Biometric data evaluation server, biometric data evaluation system, and biometric data evaluation method

Abstract

It is provided a biometric data evaluation server (1) including a processor (2) and a memory (3) for evaluating biometric data, the biometric data evaluation server (1) comprising: a data collection module (21) configured to receive beat-to-beat interval equivalent data from the biometric data on a subject; and a Lorenz plot generation module configured to calculate a Lorenz plot from the beat-to-beat interval equivalent data at a predetermined period, and output the obtained Lorenz plots as an aggregate Lorenz plot.

Description

Biometric data evaluation server, biometric data evaluation system, and biometric data evaluation method Incorporation by Reference

[0001] This application claims priority from Japanese Patent Application No. 2021-052246, filed on March 25, 2021, the contents of which are incorporated herein by reference.

[0002] The present invention relates to a biometric data evaluation server, system, and method used to evaluate the reliability of biometric data measured when promoting safe operation of transportation facilities.

[0003] In recent years, quantitative assessment of biological status has been conducted to prevent accidents caused by the health of transportation drivers. Among biological status assessments, autonomic nervous function assessment is being conducted based on beat-to-beat interval (BBI) data measured using various types of heart rate sensors, which are easy to measure.

[0004] For example, Patent Document 1 discloses a medical device that creates a Lorenz plot (LP) (described below) for R-wave interval (RRI = R-R Interval) data of heart rate data continuously acquired during a predetermined period, and uses feature quantities related to the created Lorenz plot to distinguish atrial fibrillation and atrial tachycardia, which are types of arrhythmia, and can detect arrhythmia.

[0005] Special table number 2008-539017

[0006] Patent Document 1 did not take into consideration the possibility that when measuring heart rate interval data in a state that is not necessarily at rest, such as during work that involves driving, heart rate interval data may be irregularly lost in many sections during a specified period due to poor measurement or communication failure.

[0007] In the case of partially missing or missing beat-to-beat data, there has been a problem in that the degree of occurrence of arrhythmia-like outliers cannot be quantified.

[0008] The present invention has been made in consideration of the above problems, and has as its object to make it possible to evaluate the degree of occurrence of arrhythmia-like abnormal values ​​even for heartbeat interval data that includes missing data.

[0009] The present invention provides a biometric data evaluation server that has a processor and memory and evaluates biometric data, and includes a data collection unit that receives data corresponding to heartbeat intervals from the biometric data of a subject, and a Lorenz plot generation unit that calculates a Lorenz plot from the data corresponding to heartbeat intervals over a predetermined period of time and outputs it as an aggregated Lorenz plot.

[0010] Therefore, according to one aspect of the present invention, even for heart rate interval data with missing or missing data, the degree of occurrence of arrhythmia-like abnormal values ​​can be evaluated from the generated Lorenz plot, thereby enabling evaluation of the reliability of autonomic nervous function indices obtained from heart rate interval data measured during work.

[0011] The details of at least one implementation of the subject matter disclosed herein are set forth in the accompanying drawings and the description below. Other features, aspects, and advantages of the disclosed subject matter will become apparent from the following disclosure, drawings, and claims.

