JP2020048674A - Biological information acquisition method, biological information acquisition model learning method, device, and program - Google Patents

Abstract

To provide a biological information acquisition method capable of acquiring biological information from measurement information acquired from a subject, a biological information acquisition model learning method, a device, and a program.SOLUTION: A measurement information acquisition unit 25 of a biological information acquisition apparatus 10 acquires measurement information on a subject. A biological information acquisition unit 26 inputs the measurement information acquired by the measurement information acquisition unit 25 into a learned model learned beforehand for acquiring biological information indicating a state of a subject from the measurement information, and acquires the biological information on the subject.SELECTED DRAWING: Figure 1

Description

  The present disclosure relates to a biological information acquisition method, a biological information acquisition model learning method, an apparatus, and a program.

  In recent years, it has been studied to apply a piezoelectric body containing a helical chiral polymer to a piezoelectric device such as a sensor or an actuator. Such a piezoelectric device uses a film-shaped piezoelectric body.

  Attention has been paid to using a polymer having optical activity such as a polypeptide or a polylactic acid-based polymer as the helical chiral polymer in the piezoelectric body. Among them, polylactic acid-based polymers are known to exhibit piezoelectricity only by a mechanical stretching operation. It is known that a poling process is not required for a piezoelectric material using a polylactic acid-based polymer, and that the piezoelectricity does not decrease over several years.

  For example, as a piezoelectric body containing a polylactic acid-based polymer, a piezoelectric body having a large piezoelectric constant d14 and excellent transparency has been reported (for example, see Patent Documents 1 and 2).

  In addition, recently, an attempt has been made to use a material having piezoelectricity by covering the conductor. For example, a piezo cable is known, which includes a center conductor, a piezoelectric material layer, an outer conductor, and a jacket arranged coaxially in order from the center to the outside (for example, see Patent Document 3).

  In addition, a piezoelectric unit in which a fiber made of a piezoelectric polymer is coated with a conductive fiber is known (for example, see Patent Document 4).

Japanese Patent No. 4934235 International Publication No. WO 2010/104196 JP-A-10-132669 International Publication No. WO 2014/058077

  By the way, for example, a piezoelectric element manufactured by using a piezoelectric material as described in Patent Documents 1 to 4 is attached to a subject, and biological information of the subject is to be obtained from measurement information obtained from the piezoelectric element. In such a case, it is necessary to perform an appropriate conversion process on the measurement information.

  However, there is a problem in that it is not known how to perform the conversion process on the measurement information obtained from the piezoelectric element attached to the subject to obtain the biological information of the subject.

  An object of the present disclosure is to provide a biological information acquisition method, a biological information acquisition model learning method, an apparatus, and a program that can acquire biological information from measurement information obtained from a subject.

  The biological information obtaining method of the present disclosure is a step of obtaining measurement information obtained from a subject, and the obtained measurement information is pre-learned for obtaining biological information representing the state of the subject from the measurement information. Acquiring the biological information of the subject by inputting the information to the trained model.

  Further, the learned model of the biological information acquisition method of the present disclosure can be a neural network that is learned in advance based on learning data representing a combination of the measurement information for learning and the biological information for learning. .

  Further, the measurement information of the biological information acquiring method of the present disclosure is piezoelectric information representing a voltage value obtained from a piezoelectric element in contact with the subject, and the biological information is a heartbeat representing a state of the subject's heartbeat. It can be information.

  The piezoelectric element may be a piezoelectric element installed on a chair on which the subject sits.

  The biological information acquisition model learning method of the present disclosure is a step of acquiring learning data representing a combination of measurement information of a subject for learning and biological information representing a state of the subject for learning, and the acquired learning data. Acquiring a learned model for acquiring the biological information from the measurement information based on the measurement information.

  The biological information acquisition model learning method of the present disclosure corrects the drift region of the measurement information of the subject for learning, and uses the corrected measurement information as the biological information, the measurement information for learning and the learning information. The method may further include a step of generating a combination with biological information as the learning data.

  The biological information acquisition model learning method of the present disclosure excludes an unmeasured area in the measurement information of the subject for learning, sets the measurement information excluding the unmeasured area as the biological information, The method may further include a step of generating a combination of the measurement information and the biological information for learning as the learning data.

