Biological measurement data processing device and biological measurement data processing method

Abstract

To provide a processing device that can notify a user of detection of an event at appropriate timing for the user when an event is detected from biological measurement data of the user.SOLUTION: A biological measurement data processing device includes: a reception unit 51 which receives the input of biological measurement data 81 of a user and situation expression data 82 expressing the situation of the user; an event score evaluation unit 54 which evaluates an event score that indicates a degree at which a confirmation or intervention action should be performed to the user for the event that has occurred in the user on the basis of the biological measurement data 81; a situation score evaluation unit 55 which evaluates a situation score that indicates the degree of a situation where the user is more likely to take action on the notification on the basis of the situation expression data 82; and a notification score evaluation unit 56 which calculates a notification score representing the degree at which notification of the occurrence of the event can be performed to the user on the basis of the event score and the situation score and outputs the notification score.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a biometric data processing device and a biometric data processing method for processing data on the biological condition measured from a user. [Background technology]

[0002] Research is currently being conducted into technology that estimates the mental and physical health state of a user, such as emotions, fatigue, and mood, based on data obtained by measuring the biological condition in daily life (biometric data).By using such technology, it is possible to determine whether an abnormality has occurred in the user's body from the biometric data, and to implement intervention measures such as resolving the abnormality based on the determination results.

[0003] An example of a conventional technique for determining whether or not an abnormality has occurred in a user's living body from biometric data is disclosed in Patent Document 1. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2016-122434 A Summary of the Invention [Problem to be solved by the invention]

[0005] In the home medical support system described in Patent Document 1, the vital signs of the support recipient (pulse, blood pressure, and oxygen saturation) are analyzed, and based on the vital signs, the system determines whether there is an abnormality in the support recipient's body and issues a notification. This conventional technology is suitable for cases where a medical professional needs to always respond when a notification is received, such as in a medical support system.

[0006] However, in cases where a specific event that occurs in a user during daily life (for example, an abnormality in a subjective state such as the perception of stress) is detected and the user is notified of the occurrence of this event to encourage the user to take an intervention action to improve the condition, it may not be necessary to immediately notify the user of the occurrence of the event. Furthermore, unless the notification is given in a situation where the user can check the notification and take the intervention action, the effect of encouraging the user to reflect on the content of the notification and take the intervention action is reduced. Conventional technologies have the above-mentioned problems, and there is a demand for technology that can notify the user of the detection of an event at a timing appropriate for the user.

[0007] An object of the present invention is to provide a processing device and a processing method that, when an event is detected from biometric data of a user, can notify the user of the detection of the event at a timing appropriate for the user. [Means for solving the problem]

[0008] The biomeasurement data processing device according to the present invention comprises a reception unit that inputs a user's biomeasurement data and situation expression data that expresses the user's situation, an event score evaluation unit that evaluates an event score indicating the degree to which confirmation or intervention should be performed on the user regarding an event that has occurred to the user based on the biomeasurement data, a situation score evaluation unit that evaluates a situation score indicating the degree to which the user is likely to take action in response to a notification based on the situation expression data, and a notification score evaluation unit that calculates a notification score that indicates the degree to which it is appropriate to notify the user of the occurrence of the event based on the event score and the situation score, and outputs the notification score.

[0009] The biomeasurement data processing method according to the present invention includes a reception step of inputting a user's biomeasurement data and situation expression data expressing the user's situation; an event score evaluation step of evaluating an event score indicating the degree to which confirmation or intervention should be performed on the user regarding an event that has occurred to the user based on the biomeasurement data; a situation score evaluation step of evaluating a situation score indicating the degree to which the user is likely to take action in response to a notification based on the situation expression data; and a notification score evaluation step of calculating a notification score indicating the degree to which it is appropriate to notify the user of the occurrence of the event based on the event score and the situation score, and outputting the notification score. Effect of the Invention

[0010] According to the present invention, it is possible to provide a processing device and a processing method that, when an event is detected from a user's biometric data, can notify the user of the detection of the event at a timing appropriate for the user. [Brief description of the drawings]

[0011] [Figure 1] 1 is a block diagram showing an example of a main configuration of a biomeasurement data processing system and a biomeasurement data processing device according to a first embodiment of the present invention. [Diagram 2] 13 is a flowchart showing an example of a process in which the biometric data processing device receives data from the user terminal 7. [Diagram 3] 13 is a flowchart showing an example of a process for learning an event rating model performed by the biomeasurement data processing device. [Figure 4] 13 is a flowchart showing an example of a process for learning a situation expression evaluation model performed by the biomeasurement data processing device. [Diagram 5] 13 is a flowchart showing an example of a process for learning a notification score evaluation model performed by the biometric data processing device. [Figure 6] 11 is a flowchart showing an example of a process performed by the biometric data processing device to evaluate a notification score based on biometric data and situation expression data. [Figure 7A] 13 is a flowchart showing an example of details of an event score evaluation process performed by an event score evaluation unit of the biomeasurement data processing device. [Figure 7B] 13 is a flowchart showing an example of details of a situation expression evaluation process performed by a situation score evaluation unit of the biomeasurement data processing device. [Figure 7C] 13 is a flowchart showing an example of details of a report score evaluation process performed by a report score evaluation unit of the biomeasurement data processing device. [Figure 7D] 11 is a flowchart showing an example of details of a notification determination process performed by a notification determination unit of the biomeasurement data processing device. [Figure 7E] 11 is a flowchart showing an example of a receiving process of a response result according to a notification output, which is performed by the biometric data processing device. [Figure 8A] 13 is a diagram showing an example of a notification output screen that the result display unit displays on the screen of the user terminal, and is an example of a display screen based on a notification score. FIG. [Figure 8B] 13 is a diagram showing an example of a notification output screen that the result display unit displays on the screen of the user terminal, and is another example of a display screen based on a notification score. FIG. [Figure 8C] 13 is a diagram showing an example of a notification output screen that the result display unit displays on the screen of the user terminal, and is an example of a display screen based on a notification score and an event score. FIG. [Figure 9A] 10 is a diagram showing an example of a data structure of event score data held by the biomeasurement data processing device. FIG. [Figure 9B] 11 is a diagram showing an example of a data structure of situation score data held by the biometric data processing device. FIG. [Figure 9C] 11 is a diagram showing an example of a data structure of notification score data held by the biometric data processing device. FIG. [Figure 9D] 10 is a diagram showing an example of a data structure of history data held by a biometric data processing device; [Figure 9E] 10 is a diagram showing an example of a data structure of user characteristic data held by a biometric data processing device; [Figure 9F]11 is a diagram showing an example of a data structure of notification settings stored in the biometric data processing device. FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] The present invention relates to a biometric data processing device and a biometric data processing method that are used to determine, for example, when a user is in a subjective state that is different from usual, based on the biological condition (biometric data) measured from the user.

[0013] With the biomeasurement data processing device and biomeasurement data processing method of the present invention, when a target event (e.g., a change in subjective state) that requires confirmation and intervention action is detected from biomeasurement data measured in the user's daily life, the user can be notified of the event detection at a timing when it is most convenient for the user to take confirmation and intervention action.

[0014] In the present invention, a notification score is calculated and output based on an event score that indicates the likelihood of notification, estimated from biometric data, and a situation score that indicates the appropriateness of the notification timing, estimated based on situation expression data. Since the present invention uses the notification score, it is possible to notify the user of the occurrence of a target event at a timing that takes into account appropriateness and immediacy. This leads to promotion of user behavior based on notifications, such as improving the acceptability of intervention measures based on notifications.

[0015] Hereinafter, a biometric data processing apparatus and a biometric data processing method according to an embodiment of the present invention will be described with reference to the drawings. The biometric data processing method according to the embodiment is executed by the biometric data processing apparatus according to the embodiment.

[0016] In the following description, the biological condition of the user refers to the physical condition of the user, and includes, for example, the user's heart rate, the amount of sweat, and movement, etc. The biological measurement data refers to data obtained by measuring the biological condition of the user.

[0017] The subjective state of the user's mind and body refers to the state of the user's own body and mind as felt by the user, and is a state other than an objective state obtained by measuring, for example, blood pressure or pulse rate using a sensor. Examples of subjective states of the mind and body include mental and physical states measured using psychological questionnaires used in clinical settings, such as the Pittsburgh Sleep Inventory, mental and physical states such as attention function and processing speed measured by psychological experiments, such as the trail making test, and mental and physical states measured using a Likert scale or visual analogue scale to measure the level of emotion or the amount of stress load at a certain time or period. The subjective state of the user's mind and body also includes the physical and mental states of the user obtained by observing and inferring the user from a person other than the user.

[0018] An event is a change in the user's subjective state or an abnormality in the user's subjective state. In an embodiment of the present invention, the user's mental and physical subjective state is an estimation target based on biometric data (biometric information), and the change or abnormality is detected as an occurrence of an event and is notified to the user at an appropriate timing. EXAMPLES

[0019] A biometric data processing device and a biometric data processing method according to a first embodiment of the present invention will be described below. The biometric data processing device according to this embodiment can be provided in, for example, a biometric data processing system.

[0020] 1 is a block diagram showing an example of a biometric data processing system and a main configuration of a biometric data processing device according to this embodiment. The biometric data processing system includes one or more user terminals 7, one or more administrator terminals 8, and a biometric data processing device 1 according to this embodiment. The user terminals 7, the administrator terminal 8, and the biometric data processing device 1 are connected to each other via a network 9. The biometric data processing device 1 receives data from the user terminal 7 via the network 9 and processes the received data.

