Biological information calculation system and server

Abstract

A biological information calculation system capable of improving accuracy in evaluating biological information is provided. The system includes an acquisition means for acquiring first evaluation data and second evaluation data by performing different types of processing on a single piece of pulse wave data based on a user's pulse wave, a database, a generation means for referencing the database and generating a first evaluation result for the first evaluation data including first biometric information and a second evaluation result for the second evaluation data including second biometric information of a type different from the first biometric information, and a storage means for saving the first evaluation result and the second evaluation result. The database stores classification information used to process the first evaluation data and the second evaluation data.

Description

Technical Field

[0001] The present invention relates to a biological information calculation system, and server to the and is related thereto.

Background Art

[0002] Conventionally, as a method for evaluating biological information such as the partial pressure of carbon dioxide in the blood (PaCO 2 2) of a user, for example, a method such as that of Patent Document 1 has been proposed.

[0003] In Patent Document 1, after constructing an average frame for each of at least two volume pulse waves having different light wavelengths from each other, it can be used to estimate the gain between the two average frames for the two volume pulse waves, and it is disclosed that the gain value may be used for information for obtaining blood oxygen saturation or for estimating other components present in the blood, such as hemoglobin, carbon dioxide, or others.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] Here, for example, when evaluating a user's biological information, it is desired to evaluate a plurality of pieces of biological information at once. In this regard, in the disclosed technology of Patent Document 1, when measuring the blood carbon dioxide saturation, hemoglobin, etc. among the biological information, it is premised on using two volume pulse waves. Therefore, the variation in data due to the measurement conditions of each volume pulse wave may greatly affect the estimation accuracy. Further, when estimating a plurality of pieces of biological information using the disclosed technology of Patent Document 1, it is necessary to acquire a plurality of volume pulse waves corresponding to the number and type of the biological information. Therefore, a decrease in the estimation accuracy due to the variation for each volume pulse wave is a concern in proportion to the number of volume pulse waves required for estimating a plurality of pieces of biological information. Therefore, an improvement in accuracy when evaluating biological information is desired.

[0006] Therefore, the present invention has been devised in view of the above-described problems, and an object thereof is to provide a biological information calculation system capable of improving the accuracy when evaluating biological information. and Serv the To provide.

Means for Solving the Problems

[0007] The biological information calculation system according to the first invention is a biological information calculation system for evaluating a user's biological information, and for one piece of pulse wave data corresponding to either a velocity pulse wave or an acceleration pulse wave based on the pulse wave of the user, by performing different types of processing on each, for one piece of the said pulse wave data An acquisition means for acquiring first evaluation data and second evaluation data, a database in which classification information used for processing the first evaluation data and the second evaluation data is stored, referring to the database, a first evaluation result including first biological information for the first evaluation data, and a second evaluation result including second biological information of a type different from the first biological information for the second evaluation data, and a generation means for generating each, and a storage means for storing the first evaluation result and the second evaluation result.

[0008] According to the second invention In the first invention, the biological information calculation system, the first evaluation data and the second evaluation data are data corresponding to either the speed pulse wave or the acceleration pulse wave of the user It is characterized by the above.

[0009] According to the third invention The server stores the first evaluation result and the second evaluation result in the first invention It is characterized by the following.

Advantages of the Invention

[0010] According to the first invention, the acquisition means corresponding to either the speed pulse wave or the acceleration pulse wave For one pulse wave data, by performing different types of processing respectively, the first evaluation data and the second evaluation data are acquired. Further, the generation means generates a first evaluation result including first biological information for the first evaluation data and a second evaluation result including second biological information of a type different from the first biological information for the second evaluation data, respectively. That is, the first biological information and the second biological information are calculated based on the pulse wave of one user. Therefore, when calculating each biological information, variations caused by the measurement conditions of the pulse wave can be excluded. Thereby, it becomes possible to improve the accuracy when evaluating biological information.

[0012] In particular, according to the third invention The server stores the first evaluation result and the second evaluation result, which aim to improve the accuracy when evaluating biological information This becomes possible.

Brief Description of the Drawings

[0013]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

BEST MODE FOR CARRYING OUT THE INVENTION

[0014] Hereinafter, an example of the biological information calculation system, server, and data structure in the embodiment of the present invention will be described with reference to the drawings.

[0015] (First Embodiment: Biological Information Calculation System 100) FIG. 1 is a schematic diagram showing an example of a biological information calculation system 100 according to the first embodiment.

[0016] The biological information calculation system 100 is used to evaluate the biological information of a user. The biological information calculation system 100 can generate a plurality of evaluation results including different types of biological information from a plurality of evaluation data based on the user's pulse wave, and store each evaluation result. That is, based on one pulse wave measured from the user, generation of evaluation results including a plurality of types of biological information can be realized. Note that the "biological information" indicates, for example, characteristics of blood that can be estimated from the pulse wave, characteristics of the body, and the like.

[0017] As the biological information, for example, characteristics of carbon dioxide in the blood are used, and in addition, for example, blood glucose level, blood pressure, oxygen saturation, lactic acid level, pulse rate, respiratory rate, stress level, vascular age, degree of diabetes, etc. are used. Note that the "characteristics of carbon dioxide in the blood" indicates the degree of carbon dioxide contained in the user's blood. As the characteristics of carbon dioxide in the blood, for example, the value of partial pressure of carbon dioxide in the blood (PaCO 2 ) is used, and in addition, the dissolved concentration of carbon dioxide in the blood or the concentration of bicarbonate (HCO 3 - ) in the blood may be used, and a value considering the pH of the blood may be used according to the situation.

[0018] The biological information calculation system 100 includes, for example, a biological information calculation device 1 as shown in FIG. 1, and may include at least one of, for example, a sensor 5 and a server 4. The biological information calculation device 1 is connected to the sensor 5 and the server 4 via, for example, a communication network 3.

[0019] In the biological information calculation system 100, for example, as shown in Fig. 2(a), the biological information calculation device 1 acquires sensor data generated by the sensor 5 or the like. The sensor data indicates data including the characteristics of the pulse wave of one user measured during a specific period. Then, the biological information calculation device 1 performs preprocessing such as filtering on the acquired one piece of sensor data to acquire a plurality of evaluation data (for example, first evaluation data and second evaluation data). That is, when acquiring each evaluation data, the biological information calculation device 1 performs different types of preprocessing on one piece of sensor data.

[0020] The biological information calculation device 1 refers to a database and calculates different types of biological information (for example, first biological information and second biological information) for each evaluation data. Then, the biological information calculation device 1 generates a plurality of evaluation results (for example, first evaluation result and second evaluation result) including different types of biological information. That is, the plurality of biological information is calculated based on the pulse wave of one user. Therefore, when calculating each biological information, variations caused by the measurement conditions of the pulse wave can be eliminated. Thereby, it is possible to improve the accuracy when evaluating the biological information.

[0021] Here, when calculating the biological information for each evaluation data, the biological information calculation device 1 refers to a database. The database stores classification information generated using a plurality of learning data.

[0022] The classification information is generated using a plurality of learning data, for example, as shown in Fig. 3(a), a pair of reference data including input data based on the learning pulse wave acquired in the past and biological information associated with the input data is used as the learning data. Therefore, when calculating the biological information, quantitative evaluation results can be generated based on the connection between the characteristics of the pulse wave with a proven track record in the past and the biological information. Thereby, it is possible to suppress variations in evaluation due to the subjectivity of the user or the like.

[0023] Note that the classification information may include a plurality of pieces of classification information (for example, first classification information and second classification information) generated using different types of learning data, as shown in, for example, FIG. 3(b). In this case, the optimal classification information can be referred to according to the type of each evaluation data, and each evaluation result can be generated.

[0024] The biological information calculation device 1 stores the generated plurality of evaluation results in the server 4 or the like. Thereby, secondary utilization of each evaluation result can be easily realized.

[0025] The biological information calculation device 1 outputs each generated evaluation result to a display or the like, for example. Thereby, the user can grasp the plurality of generated evaluation results.