[0012] FIG. 1 is a block diagram showing an example of a configuration of a biological data evaluation system, illustrating a first embodiment of the present invention. FIG. 1 is a flowchart showing an example of an RRI data transmission process performed in a vehicle driving data collection device. FIG. 1 is a flowchart showing an example of a learning process for a chronic occurrence discrimination model of arrhythmia-like abnormal values, performed in a biological data evaluation server. FIG. 1 is a diagram showing an example of a mask region definition used as a feature extraction model used in the biological data evaluation server. FIG. 1 is a diagram showing an example of an poor measurement-like mask used in the biological data evaluation server. FIG. 1 is a diagram showing an example of an normal range mask used in the biological data evaluation server. FIG. 1 is a diagram showing an example of a PVC-like abnormal value mask used in the biological data evaluation server. FIG. 1 is a diagram showing an example of a one-beat detection missed mask used in the biological data evaluation server. FIG. 1 is a diagram showing an example of an consecutive two-beat detection missed mask used in the biological data evaluation server. FIG. 1 is a flowchart showing an example of a process for evaluating the degree of chronic occurrence of arrhythmia-like abnormal values, performed in a biological data evaluation server. FIG. 1 is a flowchart showing an example of a process for determining a driver who is unsuitable for autonomic nervous function evaluation, performed in a biological data evaluation server. FIG. 1 is a flowchart illustrating an example of a calculation process of an autonomic nervous function index performed by a biological data evaluation server, showing Example 1 of the present invention. FIG. 2 is a diagram illustrating an example of an autonomic nervous function evaluation result screen, showing Example 1 of the present invention. FIG. 3 is a diagram illustrating an example of a screen for performing a detailed analysis of the reliability of RRI data measured during period A, showing Example 1 of the present invention. FIG. 4 is a diagram illustrating an example of a data structure of period B unit RRI data, showing Example 1 of the present invention. FIG. 5 is a diagram illustrating an example of a data structure of period B unit LP data, showing Example 1 of the present invention. FIG. 6 is a diagram illustrating an example of a data structure of period A unit aggregated LP data, showing Example 1 of the present invention. FIG. 7 is a diagram illustrating an example of a data structure of period A unit aggregated LP feature amount data, showing Example 1 of the present invention. FIG. 8 is a diagram illustrating an example of a data structure of abnormality degree data, showing Example 1 of the present invention.FIG. 1 is a diagram showing an example of a data structure of inadequacy determination data, illustrating Example 1 of the present invention; FIG. 1 is a diagram showing an example of a data structure of autonomic nervous function index data, illustrating Example 1 of the present invention; FIG. 1 is a diagram showing an example of a data structure of work status data, illustrating Example 1 of the present invention; FIG. 1 is a diagram showing an example of a data structure of history data, illustrating Example 1 of the present invention; FIG. 1 is a diagram showing an example of a data structure of chronic occurrence correct answer data, illustrating Example 1 of the present invention; FIG. 1 is a diagram showing an example of the definition of period A and period B and the occurrence of data loss, illustrating Example 2 of the present invention;

[0013] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0014] First, a first embodiment of the present invention will be described.

[0015] 1 is a block diagram showing an example of a main configuration of a biological data evaluation system according to a first embodiment of the present invention. The biological data evaluation system according to this embodiment includes a biological data evaluation server 1 that processes data received from one or more vehicles 7 via a network 13.

[0016] The vehicle 7 includes a biosensor 12 that detects the driver's biometric data, a driver ID reader 11 that identifies the driver, and a driving data collection device 10 that collects the detected biometric data and driver ID and transmits them to the biometric data evaluation server 1.

[0017] The biosensor 12 includes a heart rate sensor 14 that detects RRI and an acceleration sensor 15 that detects the driver's movement. The heart rate sensor 14 can be a sensor that detects the heart rate based on an electrocardiogram, a pulse wave, or heart sounds.

[0018] The biosensor 12 is not limited to the above, and in addition to the heart rate sensor 14, sensors that detect sweat rate, body temperature, blinking, eye movement, electromyography, brain waves, etc. can be used as the biosensor 12. In addition to a wearable device that can be worn by the driver, sensing devices attached to the interior of the vehicle, such as the steering wheel, seat, or seat belt, and an image recognition system that captures and analyzes images of the driver's facial expressions and behavior can also be used.

[0019] The heart rate sensor 14 may detect a heart rate interval other than the RRI, such as a pulse wave interval (PPI). Alternatively, the heart rate interval may be estimated from image data of the driver's face to obtain data equivalent to the heart rate interval. In this embodiment, any biological data from which the heart rate interval can be calculated may be used, and may include the data equivalent to the heart rate interval described above.

[0020] The driver ID reader 11 reads a card on which a driver's identifier is recorded. The driving data collection device 10 collects data from a biometric sensor 12 at a predetermined period and transmits the data to the biometric data evaluation server 1 via a network 13.

[0021] In the illustrated example, the driver ID reader 11 is configured as a device that reads a card on which a driver's identifier is recorded, but a different configuration may be used. For example, if the driver ID reader 11 is configured as a single mobile terminal and the mobile terminal is made to function as a driver ID reader, the driver ID may be read by having the driver input the driver's identifier, or by identifying the driver using a known face recognition technology using a camera in the mobile terminal.

