data 125, and peak boundary candidate information (S1401).

[0079] The parameter updating unit 1123 adopts the acquired peak boundary candidate information as the peak start time 1211 and the peak end time 1212 related to the peak. The parameter updating unit 1123 calculates a physical quantity related to the waveform 400, and compares the calculated physical quantity with a physical quantity related to the waveform 400 calculated using the start time 1211 and the end time 1212 stored in the peak boundary data 1102. The parameter updating unit 1123 evaluates a difference obtained as a result of the comparison based on setting information I specified in the loss function specification field 550, the peak overdetection behavior setting field 560, the peak underdetection behavior setting field 570, the preprocessing information setting field 580, and the like, and calculates difference information (S1402).

[0080] In one embodiment, the comparison of the physical quantities is a direct comparison of the start time 1211 or the end time 1212. In another embodiment, the comparison of the physical quantities is a comparison of the time of the clotting start point or the clotting end point, or the area enclosed by the baseline 1221 and the waveform 400, which is obtained by connecting the peak start time 1211 and the peak end time 1212 with a line segment or a smooth curve. In yet another embodiment, the comparison is a comparison of a weighted linear sum of one or more physical quantities.

[0081] The parameter update unit 1123 updates the parameter data 124 and the difference information 125 based on the calculated difference information, similarly to steps S803 and S804 in the parameter update unit 123 of the first embodiment.

[0082] In this way, in the second embodiment, when extracting physical quantities related to phase transition from waveform data related to thermal properties obtained by thermal analysis, the learning target is limited to only a small number of parameters that control the behavior of extraction, such as the threshold value of curvature, etc. and the threshold value of section curvature, etc. As a result, according to the second embodiment, the user can extract peak boundaries that reflect the analysis purpose for each use case by simply creating a relatively small number of peak boundary data 1102, and can perform machine learning to calculate physical quantities based on the data. EXAMPLES

[0083] 15-17, a third embodiment will be described. In the third embodiment, when a user is unable to create peak data 112 or peak boundary data 1102 and is given only external knowledge regarding the physical quantity of a material to be analyzed, machine learning is performed on determining a peak boundary candidate by comparison with the physical quantity, and parameters suitable for the peak boundary candidate are obtained.

[0084] 15 is a block diagram of an information processing device 1B according to the third embodiment. In the third embodiment, the teacher waveform data 110 included in the computer 100-1 stores only the input waveform data 111, and does not include the peak data 112 or the peak boundary data 1102 corresponding to all the input waveform data 111. The computer 100-1 of the third embodiment includes material data 1510. The material data 1510 stores material physical quantity data 1502 that records the physical quantity related to the substance corresponding to the input waveform data 111. In the third embodiment, the computer 100-2 includes a learning information input receiving unit 120, a curvature etc. calculating unit 121, a peak determining unit 122, a boundary determining unit 1122, parameter data 124, and difference data 125, as well as a parameter updating unit 1523.

[0085] FIG. 16 is an explanatory diagram showing an example of material physical quantity data 1502 according to the third embodiment. The material physical quantity data is assigned with an input waveform data ID 311 that identifies the corresponding material and the experimental conditions under which the data was measured. Furthermore, the material physical quantity data 1502 is assigned with a peak ID 1610 that is an individual identification number that identifies which phase transition point the physical quantity is related to. Furthermore, the material physical quantity data 1502 stores a value 1621 of the physical quantity for the peak for each type of physical quantity. Each record of the material physical quantity data 1502 does not prevent values ​​from being recorded for all physical quantities 1621 for each identified peak. The peak ID 1610 does not prevent a peak from being identified by a single value, but by a range of time of the waveform 400 for identifying the calculated peak candidate.

[0086] 15, the computer 100-2 has a parameter update unit 1523. The parameter update unit 1523 optimizes a parameter set for extracting peak boundary candidates so as to reproduce the physical quantities recorded in the material physical quantity data 1502.

[0087] 17 is a flowchart showing an example of a parameter update procedure by the parameter update unit 1523. The parameter update unit 1523 acquires setting information I specified by a user operating the terminal 101, input waveform data 111, material physical quantity data 1502, parameter data 124, difference data 125, peak candidate information, and peak boundary candidate information (S1701).