[0026] Note that in the biological information calculation system 100, a plurality of pieces of evaluation data may be acquired from the sensor 5 or the like, for example. In this case, the preprocessing for acquiring a plurality of pieces of evaluation data from the sensor data is performed by the sensor 5 or the like.

[0027] <Sensor data> The sensor data includes data indicating the characteristics of the user's pulse wave, and may include, for example, data (noise) indicating characteristics other than the pulse wave. The sensor data is data indicating the amplitude with respect to the measurement time, and by performing filter processing according to the application and the generation conditions of the sensor data, data corresponding to an acceleration pulse wave, a velocity pulse wave, or the like can be acquired from the sensor data.

[0028] The sensor data can be generated by a known sensor such as a strain sensor, a gyro sensor, a photoplethysmogram (PPG) sensor, or a pressure sensor. The sensor data may be an analog signal in addition to a digital signal. Note that the measurement time when generating the sensor data is, for example, a measurement time for 1 to 20 cycles of the pulse wave, and can be arbitrarily set according to conditions such as the processing method of the sensor data and the data communication method.

[0029] <Evaluation data> The evaluation data indicates data for calculating biological information. The evaluation data indicates data corresponding to, for example, an acceleration pulse wave based on the user's pulse wave, and indicates the amplitude for a specific period (for example, one period).

[0030] The evaluation data is obtained by performing processing (preprocessing) on the sensor data by the biological information calculation device 1 or the like. For example, as shown in FIGS. 4(a) to 4(d), the evaluation data can be obtained by performing a plurality of processes on the sensor data. Details of each process will be described later.

[0031] <Database> The database is mainly used when generating an evaluation result for the evaluation data. In addition to storing one or more pieces of classification information, the database may store, for example, a plurality of learning data used for generating the classification information.

[0032] The classification information is, for example, a function indicating the correlation between past evaluation data (input data) acquired in advance and reference data including biological information. The classification information indicates, for example, a calibration model generated by analyzing input data as an explanatory variable and reference data as a target variable by regression analysis or the like and based on the analysis result. The classification information can be updated periodically, for example, and may include a plurality of calibration models generated for each attribute information such as the user's gender, age, and exercise content.

[0033] As a method of regression analysis used for generating the classification information, for example, PLS (Partial Least Squares) regression analysis, regression analysis using the SIMCA (Soft Independent Modeling of Class Analogy) method in which principal component analysis is performed for each class to obtain a principal component model, etc. can be used.

[0034] The classification information may include a trained model generated by machine learning using, for example, a plurality of learning data. The trained model may represent a neural network model such as a CNN (Convolutional Neural Network), or may represent an SVM (Support vector machine), etc. Further, as the machine learning, for example, deep learning can be used.

[0035] The input data uses data of the same type as the evaluation data, and represents, for example, past evaluation data for which the corresponding biological information is clear. For example, the subject is made to wear a sensor 5 or the like, and sensor data (learning sensor data) indicating the characteristics of the learning pulse wave is generated. Then, by performing processing on the learning sensor data, the input data can be obtained. Note that the input data may be obtained from the user of the biological information calculation system 100, or may be obtained from, for example, a user different from the user. That is, the above-described subject may be the user of the biological information calculation system 100, or may be targeted at non-users, and may be a specific or unspecific number.

[0036] The input data is preferably obtained by the same content as, for example, the type of the sensor 5 or the like used when obtaining the evaluation data, the generation conditions of the sensor data, and the processing conditions for the sensor data. For example, by unifying the above three contents, it is possible to dramatically improve the accuracy when generating biological information.

[0037] The reference data includes the biological information of the subject measured using a measuring device or the like. For example, when generating learning sensor data by making the subject wear a sensor 5 or the like, by measuring biological information such as the characteristics of carbon dioxide in the subject's blood, reference data associated with the input data can be obtained. In this case, the timing of measuring the biological information is preferably the same as the timing of generating the learning sensor data, but may be, for example, about 1 to 10 minutes before or after.

[0038] The reference data is measured using a known measuring device. For example, when measuring the characteristics of blood carbon dioxide concentration, devices such as the transcutaneous blood gas monitor TCM5 (manufactured by Radiometer Basel) are used as the measuring device. For example, when measuring the amount of lactic acid in blood, known devices such as Lactate Pro 2 (manufactured by Arkray, Inc.) are used as the measuring device. For example, when measuring oxygen saturation, known devices such as PULSOX-Neo (manufactured by Konica Minolta, Inc.) are used as the measuring device.

[0039] <Biological information> The biological information calculated in the biological information calculation system 100 is calculated as data of the same type as the reference data. The biological information refers to classification information and is calculated as data identical or similar to the reference data. In the biological information calculation system 100, for example, a plurality of evaluation data are respectively acquired along an arbitrary time series, and a plurality of biological information for each evaluation data are generated. Also, in the biological information calculation system 100, for example, a plurality of evaluation data may be acquired at arbitrary timings, and a plurality of biological information for each evaluation data may be calculated.

[0040] <Evaluation result> The evaluation result includes the biological information of the user calculated by the biological information calculation device 1. The evaluation result may include, in addition to the biological information, for example, a comparison result with a preset threshold value. The evaluation result may include, for example, a value derived based on a plurality of biological information along a time series. The evaluation result may include information indicating an evaluation of the user's health status, advice leading to health maintenance, and a tendency of exercise ability, such as "healthy", "exercise required", "during anaerobic exercise", etc. Thereby, the change over time of each of the plurality of biological information can be easily grasped. For example, the biological information of the user can be grasped by outputting the evaluation result.

[0041] <Biological information calculation device 1> The biological information computing device 1 represents an electronic device such as a personal computer (PC), a mobile phone, a smartphone, a tablet terminal, a wearable terminal, etc., and represents an electronic device capable of communicating via the communication network 3, for example, based on a user's operation. Note that the biological information computing device 1 may incorporate the sensor 5. Hereinafter, an example in the case where a PC is used as the biological information computing device 1 will be described.

[0042] FIG. 5(a) is a schematic diagram showing an example of the configuration of the biological information computing device 1, and FIG. 5(b) is a schematic diagram showing an example of the function of the biological information computing device 1.

[0043] As shown in FIG. 5(a) for example, the biological information computing device 1 includes a housing 10, a CPU (Central Processing Unit) 101, a ROM (Read Only Memory) 102, a RAM (Random Access Memory) 103, a storage unit 104, and I / Fs 105 to 107. Each component 101 to 107 is connected by an internal bus 110.

[0044] The CPU 101 controls the entire biological information computing device 1. The ROM 102 stores the operation code of the CPU 101. The RAM 103 is a work area used during the operation of the CPU 101. The storage unit 104 stores various information such as a database and evaluation data. As the storage unit 104, for example, in addition to an HDD (Hard Disk Drive), a data storage device such as an SSD (Solid State Drive) is used. Note that, for example, the biological information computing device 1 may have a GPU (Graphics Processing Unit) not shown.

[0045] I / F105 is an interface for transmitting and receiving various information with servers 4, sensors 5, etc. via communication network 3 as necessary. I / F106 is an interface for transmitting and receiving information with input unit 108. As input unit 108, for example, a keyboard is used, and a user of biological information arithmetic device 1 inputs various information or control commands of biological information arithmetic device 1 via input unit 108. I / F107 is an interface for transmitting and receiving various information with display unit 109. Display unit 109 displays various information stored in storage unit 104 or evaluation results, etc. As display unit 109, a display is used, and in the case of a touch panel type, for example, it is provided integrally with input unit 108.

[0046] FIG. 5(b) is a schematic diagram showing an example of the functions of biological information arithmetic device 1. Biological information arithmetic device 1 includes acquisition unit 11, generation unit 12, output unit 13, and storage unit 14, and may include learning unit 15, for example. Each function shown in FIG. 5(b) is realized by CPU 101 executing a program stored in storage unit 104, etc. with RAM 103 as a work area.