  The biological information acquisition device of the present disclosure acquires a measurement information acquisition unit that acquires measurement information of a subject, the measurement information acquired by the measurement information acquisition unit, and acquires biological information representing a state of the subject from the measurement information. And a biological information acquisition unit that acquires the biological information of the subject by inputting to a learned model that has been learned in advance.

  A biological information acquisition model learning device according to the present disclosure includes a learning data acquisition unit that acquires learning data representing a combination of measurement information of a subject for learning and biological information representing a state of the subject for learning. A biological information acquisition model learning device, comprising: a learning unit that acquires a learned model for acquiring the biological information from the measurement information based on the learning data acquired by the data acquisition unit.

  A first program according to an embodiment of the present disclosure provides a computer, comprising: a measurement information acquisition unit that acquires measurement information of a subject; and the measurement information acquired by the measurement information acquisition unit. This is a program for inputting to a learned model that has been learned in advance for acquiring information, and for functioning as a biological information acquiring unit that acquires the biological information of the subject.

  A second program according to an embodiment of the present disclosure is directed to a learning data acquisition unit configured to acquire a learning data representing a combination of measurement information of a subject for learning and biological information representing a state of the subject for learning. A program for functioning as a learning unit that acquires a learned model for acquiring the biological information from the measurement information based on the learning data acquired by the acquisition data acquisition unit.

  According to the biological information acquisition method, the biological information acquisition model learning method, the apparatus, and the program of the present disclosure, an advantage is obtained in that biological information can be acquired from measurement information obtained from a subject.

It is a schematic diagram showing an example of composition of a living body information acquisition device of this embodiment. It is a schematic block diagram of the computer which functions as a biological information acquisition device. It is an explanatory view for explaining measurement information of this embodiment. FIG. 4 is an explanatory diagram for describing learning data of the present embodiment. FIG. 4 is an explanatory diagram for describing learning data of the present embodiment. FIG. 2 is an explanatory diagram for describing U-Net, which is an example of a neural network used in the present embodiment. It is a figure showing an example of piezoelectric information inputted into a learned neural network. It is a figure showing an example of the heartbeat information outputted from the learned neural network. FIG. 7 is a diagram illustrating an example of a learning data generation processing routine executed by the biological information acquisition device. FIG. 4 is a diagram illustrating an example of a learning processing routine executed by the biological information acquisition device. FIG. 4 is a diagram illustrating an example of a biological information acquisition processing routine executed by the biological information acquisition device. It is a figure showing a result of an example. It is a figure showing a result of an example. It is a figure showing a result of an example. It is a figure showing a result of an example. It is a figure showing a result of an example. It is a figure showing a result of an example.

  Hereinafter, the present embodiment will be described in detail.

<System Configuration of Biological Information Acquisition Device According to the Present Embodiment>

  FIG. 1 is a schematic diagram illustrating an example of a configuration of a biological information acquisition device 10 according to the present embodiment. The biological information acquiring apparatus 10 having the configuration shown in FIG. 1 can be configured by a computer including a CPU, a RAM, and a ROM storing programs and various data for executing respective processing routines described below.

  For example, the biological information acquisition device 10 can be realized by the computer 50 shown in FIG. The computer 50 includes a CPU 51, a memory 52 as a temporary storage area, and a nonvolatile storage unit 53. The computer 50 includes an input / output interface (I / F) 54 to which input / output devices and the like (not shown) are connected, and a read / write (R / W) unit 55 that controls reading and writing of data from and to a recording medium. Is provided. Further, the computer 50 includes a network I / F 56 connected to a network such as the Internet. The CPU 51, the memory 52, the storage unit 53, the input / output I / F 54, the R / W unit 55, and the network I / F 56 are connected to each other via a bus 57.

  The storage unit 53 can be realized by a hard disk drive (HDD), a solid state drive (SSD), a flash memory, or the like. The storage unit 53 as a storage medium stores a program for causing the computer 50 to function. The CPU 51 reads the program from the storage unit 53, expands the program in the memory 52, and sequentially executes the processes of the program.

  The biological information acquiring apparatus 10 functionally includes an input unit 12, a calculation unit 14, and an output unit 16, as shown in FIG.

  The biological information acquisition device 10 of the present embodiment converts measurement information obtained from a subject into biological information of the subject. FIG. 3 is an explanatory diagram for explaining the measurement information of the present embodiment. As shown in FIG. 3, the piezoelectric element S is installed on the chair C. The piezoelectric element S is located on the back side of the thigh of the subject U sitting on the chair C.