[0088] The parameter update unit 1523 employs the acquired peak boundary candidate information as the peak start time 1211 and the peak end time 1212 related to the peak, calculates a physical quantity related to the waveform 400, compares it with the physical quantity value 1621 recorded in the material physical quantity data 1502 specified by the corresponding input waveform data ID 311 and peak ID 1610, evaluates the difference based on the setting information I specified in the loss function specification field 550, the peak overdetection behavior setting field 560, the peak underdetection behavior setting field 570, and the preprocessing information setting field 580, and calculates difference information (S1702).

[0089] Thereafter, the parameter update unit 1523 updates the parameter data 124 and the difference data 125 based on the calculated difference information in the same process as the parameter update unit 1123 according to the second embodiment (S803, S804).

[0090] Thus, according to Example 3, even if peak boundary data is not obtained and only external knowledge regarding the physical quantities of the material to be analyzed is given, machine learning can be performed to determine peak boundary candidates by comparison with the physical quantities, and parameters suitable for the peak boundary candidates can be obtained. EXAMPLES

[0091] 18 to 20C, a fourth embodiment will be described. In the fourth embodiment, an example of an information processing device 1C is shown for extracting peak candidates from new waveform data using a parameter set for extracting peak candidates optimized in the first embodiment, and simultaneously displaying the result of extracting the peak candidates as a robustness evaluation result even when a small perturbation is applied to the value of the parameter set.

[0092] 18 is a block diagram of an information processing device 1C according to the fourth embodiment. In the fourth embodiment, the waveform data 1810 included in the computer 100-1 stores the input waveform data 111. The computer 100-2 includes a robustness information calculation unit 1823 in addition to the learning information input reception unit 120, the curvature etc. calculation unit 121, the peak determination unit 122, and the parameter data 124.

[0093] 19 is a flowchart illustrating an example of a robustness information calculation procedure by the robustness information calculation unit 1823 according to the embodiment 4. The robustness information calculation unit 1823 acquires setting information I, curvature information, etc., input waveform data 111, and parameter data 124 (S1901).

[0094] The robustness information calculation unit 1823 references the feature 310 of the input waveform data 111 and the optimum flag 920 of the parameter data 124 to obtain a parameter set P used to calculate peak candidates, and applies perturbations to the values ​​of various parameters in the parameter set P to create one or more robustness evaluation parameter sets P' (S1902). Perturbations do not necessarily need to be applied to all parameters in the parameter set P, but can be applied to only a small number of parameters selected by any method. There are also no limitations on the magnitude and distribution of the perturbations.

[0095] The robustness information calculation unit 1823 creates a curvature etc. threshold information set by calculating and combining curvature etc. threshold information based on each of the robustness evaluation parameter sets P' in a manner similar to that in which the peak determination unit 122 in Example 1 calculates curvature etc. threshold information based on the setting information I and the learning target parameter set P (S1903).

[0096] The robustness information calculation unit 1823 extracts peak candidate information by comparing each of the curvature etc. threshold information included in the created curvature etc. threshold information set with the received curvature etc. information, in a similar manner to the peak determination unit 122 according to the first embodiment, which compares the curvature etc. information with the curvature etc. threshold information, and calculates a peak candidate information set by combining them (S1904).

[0097] The robustness information calculation unit 1823 associates each record of the calculated peak candidate information set with each robustness evaluation parameter set P'. The robustness information calculation unit 1823 refers to the setting information I and creates robustness information required for displaying a robustness information display screen, which will be described later, on the terminal (S1905). The robustness information is information that associates the difference between the value of each record of the parameter set P, which is optimal for analyzing the target input waveform data 111, and the robustness evaluation parameter set P' with the time of the peak candidate recorded in the peak candidate information. In one embodiment, the robustness information is created using only records of the peak candidate information set, the magnitude of the difference from the peak candidate based on the parameter set P exceeds a threshold value set by the setting information I, rather than using all the records of the robustness evaluation parameter set P'.

[0098] The robustness information calculation unit 1823 transmits the generated robustness information and ends the process (S1906). The transmitted robustness information is output to the terminal 101 as a robustness information display screen and is perceived by the user.

[0099] 20A is an explanatory diagram showing an example of a robustness information display screen according to Example 4. As an example, a robustness information display screen 2000A can include an input waveform specification field 2001 and a perturbation variation display field 2011. When one input waveform data 111 includes multiple peak candidates, it is also possible to display multiple sets of this information for each peak candidate on the same screen or on multiple screens that can be switched by operation.