[0047] <Acquisition unit 11> Acquisition unit 11 acquires a plurality of evaluation data based on the user's pulse wave. Acquisition unit 11 acquires evaluation data by, for example, acquiring sensor data from sensor 5, etc. and then performing processing on the sensor data. Acquisition unit 11 acquires a plurality of evaluation data for one sensor data by performing different types of processing respectively.

[0048] As shown in, for example, Fig. 4(a), the acquisition unit 11 performs filtering processing (filtering) on the acquired sensor data. In the filtering process, for example, a band-pass filter with a frequency range of 0.5 to 5.0 Hz is used. As a result, the acquisition unit 11 extracts data corresponding to the user's pulse wave (pulse wave data). The pulse wave data indicates data corresponding to, for example, the velocity pulse wave. Note that the pulse wave data may indicate data corresponding to, for example, the acceleration pulse wave or the volume pulse wave, and can be arbitrarily set according to the type and use of the sensor. Also, the filter range of the band-pass filter can be arbitrarily set according to the use.

[0049] The acquisition unit 11 performs, for example, differentiation processing on the pulse wave data. For example, when differentiation processing is performed on pulse wave data corresponding to the velocity pulse wave, the acquisition unit 11 acquires data corresponding to the acceleration pulse wave (differentiated data). Note that in the differentiation processing, second-order differentiation may be performed in addition to the first-order differentiation.

[0050] The acquisition unit 11 performs, for example, division processing on the differentiated data. In the division processing, for example, the differentiated data corresponding to the acceleration pulse wave of a plurality of cycles is divided into data corresponding to the acceleration pulse wave of each cycle (divided data). Therefore, the acquisition unit 11 can acquire a plurality of divided data by performing, for example, differentiation processing on one piece of differentiated data. Note that in the division processing, the differentiated data can be divided at an arbitrary period (for example, a positive multiple of the period) according to the use.

[0051] For example, in the division processing, the amount of data in each of the divided data may be different. In this case, the acquisition unit 11 may identify the divided data with the smallest amount of data and perform data amount reduction (trimming) on the other divided data. As a result, the amount of data in each divided data can be unified, and the comparison of the data in each divided data becomes easy.

[0052] In addition to the above, for example, normalization processing may be performed on the values corresponding to the time axis of the divided data. In the normalization processing, for example, normalization is performed such that the minimum value of the value corresponding to the time axis is 0 and the maximum value is 1. This facilitates the comparison of data in each divided data.

[0053] The acquisition unit 11 may calculate, for example, the average of a plurality of divided data for which data volume reduction or normalization has been performed, and use it as the divided data.

[0054] The acquisition unit 11 performs normalization processing on the divided data. In the normalization processing, normalized data (normalized data) is generated for the value corresponding to the amplitude. In the normalization processing, for example, normalization is performed such that the minimum value of the amplitude is 0 and the maximum value of the amplitude is 1. The acquisition unit 11 acquires, for example, the normalized data as evaluation data (for example, evaluation data A). In this case, data corresponding to the user's acceleration pulse wave is obtained as the evaluation data A.

[0055] In addition to sequentially performing each of the above-described processes, the acquisition unit 11 does not have to perform differential processing, for example, as shown in FIG. 4(b). In this case, data corresponding to the user's velocity pulse wave is obtained as the evaluation data (for example, evaluation data B).

[0056] Further, the acquisition unit 11 may perform only a part of each of the above-described processes, for example. In this case, the acquisition unit 11 may acquire any one of the pulse wave data, the differential data, the divided data, the trimmed divided data, and the divided data obtained by normalizing the value corresponding to the time axis as the evaluation data, which can be arbitrarily set according to the application.

[0057] The acquisition unit 11 may acquire evaluation data C suitable for calculating the pulse rate as the biological information, for example, as shown in FIG. 4(c).

[0058] In this case, the acquisition unit 11 performs the above-described filter processing on the sensor data to extract pulse wave data. Then, the acquisition unit 11 performs peak position calculation processing on the pulse wave data. In the peak position calculation processing, a plurality of peaks (maximum values of amplitudes) included in the pulse wave data are detected, and the sampling order (corresponding to the time from the start of measurement) is specified. Thereby, the acquisition unit 11 acquires peak position data included in the pulse wave data.

[0059] Thereafter, the acquisition unit 11 performs peak interval average calculation processing on the peak position data. The peak interval average calculation processing calculates the interval between peaks (the difference in the sampling order of adjacent peaks) included in the peak position data, and calculates, for example, the average value of the peak intervals. Thereafter, the acquisition unit 11 divides the peak interval or the average value of the peak intervals by the sampling rate of the sensor data, and acquires data indicating the peak interval corresponding to the number of seconds as evaluation data (for example, evaluation data C).

[0060] The acquisition unit 11 may acquire evaluation data D suitable for calculating the respiration rate as biological information, as shown in FIG. 4(d), for example.

[0061] In this case, the acquisition unit 11 performs the above-described filter processing on the sensor data to extract pulse wave data. Thereafter, the acquisition unit 11 performs Fourier transform processing on the pulse wave data. In the Fourier transform processing, for example, the pulse wave data indicating the sampling time vs. amplitude is converted into frequency data indicating the frequency vs. intensity. Thereby, the acquisition unit 11 acquires frequency data for the pulse wave data.

[0062] Thereafter, the acquisition unit 11 performs maximum frequency detection processing on the frequency data. In the maximum frequency detection processing, the frequency with the maximum intensity between 0.15 and 0.35 Hz among the frequency data is specified. Thereby, the acquisition unit 11 acquires the value of the specified frequency as evaluation data D.

[0063] <Generation unit 12> The generation unit 12 refers to the database and generates an evaluation result for the evaluation data. For example, the generation unit 12 refers to the classification information stored in the database, calculates the biological information for the evaluation data, and generates it as an evaluation result. The generation unit 12 generates a plurality of evaluation results for each of a plurality of different evaluation data.

[0064] The generation unit 12 may generate a plurality of evaluation data by referring to the same classification information for a plurality of evaluation data, for example. In this case, by obtaining a plurality of evaluation data using, for example, different types of preprocessing, different types of biological information can be calculated even using the same classification information. Therefore, it is not necessary to generate classification information for each evaluation data, and the data capacity of the database can be suppressed.

[0065] The generation unit 12 may calculate a plurality of biological information by referring to different classification information for a plurality of evaluation data, for example. In this case, the optimal classification information can be referred to according to the type of each evaluation data, and each evaluation result can be generated.

[0066] The generation unit 12 may generate an evaluation result obtained by converting the biological information into a format understandable by the user using, for example, a display format stored in advance in the storage unit 104 or the like.

[0067] <Output unit 13> The output unit 13 outputs a plurality of evaluation results. The output unit 13 outputs a plurality of evaluation results to the display unit 109, and may also output a plurality of evaluation results to, for example, the sensor 5 or the like.

[0068] <Storage unit 14> The storage unit 14 retrieves various data such as the database stored in the storage unit 104 as needed. The storage unit 14 stores various data obtained or generated by each of the components 11 to 13, 15 in the storage unit 104 as needed.

[0069] The storage unit 14 may store, for example, sensor data associated with a plurality of evaluation results in the storage unit 104. For example, the storage unit 14 may also store a plurality of evaluation data generated using the sensor data in the storage unit 104.

[0070] <Learning unit 15> The learning unit 15 generates classification information using, for example, a plurality of learning data. The learning unit 15 may acquire, for example, new learning data and update the existing classification information.

[0071] <Communication network 3> The communication network 3 is a known Internet network or the like that connects the biological information computing device 1, the server 4, and the sensor 5 via a communication line. When the biological information computing system 100 is operated within a certain narrow area, the communication network 3 may be composed of a LAN (Local Area Network) or the like. Further, the communication network 3 may be composed of a so-called optical fiber communication network. Also, the communication network 3 is not limited to a wired communication network and may be realized by a wireless communication network, which can be arbitrarily set according to the application.