[0021] The user terminal 7 is used by the user and includes a biometric sensor 11 that measures the biometric condition of the user, a biometric device 12 that controls the biometric sensor 11, an input / output device 13, a communication device 14, and a notification / notification device 15. The user terminal 7 also includes a screen on which notifications to the user and acquired data are displayed.

[0022] The biometric sensor 11 includes a heart rate sensor 21 that detects the user's heart rate interval (RR Interval, RRI), an electrodermal activity sensor 22 that detects the user's sweat rate, and an acceleration sensor 23 that detects the user's movement. The heart rate sensor 21 may be, for example, a sensor that detects the heart rate based on an electrocardiogram, a pulse wave, a pressure change, or a heart sound.

[0023] The biometric sensor 11 is not limited to the above sensors, and may include sensors that detect body temperature, blinking, eye movement, electromyography, or brain waves, etc. The biometric sensor 11 may be a wearable device that the user can wear, or a system built into a smartphone that the user can carry around.

[0024] The biomeasurement device 12 controls the biomeasurement sensor 11 and generates biomeasurement data 81 from the biostatus measured by the biomeasurement sensor 11. The biomeasurement data 81 is data measured by the biomeasurement sensor 11 and is bioinformation of the user. The biomeasurement device 12 performs calculation processing and compression processing on the biostatus as necessary to generate the biomeasurement data 81.

[0025] The input / output device 13 displays on the screen of the user terminal 7 and accepts input from the user. The input from the user includes input of subjective value correct data 88, which is correct data on the user's subjective mental and physical state. The correct data on the user's subjective mental and physical state is his / her own subjective state as recognized by the user, and is input by the user to the user terminal 7 using the input / output device 13, for example.

[0026] The communication device 14 executes a process for the user terminal 7 to communicate with the biometric data processing device 1 and the administrator terminal 8 via the network 9.

[0027] The notification device 15 provides necessary notifications to the user according to instructions from the biomeasurement data processing device 1. For example, the notification device 15 notifies the user of the occurrence of an event (a change in the user's subjective state or the occurrence of an abnormality). The notification device 15 displays a notification on the screen of the user terminal 7 via the input / output device 13. The notification device 15 may also provide notifications to the user using, for example, vibration or sound.

[0028] In this embodiment, the user terminal 7 is configured as one device, but the user terminal 7 does not necessarily have to be configured as one device. For example, the input / output device 13 and the communication device 14 may be provided in a smartphone, and the biometric device 12, the biometric sensor 11, and the notification device 15 may be provided in a smartwatch, and the smartphone and the smartwatch may be considered to configure one user terminal 7.

[0029] The administrator terminal 8 includes an input / output device 31, a communication device 32, and a notification / informing device 33, and is used by the administrator. The administrator terminal 8 also includes a screen, and displays notifications to the administrator, acquired data, and the like on the screen.

[0030] The input / output device 31 displays information on the screen of the manager terminal 8 and receives input from the manager.

[0031] The communication device 32 executes a process for the administrator terminal 8 to communicate with the biometric data processing device 1 and the user terminal 7 via the network 9.

[0032] The notification device 33 issues necessary notifications to the administrator in accordance with instructions from the biomeasurement data processing device 1. The notification device 33 displays notifications on the screen of the administrator terminal 8 via the input / output device 31. The notification device 33 may also notify the administrator using, for example, vibration or sound.

[0033] The biomeasurement data processing device 1 is composed of a computer, and includes a memory 3, a processor 2, a storage device 4, an input / output device 5, and a communication device 6. The biomeasurement data processing device 1 includes, as functional units, a reception unit 51, a preprocessing unit 52, an event score evaluation unit 54, a situation score evaluation unit 55, a notification score evaluation unit 56, a notification determination unit 57, a notification output unit 58, and a result display unit 59. Details of these functional units will be described later.

[0034] The memory 3 loads programs for implementing each functional unit of the biomeasurement data processing device 1. The programs for implementing these functional units are executed by the processor 2.

[0035] The processor 2 operates as a functional unit that provides a predetermined function by executing processes according to a program for realizing each functional unit. For example, the processor 2 functions as an event score evaluation unit 54 by executing an event score evaluation program. The same applies to the other functional units of the biomeasurement data processing device 1. Furthermore, the processor 2 also operates as a functional unit that provides each function of a plurality of processes executed by each program.

[0036] The storage device 4 stores data used by the above-mentioned functional units. For example, the storage device 4 stores biometric data 81, situation expression data 82, event score data 83, situation score data 84, notification score data 85, history data 86, user characteristic data 87, subjective value correct answer data 88, an event evaluation model 90, a situation expression evaluation model 91, a notification score evaluation model 92, and a notification setting 89.

[0037] The input / output device 5 includes an input device and an output device. Examples of the input device include a mouse, a keyboard, a touch panel, and a microphone. Examples of the output device include a display and a speaker.

[0038] The communication device 6 executes a process for the biometric data processing device 1 to communicate with the user terminal 7 and the administrator terminal 8 via the network 9.

[0039] In this embodiment, an example will be described in which the user always wears or carries the user terminal 7 in daily life, and the biometric sensor 11 is always operating. However, the biometric data processing device 1 according to this embodiment can be used in ways other than those described above. For example, the user may operate the biometric sensor 11 using the user terminal 7 several times a day, such as when waking up or going to bed.

[0040] 2 is a flowchart showing an example of a process in which the biometric data processing device 1 receives data from the user terminal 7. This process is executed by the reception unit 51 of the biometric data processing device 1.

[0041] When a connection with the user terminal 7 is established via the network 9, the reception unit 51 starts a data reception process S21 and receives data from the user terminal 7. The data reception process S21 continues until the connection between the reception unit 51 and the user terminal 7 is disconnected.

[0042] The biometric data processing device 1 receives biometric data 81 (biometric information) generated by the biometric device 12 of the user terminal 7 as data from the user terminal 7. In the following, as an example, a case where the biometric data 81 is heartbeat interval data, electrodermal activity data, and acceleration data will be described. That is, a case where the biometric information of the user is the heartbeat interval, the amount of sweat, and movement will be described.

[0043] Moreover, when the subjective value correct answer data 88 is input to the user terminal 7 via the input / output device 13, the biomeasurement data processing device 1 receives the subjective value correct answer data 88. As described above, the subjective value correct answer data 88 is correct answer data on the user's mental and physical subjective state, and the user's mental and physical subjective state is an object to be estimated based on the biomeasurement data 81 (biometric information).

[0044] In addition, when a response to a notification to the user is input to the user terminal 7 via the input / output device 13, the biometric data processing device 1 also receives information such as the response to the notification to the user as history data 86.

[0045] In the following, as an example, a case will be described in which natural emotions in daily life are the subject of the subjective state of mind and body (an estimation target based on biological information, and a target for detecting changes or abnormalities as an event). In this case, the subjective value correct answer data 88 can measure the natural emotion in an emotional dimension consisting of the arousal level (Arousal) and the emotional value (Valence). When the natural emotion is measured in the emotional dimension, the subjective state of mind and body can be measured using an Affective Slider that represents and measures the emotional dimension with pictograms at both ends of a visual scale, a Visual Analogue Scale (VAS), or a Self-Assessment Manikin (SAM) that measures with multi-level pictograms, and expressed as a numerical value as a subjective value. The subjective value correct answer data 88 can be the correct answer data of the subjective value expressed in such a numerical value.

[0046] Furthermore, the subjective value correct answer data 88 can be measured not only by the emotion dimension but also by the experience emotion. For example, the subjective value correct answer data 88 can be measured and expressed using the Positive and Negative Affect Schedule (PANAS), which measures discrete emotions such as happiness based on the degree of applicability to adjectives that indicate the emotion.

[0047] In this embodiment, an example has been described in which the biometric data processing device 1 continuously receives the biometric data 81. The biometric data processing device 1 does not necessarily have to continuously receive the biometric data 81. For example, the biometric data processing device 1 may receive the biometric data 81 from the user terminal 7 at regular time intervals. The user terminal 7 can transmit the biometric data 81 at multiple measurement times collectively to the biometric data processing device 1 at regular time intervals, such as every 2 minutes or 30 minutes. Also, the reception unit 51 may establish a connection with the user terminal 7 and perform the data reception process S21 only when the transmission process is performed from the user terminal 7.

[0048] 3 is a flowchart showing an example of a learning process of the event evaluation model 90 performed by the biomeasurement data processing device 1. The event evaluation model 90 is a model for detecting an event based on the biomeasurement data 81.

[0049] In the data reading process S31, the accepting unit 51 of the biometric data processing device 1 inputs the subjective value correct answer data 88, the biometric data 81, and the user characteristic data 87 used for learning.

[0050] The user characteristic data 87 is data about the user from whom the biometric data 81 was acquired, and is data expressing the user's situation. The type of the user characteristic data 87 is not limited as long as it is a type of data that is relatively low in dependency on time and can express the user's situation. For example, the user characteristic data 87 can be composed of demographic variables such as the user's age and gender, personality variables measured based on the Big Five theory, and the like.

[0051] In the following, unless otherwise stated, an example is shown in which a set of biomeasurement data 81 is made up of 30 minutes of heartbeat interval data, electrodermal activity data, and acceleration data, and a set of subjective value correct answer data 88 is the intensities of valence and arousal for 30 minutes. The biomeasurement data processing device 1 performs learning processing of the event evaluation model 90 by using multiple sets of these data.