  The biological information acquisition device 10 of the present embodiment uses, as measurement information, piezoelectric information indicating a voltage obtained from the piezoelectric element S in contact with the subject U. Then, the biological information acquisition device 10 converts the piezoelectric information obtained from the piezoelectric element S into heart rate information indicating the state of the heart rate of the subject U. The heart rate information is an example of biological information indicating the state of the subject.

  The input unit 12 receives piezoelectric information as measurement information obtained from a subject. The input unit 12 receives a combination of the learning piezoelectric information and the learning heartbeat information.

  The combination of the learning piezoelectric information and the learning heart rate information is data obtained in advance from the subject. Further, in the combination of the learning piezoelectric information and the learning heartbeat information, the measured time corresponds to the learning piezoelectric information and the learning heartbeat information.

  For example, learning piezoelectric information obtained from a piezoelectric element installed on a chair on which a subject sits and heart rate information obtained from an electrocardiograph installed on the subject's chest are acquired in advance as a set of data. . Based on these data, learning data is generated by a process described later.

  The calculation unit 14 generates a learned model for acquiring heart rate information from the piezoelectric information based on the combination of the learning piezoelectric information and the learning heart rate information received by the input unit 12. In addition, the arithmetic unit 14 converts the piezoelectric information received by the input unit 12 into heartbeat information. As shown in FIG. 1, the calculation unit 14 includes a learning data generation unit 17, a learning data storage unit 18, a learning data acquisition unit 20, a learning unit 22, a learned model storage unit 24, A measurement information acquisition unit 25 and a biological information acquisition unit 26 are provided.

  The learning data generation unit 17 acquires each of the combinations of the learning piezoelectric information and the learning heartbeat information received by the input unit 12. Then, the learning data generation unit 17 processes the heart rate information for learning to generate learning data.

  FIG. 4 is an explanatory diagram for explaining the learning data. The horizontal axis of the graph D1 shown in FIG. 4 represents time, and the vertical axis represents voltage values. The solid line (ECG) shown in FIG. 4 is heart rate information for learning. The broken line (ECG_fir) shown in FIG. 4 is data obtained by processing the heartbeat information for learning.

  The time-series data of the heartbeat information for learning indicated by the solid line (ECG) shown in FIG. 4 is wavy as a whole and includes a drift component. This drift component is generated, for example, when a subject moves while measuring heart rate information for learning.

  Therefore, the learning data generation unit 17 processes the learning heart rate information by applying an existing high-pass filter to the learning heart rate information including the drift component. Whether or not a drift component is included in the learning heartbeat information is determined according to the peak value of the learning heartbeat information. For example, when the peak value of the learning heartbeat information is equal to or greater than a predetermined threshold, the learning data generation unit 17 determines that the learning heartbeat information includes a drift component. In the present embodiment, an FIR (Finite Impulse Response) filter is used as a high-pass filter.

  By applying the high-pass filter by the learning data generation unit 17, the heartbeat information for learning indicated by the solid line (ECG) illustrated in FIG. 4 becomes time-series data such as a broken line (ECG_file). The time-series data indicated by the broken line (ECG_fir) shown in FIG. 4 is data obtained when the number of taps, which are parameters of the FIR filter, is set to 127 and the cutoff frequency is set to 1.5 Hz. The number of taps is a parameter indicating how much delay is calculated when filtering is performed.

  For this reason, the learning data generation unit 17 of the present embodiment generates, as learning data, a combination of the learning piezoelectric information and the processed learning heartbeat information in which the drift component has been corrected.

  FIG. 5 is another explanatory diagram for explaining the learning data. Like the graph D1 of FIG. 4, the horizontal axis of the graph D2 shown in FIG. 5 represents time, and the vertical axis represents the voltage value.

  As indicated by D2 in FIG. 5, the heartbeat information for learning may include an unmeasured region (a portion surrounded by an ellipse in the drawing). Therefore, the learning data generation unit 17 excludes an unmeasured area in the heartbeat information for learning. The presence or absence of an unmeasured region of the learning heart rate information is determined according to the peak value of the learning heart rate information. For example, if the time during which the peak value of the heartbeat information for learning is less than a value in a predetermined range (for example, −4 to +4) continues for a predetermined time or more, the learning data generation unit 17 determines that location. Is determined to include an unmeasured area. Then, the learning data generation unit 17 generates, as learning data, a combination of the learning piezoelectric information and the processed learning heart rate information excluding the unmeasured region.