[0072] <Server 4> The server 4 stores and accumulates various information such as evaluation results sent via the communication network 3. The server 4 transmits the information accumulated via the communication network 3 to the biological information computing device 1 based on a request from the biological information computing device 1.

[0073] The server 4 may be connected to, for example, a plurality of biological information computing devices 1, acquire various information such as evaluation results from each biological information computing device 1, and store them collectively. Note that the server 4 may have at least some of the functions provided in the above-described biological information computing device 1. Also, the server 4 may store a database or the like stored in the above-described biological information computing device 1.

[0074] <Sensor 5> Sensor 5 generates sensor data. As shown in, for example, FIG. 6(a), the sensor 5 includes a detection unit 6. The sensor 5 is attached to a position where the user's pulse wave can be detected via the detection unit 6, and is fixed to, for example, a wristband 55.

[0075] For the detection unit 6, a known detection device capable of detecting the user's pulse wave is used. As the detection unit 6, for example, at least one of a strain sensor such as a fiber Bragg grating (FBG) sensor, a gyro sensor, one or more electrodes for measuring a pulse wave signal, a photoelectric plethysmogram (PPG) sensor, a pressure sensor, and a light detection module is used. A plurality of detection units 6 may be arranged, for example.

[0076] Note that the sensor 5 may be embedded in clothing. In addition, the user wearing the sensor 5 may be, in addition to humans, pets such as dogs and cats, and may be, for example, livestock such as cows and pigs, or aquaculture such as fish.

[0077] As shown in, for example, FIG. 6(b), the sensor 5 includes an acquisition unit 50, a communication I / F 51, a memory 52, and a command unit 53, and each component is connected by an internal bus 54.

[0078] The acquisition unit 50 measures the user's pulse wave via the detection unit 6 and generates sensor data. The acquisition unit 50 transmits the generated sensor data to, for example, the communication I / F 51 or the memory 52.

[0079] The communication I / F 51 transmits various data such as sensor data to the biological information arithmetic device 1 or the server 4 via the communication network 3. In addition, the communication I / F 51 is equipped with a line control circuit for connecting to the communication network 3, a signal conversion circuit for performing data communication with the biological information arithmetic device 1 and the server 4, and the like. The communication I / F 51 performs conversion processing on various commands from the internal bus 54 and sends them to the communication network 3 side. When receiving data from the communication network 3, the communication I / F 51 performs predetermined conversion processing on the data and transmits it to the internal bus 54.

[0080] The memory 52 stores various data such as sensor data transmitted from the acquisition unit 50. The memory 52 transmits the stored various data such as sensor data to the communication I / F 51 by receiving a command from another terminal device connected via the communication network 3, for example.

[0081] The command unit 53 includes an operation button, a keyboard, etc. for acquiring sensor data and includes a processor such as a CPU, for example. When the command unit 53 receives a command to acquire sensor data, it notifies the acquisition unit 50 of this. Upon receiving this notification, the acquisition unit 50 acquires sensor data. Note that the command unit 53 may perform processing for acquiring a plurality of evaluation data from the sensor data, for example, as shown in FIGS. 4(a) to 4(d).

[0082] Here, as an example of acquiring sensor data, the case of using an FBG sensor will be described.

[0083] The FBG sensor has a diffraction grating structure formed at predetermined intervals in a single optical fiber. The FBG sensor has characteristics such as a sensor portion length of 10 mm, a wavelength resolution of ±0.1 pm, a wavelength range of 1550 ± 0.5 nm, a fiber diameter of 145 μm, and a core diameter of 10.5 μm, for example. With the FBG sensor as the detection unit 6 described above, measurement can be performed while in contact with the user's skin.

[0084] For example, as a light source used for an optical fiber, an ASE (Amplified Spontaneous Emission) light source with a wavelength range of 1525 to 1570 nm is used. The emitted light from the light source is made to enter the FBG sensor via a circulator. The reflected light from the FBG sensor is guided to a Mach-Zehnder interferometer via the circulator, and the output light from the Mach-Zehnder interferometer is detected by a photodetector. The Mach-Zehnder interferometer is for separating into two optical paths with an optical path difference by a beam splitter and recombining them into one by the beam splitter again to create interference light. To create an optical path difference, for example, the length of one of the optical fibers may be increased. Since coherent light generates interference fringes according to the optical path difference, by measuring the pattern of the interference fringes, it is possible to detect a change in the strain generated in the FBG sensor, that is, a pulse wave. The acquisition unit 50 generates sensor data based on the detected pulse wave. Thereby, sensor data is acquired.

[0085] Note that an optical fiber sensor system that detects the amount of strain of an FBG sensor and detects the waveform of a pulse wave includes, in addition to the light source that is made to enter the FBG sensor, an optical system such as a wide-band ASE light source, a circulator, a Mach-Zehnder interferometer, and a beam splitter, a light receiving sensor included in the photodetector, and an analysis method for analyzing the wavelength shift amount. The optical fiber sensor system can select and use a light source and band light according to the characteristics of the FBG sensor to be used, and various methods can also be adopted for analysis methods such as a detection method.

[0086] <Data Structure> For example, a data structure including a plurality of evaluation results (for example, a first evaluation result and a second evaluation result) generated by the above-described biological information calculation system 100 is stored in the server 4 or the storage unit 104. The data structure is used for the above-described biological information calculation device 1 (a computer including a display unit 109, a CPU 101 (control unit), and a storage unit 104). The data structure including a plurality of evaluation results is used, for example, when the generation unit 12 controlled by the CPU 101 generates a comprehensive evaluation result based on each evaluation result. Note that the comprehensive evaluation result will be described later.

[0087] (First Embodiment: Operation of the Biological Information Calculation System 100) Next, an example of the operation of the biological information calculation system 100 in this embodiment will be described. FIG. 7 is a flowchart showing an example of the operation of the biological information calculation system 100 in this embodiment.

[0088] The biological information calculation system 100 is executed, for example, via a biological information calculation program installed in the biological information calculation device 1. That is, the user can operate the biological information calculation device 1 or the sensor 5, and through the biological information calculation program installed in the biological information calculation device 1, obtain a plurality of evaluation results including the user's biological information from the sensor data.

[0089] The operation of the biological information calculation system 100 includes an acquisition step S110, a generation step S120, and a storage step S140, and may include, for example, an output step S130.

[0090] <Acquisition Step S110> In the acquisition step S110, a plurality of evaluation data are acquired based on the user's pulse wave. For example, the acquisition unit 50 of the sensor 5 measures the user's pulse wave via the detection unit 6 and generates sensor data. The acquisition unit 50 transmits the sensor data to the biological information calculation device 1 via the communication I / F 51 and the communication network 3. The acquisition unit 11 of the biological information calculation device 1 receives the sensor data from the sensor 5.

[0091] The acquisition unit 11 performs the processes shown in FIGS. 4(a) and 4(b), for example, on the sensor data to acquire first evaluation data and second evaluation data. The acquisition unit 11 stores each acquired evaluation data in the storage unit 104 via, for example, the storage unit 14. Note that conditions such as the frequency at which the acquisition unit 11 acquires sensor data from the sensor 5 can be arbitrarily set according to the application. For example, the acquisition unit 11 acquires each evaluation data at a preset cycle.

[0092] <Generation Step S120> Next, the generation step S120 refers to the database and generates a plurality of evaluation results including biological information for each evaluation data. For example, the generation unit 12 refers to the classification information, calculates the value of the partial pressure of carbon dioxide in the blood for the first evaluation data as the first biological information, and calculates the blood glucose level for the second evaluation data as the second biological information. The generation unit 12 generates a first evaluation result including the first biological information and a second evaluation result including the second biological information.

[0093] The generation unit 12 generates a first evaluation result for the first evaluation data by referring to, for example, the first classification information, and generates a second evaluation result for the second evaluation data by referring to the second classification information. At this time, the first classification information and the second classification information are included in the classification information and are generated using different types of learning data, respectively.