[0022] The biological data evaluation server 1 is a computer including a processor 2, a memory 3, a storage device 4, an input / output device 5, and a communication device 6. The memory 3 loads each of the following functional units as a program: a data collection unit 21, a chronic occurrence discrimination model learning unit 22, a period B unit LP generation unit 23, a period A unit aggregated LP processing unit 24, an abnormal value chronic occurrence evaluation unit 25, an inappropriate driver determination unit 26, an autonomic nervous function index calculation unit 27, and a result display unit 28. Each program is executed by the processor. Details of each functional unit will be described later.

[0023] The processor 2 operates as a functional unit that provides a predetermined function by executing processing according to the program of each functional unit. For example, the processor 2 functions as the chronic abnormal value occurrence evaluation unit 25 by executing the abnormal value chronic occurrence evaluation program. The same applies to other programs. Furthermore, the processor 2 also operates as a functional unit that provides each function of the multiple processes executed by each program. A computer and a computer system are devices and systems that include these functional units.

[0024] The storage device 4 stores data used by the above-mentioned functional units. The storage device 4 stores period B unit RRI data 41, period B unit LP data 43, period A unit aggregated LP data 45, aggregated LP feature amount data 47, abnormality degree data 49, period A unit abnormality discrimination data 51, autonomic nerve function index data 53, work status data 42, history data 44, chronic occurrence correct answer data 46, inappropriateness judgment data 48, feature extraction model 50, chronic occurrence discrimination model 52, and inappropriate driver judgment model 54. Note that "LP" is an abbreviation for Lorenz plot (hereinafter also referred to as LP, or Poincaré plot), and the same notation will be used in the following description.

[0025] The input / output device 5 includes input devices such as a mouse, a keyboard, a touch panel, or a microphone, and output devices such as a display, a speaker, etc. The communication device 6 communicates with the vehicle via a network 13.

[0026] In this embodiment, the case where biometric data measured from a driver operating a vehicle 7 is the target is exemplified, but the form is not limited to this embodiment. For example, the target may be a driver operating a moving body such as an airplane or a train, instead of a driver operating a vehicle 7. Furthermore, for example, the target may not be limited to drivers, but may be a general employee whose biometric data is measured during work, or may be people who live their daily lives, not just at work.

[0027] 2 is a flowchart showing an example of the RRI data transmission process performed in the vehicle driving data collection device 10. In this example, a first period A (window width), which is a target period for evaluating the degree of occurrence of chronic arrhythmia-like abnormal values, is set to, for example, one business day, and a second period B having a window width equal to or smaller than the period A is set to, for example, two-minute units.

[0028] Note that period A and period B may be defined as intervals that define a time span as in this embodiment, or may be defined as the number of data points. For example, period A may be set to the same as one business day, and period B may be set to 120 data points.

[0029] Furthermore, it is preferable that period B is equal to or shorter than the first period A and equal to or longer than the time width required for heart rate variability analysis. Heart rate variability analysis is difficult with only one beat and takes about 10 seconds. Furthermore, period B may be determined based on information on the time width of missing or missing RRI data received from an input device.

[0030] First, the driving data collection device 10 starts RRI data measurement (S10) upon receiving a login input 71 from the driver. For example, the login input 71 may be an event in which a card recording the driver's identifier is read using the driver ID reader 11.

[0031] Next, the driving data collection device 10 writes out (S12) and transmits (S13) the measured RRI data until step S11, at which a logout input 72 from the driver is received. In this embodiment, the driving data collection device 10 of the vehicle 7 divides the measured RRI data into period B units in advance and writes it out for each period B, regardless of the measurement situation, and sequentially transmits the RRI data in period B units to the biological data evaluation server 1. In the biological data evaluation server 1, the data collection unit 21 receives the RRI data and stores it in the period B unit RRI data 41.