[0100] The input waveform identification field 2001 displays information related to the characteristics 310 of the target input waveform data 111 and information for identifying the target peak candidate. These can be identifiers that are assigned in the same manner as the input waveform data ID 311 and the peak ID 1610.

[0101] The perturbation variation display field 2011 displays robustness information. In one embodiment, for each robustness evaluation parameter set P' in which one or two parameters selected by any method from the parameter set P are perturbed, the robustness information visually displays the difference between the calculated peak candidate time and the peak candidate time associated with the parameter set P. In one embodiment, the difference is displayed using color shading or the like, allowing the magnitude of the change in the peak candidate time in response to the change in parameters to be visually recognized from the degree of change in color shading.

[0102] 20B is an explanatory diagram showing another example of the robustness information display screen according to Example 4. As an example, a robustness information display screen 2000B displays an input waveform identification field 2001, parameter set variation information 2021, and peak candidate variation information 2022 on a command line. In addition, when one input waveform data 111 includes multiple peak candidates, it is also possible to display multiple sets of this information for each peak candidate on the same screen or multiple screens that can be switched by operation.

[0103] The parameter set variation information 2021 is information related to the robustness evaluation parameter set P' out of the robustness information. The peak candidate variation information 2022 is information related to the difference with the corresponding peak candidate information or peak candidate related to the parameter set P. These do not necessarily have to be displayed for all records of the robustness evaluation parameter set P', and may be displayed only for representative records extracted by an appropriate method.

[0104] 20C is an explanatory diagram showing another example of the robustness information display screen according to Example 4. As an example, a robustness information display screen 2000C displays an input waveform identification field 2001, a setting safe range display field 2031, a parameter acceptable range display field 2032, and the like on the terminal 101 and is perceived by the user. When one input waveform data 111 includes multiple peak candidates, it is also possible to display multiple sets of this information for each peak candidate on the same screen or multiple screens that can be switched by operation.

[0105] The set safe range display field 2031 is information related to the range of allowable error for the peak candidate. In one embodiment, this range is determined by the setting information I.

[0106] The parameter acceptable range display field 2032 displays information on boundary values ​​regarding whether a difference between the time of a peak candidate calculated for the robustness evaluation parameter set P' and the time of a peak candidate related to the parameter set P deviates from a range of acceptable error related to the peak candidate, together with the value of the robustness evaluation parameter set P'. In one embodiment, the robustness evaluation parameter set P' is generated by perturbing only one parameter from the parameter set P, and the parameter acceptable range display field 2032 displays information on the boundary value indicating whether the deviation occurs. In one embodiment, the parameter acceptable range display field 2032 simultaneously displays an evaluation of the magnitude of the boundary value displayed in this field. The evaluation can be a result of classification into a finite number of classes based on the magnitude of the boundary value, which is determined based on the setting information I. The evaluation can be a result of classification into a finite number of classes based on the magnitude of the boundary value, which is determined based on the distribution of the boundary value obtained by performing the same process on similar input waveform data extracted based on the feature 310 of the input waveform data 111.

[0107] Thus, according to the fourth embodiment, when peak candidates are extracted from new waveform data using a parameter set for peak candidate extraction, a result of extracting peak candidates can be obtained as a robustness evaluation result even when a small perturbation is applied to the value of the parameter set. In particular, by employing the perturbation variation display field 2011 and the parameter acceptable range display field 2032 as a display method for calling attention to perturbations that are low in robustness and may cause problems in terms of reproducibility of experiments, the user can limit the subjects of consideration to experiments that may include problems, without making a judgment on the majority of experiments with few problems. EXAMPLES

[0108] 21 to 26C, a fifth embodiment will be described. In the fifth embodiment, an example of an information processing device is shown for extracting peak boundary candidates from new waveform data using a parameter set for extracting peak boundary candidates optimized in the second embodiment, and simultaneously displaying the results of extracting peak boundary candidates and calculating physical quantities as robustness evaluation results even when a minute perturbation is applied to the value of the parameter set.

[0109] 21 is a block diagram of an information processing device 1D according to the fifth embodiment. In the fifth embodiment, a computer 100-2 includes a robustness information calculation unit 2123 in addition to a learning information input receiving unit 120, a curvature etc. calculation unit 121, a boundary determination unit 1122, a peak determination unit 122, and parameter data 124.