[0094] The generation unit 12 stores each generated evaluation result in the storage unit 104, for example, via the storage unit 14. In addition to indicating a specific value, an error range (for example, "○○±2 mmHg", etc.) may be calculated as each evaluation result.

[0095] For example, when calculating the pulse rate as biological information, evaluation data C shown in FIG. 4(c), for example, is used as the evaluation data, and the generation unit 12 refers to the classification information for the pulse rate included in the classification information. The classification information for the pulse rate represents, for example, a function that divides 60 [seconds] by the peak interval. Therefore, the generation unit 12 can calculate, for example, the pulse rate (=71 [bpm]) for the evaluation data C (peak interval = 0.85 [seconds]). Thereby, the generation unit 12 can generate an evaluation result including biological information indicating the pulse rate.

[0096] For example, when calculating the respiratory rate as biometric information, evaluation data D shown in FIG. 4(d), for example, is used as the evaluation data, and the generation unit 12 refers to the classification information for the respiratory rate included in the classification information. The classification information for the respiratory rate indicates, for example, a function that multiplies a specific frequency by 60 [seconds]. Therefore, the generation unit 12 can calculate, for example, the respiratory rate (= 13.5 [bpm]) for the evaluation data D (specific frequency = 0.225 Hz). Thereby, the generation unit 12 can generate an evaluation result including biometric information indicating the respiratory rate.

[0097] <Output step S130> Next, for example, the output step S130 may output a plurality of evaluation results. For example, the output unit 13 outputs the first evaluation result and the second evaluation result to the display unit 109.

[0098] <Save step S140> Next, the save step S140 saves the first evaluation result and the second evaluation result. For example, the storage unit 14 saves the first evaluation result and the second evaluation result in the storage unit 104. For example, the output unit 13 may output the first evaluation result and the second evaluation result to the server 4 via the communication network 3 and save them. For example, the save step S140 may be performed before the output step S130.

[0099] Note that the save step S140 may save, for example, sensor data associated with a plurality of evaluation results. In this case, the sensor data is used for generating a plurality of evaluation data and indicates the characteristics of the user's pulse wave.

[0100] Thereby, the operation of the biometric information calculation system 100 ends. Note that the frequency and order of performing each step can be arbitrarily set according to the application.

[0101] In the biological information calculation system 100, for example, in addition to the above-described respective steps S110 and S120 being performed by the biological information calculation device 1, at least a part thereof may be performed by the server 4. In this case, the above-described respective steps S110 and S120 include processes for the server 4 to transmit and receive various information via the communication network 3. Note that communication between the biological information calculation device 1 and the server 4 can be realized using known techniques.

[0102] For example, in the acquisition step S110, the server 4 may acquire a plurality of evaluation data. In this case, the acquisition unit included in the server 4 acquires the plurality of evaluation data transmitted from the biological information calculation device 1 via the communication network 3.

[0103] The acquisition unit included in the server 4 may acquire, for example, sensor data transmitted from the biological information calculation device 1 or the sensor 5, and perform the above-described preprocessing to acquire a plurality of evaluation data. In this case, in the biological information calculation device 1, it is possible to reduce the load of performing the above-described preprocessing.

[0104] For example, in the generation step S120, the server 4 may generate a plurality of evaluation results for each evaluation data. In this case, the generation unit included in the server 4 refers to the database stored in the server 4 and generates a plurality of evaluation results. In this case, in the biological information calculation device 1, it is possible to reduce the load of performing the process of generating the above-described plurality of evaluation results.

[0105] Note that when the generation step S120 is performed by the server 4, in the output step S130, for example, the output unit included in the server 4 transmits a plurality of evaluation results to the biological information calculation device 1 or the like via the communication network 3. In this case, the output unit 13 of the biological information calculation device 1 outputs the received plurality of evaluation results to the display unit 109.

[0106] As described above, each of the steps S110 to S140 in the biological information calculation system 100 can be performed by either the biological information calculation device 1 or the server 4. In particular, by performing the acquisition step S110 and the generation step S120 by the server 4, it is possible to reduce the load on the biological information calculation device 1 and the like. Since the same applies to each of the embodiments described later, the description thereof will be omitted.

[0107] According to the present embodiment, the acquisition unit 11 acquires first evaluation data and second evaluation data based on the pulse wave of the user. Further, the generation unit 12 generates a first evaluation result including first biological information for the first evaluation data and a second evaluation result including second biological information of a type different from the first biological information for the second evaluation data, respectively. That is, the first biological information and the second biological information are calculated based on the pulse wave of one user. Therefore, when calculating each biological information, variations caused by the measurement conditions of the pulse wave can be eliminated. Thereby, it is possible to improve the accuracy when evaluating the biological information.

[0108] Further, according to the present embodiment, the generation unit 12 refers to a database and generates a first evaluation result and a second evaluation result. The database stores classification information calculated using a plurality of learning data. Therefore, when generating each evaluation result, it is possible to generate a quantitative evaluation result based on the connection between the characteristics of the pulse wave with a proven track record in the past and the biological information. Thereby, it is possible to suppress variations in evaluation due to the subjectivity of the user or the like.

[0109] Further, according to the present embodiment, the classification information includes first classification information and second classification information generated using different types of learning data. Therefore, it is possible to generate each evaluation result by referring to the optimal classification information according to the type of each evaluation data. Thereby, it is possible to further improve the accuracy when evaluating the biological information.

[0110] Also, according to the present embodiment, the classification information is a calibration model obtained by using PLS regression analysis with the input data as the explanatory variable and the reference data as the target variable. Therefore, compared with the case of calculating the classification information using machine learning or the like, the number of learning data can be significantly reduced, and the calibration model can be easily updated. As a result, it is possible to facilitate the construction and update of the biological information calculation system 100.

[0111] Also, according to the present embodiment, the first biological information indicates a blood glucose level, and the second biological information indicates at least one of blood pressure, pulse rate, respiratory rate, characteristics of blood carbon dioxide concentration, lactic acid level, and oxygen saturation. Therefore, compared with the conventional measurement method, an invasive measurement method is not required, and each piece of information can be easily acquired. As a result, it is possible to significantly reduce the burden on the user.

[0112] Also, according to the present embodiment, the storage unit 14 or the server 4 includes storing the sensor data associated with the first evaluation result and the second evaluation result. Therefore, when updating or newly generating the classification information, the learning data can be easily prepared. As a result, it is possible to easily realize the maintenance of the biological information calculation system 100.

[0113] Also, according to this embodiment, the server 4 generates a first evaluation result and a second evaluation result by a generation unit included in the server 4. Further, the biological information calculation device 1 receives and displays the first evaluation result and the second evaluation result from the server 4. Therefore, the load on the biological information calculation device 1 when generating each evaluation result can be reduced. Thereby, the convenience of the biological information calculation device 1 can be improved. Also, there is no need for the biological information calculation device 1 to store a database. Thereby, the data storage capacity of the biological information calculation device 1 can be significantly reduced. Also, since the database is stored in the server 4, it is possible to output the evaluation results generated by referring to one classification information to a plurality of biological information calculation devices 1. Thereby, it is possible to reduce the enormous time and cost required to update the database for each biological information calculation device 1 along with maintenance such as database update.

[0114] Also, according to this embodiment, the server 4 can store a first evaluation result and a second evaluation result that improve the accuracy when evaluating biological information.

[0115] Also, according to this embodiment, the data structure includes a first evaluation result and a second evaluation result that improve the accuracy when evaluating biological information, and can be used when generating a comprehensive evaluation result.

[0116] (Second Embodiment: Biological Information Calculation System 100) Next, an example of the biological information calculation system 100 in the second embodiment will be described. The difference between the above-described embodiment and the second embodiment is the use of additional information. Note that the description of the same content as the above-described embodiment will be omitted.

[0117] The biological information calculation system 100 in this embodiment includes, for example, a comprehensive evaluation step S150. In the biological information calculation system 100, for example, after the above-described generation step S120, the comprehensive evaluation step S150 is performed, and after the comprehensive evaluation step S150, the storage step S140 is performed.