  Note that the learning data generation unit 17 determines the learning piezoelectric information and the learning heart rate information for the learning heart rate information not including the drift component and the learning heart rate information not including the unmeasured area. The combination with the information is directly generated as learning data.

  Then, the learning data generation unit 17 stores each of the learning data in the learning data storage unit 18. These learning data are used for neural network learning described later. As described above, by correcting the drift component included in the heartbeat information for learning and excluding the unmeasured region included in the heartbeat information for learning, it is possible to obtain a highly accurate learned model.

  Each of the learning data generated by the learning data generation unit 17 is stored in the learning data storage unit 18. The learning data of the present embodiment is data representing a combination of the piezoelectric information of the learning subject and the heartbeat information of the learning subject.

  The learning data acquisition unit 20 acquires each of the learning data stored in the learning data storage unit 18.

  The learning unit 22 learns a neural network, which is an example of a model for acquiring biological information from measurement information, based on the learning data acquired by the learning data acquisition unit 20. Note that a well-known deep learning or the like may be used as the learning algorithm. And the learning part 22 acquires the learned neural network as an example of the learned model.

  FIG. 6 is an explanatory diagram for explaining the learned neural network of the present embodiment. As shown in FIG. 6, in the present embodiment, a U-Net using a CNN (Convolutional Neural Network) which is a kind of a neural network (for example, a reference (Olaf Ronneberger, Philipp Fischer, and Thomas Brox, "U-Net") Net: Convolutional Networks for Biomedical Image Segmentation "). The channel shown in FIG. 6 is a U-Net parameter, and is set to a value as shown in FIG. 6 in the present embodiment.

  When the subject's piezoelectric information is input as input data (INPUT) to the learned neural network as shown in FIG. 6, the subject's heart rate information is output as output data (OUTPUT).

  For example, when the piezoelectric information as shown in FIG. 7 is input to the learned neural network, the heart rate information as shown in FIG. 8 is obtained. Note that the horizontal axes of the graphs in FIGS. 7 and 8 represent time, and the vertical axes represent voltage values.

  In the learned model storage unit 24, the learned neural network acquired by the learning unit 22 is stored.

  The measurement information acquisition unit 25 acquires the piezoelectric information of the subject to be converted, which is received by the input unit 12.

  The biological information acquisition unit 26 acquires the subject's conversion target piezoelectric information acquired by the measurement information acquisition unit 25. Further, the biological information acquisition unit 26 reads out the learned neural network stored in the learned model storage unit 24. Then, the biological information obtaining unit 26 inputs the subject's conversion target piezoelectric information to the learned neural network, and obtains the subject's heart rate information.

  Thus, by preparing learning data in which the piezoelectric information for learning and the heartbeat information for learning are associated with each other, and learning the neural network using the learning data, the conversion from the piezoelectric information to the heartbeat information is performed. Processing is performed properly. Therefore, the heart rate information of the subject can be sequentially acquired without attaching the electrocardiograph to the subject.

  The output unit 16 outputs the subject's heart rate information acquired by the biological information acquiring unit 26 as a result.

<Operation of biological information acquisition device>

  Next, the operation of the biological information acquiring apparatus 10 will be described with reference to FIGS. 9, 10, and 11. When each of the combination of the learning piezoelectric information and the learning heartbeat information is input to the biological information acquisition device 10, the input unit 12 receives each of the combination of the learning piezoelectric information and the learning heartbeat information. . Then, the biological information acquiring apparatus 10 executes a learning data generation processing routine shown in FIG.

<Learning data generation processing routine>

  In step S100, the learning data generation unit 17 acquires each of the combinations of the learning piezoelectric information and the learning heart rate information received by the input unit 12.

  In step S102, the learning data generation unit 17 applies an existing high-pass filter to the learning heartbeat information including the drift component among the learning heartbeat information acquired in step S100. Then, the learning data generation unit 17 generates, as learning data, a combination of the learning piezoelectric information and the processed learning heartbeat information in which the drift component has been corrected.