[0110] 22 is a flowchart showing an example of a robustness information calculation procedure by the robustness information calculation unit 2123 according to the fifth embodiment. The robustness information calculation unit 2123 acquires information in the same manner as the robustness information calculation unit 1823 according to the fourth embodiment (S1901), creates a robustness evaluation parameter set P' (S1902), creates a curvature etc. threshold information set (S1903), and calculates a peak candidate information set (S1904). However, in the fifth embodiment, the robustness evaluation parameter set P' to which perturbation is applied is not limited to only parameters included in the parameter set P, and does not prevent perturbation from being applied directly to the peak start time and peak end time calculated using the parameter set P, for example.

[0111] The robustness information calculation unit 2123 associates each record of the robustness evaluation parameter set P' with each record of the peak candidate information set created based on it, and transmits them to the boundary determination unit 1122 together with the setting information I. The boundary determination unit 1122 transmits peak boundary candidate information for the set of records in the same manner as in the second embodiment, and ends the process. The robustness information calculation unit 2123 combines the peak boundary candidate information to create a peak boundary candidate information set (S2205).

[0112] The robustness information calculation unit 2123 employs each record of the peak boundary candidate information set as the peak start time 1211 and the peak end time 1212 related to the peak, calculates physical quantities related to the waveform 400, and creates a physical quantity set (S2206).

[0113] The robustness information calculation unit 2123 associates the robustness evaluation parameter set P' with records in the physical quantity set calculated based on each record, and creates robustness information therefrom (S2207). The robustness information is information that associates the difference between the values ​​of each record of the parameter set P that is optimal for analyzing the target input waveform data 111 and the robustness evaluation parameter set P' with the difference in the values ​​of the physical quantities calculated based on each. In one embodiment, the robustness information is created using only records of the robustness evaluation parameter set P' in which the difference between the physical quantities exceeds the safety range threshold included in the setting information I, rather than using all records of the robustness evaluation parameter set P'.

[0114] The robustness information calculation unit 2123 transmits the generated robustness information and ends the process (S2208). The transmitted robustness information is output to the terminal 101 as a robustness information display screen and is perceived by the user.

[0115] FIG. 23A is an explanatory diagram showing an example of a robustness information display screen according to the fifth embodiment. The robustness information display screen 2300A may include, for example, an input waveform identification field 2001 and a perturbation variation display field 2311. When one input waveform data 111 includes multiple peak candidates, it is also possible to display multiple sets of information for each peak candidate on the same screen or multiple screens that can be switched by operation. It is also possible to simultaneously display multiple sets of perturbation variation display fields 2311 for multiple physical quantities on the same screen or multiple screens that can be switched by operation. In the fifth embodiment, the input waveform identification field 2001 does not prevent the display of the value of the physical quantity related to the parameter set P at the same time as the information related to the feature 310 of the target input waveform data 111 and the information identifying the target peak candidate.

[0116] The perturbation variation display field 2311 displays robustness information. In one embodiment, for each robustness evaluation parameter set P' in which perturbation is performed on one or two parameters selected by an arbitrary method from among the parameter set P, the difference between the time of the calculated physical quantity and the time of the physical quantity related to the parameter set P is visually displayed. In another embodiment, the difference is displayed by a shade of color or the like, so that the magnitude of the change in the time of the peak candidate according to the change in the parameter can be visually recognized from the degree of change in the shade of color. In yet another embodiment, the difference in the physical quantity can be visually displayed by emphasizing only the parameter region in which the difference deviates from the range determined based on the setting information I or only the parameter region in which the difference does not deviate from the range.

[0117] 23B is an explanatory diagram showing another example of the robustness information display screen according to Example 5. As an example, a robustness information display screen 2300B displays an input waveform identification field 2001, parameter set variation information 2321, and physical quantity variation information 2322 on a command line. When one input waveform data 111 includes multiple peak candidates, it is also possible to display multiple sets of this information for each peak candidate on the same screen or multiple screens that can be switched by operation.

[0118] The parameter set variation information 2321 is information related to the robustness evaluation parameter set P' out of the robustness information. The physical quantity variation information 2322 is information related to the corresponding physical quantity or information related to the difference with the physical quantity related to the parameter set P. These do not necessarily have to be displayed for all records of the robustness evaluation parameter set P', and may be displayed only for representative records extracted by an appropriate method.