[0118] As shown in FIG. 8 for example, the comprehensive evaluation step S150 acquires additional information, and generates a comprehensive evaluation result based on a plurality of evaluation results (for example, a first evaluation result and a second evaluation result) and the additional information. The comprehensive evaluation step S150 can be executed by, for example, a comprehensive evaluation unit included in the generation unit 12.

[0119] The additional information indicates the characteristics of the user, and indicates information different from the biological information described above, for example. In this case, as the additional information, for example, attribute information such as the user's gender and age is used, and information specifying the user's health status such as a diagnosis result and an amount of exercise may also be used. The additional information is input by the user via, for example, the input unit 108 and acquired by a comprehensive acquisition unit or the like.

[0120] The comprehensive evaluation result indicates the result of comprehensively evaluating the characteristics of the user. The comprehensive evaluation result indicates the result of performing correction processing or the like based on the additional information on the biological information included in each evaluation result. For example, when the user's age is used as the additional information, a comparison result between a preset reference value for each age group and each evaluation result is generated as the comprehensive evaluation result.

[0121] In addition to the above, as the comprehensive evaluation result, for example, a character string representing the characteristics of each user such as "high blood glucose level", "high blood pressure", "high exercise ability", and "it is better to suppress the amount of exercise" is used. In addition, numerical values such as a difference from an arbitrary reference value and a deviation value may be used.

[0122] Further, the comprehensive evaluation result indicates, for example, estimated insurance information including an insurance premium. The estimated insurance information includes, for example, a value indicating an insurance premium estimated based on each evaluation result, and may also include a character string indicating the type of insurance or the like. The estimated insurance premium is calculated based on, for example, insurance mathematics.

[0123] The comprehensive evaluation unit refers to data in a recognizable format for the user, such as data previously stored in the storage unit 104, etc., and generates a comprehensive evaluation result. The comprehensive evaluation unit may refer to, for example, a post-processing database and generate a comprehensive evaluation result suitable for a plurality of evaluation results and additional information. The post-processing database is stored, for example, in the storage unit 104.

[0124] In the post-processing database, similar to the above-described database, post-processing classification information for generating a comprehensive evaluation result for a plurality of evaluation results and additional information may be stored. In addition to storing one or more pieces of post-processing classification information, the post-processing database may store, for example, a plurality of post-processing learning data used for generating the post-processing classification information.

[0125] The post-processing classification information is, for example, a function indicating the correlation between a plurality of past evaluation results and past additional information (post-processing input data) acquired in advance and post-processing reference data associated with the post-processing input data. The post-processing reference data indicates the result of comprehensively evaluating the characteristics of the user. The post-processing classification information is generated using a plurality of post-processing learning data with the post-processing input data and the post-processing reference data as a pair of post-processing learning data.

[0126] The post-processing classification information is, for example, a calibration model that uses the post-processing input data as an explanatory variable, the post-processing reference data as a target variable, analyzes them by the above-described regression analysis, etc., and is generated based on the analysis result. The post-processing classification information can be updated periodically, for example, for the calibration model (post-processing calibration model), and can also be generated separately for each additional information. Note that the post-processing classification information may include a learned model (post-processing learned model) generated by machine learning using a plurality of post-processing learning data, similar to the above-described classification information.

[0127] The saving step S140 saves the comprehensive evaluation result. In the saving step S140, the comprehensive evaluation result is saved in at least one of the storage unit 104 and the server 4 by executing the same processing as in the above-described embodiment.

[0128] According to the present embodiment, in addition to the effects of the above-described embodiments, the comprehensive evaluation unit generates a comprehensive evaluation result obtained by comprehensively evaluating the characteristics of the user based on the first evaluation result, the second evaluation result, and the additional information. Therefore, for each evaluation result, it is possible to realize an evaluation considering the characteristics of the user. As a result, it becomes possible to generate an evaluation result suitable for each user.

[0129] (Second Embodiment: Modification Example of the Biological Information Calculation System 100) Next, a modification example of the biological information calculation system 100 in the second embodiment will be described. The difference between the above-described second embodiment and the modification example is that the additional information described above is acquired in the generation step S120. Note that descriptions of the same content as in the above-described embodiments will be omitted.

[0130] In this modification example, for example, as shown in FIG. 9, the generation step S120 includes acquiring additional information and generating a first evaluation result based on the first evaluation data and the additional information. The additional information is the same as described above, and is input by the user via the input unit 108 or the like and acquired by the generation unit 12 or the like.

[0131] The generation unit 12 may determine an arithmetic method for the first evaluation data according to the content of the additional information, for example. In this case, different functions and the like for each type of additional information are included in the classification information. Note that the generation unit 12 may generate the first evaluation result based on, for example, information combining the first evaluation data and the additional information.

[0132] According to this modification example, the generation unit 12 includes acquiring additional information and generating a first evaluation result based on the first evaluation data and the additional information. Therefore, in addition to the first evaluation data, it is possible to generate a multi-faceted first evaluation result considering the characteristics of the user. As a result, it becomes possible to generate an evaluation of the user's biological information with higher accuracy.

[0133] (Third Embodiment: Biological Information Calculation System 100) Next, an example of the biological information calculation system 100 in the third embodiment will be described. The difference between the above-described embodiment and the third embodiment is that when generating the second evaluation result, the first evaluation result is used in addition to the second evaluation data. Note that descriptions of the same content as in the above-described embodiment will be omitted.

[0134] In the biological information calculation system 100 in this embodiment, for example, as shown in FIG. 10, the generation step S120 includes referring to a database and generating a second evaluation result based on the first evaluation result and the second evaluation data. For example, after generating the first evaluation result, the generation unit 12 generates the second evaluation result.

[0135] The generation unit 12 may determine a calculation method for the second evaluation data according to the content of the first evaluation result, for example. In this case, different functions and the like for each feature of the content of the first evaluation result are included in the classification information. Note that the generation unit 12 may generate the second evaluation result based on, for example, information combining the first evaluation result and the second evaluation data.

[0136] According to this embodiment, in addition to the effects of the above-described embodiment, the generation unit 12 generates a second evaluation result based on the first evaluation result and the second evaluation data. Therefore, a second evaluation result based on the first evaluation result can be generated. As a result, it is possible to generate an evaluation of the user's biological information with higher accuracy.

[0137] (Fourth Embodiment: Biological Information Calculation System 100) Next, an example of the biological information calculation system 100 in the fourth embodiment will be described. The difference between the above-described embodiment and the fourth embodiment is that attribute classification information suitable for the evaluation data is selected from a plurality of attribute classification information included in the classification information. Note that descriptions of the same content as in the above-described embodiment will be omitted.

[0138] In the biological information calculation device 1 according to this embodiment, for example, as shown in FIG. 11, the generation step S120 includes a selection step S121 and an attribute-based generation step S122. Note that in FIG. 11, the description of the content of the second evaluation data and the second evaluation result is omitted.

[0139] The selection step S121 refers to the preliminary evaluation data and selects specific attribute-based classification information (for example, the first classification information) from among a plurality of pieces of attribute-based classification information. The selection step S121 can be executed, for example, by a selection unit included in the generation unit 12. The preliminary evaluation data shows characteristics different from those of the first evaluation data and shows characteristics similar to those of the second data, for example.

[0140] The attribute-based generation step S122 refers to the selected first classification information, calculates a first biological information (for example, the value of the partial pressure of carbon dioxide in the blood) for the first evaluation data, and generates a first evaluation result. The attribute-based generation step S122 can be executed, for example, by an attribute-based generation unit included in the generation unit 12.

[0141] The plurality of pieces of attribute-based classification information are calculated using different learning data. For example, when data corresponding to the acceleration pulse wave of the subject is used as the input data of the learning data, the input data is prepared for each of seven types (A to G) as shown in FIG. 12, for example, and seven types of attribute classification information are generated.