[0032] In addition, instead of transmitting RRI data divided into period B units in advance on the driving data collection device 10 side, for example, RRI data for period A units can be measured and transmitted to the biometric data evaluation server 1 for period A units, and then the data collection unit 21 of the biometric data evaluation server 1 can divide the RRI data for period A units into period B units and store it in the period B unit RRI data 41.

[0033] In addition, the driving data collection device 10 does not necessarily have to transmit RRI data divided into period B units for each period B. It may monitor the measurement situation and extract the RRI data into period B units and transmit them to the biological data evaluation server 1 only when a loss of RRI data meets certain conditions.

[0034] When the RRI data for period B is measured, the driving data collecting device 10 executes a process (S12) of writing the RRI data in a data transmission format in units of period B. After the period B unit writing process (S12) is completed, the driving data collecting device 10 transmits the written period B unit RRI data 41 to the biological data evaluating server 1, and stores measurement information related to the period B unit RRI data 41 in the history data 44 of the biological data evaluating server 1.

[0035] The driving data collecting device 10 executes the above process for each period B until it receives a logout input 72 from the driver (S11). For example, an event timer may be provided in the driving data collecting device 10, which counts the passage of two minutes, which is an example of the period B, and then executes step S11.

[0036] Furthermore, the logout input 72 may be an event in which a card recording the driver's identifier is read using the driver ID reader 11 for the first time after the login input 71 is performed.

[0037] The history data 44 stores information related to each piece of the period B unit RRI data 41 measured through the driving data collection device 10. For example, a driver ID and a vehicle ID for linking the period B unit RRI data 41 with the driver and the vehicle 7 are stored. The time when the data was transmitted to the biometric data evaluation server 1 and the name of the transmitted file may also be stored. In addition, the driver's state during period B may also be stored. The driver's state is information indicating the measurement conditions under which the period B unit RRI data 41 was measured, and may store, for example, "driving" or "parked" classified by the biometric sensor 12.

[0038] The driver's state does not need to be explicitly stored in the history data 44. For example, if the driving data collection device 10 is configured to perform the period B unit writing process S12 only while the vehicle is traveling and to discard RRI data measured when the vehicle is not traveling, it is obvious that all of the period B unit RRI data transmitted to the biological data evaluation server 1 was measured while the vehicle was traveling, and therefore the driver's state does not need to be stored.

[0039] In this case, a loss occurs in a partial section (period B) of the RRI data in units of period A due to an external factor 73 during the period B unit write process (S12) or data transmission process (S13).

[0040] In this embodiment, an example has been shown in which the period B unit write process occurs every two minutes regardless of the measurement situation, but for example, there may be cases where the RRI cannot be detected due to a measurement error, resulting in the generation of empty period B unit RRI data 41, i.e., the RRI data being lost. Also, for example, there may be cases in which the transmission process fails due to a communication failure or the like in the data transmission process (S13), resulting in the loss of period B unit RRI data 41.

[0041] As described above, missing RRI data in the unit of period A occurs when there is no RRI data 41 in the unit of period B and the data is missing, or when there is data but the valid RRI data is extremely scarce or empty.

[0042] When the driving data collection device 10 receives the logout input 72, the process proceeds to step S14 of the RRI data measurement termination process. In the RRI data measurement termination process (S14), work status data 42 including work information related to the driver's work period A is generated and transmitted to the biological data evaluation server 1.

[0043] If there is no valid RRI data and empty period B unit RRI data 41 is generated, the subsequent data transmission process (S13) may not be performed.

[0044] Through the above processing, when the driving data collection device 10 starts measuring RRI data, it transmits the RRI data to the biometric data evaluation server 1 in units of period B, and the biometric data evaluation server 1 accumulates RRI data 41 in units of period B for each driver.

[0045] 3 is a flowchart showing an example of a learning process of the chronic onset discrimination model 52 for arrhythmia-like abnormal values, which is performed in the biological data evaluation server 1. First, the chronic onset discrimination model learning unit 22 refers to chronic onset correct answer data 46 that defines whether or not arrhythmia-like abnormal values ​​are chronically occurring in RRI data measured during a certain period A, and determines whether or not there is any chronic onset correct answer data 46 to be learned (S21).