[0119] 23C is an explanatory diagram showing another example of the robustness information display screen according to Example 5. As an example, the robustness information display screen 2300C displays an input waveform identification field 2001, a setting safe range display field 2331, a parameter acceptable range display field 2332, and the like on the terminal 101 and is perceived by the user. When one input waveform data 111 includes multiple peak candidates, it is also possible to display multiple sets of this information for each peak candidate on the same screen or multiple screens that can be switched by operation.

[0120] The set safe range display field 2331 is information related to the range of allowable error related to the physical quantity. In one embodiment, this range is determined by the set information I.

[0121] The physical quantity allowable range display field 2332 displays information on boundary values ​​indicating whether a difference between a physical quantity calculated for a robustness evaluation parameter set P' and a physical quantity calculated based on the parameter set P deviates from a range of allowable errors related to the physical quantity, together with the value of the robustness evaluation parameter set P'. In one embodiment, the robustness evaluation parameter set P' is generated by perturbing only one parameter from the parameter set P, and the physical quantity allowable range display field 2332 displays information on the boundary value indicating whether the deviation occurs. In one embodiment, the physical quantity allowable range display field 2332 simultaneously displays an evaluation of the magnitude of the boundary value displayed in this field. The evaluation can be a result of classification into a finite number of classes based on the magnitude of the boundary value, which is determined based on the setting information I. The evaluation can be a result of classification into a finite number of classes based on the magnitude of the boundary value, which is determined based on the distribution of the boundary value obtained by performing the same process on similar input waveform data extracted based on the feature 310 of the input waveform data 111.

[0122] In this way, according to the fifth embodiment, when a peak boundary candidate is extracted from new waveform data using a parameter set for extracting a peak boundary candidate, a direct robustness is evaluated based on the physical quantity that is the final target of the thermal analysis when a small perturbation is applied to the value of the parameter set, and the result is obtained as a robustness evaluation result. In addition, by directly applying a perturbation to the value of the peak boundary candidate, it is possible to evaluate the robustness of the result of extracting the peak boundary candidate itself with respect to the measurement of the physical quantity. In particular, by adopting the perturbation variation value display field 2311 and the physical quantity acceptable range display field 2332 as a display method for calling attention to perturbations that are low in robustness and may cause problems in terms of reproducibility of the experiment, the user can limit the subjects of consideration to experiments that may include problems without making a judgment on the experiments with few problems that account for the majority. EXAMPLES

[0123] Example 6 will be described with reference to Figures 24 to 26. Example 6 shows an example of an information processing device for performing machine learning for determining peak candidates and obtaining parameters suitable for peak candidates, based on the assumption that similar peak candidates are present when a user is unable to create peak data and only input waveform data relating to similar materials or similar experimental conditions are available.

[0124] 24 is a block diagram of an information processing device 1E according to the sixth embodiment. In the sixth embodiment, the teacher waveform data 110 included in the computer 100-1 stores a plurality of input waveform data 2411. The computer 100-2 includes a learning information input receiving unit 120, a curvature etc. calculating unit 121, a peak determining unit 122, parameter data 124, and difference data 125, as well as a parameter updating unit 2423.

[0125] 25 is an explanatory diagram showing an example of input waveform data 2411 according to Example 6. The input waveform data includes an attribute 310 that describes the attribute of the waveform, and a waveform descriptor 320 that describes the measurement value for each time and temperature. Of these, the waveform descriptor 320 is configured with the same content as the input waveform data 111 according to Example 1.

[0126] The feature 310 according to the sixth embodiment is assigned an input waveform data ID 311 which is an individual identification number for the input waveform data 2411. The feature 310 may include information used in analyzing the input waveform data, such as a temperature change computer program for performing unit conversion for the numerical value stored in the waveform descriptor 320, limiting the measurement target, and the like, and a sample amount. The feature 310 according to the sixth embodiment includes main material group information 2512 which is information required to characterize a relationship between the input waveform data 2411 for determining whether or not the input waveform data 2411 have peak candidates at similar times. In one embodiment, the main material group information 2512 includes information related to the composition of the main material of the target substance related to the feature 310 for the input waveform data 2411, as information sufficient to determine whether or not the input waveform data 2411 have peak candidates at similar times. In another embodiment, the main material group information 2512 includes thermal history information related to thermal analysis.