[0142] When such a plurality of pieces of attribute-based classification information are stored in the database, for example, the acquisition unit 11 acquires evaluation data and preliminary evaluation data corresponding to the acceleration pulse wave of the user. Then, the generation unit 12 refers to the preliminary evaluation data and selects the first classification information. Thereafter, the generation unit 12 refers to the first classification information and generates a first evaluation result for the first evaluation data. Therefore, among the pieces of each attribute classification information, the classification information optimal for the user can be selected.

[0143] In addition, for example, when data corresponding to the subject's velocity pulse wave is used as input data for learning data, the input data may be prepared for each of two types (Group 1, Group 2) as shown in FIG. 13, for example, and two types of attribute classification information may be generated.

[0144] Here, the data corresponding to the acceleration pulse wave shown in FIG. 12 is easy to classify in detail based on features, but on the other hand, when calculating biological information, a decrease in accuracy due to false detection of peaks and the like is a concern. In addition, the data corresponding to the velocity pulse wave shown in FIG. 13 is difficult to classify in detail based on features compared to the data corresponding to the acceleration pulse wave, but since false detection of peaks and the like is less, biological information can be calculated with high accuracy.

[0145] Based on the above, the plurality of attribute classification information includes data corresponding to an acceleration pulse wave as shown in FIG. 12, for example, as selection data used to select specific classification information, and data corresponding to a velocity pulse wave may be used as learning data when generating the attribute classification information.

[0146] In this case, as the acquisition step S110, for example, the acquisition unit 11 acquires data corresponding to the velocity pulse wave from the sensor data based on the user's pulse wave as the first evaluation data. In addition, the acquisition unit 11 acquires data corresponding to the acceleration pulse wave from the sensor data as preliminary evaluation data.

[0147] Next, as the selection step S121, for example, the generation unit 12 refers to the preliminary evaluation data, identifies the selection data (first selection data) most similar to the preliminary evaluation data among the plurality of selection data including the data corresponding to the acceleration pulse wave, and selects the first classification information associated with the first selection data. Then, as the attribute-specific generation step S122, the generation unit 12 refers to the first classification information and generates a first evaluation result for the first evaluation data. Thereby, it becomes possible to further improve the evaluation accuracy.

[0148] Here, an example of the data used for the above-described selection data and the like will be described.

[0149] For example, as shown in FIG. 12, the acceleration pulse wave has inflection points a to e. For example, when the maximum peak in the acceleration pulse wave is point a, and the inflection points are sequentially designated as point b, point c, point d, and point e from point a, and normalization is performed with point a being 1 and the minimum value, point b or point d, being 0, the acceleration pulse wave can be classified into seven patterns using a method of classification based on the values of the inflection points and the magnitude relationship of their differences. First, when the value of the inflection point b < d, it is classified into pattern A or B. If b < d and further c ≧ 0.5, it is classified into A; otherwise, it is classified into B. Next, when the value of the inflection point b ≒ d, it is classified into pattern C or D. If b ≒ d and further c ≒ 0, it is classified into pattern D; otherwise, it is classified into pattern C. Finally, when b > d, it can be classified into any of patterns E, F, and G. If b > d and further b < c, it is classified into pattern E; if b ≒ c, it is classified into pattern F; if b > c, it is classified into pattern G.

[0150] For example, the generation unit 12 determines which pattern of FIG. 12 the preliminary evaluation data corresponds to, and specifies the first selection data. For example, if the inflection point b of the input preliminary evaluation data is smaller than the inflection point d, and further the inflection point c ≧ 0.5, then pattern A is used as the first selection data. Thereby, by referring to the classification information suitable for the characteristics of the first evaluation data, the biological information can be calculated with high accuracy.

[0151] According to the present embodiment, in addition to the effects of the above-described embodiment, the generation unit 12 includes a selection unit that refers to the preliminary evaluation data and selects the first classification information, and an attribute-based generation unit that refers to the first classification information and generates a first evaluation result for the first evaluation data. Therefore, after selecting the first classification information optimal for the characteristics of the pulse wave, a first evaluation result for the first evaluation data can be generated. Thereby, it becomes possible to further improve the evaluation accuracy.

[0152] Also, according to the present embodiment, the acquisition unit 11 acquires data corresponding to the velocity pulse wave based on the pulse wave as the first evaluation data. Further, the acquisition unit 11 acquires data corresponding to the acceleration pulse wave based on the pulse wave as the preliminary evaluation data. Therefore, attribute classification information can be selected using the acceleration pulse wave, which is easier to classify the characteristics of the pulse wave than the velocity pulse wave. Also, the first evaluation result can be generated using the velocity pulse wave, which is easier to calculate the biological information than the acceleration pulse wave. Thereby, it becomes possible to further improve the evaluation accuracy.

[0153] (Fourth Embodiment: First Modification Example of the Biological Information Calculation System 100) Next, a first modification example of the biological information calculation system 100 in the fourth embodiment will be described. The difference between an example of the above-described fourth embodiment and the first modification example is the point of selecting classification information using the evaluation result. Note that the description of the same content as the above-described embodiment will be omitted.

[0154] In this modification example, for example, as shown in FIG. 14, in the generation step S120, among the classification information, the first classification information is selected based on the second evaluation result, the first classification information is referred to, and the first evaluation result for the first evaluation data is generated. For example, the generation unit 12 refers to the second evaluation result and selects specific attribute-based classification information among the plurality of attribute-based classification information in the same manner as the above-described selection step S121.

[0155] The generation unit 12 selects the first classification information based on, for example, the value of the biological information included in the second evaluation result. At this time, values for selection are preset in the plurality of attribute information.

[0156] The generation unit 12 refers to the selected first classification information, calculates the first biological information for the first evaluation data, and generates the first evaluation result in the same manner as the above-described attribute-based generation step S122.

[0157] According to this modification example, the generation unit 12 selects the first classification information based on the second evaluation result, refers to the first classification information, and generates the first evaluation result for the first evaluation data. Therefore, after selecting the optimal first classification information according to the second evaluation result, the first evaluation result for the first evaluation data can be generated. Thereby, it becomes possible to further improve the evaluation accuracy.

[0158] (Fourth Embodiment: Second Modification Example of the Biological Information Calculation System 100) Next, a second modification example of the biological information calculation system 100 in the fourth embodiment will be described. The difference between an example of the above-described fourth embodiment and the second modification example is the point of selecting the first classification information based on the characteristics of the pulse wave. Note that descriptions of the same content as in the above-described embodiments will be omitted.

[0159] In this modification example, for example, as shown in FIG. 15, in the generation step S120, among the classification information, the first classification information is selected based on the characteristics of the pulse wave (for example, sensor data), the first classification information is referred to, and the first evaluation result for the first evaluation data is generated. For example, the generation unit 12 refers to the sensor data and selects specific attribute-based classification information from among the plurality of attribute-based classification information in the same manner as in the above-described selection step S121.

[0160] Note that, as the "characteristics of the pulse wave", for example, data after at least a part of each process shown in FIGS. 4(a) to 4(d) is performed on the sensor data may be used. In particular, by using the pulse wave data after performing a filtering process on the sensor data as the characteristics of the pulse wave, it becomes possible to improve the accuracy when selecting specific attribute classification information.

[0161] The generation unit 12 compares, for example, the above-described selection data with the characteristics of the pulse wave, and selects the first classification information. The generation unit 12 may select the first classification information based on, for example, the half-value width or relative intensity of the peak included in the sensor data or the like. At this time, values for selection are preset for the plurality of attribute information.

[0162] Similar to the above-described generation step S122 for each attribute, the generation unit 12 refers to the selected first classification information, calculates first biological information for the first evaluation data, and generates a first evaluation result.

[0163] According to this modification example, the generation unit 12 selects first classification information based on the characteristics of the pulse wave, refers to the first classification information, and generates a first evaluation result for the first evaluation data. Therefore, after selecting the optimal first classification information according to the characteristics of the pulse wave, it is possible to generate a first evaluation result for the first evaluation data. As a result, it is possible to further improve the evaluation accuracy.