[0052] In the data pre-processing process S32, the pre-processing unit 52 of the biometric data processing device 1 performs pre-processing of the data (at least the biometric data 81) using the user characteristic data 87 and the biometric data 81. For example, the pre-processing unit 52 performs at least one of a correction process for individual differences contained in the biometric data 81, a process for extracting features from the biometric data 81, and a compression process (dimension reduction) of the features extracted from the biometric data 81. The pre-processing unit 52 may explicitly execute a plurality of processes in sequence as a pipeline for these processes, or may execute them end-to-end by separately preparing a typical processing means.

[0053] For example, the series of data pre-processing steps S32 may be configured as a correction process for individual differences by performing data normalization processing based on a series of biometric data 81 previously measured from the user himself, and by performing feature compression processing using principal component analysis with the biometric data 81 normalized for each user as input, without performing feature extraction processing.

[0054] In addition, when processing is performed end-to-end, the data pre-processing process S32 may be configured to set a process for removing measurement noise from the biomeasurement data 81, and the feature extraction process and feature compression process may be configured to use the latent vectors of a Variational Auto Encoder (VAE), which is a deep generative model that uses the noise-removed biomeasurement data 81 as input.

[0055] In the correction of individual differences, normalization processing of the signal scale to be used or noise removal processing may be performed. For example, in the normalization processing, min-max normalization, which normalizes the maximum and minimum values ​​for each user, for each measurement date, for each measurement date of a user, or among all users, z-score normalization, which normalizes the average and standard deviation of the signal, or quantile normalization, which normalizes the signal intensity distribution using the quantile, may be used. In addition, if it is known that the signal intensity varies due to aging, etc., deviation value processing, which normalizes the signal intensity for each age group in consideration of the user's age information included in the user characteristic data 87, may be performed. Furthermore, in the noise removal processing, clipping processing or winsorization processing, which removes abnormal values ​​of the signal and places them within a certain range, or moving average processing, which suppresses and smoothes sudden fluctuations at one time, or zeroth order differentiation processing using a Savitzky-Golay filter, etc. may be performed.

[0056] In the process of extracting features from the biomeasurement data 81, features may be extracted according to the biosignals of the biomeasurement data 81 used. For example, for the heartbeat interval data acquired by the heartbeat sensor 21, the average heart rate, the low frequency component (LF) and the high frequency component (HF) obtained by frequency domain analysis and known to mainly reflect sympathetic nerve activity and parasympathetic nerve activity, respectively, the SDNN, RMSSD, and NN50 used in the time domain analysis, the feature using the Lorenz plot used in the nonlinear domain analysis, the feature obtained by the detrended fluctuation analysis, and the feature obtained by the complex demodulation method, etc. may be used. For the electrodermal activity data acquired by the electrodermal activity sensor 22, the skin conductance level (SCL) and the skin conductance response (SCR) may be used. In addition, for the three-axis acceleration data obtained from the acceleration sensor 23, the acceleration norm or the number of zero crossings, which is the number of times that a signal processed by a band-pass filter for the acceleration norm passes through a threshold of ±0.01 G when the gravitational acceleration is 1 G, may be used.

[0057] Furthermore, in addition to the biomeasurement data 81, the subjective value correct answer data 88 may also be subjected to a predetermined data pre-processing. For example, when estimating the strength of valence and arousal, pre-processing may be performed according to the type of event evaluation model 90 used in the learning process of the event evaluation model 90 described later. For example, when valence and arousal are measured on a five-point Likert scale from 1 to 5, this scale may be converted to a range from -1 to 1 when learning a regression model. In addition, in the case of a classification model, the values ​​may be binarized except for the intermediate value 3, and 1 and 2 may be set as negative examples 0, and 4 and 5 may be set as positive examples 1.

[0058] The feature compression process can use a known algorithm, such as the above-mentioned principal component analysis, an autoencoder (AE), or uniform manifold approximation and projection (UMAP).

[0059] In addition, when a typical processing means for preprocessing is prepared separately, a data preprocessing model for data preprocessing may be trained and used as the processing means. In this case, since it is typically based on unsupervised learning, learning processing may be performed using biometric data 81 that does not correspond to the subjective value correct answer data 88. Since the subjective value correct answer data 88 is expensive to obtain, by configuring in this way, it is possible to train a data preprocessing model from a larger number of biometric data 81, and it is possible to train a data preprocessing model that can generate preprocessed data that can express a wider variety of states as features.

[0060] As described above, the preprocessing unit 52 performs preprocessing on the biometric data 81 and, if necessary, the subjective answer data 88.

[0061] In the event evaluation model learning process S33, the event score evaluation unit 54 uses the preprocessed biometric measurement data 81 and, if necessary, the preprocessed subjective value correct answer data 88 to learn the event evaluation model 90, and generates the event evaluation model 90.

[0062] In the following, a case will be illustrated in which the event score evaluation unit 54 sequentially performs the subjective value estimation process S34 and the event score evaluation process S35 in the event score evaluation process shown in Fig. 7A. Note that the event score evaluation unit 54 is not limited to a configuration that performs such multi-stage step processing, and may have a configuration that performs the event score evaluation process S35 directly from the biomeasurement data 81, for example.

[0063] In the case where the event evaluation model 90 in which the subjective value estimation process S34 is performed by the event score evaluation unit 54 is a model for estimating natural emotions in the user's daily life, for example, the event evaluation model 90 may learn an emotion dimension estimation model that estimates "the intensities of valence and arousal for a certain 30 minutes" as the subjective value correct answer data 88 by supervised learning. The subjective value estimation process S34 can be executed using a known algorithm. For example, a logistic regression model, a decision tree, a Random Forest, a Support Vector Machine, a neural network, a Bayesian neural network, a deep learning model, etc. can be used as the machine learning algorithm. As for the algorithm, a classification algorithm or a regression algorithm can be used depending on the subjective value to be estimated. For example, a regression algorithm can be used when estimating the intensities of valence and arousal as values ​​from -1 to 1, and a classification algorithm can be used instead of a regression algorithm when estimating the high and low intensities of valence and arousal.

[0064] The subjective value correct answer data 88, which is the subject of the subjective value estimation process S34 of the event evaluation model 90, is often data that is subjectively annotated by the user himself, especially when the subjective value correct answer data 88 is obtained in daily life. For this reason, the subjective value correct answer data 88 may be unreliable. In consideration of learning from such unreliable correct answer data, the event evaluation model 90 may have a model configuration suitable for such learning. For example, the event evaluation model 90 may be learned using the subjective value correct answer data 88 weighted according to the reliability of the answer of each user. In addition, a known algorithm may be used as a model configuration for correct answer data with low reliability or certainty. For example, although correct answer data is assigned to the entire biomeasurement data 81 for the last 30 minutes, multiple instance learning may be used in consideration of the fact that it is not possible to determine which time the correct answer data corresponds to exactly. In the case where the correct answer data is not determined as a single data, while the reliability of the distribution position or order itself is relatively high, a Bayesian deep learning model or label distribution learning may be used.

[0065] Furthermore, the event rating model 90 may be composed of a plurality of models that take into account individual differences. In this case, it becomes possible to estimate a subjective value that is suitable for each user, and this has the effect of improving suitability to users and user acceptability of the subjective value estimation result.

[0066] When the event evaluation model 90 is configured with a plurality of models that take into account individual differences, a dedicated process may be added to the event evaluation model 90, or the event evaluation model 90 itself may be configured as an end-to-end model. For example, when a dedicated process is added, the answering style of the subjective value correct answer data 88 of the user may be regarded as the cognitive tendency of the user, and the subjective value that applies to all users may be estimated using a classification model or a regression model, and then a process may be added to perform a correction on the subjective value estimation result that takes into account the central response tendency and extreme response tendency, which are the answering styles, to obtain data on the estimated subjective value. In addition, when configured as an end-to-end model, the event evaluation model 90 may be configured as a neural network and a layer close to the final layer may be configured by multi-task learning that divides the layer for each user, so that estimation that learns the cognitive tendency according to the user can be realized, or an event evaluation model 90 common to users may be created, and the event evaluation model 90 may be configured to be adapted to a specific user by fine tuning the event evaluation model 90 for each user.

[0067] When learning of the event rating model 90 in which the subjective value estimation process S34 is performed is completed, in the event score evaluation process S35, the event score evaluation unit 54 uses the estimated subjective value estimated from the biometric data 81 in the subjective value estimation process S34 to evaluate the event score using the event rating model 90. The event score is a value indicating the degree to which the user should be checked or an intervention action should be taken regarding an event that has occurred to the user, and is an index indicating the degree to which the biometric data 81 or the estimated subjective value deviates from normal times.

[0068] In the event score evaluation process S35, the event score evaluation unit 54 uses the event evaluation model 90 to evaluate, as an event score, the extent to which the input biometric data 81 and estimated subjective values ​​deviate from normal data.

[0069] The event evaluation model 90 is typically a model that learns by unsupervised learning using a known anomaly detection algorithm, and can be configured as a known statistical model or machine learning model. As the statistical model, for example, a statistical model that outputs a z-score using the average value or standard deviation for the data distribution of the preprocessed biometric data 81 or the estimated subjective value obtained by the subjective value estimation process, a statistical model that outputs a deviation value in this data distribution, and a statistical model that outputs a quantile on this data distribution can be used. As the machine learning model, for example, a machine learning model that outputs a distance based on the cluster center of the data distribution estimated nonparametrically from the preprocessed biometric data 81 or the estimated subjective value obtained by the subjective value estimation process S34 can be used.