[0127] 26 is a flowchart showing an example of a parameter updating procedure by the parameter updating unit 2423 according to the sixth embodiment. The parameter updating unit 2423 acquires setting information I, peak candidate information, and parameter data 124 for each piece of input waveform data 2411 (S2601). The parameter updating unit 2423 does not necessarily need to acquire peak candidate information for all pieces of input waveform data 2411, and does not prevent the parameter updating unit 2423 from acquiring information limited to only waveforms having peak candidates at similar times by referring to main material group information 2512 for a specific waveform to be learned among the input waveform data 2411.

[0128] The parameter update unit 2423 refers to the main material group information 2512 for a specific waveform to be learned from the input waveform data 2411, and calculates difference information based on the setting information I from the difference between the times of the peak candidates related to the peak candidate information for waveforms estimated to have peak candidates at similar times (S2602).

[0129] The parameter update unit 2423 stores the currently tried parameter set P to be learned in the parameter data 124, and correspondingly stores the difference information in the difference data 125 together with the input waveform data ID 311 relating to the specific waveform to be learned among the input waveform data 2411 (S2603).

[0130] The parameter update unit 2423, in a similar process to that of the parameter update unit 123 according to the first embodiment, refers to the differential data 125, and performs an update process on the learning parameter set P stored in the parameter data 124 as necessary, and terminates the process (S804).

[0131] Thus, according to Example 6, even if the user is unable to create peak data and only input waveform data relating to similar materials or similar experimental conditions is available, machine learning can be performed to determine peak candidates based on the assumption that they have similar peak candidates, and parameters suitable for the peak candidates can be obtained.

[0132] The present invention is not limited to the above-described embodiments, and includes various modified examples and equivalent configurations within the spirit of the appended claims. For example, the above-described embodiments have been described in detail to clearly explain the present invention, and the present invention is not necessarily limited to those having all of the configurations described. Also, a part of the configuration of one embodiment may be replaced with a configuration of another embodiment. Also, a configuration of another embodiment may be added to a configuration of one embodiment. Also, a part of the configuration of each embodiment may be added to, deleted from, or replaced with another configuration.

[0133] Furthermore, each of the aforementioned configurations, functions, processing units, processing means, etc. may be realized in hardware, part or all of which may be designed, for example, as an integrated circuit, or may be realized in software, by a processor interpreting and executing a computer program that realizes each function.

[0134] Information such as computer programs, tables, files, etc. that realize each function can be stored in a storage device such as a memory, a hard disk, or an SSD (Solid State Drive), or in a recording medium such as an IC (Integrated Circuit) card, an SD card, or a DVD (Digital Versatile Disc).

[0135] In addition, the control lines and information lines shown are those that are considered necessary for the explanation, and do not necessarily show all the control lines and information lines that are necessary for implementation. In reality, it can be considered that almost all components are connected to each other.

[0136] The above-described embodiment discloses a configuration that can be expressed as follows.

[0137] (Representation 1) An information processing device that performs data analysis based on waveform data related to thermal characteristics through machine learning, comprising a processor that executes a computer program and a storage device that stores the computer program, wherein the storage device further stores parameters used in the data analysis derived based on teacher data including a plurality of waveform data, each of which is annotated to indicate a peak, and wherein the processor receives waveform data related to thermal characteristics, identifies a peak of the waveform based on a curvature or variation value of the waveform data and a threshold value included in the parameters, and updates the threshold value based on the identified peak of the waveform data and the peak of the teacher data.

[0138] (Representation 2) An information processing device according to Representation 1, wherein each of the multiple waveform data of the teacher data is further provided with an annotation indicating a peak boundary, and the processor divides the waveform data into multiple section waveform data based on the identified peaks, calculates section features characterizing the section waveform data using the parameters, identifies peak boundaries of the waveform data based on the calculated section features, and updates the parameters based on the peak boundaries of the identified waveform and the peak boundaries of the teacher data.

[0139] (Representation 3) An information processing device according to Representation 1 or 2, wherein the processor identifies a plurality of peaks in waveform data based on a plurality of types of the parameters set to different values, and performs an analysis robustness evaluation from the identified plurality of peaks.

[0140] (Representation 4) An information processing device according to any one of Representations 1-3, wherein the processor identifies a plurality of peak boundaries in waveform data based on a plurality of types of the parameters set to different values, calculates a plurality of peak physical quantities based on the identified peak boundaries, and evaluates the robustness of the analysis from the calculated peak physical quantities.