  In step S102, the learning data generation unit 17 excludes an unmeasured region in the learning heartbeat information acquired in step S100. Then, the learning data generation unit 17 generates, as learning data, a combination of the learning piezoelectric information and the processed learning heart rate information excluding the unmeasured region.

  In step S104, the learning data generation unit 17 stores each of the learning data obtained in step S102 in the learning data storage unit 18, and ends the learning data generation processing routine.

  Next, when receiving the start signal of the learning process, the biological information acquiring apparatus 10 executes the learning process routine shown in FIG.

<Learning process routine>

  In step S200, the learning data acquisition unit 20 acquires each of the learning data stored in the learning data storage unit 18.

  In step S202, the learning unit 22 learns a neural network for acquiring heart rate information from piezoelectric information based on each of the learning data acquired in step S200. Then, the learning unit 22 acquires the learned neural network.

  In step S204, the learning unit 22 stores the learned neural network acquired in step S202 in the learned model storage unit 24, and ends the learning processing routine.

  Next, when receiving the input of the piezoelectric information to be converted, the biological information acquiring apparatus 10 executes a biological information acquiring processing routine shown in FIG.

<Biological information acquisition processing routine>

  In step S300, the measurement information acquisition unit 25 acquires the subject's conversion target piezoelectric information received by the input unit 12.

  In step S302, the biological information acquisition unit 26 reads the learned neural network stored in the learned model storage unit 24.

  In step S304, the biological information acquiring unit 26 inputs the subject's conversion target piezoelectric information acquired in step S300 to the learned neural network read in step S302, and acquires the subject's heart rate information. get.

  In step S306, the output unit 16 outputs the subject's heart rate information acquired in step S304 as a result.

  As described above, the biological information acquisition device 10 according to the present embodiment inputs the piezoelectric information obtained from the subject to a learned neural network that has been learned in advance to acquire heart rate information from the piezoelectric information, Obtain heart rate information of the subject. Thus, heart rate information can be obtained from the piezoelectric information obtained from the subject. Further, the heart rate information of the subject can be sequentially obtained without attaching the electrocardiograph to the subject.

  In addition, the biological information acquisition device 10 according to the present embodiment converts heart rate information from piezoelectric information based on learning data indicating a combination of the piezoelectric information of the learning subject and heart rate information indicating the state of the learning subject. Get the trained model to get. Thereby, a learned model for acquiring heart rate information from piezoelectric information obtained from a subject can be obtained. In addition, when generating the learning data, the biological information acquiring apparatus 10 according to the present embodiment excludes the drift component and the unmeasured region included in the heartbeat information for learning, thereby achieving highly accurate learning. You can get a model.

<Example>

  Next, examples will be described. In the present embodiment, the U-Net shown in FIG. 6 was learned. In this example, the U-Net model was used for each of the stationary data representing data acquired when the subject was stationary and the moving data acquired when the subject was moving. Learned. Also, when learning the U-Net, a learning process of 300 epochs was performed for each. The number of learning data used for the U-Net learning and the number of evaluation data used for the evaluation of the trained U-Net model are as follows.

  FIG. 12 shows the transition of the accuracy of the learned U-Net when the learning process is performed using the stationary data.

  The horizontal axis of the graph shown in FIG. 12 is the epoch number representing the number of repetitions of learning, and the vertical axis is the heart rate information and electrocardiograph (portable electrocardiograph HCG-801 OMRON) output from the trained U-Net. (Hereinafter, simply referred to as a “loss value”).

  As shown in FIG. 12, the loss value decreases as the learning progresses and the number of epochs increases, and it can be seen that the learning is performed without any problem. The dotted line (loss) shown in FIG. 12 represents a loss value between the heartbeat information output when the learning piezoelectric information is input to the learned U-Net and the actual heartbeat information. I have. Further, the solid line (val_loss) shown in FIG. 12 indicates the heart rate information output when the evaluation piezoelectric information different from the learning piezoelectric information is input to the learned U-Net and the actual heart rate information. Represents the loss value between the two.

  FIG. 13 shows the transition of the accuracy of the learned U-Net when the learning process is performed using the moving data. Similarly to FIG. 12, also in FIG. 13, the loss value decreases as the learning progresses and the number of epochs increases, and it can be seen that the learning is performed without any problem.

  FIGS. 14, 15, 16 and 17 show waveforms of heartbeat information output when piezoelectric information for evaluation different from the piezoelectric information for learning is input to the trained U-Net. Is shown. 14 and 15 show the results in the case of data at rest, and FIGS. 16 and 17 show the results in the case of data at movement.