[0070] For example, when Auto Encoder, a typical example of a machine learning model, is selected, a sub-model of the event evaluation model 90 used in the event score evaluation process S35 may be configured as a model that inputs one or both of the preprocessed biometric data 81 and the estimated subjective value obtained by the subjective value estimation process S34, and calculates a reconstruction error indicating how well the input data was reconstructed by Auto Encoder. In such a configuration, when the input data is close to the biometric data 81 measured at normal times or the estimated subjective value estimated from the biometric data 81, the event score becomes small, and when there is an abnormality in the biometric state or the estimated subjective value or there is a problem with the measurement conditions of the biometric state, the event score becomes large, and the difference from normal times can be evaluated as the event score.

[0071] 3, the data pre-processing process S32 and the event evaluation model learning process S33 are different processes, but parts of both processes may be executed together. For example, the feature extraction process and feature compression process described in the data pre-processing process S32, the subjective value estimation process S34, and the event score evaluation process S35 may be configured as an end-to-end learning process of the event evaluation model 90. In this case, they may be configured in the form of a deep learning model consisting of a fully connected layer and a Long Short Term Memory, Graph Neural Network, Convolutional Neural Network, Self Attention, or Transformer, which are good at handling time-series data.

[0072] The process S33 of learning the event evaluation model in the flowchart of Fig. 3 is executed at least once before the process of evaluating the level of the event score shown in Fig. 5 and Fig. 6 described later. In addition, by executing this process at regular intervals as the subjective value correct answer data 88 and the biometric data 81 increase, the event evaluation model 90 for the process S34 of estimating the subjective value and the process S35 of evaluating the event score can be re-learned. As a result, a model with even higher evaluation accuracy can be generated.

[0073] In addition, in this embodiment, the event evaluation model 90 is described as a multi-stage model used in the subjective value estimation process S34 and the event score evaluation process S35, and is learned and used for each process, but typically, it is desirable to prepare a number of models for each process and use them in combination. For example, estimation processes and evaluation processes using a number of methods may be prepared for the subjective value estimation process S34 and the event score evaluation process S35, so that a number of estimated subjective values ​​and event scores can be evaluated. As described above, when evaluating a notification score using an event score and making a notification decision based on the notification score, which will be described later, it becomes possible to realize a notification decision from a variety of perspectives.

[0074] 4 is a flowchart showing an example of a learning process of the situation expression evaluation model 91, which is performed by the biomeasurement data processing device 1. The situation expression evaluation model 91 is a model that represents the situation of the user (a situation related to a reaction to a notification).

[0075] In the data reading process S41, the reception unit 51 of the biometric data processing device 1 inputs situation expression data 82. The situation expression data 82 is data expressing a situation (behavioral situation) of the user, and is data reflecting, for example, the schedule of the user. The situation expression data 82 includes, for example, a start time and an end time of the user's behavior. The situation expression data 82 may also include a situation score for uniquely identifying the data. At this time, the reception unit 51 may also input user characteristic data 87 and history data 86 for the user to whom the situation expression data 82 is input. The following illustrates an example in which the reception unit 51 inputs the user characteristic data 87 and history data 86 in addition to the situation expression data 82.

[0076] The type of the situation expression data 82 is not limited as long as it is data of a type that can express the user's situation at a certain time. The situation expression data 82 can include, for example, the user's schedule data consisting of the user's errands and their start and end times, GPS data that can express the user's past behavioral patterns, and sensor data obtained from a sensor such as an acceleration sensor and that can express the user's activity status.

[0077] The history data 86 comprehensively stores information such as the user's reaction to the notification. The history data 86 can include data such as the start and end times of the user's business, the notification status from the system, and the reaction latency of the user to the notification. These data can be acquired as subjective correct answer data 88. The history data 86 may also include, as data, items including the answer time indicating the time at which the user was able to answer, in addition to the subjective correct answer data 88. In addition, if there is situation expression data 82 linked to the history data 86 at this time, the situation expression data 82 may be included in the history data 86 in a form that makes the correspondence clear.

[0078] In the data pre-processing step S42, the pre-processing unit 52 performs predetermined pre-processing as necessary on the situation expression data 82, the user characteristic data 87, and the history data 86. For example, when the correspondence between the history data 86 and the situation expression data 82 is clearly indicated, a data set combining these data may be created and the history data 86 may be updated.

[0079] In the process S43 of learning the situation expression evaluation model, the situation score evaluation unit 55 inputs the preprocessed situation expression data 82, the user characteristic data 87, and the history data 86, learns the situation expression evaluation model 91, and generates the situation expression evaluation model 91. In learning the situation expression evaluation model 91, the situation score evaluation unit 55 can execute a plurality of processes in parallel or in sequence.

[0080] In the following, a case will be illustrated in which the situation score evaluation unit 55 performs the situation expression similarity search process S45 and the situation score estimation process S46 in the situation expression evaluation process shown in FIG. 7B.

[0081] In the situation expression similarity search process S45, the situation score evaluation unit 55 searches for a similar behavior pattern from the situation expression data 82, and estimates the user's situation (behavior situation) using the situation expression evaluation model 91.

[0082] In the situation score estimation process S46, the situation score evaluation unit 55 evaluates the situation score indicating the user's acceptability of the notification using the situation expression evaluation model 91. The situation score is a value indicating the appropriateness of the timing of the notification to the user, and is a value indicating the degree to which the situation makes it easy for the user to take action in response to the notification. Specifically, the situation score is a value that associates the user's situation (behavioral situation) with the user's acceptability of the notification (the possibility that the user can respond to the notification), and represents the probability that the user can confirm the notification and respond to it. The situation score can be expressed, for example, as a continuous value from 0 to 1.

[0083] The situation score evaluation unit 55 performing the situation expression similarity search process S45 uses the history data 86 updated by combining with the situation expression data 82 in the situation expression evaluation model learning process S43 to learn a situation expression evaluation model 91 that searches for similar behavior patterns from the situation expression data 82. The history data 86 updated by combining with the situation expression data 82 includes data that can express behavior patterns such as schedule data and GPS data based on the situation expression data 82.

[0084] The situation score evaluation unit 55 can discretize the situation expression data 82 for any given period of time into a predetermined time width, and store the discretized situation expression data 82 as a code string of a behavior pattern for this given period of time.

[0085] For example, when data that can express a behavioral pattern is coded into labels such as a location or a type of behavior, the behavioral pattern in a predetermined period of time can be expressed by a code string. In the process S45 of situation expression similarity search, learning is performed by searching the code string of this behavioral pattern from the input situation expression data 82 by partial match search. Therefore, in the learning process of the situation expression evaluation model 91 in the process S45 of situation expression similarity search, a database that stores the code string of the behavioral pattern and its partial match search algorithm may be constructed as a sub-model of the situation expression evaluation model 91. For the partial match search, a known algorithm for partial match search or approximate search of sequences can be used. As such known algorithms, for example, the Needleman-Wunsch and Smith-Waterman algorithms are known as algorithms for searching for homologous sequences of base sequences.

[0086] In this embodiment, the predetermined period is one day, the situation expression data 82 is discretized in N-minute units of less than 60 minutes, and the discretized situation expression data 82 is used as a code string of a behavior pattern in the predetermined period. In this case, the label of the behavior pattern is encoded by a representative behavior label in N-minute units. For example, if N is 10 minutes, the behavior pattern of one day is represented by a code string of 144. In addition, in accordance with this code string, the number of times per day that the user was able to independently respond and the number of times that the user was able to respond to notifications are added together with information on the time period.

[0087] When the time granularity of the code string of a behavior pattern is high, the amount of calculation required for the partial match search becomes enormous, and it is generally feared that the processing will not be completed within the calculation time required for use. On the other hand, when encoding with representative behavior labels in units of N minutes less than 60 minutes as in this embodiment, it is possible to obtain the effect of performing a partial match search in a realistic calculation time and extracting candidates for the code string of a similar behavior pattern.

[0088] In addition, by adding to the code sequence of a behavioral pattern the number of times per day that the user was able to respond independently and the number of times the user was able to respond to a notification, along with information about the time period, it is possible to achieve the effect of highly accurately evaluating the situation score, which indicates the acceptability of a notification during a specified time period, based on the additional information of the code sequence corresponding to the searched code sequence of a similar behavioral pattern in the situation score estimation process S46 described below.

[0089] The situation score evaluation unit 55, which performs the situation score estimation process S46, learns a situation expression evaluation model 91 based on the situation expression data 82. The situation expression evaluation model 91 is a model that represents a situation related to a user's reaction to a notification, and is a model for evaluating a situation score that indicates the user's acceptability of a notification in a predetermined time period. The situation score estimation process S46 may be configured according to the type of the situation expression data 82.

[0090] For example, in the case of the situation expression data 82 that employs schedule data, the process S46 of estimating the situation score can be performed based on the schedule data and history data 86 that records the user's response results.

[0091] In this case, for example, when the type of schedule is determined in advance, a sub-model of the situation expression evaluation model 91 may be constructed to estimate a situation score indicating the acceptability of a notification corresponding to the type of schedule based on learning from the schedule type and answer records or domain knowledge. Also, when the type of schedule is not determined in advance, a sub-model of the situation expression evaluation model 91 may be constructed to estimate a situation score by supervised learning using answer records for clusters obtained by clustering such that the feature values ​​or similar feature values ​​are grouped into a cluster, by which the schedule data is converted into feature values ​​by natural language processing using an input of natural sentences related to the type of schedule or the contents of the schedule.

[0092] Furthermore, if a code string of a corresponding behavioral pattern has been found by the above-mentioned situation expression similarity search process S45, a sub-model of the situation expression evaluation model 91 may be constructed to regard this code string of the behavioral pattern as schedule data with a sparse time granularity and perform a situation score estimation process for the schedule data.