[0141] (Representation 5) An information processing device that performs data analysis based on waveform data related to thermal characteristics through machine learning, comprising a processor that executes a computer program and a storage device that stores the computer program, wherein the storage device further stores parameters used in the data analysis derived based on teacher data including multiple waveform data, and the processor receives multiple waveform data related to thermal characteristics, identifies peaks of the multiple waveforms based on curvature or variation values ​​of the multiple waveform data and a threshold value included in the parameters, and updates the threshold value based on the relationship between the peaks of the identified multiple waveform data.

[0142] (Representation 6) An information processing device that performs data analysis based on waveform data related to thermal characteristics using machine learning, comprising a processor that executes a computer program and a storage device that stores the computer program, wherein the storage device further stores parameters used in the data analysis derived based on teacher data including a plurality of waveform data, each of which is annotated to indicate a physical quantity corresponding to a peak, wherein the processor receives a plurality of waveform data related to thermal characteristics, identifies peaks of the plurality of waveforms based on a curvature or variation value of the plurality of waveform data and a threshold value included in the parameters, divides the plurality of waveform data into a plurality of segmented waveform data based on the identified peaks, calculates segment features characterizing the segmented waveform data using the parameters, identifies peak boundaries of the waveform data based on the calculated segment features, calculates a peak physical quantity based on the identified plurality of peak boundaries, and updates the parameters based on the calculated peak physical quantity, the peak boundaries of the identified waveform, and the peak boundaries of the teacher data.

[0143] (Representation 7) An information processing device according to any one of Representations 1 to 6, wherein the data analysis based on waveform data relating to the thermal characteristics is a thermal analysis of a polymeric material.

[0144] (Representation 8) In the information processing device described in Representation 8, the waveform data relating to the thermal characteristics may be one or more of DSC (Differential Scanning Calorimetry) data of thermal analysis, thermogravimetry (TG) data, thermomechanical analysis (TMA) data, dynamic mechanical analysis (DMA) data, and differential thermal analysis (DTA) data.

[0145] (Representation 9) An information processing method for performing data analysis based on waveform data relating to thermal properties through machine learning using an information processing device, the information processing device comprising a processor for executing a computer program and a storage device used by the processor, the storage device storing the computer program and parameters used in the data analysis derived based on teacher data including a plurality of waveform data each of which is annotated to indicate a peak, the processor identifying a peak of the waveform based on a curvature or variation value of the waveform data and a threshold value included in the parameters, and updating the threshold value based on the identified peak of the waveform data and the peak of the teacher data.

[0146] (Representation 10) A computer program that causes a processor that executes the computer program to execute a determination process for determining a peak of the waveform based on a curvature or variation value of waveform data related to thermal characteristics and a threshold value included in the parameters, and an update process for updating the threshold value based on the determined peak of the waveform data and a peak of the teacher data.

[0147] (Representation 11) An information processing device that performs data analysis based on waveform data related to thermal characteristics through machine learning, comprising a processor that executes a computer program and a storage device that stores the computer program, wherein the storage device further stores parameters used in the data analysis derived based on teacher data including a plurality of waveform data, each of which is annotated to indicate a peak, and wherein the processor receives the waveform data related to thermal characteristics and performs a predetermined process based on a portion of the information contained in the waveform data, thereby optimizing settings used in the machine learning to analyze the waveform data.

[0148] (Representation 12) An information processing device, wherein the specified processing is a processing described in any one of Representations 1-9. [Explanation of symbols]

[0149] 1, 1A, 1B, 1C, 1D, 1E: information processing device, 100: computer, 101: terminal, 102: communication network, 110: teacher waveform data, 111: input waveform data, 112: peak data, 120: learning information input reception unit, 121: curvature etc. calculation unit, 122: peak determination unit, 123: parameter update unit, 124: parameter data, 125: difference data, 201: processor, 202: main memory device, 203: Secondary storage device, 204: network interface, 205: input device, 206: output device, 1102: peak boundary data, 1122: boundary determination unit, 1123: parameter update unit, 1502: material physical quantity data, 1510: material data, 1523: parameter update unit, 1810: waveform data, 1823: robustness information calculation unit, 2123: robustness information calculation unit, 2411: input waveform data, 2423: parameter update unit

Claims

1. An information processing device that performs data analysis based on waveform data related to thermal characteristics by machine learning, a processor for executing a computer program; a storage device for storing the computer program; The storage device further stores parameters used in the data analysis derived based on teacher data including a plurality of waveform data each having an annotation indicating a peak, The processor, receiving waveform data relating to thermal properties; Identifying a peak of the waveform based on a curvature or variation value of the waveform data and a threshold value included in the parameter; The threshold is updated based on the identified peak of the waveform data and the peak of the teacher data. Information processing device.