[0164] (Fourth Embodiment: Third Modification Example of the Biological Information Calculation System 100) Next, a third modification example of the biological information calculation system 100 in the fourth embodiment will be described. The difference between an example of the above-described fourth embodiment and the third modification example is that the first classification information is selected based on additional information. Note that descriptions of the same content as in the above-described embodiments will be omitted.

[0165] In this modification example, for example, as shown in FIG. 16, in the generation step S120, among the classification information, the first classification information is selected based on the additional information, the first classification information is referred to, and a first evaluation result for the first evaluation data is generated. For example, the generation unit 12 refers to the additional information and selects specific attribute-based classification information among the plurality of attribute-based classification information in the same manner as the above-described selection step S121. Note that the additional information is the same as the above-described additional information.

[0166] The generation unit 12 may select the first classification information based on, for example, attribute information such as age and gender included in the additional information. At this time, for the plurality of attribute information, attribute information for selection and the like are preset.

[0167] Similar to the above-described generation step S122 for each attribute, the generation unit 12 refers to the selected first classification information, calculates first biological information for the first evaluation data, and generates a first evaluation result.

[0168] According to this modification example, the generation unit 12 selects the first classification information based on the additional information, refers to the first classification information, and generates a first evaluation result for the first evaluation data. Therefore, after selecting the optimal first classification information according to the characteristics of the additional information, the first evaluation result for the first evaluation data can be generated. Thereby, it becomes possible to further improve the evaluation accuracy.

[0169] (Fifth Embodiment: Biological Information Calculation System 100) Next, an example of the biological information calculation system 100 in the fifth embodiment will be described. The difference between the above-described embodiment and the fifth embodiment is that it includes the calculation step S160. Regarding the same content as the above-described embodiment, the description will be omitted.

[0170] The biological information calculation system 100 in the present embodiment includes, for example, the calculation step S160. In the biological information calculation system 100, for example, after the above-described storage step S140, the calculation step S160 is performed.

[0171] The calculation step S160 generates a comprehensive evaluation result that comprehensively evaluates the characteristics of the user based on, for example, a plurality of evaluation results (for example, the first evaluation result and the second evaluation result) stored in the server 4 or the storage unit 104 as shown in FIG. 17. The calculation step S160 can be executed, for example, by the comprehensive evaluation unit included in the generation unit 12 of the biological information calculation device 1, or can be executed, for example, by the comprehensive evaluation unit included in the server 4.

[0172] The comprehensive evaluation result is the same as that in the above-described embodiment, and will be described below as estimated insurance information including insurance premiums as an example.

[0173] The comprehensive evaluation unit may refer to, for example, data in a data format recognizable by the user that is stored in advance in the storage unit 104 or the like, and generate estimated insurance information. The comprehensive evaluation unit may refer to, for example, a database and generate estimated insurance information suitable for a plurality of evaluation results.

[0174] The database may store classification information for insurance for generating estimated insurance information for a plurality of evaluation results, for example, in the same manner as the database described above. In addition to storing one or more pieces of classification information for insurance, the database may store, for example, a plurality of pieces of learning data for insurance used for generating the classification information for insurance.

[0175] The classification information for insurance is, for example, a function indicating the correlation between a plurality of past evaluation results (input data for insurance) acquired in advance and reference data for insurance associated with the input data for insurance. The reference data for insurance includes insurance premiums for health input data with past performance. The classification information for insurance is generated using a plurality of pieces of learning data for insurance, with the input data for insurance and the reference data for insurance as a pair of learning data for insurance.

[0176] The classification information for insurance indicates, for example, a calibration model generated by using the input data for insurance as an explanatory variable, the reference data for insurance as an objective variable, analyzing by the above-described regression analysis, etc., and based on the analysis result. The classification information for insurance can be updated periodically, for example, the calibration model (calibration model for insurance). Note that the classification information for insurance may include a learned model (learned model for insurance) generated by machine learning using a plurality of pieces of learning data for insurance, in the same manner as the classification information described above.

[0177] According to the present embodiment, in addition to the effects of the above-described embodiment, the comprehensive evaluation unit generates a comprehensive evaluation result based on the first evaluation result and the second evaluation result. Therefore, for each evaluation result, it is possible to realize an evaluation considering the characteristics of the user. As a result, it is possible to generate an evaluation result suitable for each user. In particular, when estimated insurance information is used as the comprehensive evaluation result, it is possible to suppress variations in estimated insurance premiums and the like due to the subjectivity of the user or the like.

[0178] (Sixth Embodiment: Biological Information Calculation System 100) Next, an example of the biological information calculation system 100 in the sixth embodiment will be described. The difference between the above-described embodiment and the sixth embodiment lies in the use of the determination result. Regarding the content similar to the above-described embodiment, the description will be omitted.

[0179] In the biological information calculation system 100 in this embodiment, for example, as shown in FIG. 18, in the storage step S140, the determination result determined by the user for the content of a plurality of evaluation results (for example, the first evaluation result and the second evaluation result) is acquired, and the determination result and the plurality of evaluation results are respectively associated and stored. The storage step S140 can be executed, for example, by the storage unit 14 or the server 4.

[0180] The determination result can be acquired, for example, by the user inputting, via the input unit 108 or the like, the result of comparing a plurality of output evaluation results with the biological information measured using a known measuring device.

[0181] The biological information calculation system 100 in this embodiment may include, for example, an update step S170. In this case, the update step S170 can be executed, for example, by the learning unit 15, or may be executed by the server 4.

[0182] The learning unit 15 updates the classification information based on the determination result and the plurality of evaluation results stored in the storage step S140. The learning unit 15 updates the classification information using, for example, a known technique.

[0183] According to this embodiment, in addition to the effects of the above-described embodiment, the storage unit 14 or the server 4 stores the determination result, the first evaluation result, and the second evaluation result in association with each other. Therefore, it becomes possible to easily compare each evaluation result with the determination result.

[0184] Also, according to the present embodiment, the learning unit 15 updates the classification information based on the determination result, the first evaluation result, and the second evaluation result. Therefore, when the accuracy of each evaluation result deteriorates, it can be easily improved. As a result, it becomes possible to maintain the improvement in accuracy when evaluating biological information.

[0185] Although the embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. Such novel embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the gist of the invention. These embodiments and their modifications are included in the scope and gist of the invention, and are included in the invention described in the claims and its equivalent scope.

Explanation of Reference Numerals

[0186] 1: Biological information calculation device 3: Communication network 4: Server 5: Sensor 6: Detection unit 10: Housing 11: Acquisition unit 12: Generation unit 13: Output unit 14: Storage unit 15: Learning unit 50: Acquisition unit 51: Communication I / F 52: Memory 53: Command unit 54: Internal bus 55: List band 100: Biological information calculation system 101: CPU 102: ROM 103: RAM 104: Storage unit 105: I / F 106: I / F 107: I / F 108: Input unit 109: Display unit 110: Internal bus S110: Acquisition Step S120: Generation Step S130: Output Step S140: Saving Step S150: Comprehensive Evaluation Step S160: Calculation Step S170: Update Step

Claims

1. A biological information calculation system for evaluating a user's biological information, for one piece of pulse wave data corresponding to either a velocity pulse wave or an acceleration pulse wave based on the pulse wave of the user, by performing different types of processing respectively, an acquisition means for acquiring first evaluation data and second evaluation data for one piece of the pulse wave data; a database storing classification information used for processing the first evaluation data and the second evaluation data; referencing the database, a first evaluation result including first biological information for the first evaluation data, and a second evaluation result including second biological information of a type different from the first biological information for the second evaluation data, a generation means for generating each; a storage means for storing the first evaluation result and the second evaluation result; characterized by comprising a biological information calculation system.

2. The first evaluation data and the second evaluation data are data corresponding to either the velocity pulse wave or the acceleration pulse wave of the user The biological information calculation system according to claim 1, characterized by this.

3. A server characterized in that the first evaluation result and the second evaluation result according to claim 1 are stored.

Images