[0093] Furthermore, for example, in the case of situation expression data 82 employing GPS data, the situation score may be estimated based on the GPS data and history data 86 that records the user's answering record. In this case, a model that estimates whether the user is moving or staying, and the category of the means of transportation if moving, or the category of the place of stay if staying, based on the time-series information of the GPS data, may be prepared in advance and constructed as a sub-model of the situation expression evaluation model 91. Then, for the obtained behavioral context such as the category of the means of transportation or the place of stay, the situation expression evaluation model 91 that estimates the situation score may be constructed by supervised learning using the answering record at that time or prior knowledge regarding the acceptability of notifications in the corresponding behavioral context as correct answer data for the behavioral context.

[0094] Furthermore, for example, in the case of situation expression data 82 employing sensor data from a sensor (such as an acceleration sensor) that can express the user's behavior, the situation score may be estimated based on the sensor data and history data 86 that records the user's answer record. In this case, a model that estimates behavior such as a means of transportation or daily activities from the sensor data is prepared in advance and constructed as a sub-model of the situation expression evaluation model 91. This model can be constructed based on algorithms known in the field of Human Activity Recognition. The situation expression evaluation model 91 that estimates the situation score may be constructed by the user's behavior estimated by this model, or by supervised learning using prior knowledge on notification acceptability during the corresponding behavior as correct answer data.

[0095] The series of learning processes shown in Fig. 4 is executed at least once before the process of evaluating the level of the situation score shown in Fig. 5 and Fig. 6 described later. In addition, by executing this process at regular intervals as the situation expression data 82 and history data 86 increase, it is possible to re-learn the situation expression evaluation model 91 for the situation expression similarity search process S45 and the situation score estimation process S46. As a result, it is possible to generate a model with even higher evaluation accuracy.

[0096] In this embodiment, the situation expression evaluation model 91 is a multi-stage model used in the situation expression similarity search process S45 and the situation score estimation process S46, and an example has been shown in which the situation expression evaluation model 91 is learned and used for each process. Typically, it is desirable to prepare a number of models for each process of the situation expression evaluation model 91 and use these in combination. For example, for the situation expression similarity search process S45 and the situation score estimation process S46, and for each example of the situation score estimation process S46, estimation processes and evaluation processes using a number of methods may be prepared so that a number of situation scores can be evaluated. As described above, it is possible to realize evaluation of the notification score using the situation score, and when making a notification decision based on the notification score, it is possible to realize a notification decision from various perspectives.

[0097] 5 is a flowchart showing an example of a learning process of the notification score evaluation model 92 performed by the biomeasurement data processing device 1. The notification score evaluation model 92 is a model that represents the degree of whether or not it is acceptable to notify the user, that is, a model that represents the degree of whether or not the timing of the notification is appropriate for the user.

[0098] The notification score is a value that indicates the degree to which a user should be notified of the occurrence of an event, and is an index that indicates whether or not the user should be notified of the event that has occurred. The notification score can be expressed, for example, as a continuous value from 0 to 1.

[0099] In the data reading process S51, the reception unit 51 of the biomeasurement data processing device 1 inputs the event score data 83, the situation score data 84, and the history data 86. The event score data 83 is data including an event score, as described later. The situation score data 84 is data including a situation score, as described later. The history data 86 can be used as answer data in learning.

[0100] In notification score evaluation model learning process S52, notification score evaluation unit 56 inputs event score data 83, situation score data 84, and history data 86, learns notification score evaluation model 92, and generates notification score evaluation model 92. In learning notification score evaluation model 92, notification score evaluation unit 56 can execute a plurality of processes in parallel or sequentially.

[0101] In the following, a case will be illustrated in which the notification score evaluation unit 56 performs the notification score calculation process S53 and the notification timing calculation process S55 in the notification score evaluation process shown in FIG. 7C.

[0102] In a notification score calculation process S53, the notification score evaluation unit 56 inputs the event score data 83, calculates the notification score using the notification score evaluation model 92, and outputs the notification score.

[0103] The notification score evaluation unit 56 that performs the process S53 of calculating the notification score inputs the event score data 83, the situation score data 84, and the history data 86 in the process S52 of learning the notification score evaluation model, and learns the notification score evaluation model 92.

[0104] The notification score evaluation unit 56 can obtain the notification score as a continuous value by, for example, performing identity conversion on the value obtained as the event score. The notification score evaluation unit 56 can also calculate the notification score by converting the certainty of the event of interest into a discrete value using a predetermined step function such as low, medium, and high. The notification score evaluation unit 56 can configure a model capable of calculating the notification score in this way as the notification score evaluation model 92. In addition, when there are multiple types of event score data 83, the notification score may be configured to perform normalization processing on the domain of each event score data 83 and calculate the notification score as a continuous value from 0 to 1, for example. As a result, it is possible to configure a sub-model of the notification score evaluation model 92 that calculates at least the execution time of the notification score calculation process and the notification score corresponding to this time.

[0105] The notification score evaluation unit 56, which performs the notification timing calculation process S55, evaluates the notification timing based on the execution time of the notification score calculation process obtained in the notification score calculation process S53 and the situation score, and determines the timing to notify the user of the detection of an event.

[0106] For example, when the user requires immediacy of notification (immediate notification of the occurrence of an event) because the event is highly certain regarding the subjective physical and mental state of the estimation target, it is desirable that the notification timing be as close as possible to the execution time of the notification score calculation process S53, regardless of the user's acceptability of the notification. On the other hand, when the immediacy of the notification is not important, such as when the above-mentioned certainty is low or the importance of the event that has occurred is low, it is desirable that the notification timing be a timing at which the user is highly likely to accept the notification.

[0107] In the notification timing calculation process S55, the notification score evaluation unit 56 refers to the situation scores in a predetermined time range, such as from the execution time of the notification score calculation process until a predetermined time has elapsed, for the situation score data 84, and calculates notification timing candidates. For example, if the predetermined time range is set to the current day, the time series of the evaluated situation scores for the current day after the execution time can be referred to, and the time point at which the value of the situation score shows a change of more than a predetermined threshold can be calculated as the notification timing candidate. At this time, a sub-model of the notification score evaluation model 92 can be configured by optimizing the number of candidates for the threshold and notification timing based on the response record of the history data 86.

[0108] The notification score evaluation unit 56 uses the event score data 83 and the situation score data 84 as inputs to obtain a notification score learning model capable of evaluating the notification score data 85 through the learning process of the above-mentioned notification score evaluation model 92. The notification score data 85 is data that includes at least a notification score indicating the probability that the event is one to be noted (a value indicating whether or not the event is one to be notified to the user), and can include notification timing candidates for each acceptability of the notification timing.

[0109] From the above, the notification score evaluation unit 56 can calculate an index for taking into consideration the immediacy and acceptability of a notification.

[0110] The series of learning processes shown in Fig. 5 is executed at least once before the process of evaluating the level of the notification score shown in Fig. 6, which will be described later. In addition, by executing this process at regular intervals as the event score data 83, the situation score data 84, and the history data 86 increase, it is possible to re-learn the notification score evaluation model 92 for the process S53 of calculating the notification score and the process S55 of calculating the notification timing. As a result, it is possible to generate a model with even higher evaluation accuracy.

[0111] FIG. 6 is a flowchart showing an example of a process performed by the biometric data processing device 1 to evaluate a notification score based on the biometric data 81 and situation expression data 82.

[0112] In data reading process S101, the receiving unit 51 of the biometric data processing device 1 inputs biometric data 81 up to the current time t and situation expression data 82 up to time t or time (t+T). Time (t+T) is a future time that is a period of time T after time t. The receiving unit 51 may also input user characteristic data 87 according to the configuration of each learned model.

[0113] Here, in consideration of the time-based processing, the biometric data 81 is actual data, and therefore only data up to the processing time (current time t) can exist. On the other hand, in the case of the situation expression data 82, for example, in the case of schedule data, data on plans to be made after the target time t can also exist. Therefore, in the process of evaluating the notification score, not only the situation expression data 82 up to the time t but also the situation expression data 82 up to the time (t+N) can be used.

[0114] In the process S102 of the event score evaluation, the event score evaluation unit 54 inputs the event evaluation model 90, and generates and outputs the event score data 83 from the biometric data 81 and the user characteristic data 87 using this event evaluation model 90. The process S102 of the event score evaluation will be described later.

[0115] In the process S103 of the situation expression evaluation, the situation score evaluation unit 55 inputs the situation expression evaluation model 91, and generates and outputs the situation score data 84 from the situation expression data 82 and the user characteristic data 87 using the situation expression evaluation model 91. The process S103 of the situation expression evaluation will be described later.

[0116] In this embodiment, the process S102 for evaluating the event score and the process S103 for evaluating the situation expression are performed in this order, but these two processes may be performed in parallel.

[0117] In the process S104 of the notification score evaluation, the notification score evaluation unit 56 inputs the notification score evaluation model 92, and generates and outputs the notification score data 85 from the event score data 83 and the situation score data 84 using the notification score evaluation model 92. The notification score evaluation process S104 will be described later.

[0118] As described above, the biometric data processing device 1 according to this embodiment evaluates and outputs the notification score data 85 based on the situation score data 84 indicating the appropriateness of the notification timing estimated based on the situation expression data 82, in addition to the event score data 83 indicating the probability of notification estimated from the biometric data 81. Therefore, the biometric data processing device 1 according to this embodiment can obtain a measure for notifying the occurrence of a target event at a timing that takes into consideration both appropriateness and immediacy.