[0046] If the chronic occurrence correct answer data 46 to be learned exists, the chronic occurrence discrimination model learning unit 22 proceeds to step S22 and performs the following process for each period A stored in the chronic occurrence correct answer data 46. The chronic occurrence correct answer data 46 to be learned can be set in advance via the input / output device 5.

[0047] The chronic occurrence discrimination model learning unit 22 generates aggregated LP feature data 47 used to evaluate whether arrhythmia-like abnormal values ​​are chronically occurring in the period B unit RRI data 41 measured during period A for each period A stored in the chronic occurrence correct answer data 46.

[0048] As will be described later, the aggregated LP feature data 47 is input to the chronicity occurrence discrimination model 52 to determine whether an arrhythmia-like abnormal value (an abnormal value of an arrhythmia feature) is chronic or not.

[0049] First, the chronic occurrence discrimination model learning unit 22 calls the period B unit LP generation unit 23, and the period B unit LP generation unit 23 reads the period B unit RRI data 41 obtained by dividing the RRI data within period A into period B units (S23).

[0050] Note that, when reading the period B unit RRI data 41, the period B unit LP generation unit 23 may assume a case where there is very little valid RRI data or there is no valid RRI data in the read period B unit RRI data 41, and may check the target period B unit RRI data 41 to determine whether there is any data loss. In this case, the period B unit RRI data 41 determined to be subject to data loss is not subjected to subsequent processing, and the period B is treated as having data loss.

[0051] Furthermore, the period B unit LP generating unit 23 may also read the history data 44 when reading the period B unit RRI data 41. In this case, the driver's state stored in the history data 44 may be referenced, and if the state does not match a predetermined driver's state, the reading of the period B unit RRI data 41 may be stopped and subsequent processing related to the data may be skipped.

[0052] For example, when the driver is not driving, the corresponding period B-unit RRI data 41 may not be read and may be excluded from the learning process of the chronic onset discrimination model. In this case, the measurement conditions of the period B-unit RRI data 41 used for learning the chronic onset discrimination model 52 are unified, and the evaluation accuracy of arrhythmia-like abnormal values ​​under the measurement conditions is expected to improve.

[0053] Next, the period B unit LP generating unit 23 generates a Lorenz plot for each period B using the read period B unit RRI data 41, and stores it as period B unit LP data 43 (S24).

[0054] The LP is a two-dimensional plot for performing chaos analysis on time series data T[t], which is drawn by plotting the time series data T[t] of the preceding time t (t = 0, 1, 2, ...) on one axis of Figure 4A and the time series data T[t + dt] at time t + dt, which is a period dt (dt = 1, 2, 3, ...) after time t, on the other axis.

[0055] In this example, an LP is shown in which T[t] is plotted on the x-axis and T[t+dt] is plotted on the y-axis. The characteristics of the time series data T[t] can be analyzed by analyzing the geometric figures drawn on the LP.

[0056] In particular, it is known that when an LP is drawn for RRI data over a continuous period B, its geometric characteristics can be used to evaluate measurement characteristics such as the extent to which the data measured during period B contains arrhythmias or measurement errors.

[0057] In this embodiment, an example of LP when dt = 1 beat later is shown. Also, a case where the original series RRI[t] of measured RRI data is used as time series data is shown. Note that dt does not have to be greater than 1, i.e., it does not have to be two points that are adjacent in time. Furthermore, the RRI data used is not limited to the original series RRI[t], and for example, a differential series ΔRRI[t] obtained by taking the difference between adjacent data points may also be used.

[0058] In this embodiment, the period B unit LP generation unit 23 calculates an LP matrix that expresses the frequency of occurrence of data points on the LP as density (or brightness) in order to quantitatively evaluate the geometric features in the LP. Note that, as shown in FIG. 4A (described later), the density is high when the frequency of occurrence is high, and low when the frequency of occurrence is low. For example, in this embodiment, the range of the x-axis and y-axis is set to 0 ms to 2560 ms, and a mesh region is defined that divides this range into 64 grids in each axis direction.