  In FIGS. 14, 15, 16, and 17, “X_test” represents the waveform of the piezoelectric information for evaluation, “Y_test” represents the waveform of the heart rate information of the correct answer actually measured, and “Y_predict” represents The waveform of the heartbeat information output when the evaluation piezoelectric information is input to the learned U-Net is shown.

  As shown in FIGS. 14, 15, 16, and 17, it can be seen that appropriate conversion processing is performed by the learned U-Net, and heart rate information can be accurately estimated from the piezoelectric information.

  The present invention is not limited to the above-described embodiment, and various modifications and applications can be made without departing from the gist of the present invention.

  For example, in the above embodiment, the case where U-Net using CNN is used as a model has been described as an example, but the present invention is not limited to this. Any model may be used as long as it is a trained model that can obtain heart rate information, which is an example of biological information, from piezoelectric information, which is an example of measurement information.

  Further, in the above embodiment, the case where the piezoelectric information, which is an example of the measurement information, is obtained from the piezoelectric element installed in the chair has been described as an example, but the present invention is not limited to this. Any mode may be used as long as measurement information can be obtained from a subject.

  In addition, in the specification of the present application, the embodiment is described in which the program is installed in advance. However, the program may be stored in a computer-readable recording medium and provided.

Reference Signs List 10 biological information acquisition device 12 input unit 14 operation unit 16 output unit 17 learning data generation unit 18 learning data storage unit 20 learning data acquisition unit 22 learning unit 24 learned model storage unit 25 measurement information acquisition unit 26 biological information acquisition Department

Claims (11)

Obtaining measurement information obtained from the subject;
Inputting the acquired measurement information to a pre-learned model for acquiring biological information representing the state of the subject from the measurement information, and acquiring the biological information of the subject,
A biological information acquisition method in which a computer executes processing including: The learned model is a neural network previously learned based on learning data representing a combination of the measurement information for learning and the biological information for learning.
The biological information acquisition method according to claim 1. The measurement information is piezoelectric information representing a voltage value obtained from a piezoelectric element in contact with the subject,
The biological information is heart rate information indicating a state of the heart rate of the subject,
The biological information acquisition method according to claim 1 or 2. The piezoelectric element is a piezoelectric element installed on a chair on which the subject sits,
The biological information acquisition method according to claim 3. Acquiring learning data representing a combination of the measurement information of the subject for learning and the biological information representing the state of the subject for learning,
Based on the acquired learning data, acquiring a learned model for acquiring the biological information from the measurement information,
A biological information acquisition model learning method in which a computer executes processing including: The method further includes: correcting a drift component of the biological information of the test subject for learning, and generating a combination of the measurement information for learning and the corrected biological information for learning as the learning data.
The biological information acquisition model learning method according to claim 5. An unmeasured region in the biological information of the subject for learning is excluded, and a combination of the measurement information for learning and the biological information for learning in which the unmeasured region is excluded is generated as the learning data. Further comprising the step of:
The biological information acquisition model learning method according to claim 5. A measurement information acquisition unit that acquires measurement information of the subject,
The measurement information acquired by the measurement information acquisition unit is input to a pre-learned model for acquiring biological information representing the state of the subject from the measurement information, and the biological information of the subject is obtained. A biological information acquisition unit to be acquired;
A biological information acquisition device including: A learning data acquisition unit that acquires learning data representing a combination of measurement information of the subject for learning and biological information representing the state of the subject for learning,
Based on the learning data acquired by the learning data acquisition unit, a learning unit that acquires a learned model for acquiring the biological information from the measurement information,
A biological information acquisition model learning device including: A computer configured to acquire a measurement information acquisition unit for acquiring measurement information of the subject, and the measurement information acquired by the measurement information acquisition unit, which is pre-learned for acquiring biological information representing the state of the subject from the measurement information. A program for inputting to the learned model and causing it to function as a biological information acquisition unit that acquires the biological information of the subject. A learning data acquisition unit for acquiring learning data representing a combination of measurement information of the subject for learning and biological information representing the state of the subject for learning; and the learning acquired by the learning data acquisition unit. A program for functioning as a learning unit for acquiring a learned model for acquiring the biological information from the measurement information based on the application data.