[0119] FIG. 7A is a flowchart showing an example of details of the event score evaluation process S102 (FIG. 6) performed by the event score evaluation unit 54 of the biomeasurement data processing device 1.

[0120] The pre-processing unit 52 of the biometric data processing device 1 performs data pre-processing S32 (FIG. 3) on the input biometric data 81 and user characteristic data 87 up to time t.

[0121] Thereafter, the event score evaluation unit 54 uses the input event evaluation model 90, the biometric measurement data 81 that has been subjected to data pre-processing, and the user characteristic data 87 to sequentially perform a subjective value estimation process S34 and an event score evaluation process S35 to obtain event score data 83 up to time t.

[0122] Thereafter, the event score evaluation unit 54 performs an event score storage process S36 and stores the obtained event score data 83.

[0123] FIG. 7B is a flowchart showing an example of details of the situation expression evaluation process S103 (FIG. 6) performed by the situation score evaluation unit 55 of the biomeasurement data processing device 1.

[0124] The pre-processing unit 52 of the biometric data processing device performs data pre-processing S42 (FIG. 4) on the input situation expression data 82 and user characteristic data 87 up to time t or time (t+T).

[0125] Thereafter, the situation score evaluation unit 55 uses the input situation expression evaluation model 91, the situation expression data 82 that has been subjected to data preprocessing, and the user characteristic data 87 to perform a situation score estimation process S44 including a situation expression similarity search process S45 and a situation score estimation process S46, to obtain situation score data 84 up to time t or time (t+T).

[0126] Thereafter, the situation score evaluation unit 55 performs the situation score storage process S47, and stores the obtained situation score data 84 up to the time t or the time (t+T).

[0127] In this embodiment, the evaluation value (user's situation) obtained in the situation expression similarity search process S45 is also used as an input for the situation score estimation process S46, but it does not have to be used in this way. For example, the situation expression similarity search process S45 and the situation score estimation process S46 may be performed in parallel without using the evaluation value obtained in the situation expression similarity search process S45 as an input for the situation score estimation process S46. Also, only one of the situation expression similarity search process S45 and the situation score estimation process S46 may be performed depending on the type of the situation expression data 82, and the situation expression evaluation process S103 may be performed for each of the situation expression data 82.

[0128] FIG. 7C is a flowchart showing an example of details of the report score evaluation process S104 (FIG. 6) performed by the report score evaluation unit 56 of the biomeasurement data processing device 1.

[0129] The notification score evaluation unit 56 performs a notification score calculation process S53 using the input notification score evaluation model 92, event score data 83, and situation score data 84. The notification score evaluation unit 56 can calculate the notification score up to time t from the event score data 83 up to time t and the situation score data 84 up to time t. The notification score evaluation unit 56 can also calculate the notification score up to time (t+T) from the event score data 83 up to time t and the situation score data 84 up to time (t+T). In this way, the notification score evaluation unit 56 can appropriately determine the notification timing including up to a time T after the time t.

[0130] The notification score evaluation unit 56 performs a process S54 of determining the notification target for the notification score calculated in the process S53 of calculating the notification score. In the process S54 of determining the notification target, for example, if the notification score is expressed as a continuous value from 0 to 1, and the value of the notification score exceeds a predetermined notification score threshold (for example, 0.7), the notification score evaluation unit 56 determines that the event is a notification target, performs a process S55 of calculating the notification timing, and calculates a candidate notification timing. In addition, if the notification score evaluation unit 56 determines that the event is not a notification target, it reserves the notification and does not perform the process S55 of calculating the notification timing.

[0131] Thereafter, the notification score evaluation unit 56 performs a notification score storage process S56 to store the notification score data 85 that includes at least the notification score and can also include notification timing candidates.

[0132] In this embodiment, the notification score evaluation unit 56 performs the notification timing calculation process S55 only when it is determined that the event is a notification target based on the notification score. This configuration can reduce the calculation time required to calculate the notification timing. However, the notification score evaluation unit 56 may perform the notification timing calculation process S55 regardless of whether the event is a notification target or not.

[0133] FIG. 7D is a flowchart showing an example of details of the notification determination process performed by the notification determination unit 57 of the biomeasurement data processing device 1.

[0134] In data reading process S61, notification determination unit 57 inputs notification score data 85, notification settings 89, and user characteristic data 87. Notification settings 89 are a structured file that stores a predetermined threshold (notification score threshold) for determining whether or not an event is a notification target, and settings for notification generation process S64, which will be described later.

[0135] The notification determination unit 57 performs a determination S62 as to whether or not unprocessed data exists in the notification score data 85. If unprocessed data exists, the subsequent processes S63-S65 related to the notification determination are executed until there is no unprocessed data. Note that the following description will be given of an example in which the subsequent processes S63-S65 related to the notification determination are executed in parallel for each user in the order of the earliest notification timing candidates.

[0136] In steps S63-S64, the notification determination unit 57 performs a process of determining whether or not to notify the user of the event (notification determination process).

[0137] In the detail reading process S63, the notification determination unit 57 inputs the situation expression data 82 corresponding to the situation score ID using the situation score ID stored in the notification score data 85 as a key.

[0138] In the detailed reading process S63, the notification determination unit 57 treats, among the multiple notification scores calculated at multiple times, the notification scores whose calculation times fall within a predetermined time range as a group of notification scores, and performs notification determination processing based on this group of notification scores, thereby making it possible to notify the user of multiple notifications that are close to each other in time (multiple notifications that fall within a predetermined time range).

[0139] For example, for biometric data 81 in which at least one of the start time and end time of the currently processed notification score data 85 overlap, if there are multiple notification score data 85 for the same user at nearby times, the notification determination unit 57 inputs situation expression data 82 corresponding to all of these notification score data 85. In this way, if multiple notifications are close to each other, these multiple notifications can be input together and notified.

[0140] Thereafter, the notification determination unit 57 performs a notification generation process S64 based on the target notification score data 85, the situation expression data 82, the notification settings 89, and the user characteristic data 87. In the notification generation process S64, the notification determination unit 57 determines whether or not the event is an event for which the user should be notified, based on the notification score and notification timing candidates stored in the notification score data 85, the notification conditions in the notification settings 89, and per-user notification settings (settings for each user regarding notifications) in the user characteristic data 87, which will be described later, and generates notification content if the event is a notification target.

[0141] As described above, in the notification generation process S64, the notification determination unit 57 generates notification content when the event is a notification target (when the event is an event to which the user should be notified) based on the notification score, the notification timing candidates, the notification conditions, and the notification settings for each user. For example, when the notification score for multiple notification conditions exceeds the notification score threshold and even one of the notification timing candidates is approaching the time of processing and has exceeded the notification timing threshold, the notification determination unit 57 generates notification content for the notification score data 85. The notification timing threshold is a value that indicates the user's receptivity to notification, and it can be determined whether or not to notify the user based on this value.

[0142] For example, if the target event is the occurrence of a strong emotion, the notification contents may include a notification that a strong emotion occurred and a notification requesting a response regarding the situation and the emotion felt. Also, if the target event is the occurrence of a strong stressful or anxious state, the notification may include a notification of the situation, a proposal for an intervention measure to improve the situation, and a notification requesting a response regarding whether any action was actually taken to improve the situation.

[0143] The notification output unit 58 performs notification processing S65 and outputs the generated notification content, thereby outputting a notification of the occurrence of an event.

[0144] When the notification determination unit 57 handles a plurality of notification scores as a group of notification scores and performs notification determination processing based on this group of notification scores, the notification determination unit 57 performs notification generation processing S64 based on the target group of notification score data 85, the group of situation expression data 82, notification settings 89, and user characteristic data 87. The notification output unit 58 performs notification processing S65 and outputs the generated plurality of notification contents together, thereby outputting a plurality of notifications of the occurrence of an event to the user all at once.

[0145] By handling multiple notification score data 85 for the same user at nearby times that overlap in the start and end times of the notification score data 85 as a group of notification score data 85 and notifying them, it is possible to generate notification content that takes into account the latest situation and adds more appropriateness and immediacy when the notification score or the degree of the notification timing candidate changes over time, and further to avoid multiple notifications for similar events. As a result, it is possible to reduce the annoyance for the user of receiving similar notifications multiple times and improve the appropriateness and acceptability of each notification.

[0146] Furthermore, the notification output unit 58 can determine at least one of the amount of information to be presented (e.g., the length of the message) and the amount of response required from the user (e.g., the number of items to be entered by the user) in the output notification based on a predetermined setting, for example, the length of the notification (notification length) set in the notification setting 89. This allows the biometric data processing device 1 according to this embodiment to send to the user terminal 7 a notification of an appropriate amount and content for the user.

[0147] For example, the notification output unit 58 may adjust the amount of notification or the response required from the user based on the length of the notification set in the notification setting 89, and generate the notification content based on the situation expression data 82 (including a group of situation expression data 82). This makes it possible to generate notification content according to the needs of the user or administrator, such as wanting to know about or respond to a detected event briefly, even if the notification score value is somewhat low, and can provide an effect of providing a notification in an appropriate amount in view of the notification score while ensuring the immediacy of the notification.