2. 2. The information processing device according to claim 1, An annotation indicating a peak boundary is further added to each of the plurality of waveform data of the teacher data, The processor, Dividing the waveform data into a plurality of waveform data segments based on the identified peaks; Calculating a section feature that characterizes the section waveform data using the parameters; Identifying a peak boundary of the waveform data based on the calculated division feature amount; The parameters are updated based on the peak boundaries of the identified waveform and the peak boundaries of the training data. Information processing device.

3. 2. The information processing device according to claim 1, The processor, Identifying a plurality of the peaks in the waveform data based on a plurality of types of the parameters set to different values; The analytical robustness is evaluated from the identified peaks. Information processing device.

4. 3. The information processing device according to claim 2, wherein the processor: identifying a plurality of said peak boundaries in the waveform data based on a plurality of types of said parameters set to different values; Calculating a plurality of peak physical quantities based on the identified plurality of peak boundaries; The robustness of the analysis is evaluated based on the calculated multiple peak physical quantities. Information processing device.

5. An information processing device that performs data analysis based on waveform data related to thermal characteristics by machine learning, a processor for executing a computer program; a storage device for storing the computer program; The storage device further stores parameters used in the data analysis derived based on teacher data including a plurality of waveform data; The processor, receiving multiple waveform data relating to thermal properties; identifying peaks of the plurality of waveforms based on a curvature or variation value of the plurality of waveform data and a threshold value included in the parameter; The threshold is updated based on the relationship between the peaks of the identified multiple waveform data. Information processing device.

6. An information processing device that performs data analysis based on waveform data related to thermal characteristics by machine learning, A processor that executes a computer program and a storage device that stores the computer program, The storage device further stores parameters used in the data analysis, the parameters being derived based on teacher data including a plurality of waveform data each having an annotation indicating a physical quantity corresponding to a peak; The processor, receiving multiple waveform data relating to thermal properties; identifying peaks of the plurality of waveforms based on a curvature or variation value of the plurality of waveform data and a threshold value included in the parameter; Dividing the waveform data into a plurality of section waveform data based on the identified peaks; Calculating a section feature that characterizes the section waveform data using the parameters; Identifying a peak boundary of the waveform data based on the calculated division feature amount; Calculating a peak physical quantity based on the identified plurality of peak boundaries; The parameters are updated based on the calculated peak physical quantity, the peak boundary of the identified waveform, and the peak boundary of the teacher data. Information processing device.

7. The information processing device according to any one of claims 1 to 6, The data analysis based on the waveform data regarding the thermal characteristics is a thermal analysis of a polymer material. Information processing device.

8. The information processing device according to claim 7, The waveform data relating to the thermal characteristics may be any one or more of thermal analysis DSC (Differential Scanning Calorimetry) data, thermogravimetry (TG) data, thermomechanical analysis (TMA) data, dynamic mechanical analysis (DMA) data, and differential thermal analysis (DTA) data. Information processing device.

9. An information processing method for performing data analysis based on waveform data relating to thermal characteristics by machine learning using an information processing device, comprising: The information processing device includes a processor that executes a computer program, and a storage device that is used by the processor, and the storage device stores the computer program and parameters that are used in the data analysis that are derived based on teacher data including a plurality of waveform data each having an annotation indicating a peak, The processor: Identifying a peak of the waveform based on a curvature or variation value of the waveform data and a threshold value included in the parameter; The threshold is updated based on the identified peak of the waveform data and the peak of the teacher data. Information processing methods.

10. A processor that executes a computer program A process of identifying a peak of the waveform based on a curvature or variation value of the waveform data related to thermal characteristics and a threshold value included in the parameter; an update process for updating the threshold value based on the identified peak of the waveform data and the peak of the teacher data; A computer program that executes the following:

Images