[0059] That is, in this case, each mesh represents a region with a mesh width of 40 ms and an area of ​​40 ms x 40 ms. Then, the number of data points on the LP belonging to each mesh is counted, and the density of each mesh region is defined as an element of the LP matrix. Note that the LP drawing range and the division amount of each axis, i.e., the mesh width, are not limited to this embodiment. For example, the drawing range may be the same, and the mesh region may be defined with a mesh width of 80 ms, i.e., by dividing each axis into 32.

[0060] In addition, in order to clearly evaluate the measurement characteristics when the RRI data is not measured normally, this embodiment shows an example in which, as a preprocessing step for LP generation, a threshold value is set for the density of the mesh region, and a saturation process is applied in which any density exceeding the threshold value is replaced with the threshold value.

[0061] For example, if the threshold is set to 3, even if data appears four or more times within a mesh region, the maximum density value will be 3. This processing emphasizes the geometric characteristics of abnormal RRI values ​​such as arrhythmia or measurement failure.

[0062] As described above, in this embodiment, the period B unit LP generating unit 23 generates a 64×64 LP matrix with four gradations of density from 0 to 3 as the period B unit LP data 43 .

[0063] Note that the preprocessing for generating the LP is not limited to saturation processing. For example, in order to process only arrhythmia-like abnormal values ​​using this method, an RRI having a length approximately n times the expected RRI resulting from misdetection of n consecutive R-wave beats may be subjected to an elimination or replacement process of abnormal values ​​using a median filter, which is a known time domain analysis method, or an interpolation process of misdetected beats using a Kalman filter, which is also a known method.

[0064] The chronic onset discrimination model learning unit 22 performs the process of calculating the period B unit LP data 43 from the period B unit RRI data 41 divided into the above-described period B units for all periods B included in period A (S22). Note that even if a period B is included in period A, if the period B does not exist as period B unit RRI data 41, it is treated as missing data.

[0065] Thereafter, the chronic occurrence discrimination model learning unit 22 performs a period A unit aggregated LP generation process (S25) in which the obtained period B unit LP data 43 is aggregated in period A units to generate period A unit aggregated LP data 45.

[0066] In this flowchart, an example is shown in which the LP data 43 in units of period B is generated sequentially over the period A, but the LP data 43 may be generated in parallel instead of sequentially.

[0067] When RRI data is measured continuously in a time series for period B, or when RRI data for period B is obtained by replacing, interpolating, or excluding abnormal values, previous research has been conducted on the LP generated from the RRI data for period B, and there is a wealth of knowledge regarding what geometric shapes represent arrhythmia-like abnormalities.

[0068] On the other hand, for period A having a window width equal to or greater than period B, the amount of RRI data actually measured during period A varies due to various factors, such as time periods when RRI cannot be measured continuously, time periods when measurement fails and no RRI data exists, time periods when RRI data exists but transmission to the server fails and data is missing, and cases where the start and end of one business day shown as an example of period A differ due to business reasons.

[0069] For example, if period A is simply divided by period B, there may be 200 sections, but there may be only 190 sections of period B within the actually measured period A. In this way, the generation of an LP when there is a loss of RRI data in a section within period A has not been taken into consideration in the conventional example, and the geometric characteristics shown in this case have not been clear.

[0070] In the period A unit aggregated LP generation process (S25), the chronic occurrence discrimination model learning unit 22 calls the period A unit aggregated LP processing unit 24, and the period A unit aggregated LP processing unit 24 performs an aggregation process (S25) on a group of period B unit LP data 43 for period B that exists within the period A to be evaluated, i.e., that is not a data missing period, to generate period A unit aggregated LP data 45, which is an LP that quantifies the features of the RRI data for period A.

[0071] The period A unit aggregated LP processing unit 24 performs, for example, averaging processing for each component of the LP matrix for the period B unit LP data 43 group to generate period A unit aggregated LP data 45. In the case of this embodiment, since period A is one business day, the period A unit aggregated LP processing unit 24 generates an average LP per business day and stores it as period A unit aggregated LP data 45.

[0072] The aggregation method is not limited to averaging each element of the LP matrix. For example, in order to improve the robustness of the aggregation, the aggregation may be performed using statistical processing such as calculating the N% quantile for each element of the LP matrix during period A.