[0148] In the notification process S65, the input / output device 5 performs a process of notifying the notification target via the network 9 based on the generated notification contents. For example, if the notification target is a user, the input / output device 5 performs a process of notifying the user terminal 7 of the user S65, and the notification notification device 15 (FIG. 1) of the user terminal 7 issues a notification to the user. At this time, if the user terminal 7 is a smartphone or a smart watch, the notification can be made in the form of a push notification to the smartphone or smart watch, or a message to a notification application for the user. Also, if the notification target is an administrator, the input / output device 5 performs a process of notifying the administrator terminal 8 of the administrator who collects users corresponding to the user ID of the judgment result data S65, and the notification notification device 33 (FIG. 1) of the administrator terminal 8 issues a notification to the administrator. At this time, if the administrator terminal 8 is a PC (personal computer), the notification can be made in the form of outputting an alarm sound to the PC, notifying the PC by email, and displaying a notification to an administrator application. Also, for the notification score data 85 for which the notification process has been completed, the notification status flag is updated to completed.

[0149] In this embodiment, an example in which multiple notification score thresholds and notification timing thresholds are set for users and evaluated is illustrated, but in addition to this, notification score thresholds and notification timing thresholds for administrators may be set separately in addition to users. In this case, notification judgment can be performed based on different criteria for users and administrators depending on the notification target, and a situation in which a notification should be made can be determined based on the action to be taken by the notification recipient.

[0150] As a result, by using the notification score, it is possible to notify users of the occurrence of a target event at a time that takes into account appropriateness and immediacy, which has the effect of encouraging users to take action based on notifications, such as increasing the acceptability of intervention measures based on notifications.

[0151] FIG. 7E is a flowchart showing an example of a receiving process of a response result according to a notification output, which is performed by the biomeasurement data processing device 1.

[0152] The reception unit 51 of the biometric data processing device 1 performs a process S71 of receiving a response result in order to receive a response from the terminal on which the notification process has been performed. In the following, as an example of receiving a response from the user terminal 7, a case will be described in which the user is notified of a timing when the user is assumed to be in a subjective state of emotion different from normal based on the notification score. It is assumed that the user responds to the notification using the user terminal 7 (inputs correct subjective value data into the user terminal 7). In this case, in the process S71 of receiving a response result, the reception unit 51 receives correct subjective value data 88, which represents the subjective state of emotion, generated based on the user's response from the user terminal 7. When the reception unit 51 receives the correct subjective value data 88, the reception unit 51 updates the response status flag of the history data 86 to "done."

[0153] As described above, the biometric data processing device 1 can obtain the result of the action taken by the user who received the notification in response to the notification issued at an appropriate timing for intervention measures or data collection, such as when the user is in a subjective state different from usual. For example, in the case of this embodiment, if the subjective value correct data 88 is obtained as correct data of the emotion corresponding to the moment of the notification regarding the timing when the subjective state of the emotion is assumed to be different from usual, it is possible to efficiently obtain correct data regarding the emotion that rarely occurs in daily life. In addition, if a flag value indicating whether or not the user confirmed the notification, the content of the action taken, and the actual subjective mental and physical health state at that time are obtained in response to the notification regarding the timing when the subjective state of the mental and physical state is assumed to be different from usual, such as fatigue or mood, the biometric data processing device 1 can obtain the response result data to be used for verifying the subjective value estimation accuracy and evaluating the intervention effect.

[0154] 8A, 8B, and 8C are diagrams showing examples of notification output screens that the result display unit 59 displays on the screen of the user terminal 7. In this embodiment, an example is shown in which the notification is displayed in the form of a message to a notification application for the user.

[0155] A screen 1000A in Fig. 8A is an example of a display screen based on the notification score. Fig. 8A illustrates an example in which the user terminal 7 is a smartphone.

[0156] In a conventional device, for example, a notification application displays notification 1001 to a user at irregular intervals, as in Signal#1 shown in FIG. 8A, and attempts to collect correct answer data for emotions corresponding to a certain moment. However, emotions such as strong joy or sadness do not occur frequently in daily life, so a simple irregular notification may take a long time to collect correct answer data, or the specified period may end without acquiring a sufficient number of correct answer data. In addition, it cannot be denied that situations in which strong emotions occur are different from everyday life, and even if a strong emotion is detected and an immediate notification is issued while an unusual situation continues, an effective response to the notification is often not obtained.

[0157] Using the notification score in this embodiment, in addition to the immediacy of notifying at the time when an event such as a strong emotion occurs, the appropriateness of the notification, that is, whether or not the notification at the time of the calculated notification timing candidate is likely to be accepted by the user, can be taken into consideration, and the timing when the user is in a subjective state (emotional state) different from usual can be displayed on the user terminal 7 as a notification 1002 in a format such as Event #2. The notification 1002 can be, for example, a message 2001, which is not an immediate notification, but can display information regarding when the detected event occurred based on the notification score. This provides an effect that, even if the notification is not immediate, the user can obtain material for introspecting the notification content when generating the subjective value correct answer data 88 and history data 86 regarding the detected event.

[0158] In this way, in this embodiment, compared to a conventional device that obtains subjective value correct data 88, which is correct data for emotions, based on irregular notifications such as Signal #1 of notification 1001, the user's response to the notification is received as subjective value correct data 88 and history data 86 in the response result receiving process, thereby achieving the effect of being able to obtain subjective value correct data 88 corresponding to rare emotional states with high efficiency.

[0159] Screen 1000B in Fig. 8B is another example of a display screen based on the notification score. Fig. 8B illustrates a case where the user terminal 7 is a smartwatch. The display content of screen 1000B is generally the same as that of screen 1000A, and instead of an instantaneous notification, information regarding when the detected event occurred is displayed based on the notification score. When the user terminal 7 is a smartwatch, it is possible to obtain an effect that, compared to a smartphone, it is possible to perform an effective notification by using not only a display but also other notification means such as vibration.

[0160] 8C is an example of a display screen based on the notification score and the event score. In the screen 1000C, a notification 1003 in a format such as Event #3 can be displayed on the user terminal 7 at the time when the user is in a subjective state different from usual, such as a message 2001, based on the notification score in the same way as in the screen 1000A.

[0161] Furthermore, on screen 1000C, the transition of the event score that is the basis for calculating the notification score can be depicted, for example, as in display 2002 or display 2003, to inform the user.

[0162] Display 2002 is an example of a time-dependent change in estimated subjective scores included in event score data 83, displayed on an estimated subjective score plane with valence intensity on the x-axis and arousal intensity on the y-axis. In display 2002, the higher the density of the dotted line, the more the most recent state is indicated. In display 2002, the user's usual state is shown in shading, making it possible to clearly notify that the most recent estimated subjective score is significantly different from usual.

[0163] Display 2003 is an example showing the change over time of the event score of the event score data 83. In display 2003, as in display 2002, the range of the user's usual event score is shown shaded. Compared with display 2002, which is an example shown on an estimated subjective value plane, display 2003 can easily inform the user whether a certain situation is different from usual using a single index called the event score. In this way, by notifying the user of the event score in addition to the notification score, the user can know whether the notification is immediate or not, and can obtain information for understanding why and how the situation is different from usual, which has the effect of improving the accuracy of introspection about the notification content.

[0164] As described above, the result display unit 59 can display at least one of a display screen based on the report score and a display screen based on the event score on the screen of the user terminal 7.

[0165] Next, a characteristic structure of each piece of data used in the biomeasurement data processing device 1 will be described.

[0166] Fig. 9A is a diagram showing an example of the data structure of the event score data 83 held by the biometric data processing device 1. The event score data 83 typically stores a user ID 120, a start time 121 and an end time 122 of an event, an event score ID 123 for uniquely identifying the data of the event score data 83, an estimated subjective value 124, and an event score 125. In the example shown in Fig. 9A, the estimated subjective value 124 is shown as a set of the intensity of valence and the intensity of arousal as shown in the display 2002 of Fig. 8C. In addition, when there are multiple types of event evaluation models 90, the event score data 83 may store a calculation model 126 that is information for identifying the event evaluation model 90 used.

[0167] FIG. 9B is a diagram showing an example of the data structure of the situation score data 84 held by the biometric data processing device 1. The situation score data 84 typically stores a user ID 120, a start time 132 and an end time 133 of the user's situation (behavior), a situation score ID 134 for uniquely identifying the data of the situation score data 84, and a situation score 135. In addition, when the process S45 of the situation expression similarity search is executed, the situation score data 84 may store a similar situation 136. The similar situation 136 is information for uniquely identifying a behavior pattern when searching for a similar behavior pattern in the process S45 of the situation expression similarity search. The similar situation 136 can be used to search for a similar situation (behavior pattern) in the past. In addition, when there are multiple types of situation expression evaluation models 91, the situation score data 84 may store a calculation model 137 that is information for identifying the situation expression evaluation model 91 used.

[0168] FIG. 9C is a diagram showing an example of the data structure of the notification score data 85 held by the biometric data processing device 1. The notification score data 85 typically stores a user ID 120, a start time 142 and an end time 143 of an event, an execution time 144 of the notification score evaluation, a notification score ID 145 for uniquely identifying the data of the notification score data 85, a notification score 146, and a notification timing candidate 147. When there are multiple types of notification score evaluation models 92, the notification score data 85 may store a calculation model 148 that is information for identifying the model used. Furthermore, the notification score data 85 may store an event score ID 123 and a situation score ID 134 so that the event score and the situation score information used in the calculation of the notification score can be linked to each other. In addition, a notification status 151, a notification performance time 152, and the like may be stored in order to record the notification status. The notification status 151 is information on whether or not a notification has actually been performed. The notification performance time 152 is information on the time when the notification has actually been performed.

[0169] FIG. 9D is a diagram showing an example of the data structure of the history data 86 held by the biometric data processing device 1. The history data 86 typically stores a user ID 120, a history ID 162 for uniquely identifying the data of the history data 86, a response time 163, and a response 164. The response 164 is an arbitrary value input by the user other than a subjective value. In addition, in the case of supplementing information on a reaction to a notification, the history data 86 may store a notification transmission status 165, a notification score ID 145, a situation expression start time 167, a situation expression end time 168, and a reaction latency 169, which is the time required from the notification to the response. The situation expression start time 167 and the situation expression end time 168 correspond to the start time 142 and the end time 143 of the notification score data 85, respectively.

[0170] FIG. 9E is a diagram showing an example of a data structure of user characteristic data 87 held by the biometric data processing device 1. The user characteristic data 87 typically stores a user ID 120, a registration date 182, a last update date 183, an age 184, and a gender 185. The user characteristic data 87 may also store, for example, an affiliation 186 and an occupation 187 as broader demographic variables. Furthermore, when personality and temperament information is used as a characteristic, the user characteristic data 87 may additionally store information such as a personality update date 188, which is the date on which the personality variables were measured based on the Big Five theory, and a personality N 189, which indicates neuroticism among the personality variables. In addition, when a setting for each user regarding notifications is permitted, the user characteristic data 87 may store a notification setting for each user 190.

[0171] 9F is a diagram showing an example of a data structure of a notification setting 89 held by the biometric data processing device 1. The notification setting 89 typically stores a condition ID 211 that specifies a notification condition and details of the notification condition. The details of the notification condition include conditions such as a notification score threshold 212, a notification timing threshold 213, and a notification length 214.

[0172] 9A to 9F show an example in which each data is in a table format assuming that the parameters of each data are fixed amounts, but each data used by the biomeasurement data processing device 1 does not have to be represented in the format shown in Fig. 9A to 9F. For example, if the details of the notification condition change depending on the type of the notification condition, the data of the notification setting 89 may be stored simply in the format of structured data.

[0173] As described above, the biometric data processing device 1 of this embodiment includes a reception unit 51 that inputs a user's biometric data 81 and situation expression data 82 that expresses the user's situation, an event score evaluation unit 54 that evaluates an event score indicating the degree to which confirmation or intervention should be performed on the user regarding an event that has occurred to the user based on the biometric data 81, a situation score evaluation unit 55 that evaluates a situation score indicating the degree to which the user is likely to take action in response to a notification based on the situation expression data 82, and a notification score evaluation unit 56 that calculates a notification score indicating the degree to which it is appropriate to notify the user of the occurrence of an event based on the event score and the situation score, and outputs the notification score.

[0174] As a result, the biomeasurement data processing device 1 according to this embodiment evaluates and outputs a notification score based on the situation score indicating the appropriateness of the notification timing estimated based on the situation expression data 82 in addition to the event score 125 indicating the accuracy of notification estimated from the biomeasurement data 81, so that by using the notification score, it is possible to notify the occurrence of an event at a timing that takes appropriateness and immediacy into consideration. This effect also has a secondary effect of promoting user behavior based on notification, such as improving the acceptability of intervention measures based on notification.

[0175] The present invention is not limited to the above-described embodiments, and various modifications are possible. For example, the above-described embodiments have been described in detail to clearly explain the present invention, and the present invention is not necessarily limited to an embodiment having all of the configurations described. It is also possible to replace a part of the configuration of one embodiment with the configuration of another embodiment. It is also possible to add the configuration of another embodiment to the configuration of one embodiment. It is also possible to delete a part of the configuration of each embodiment, or to add or replace another configuration.

[0176] Further, each component of the device according to the present invention may be realized in hardware, for example, by designing a part or all of them as an integrated circuit. Further, each component may be realized in software, for example, by having the processor 2 interpret and execute a program that realizes each function. Information such as a program, table, file, measurement information, and calculation information that realizes each function can be recorded in a recording device such as a memory 3, a hard disk drive, and an SSD (Solid State Drive), or a recording medium such as an IC card, an SD card, and a DVD. Thus, each component of the device according to the present invention can realize each function as a processing unit, a processing unit, a program module, or the like.

[0177] In addition, in each drawing, the control lines and information lines are shown as those considered necessary for the explanation, and not all the control lines and information lines necessary for the product are shown. In an actual product, it can be considered that almost all components are connected to each other. [Explanation of symbols]

[0178] 1...biometric data processing device, 2...processor, 3...memory, 4...storage device, 5...input / output device, 6...communication device, 7...user terminal, 8...administrator terminal, 9...network, 11...biometric sensor, 12...biometric device, 13...input / output device, 14...communication device, 15...notification / alarm device, 21...heart rate sensor, 22...electrodermal activity sensor, 23...acceleration sensor, 31...input / output device, 32...communication device, 33...notification / alarm device, 51...reception unit, 52...preprocessing unit, 54...event score evaluation unit, 55...situation score Core evaluation unit, 56...notification score evaluation unit, 57...notification determination unit, 58...notification output unit, 59...result display unit, 81...biometric data, 82...situation expression data, 83...event score data, 84...situation score data, 85...notification score data, 86...history data, 87...user characteristic data, 88...subjective value correct answer data, 89...notification setting, 90...event evaluation model, 91...situation expression evaluation model, 92...notification score evaluation model, 120...user ID, 121...start time, 122...end time, 123...event event score ID, 124...estimated subjective value, 125...event score, 126...calculation model, 120...user ID, 132...start time, 133...end time, 134...situation score ID, 135...situation score, 136...similar situation, 137...calculation model, 120...user ID, 142...start time, 143...end time, 144...execution time, 145...notification score ID, 146...notification score, 147...notification timing candidate, 148...calculation model, 151...notification status, 152...notification performance time, 120...user ID, 162...history ID, 163...answer time, 164...answer, 165...notification sending status, 167...status expression start time, 168...status expression end time, 169...response latency, 182...registration date, 183...last update date, 184...age, 185...gender, 186...affiliation, 187...occupation, 188...personality update date, 189...personality N, 190...notification setting for each user, 1000A, 1000B, 1000C...screen, 1001, 1002, 1003...notification, 2001...message, 2002, 2003...display.

Claims

1. a reception unit for inputting biometric data of a user and situation expression data expressing a situation of the user; an event score evaluation unit that evaluates an event score indicating a degree to which a confirmation or intervention action should be taken for an event occurring to the user based on the biometric data; a situation score evaluation unit that evaluates a situation score indicating a degree to which the user is likely to take an action in response to a notification based on the situation expression data; a notification score evaluation unit that calculates a notification score representing a degree of suitability for notifying the user of the occurrence of the event based on the event score and the situation score, and outputs the notification score; A biometric data processing device comprising:

2. a notification determination unit that performs notification determination to determine whether or not to notify the user of the event based on the notification score; 2. The biometric data processing device according to claim 1.

3. a notification output unit that outputs a notification of the occurrence of the event based on a result of the notification determination by the notification determination unit; 3. The biometric data processing device according to claim 2.

4. a result display unit that displays, as a notification of the occurrence of the event, at least one of the notification score calculated by the notification score evaluation unit and the event score evaluated by the event score evaluation unit on a terminal used by the user; 4. The biometric data processing device according to claim 3.

5. the event score evaluation unit evaluates the event score up to a time t; the situation score evaluation unit evaluates the situation score up to a time (t+T) that is a time T after the time t, the notification score evaluation unit calculates the notification score up to time (t+T) based on the event score up to time t and the situation score up to time (t+T); 2. The biometric data processing device according to claim 1.

6. the notification determination unit defines, as a group of notification scores, among the notification scores calculated at a plurality of times, the notification scores whose calculation times are within a predetermined time range, and performs the notification determination based on the group of notification scores; The notification output unit collectively outputs a plurality of notifications of occurrence of the event based on a result of the notification determination by the notification determination unit.

4. The biometric data processing device according to claim 3.

7. the situation score evaluation unit discretizes the situation expression data for an arbitrary period of time into a predetermined time width, and stores the discretized situation expression data as a code string of a behavior pattern for the period of time.

2. The biometric data processing device according to claim 1.

8. the notification output unit determines, based on a predetermined setting, at least one of an amount of information to be presented and an amount of response required from the user in the notification to be output; 4. The biometric data processing device according to claim 3.

9. The event occurring to the user is a change or abnormality in the subjective state of the user, The subjective state is the physical and mental state as felt by the user.

2. The biometric data processing device according to claim 1.

10. a receiving step of inputting biometric data of a user and situation expression data expressing a situation of the user; an event score evaluation step of evaluating an event score indicating a degree to which confirmation or intervention action should be taken with respect to an event occurring to the user based on the biometric data; a situation score evaluation step of evaluating a situation score indicating a degree to which the user is likely to take an action in response to a notification based on the situation expression data; a notification score evaluation step of calculating a notification score representing a degree of suitability for notifying the user of the occurrence of the event based on the event score and the situation score, and outputting the notification score; A biometric data processing method comprising:

11. a notification determination step of determining whether or not to notify the user of the event based on the notification score; 11. A method for processing biometric data according to claim 10.

12. a notification output step of outputting a notification of the occurrence of the event based on a result of the notification determination in the notification determination step.

12. A method for processing biometric data according to claim 11.

13. a result display step of displaying at least one of the notification score calculated in the notification score evaluation step and the event score evaluated in the event score evaluation step on a terminal used by the user as a notification of the occurrence of the event.

13. A method for processing biometric data according to claim 12.

14. The event occurring to the user is a change or abnormality in the subjective state of the user, The subjective state is the physical and mental state as felt by the user.

11. A method for processing biometric data according to claim 10.

Images