[0073] In this case, if aggregation processing with N=50% is selected, aggregation processing will be performed using the median for each component, and if there is period B unit LP data 43 during period A that has characteristics that are significantly different from the others, aggregation processing can be performed that reduces the influence of data with the different characteristics compared to averaging processing.

[0074] When there is missing RRI data in a section within period A, if an LP is simply generated using all RRI data, there are cases where the enhancement process for RRI abnormal values ​​based on a concentration threshold does not perform the desired function, or where geometric features that should originally appear on the LP are not observed.

[0075] On the other hand, with this method, by generating an LP for each period B in which there is no missing RRI data and aggregating this by period A, knowledge previously studied regarding period B can be applied to period A that includes missing RRI data.

[0076] In this embodiment, the period A unit aggregated LP generation process (S25) generates period A unit aggregated LP data 45, which indicates density with continuous values ​​from 0 to 3, from period B unit LP data 43 created in this embodiment with four gradations from 0 to 3.

[0077] Next, the chronic occurrence discrimination model learning unit 22 calls the period A unit aggregated LP processing unit 24, and the period A unit aggregated LP processing unit 24 performs an aggregated LP feature generation process (S26) using a feature extraction model 50, which is a model for extracting aggregated LP feature data 47 representing the degree of arrhythmia-like abnormalities and measurement failure-like abnormalities from the period A unit aggregated LP data 45.

[0078] The feature extraction model 50 is composed of an analytical means for extracting features from a two-dimensional matrix. For example, a feature extraction method using a mask pattern can be used, in which the two-dimensional matrix of the period A-unit aggregated LP data 45 is captured as an image and data density or occurrence frequency is extracted as feature quantities from a group of predefined mask regions created based on prior knowledge of arrhythmia-like abnormalities and measurement failure-like abnormalities. Alternatively, a convolutional neural network-based model, which learns information about arrhythmia-like abnormalities and measurement failure-like abnormalities as ground truth data based on the prior knowledge, or a frequency domain analysis model based on Fourier transform can be used. In this example, the feature extraction method using a mask pattern is described in detail with reference to Figures 4A to 4F.

[0079] It should be noted that when the period B unit LP generating unit 23 reads the period B unit RRI data 41 in step S23, it may also read the history data 44 and use only data that matches a predetermined driver state, and may use a feature extraction model 50 that is suitable for the predetermined driver state. For example, since the measurement characteristics of the RRI data change depending on whether the driver is driving or parked due to differences in driver behavior, it is expected that appropriate feature extraction will be performed by using different feature extraction models 50.

[0080] Thereafter, the chronic occurrence discrimination model learning unit 22 reads the chronic occurrence correct answer data 46 corresponding to the period A (S27). The chronic occurrence correct answer data 46 stores, for example, 0 or 1, whether or not an arrhythmia-like abnormal value has chronically occurred during the period A. The above process is performed on the group of chronic occurrence correct answer data 46 to be learned.

[0081] After the chronic occurrence correct data 46 and the corresponding aggregated LP feature data 47 are generated, the chronic occurrence discrimination model learning unit 22 performs a chronic occurrence discrimination model learning process (S28) to generate a chronic occurrence discrimination model 52 from the aggregated LP feature data 47.

[0082] The chronic onset discrimination model 52 can be configured using a known discrimination algorithm. For example, a machine learning algorithm among the discrimination algorithms can be used, such as a logistic regression model, a decision tree, Random Forest, a Support Vector Machine, a neural network, or a deep learning model.

[0083] The chronic occurrence discrimination model 52 can determine whether or not there is chronic occurrence of arrhythmia from the aggregated LP feature data 47, and can also use the discrimination probability of whether or not there is chronic occurrence as a calculation model for the degree of abnormality indicating the degree of arrhythmia-like RRI abnormality in period A.

[0084] When the period B unit RRI data 41 is read, if the history data 44 is also read, a plurality of chronic occurrence discrimination models 52 may be generated for each driver state stored in the history data 44. In this case, it becomes possible to evaluate the occurrence rate of arrhythmia-like abnormal values ​​based on the characteristics of the RRI data according to the measurement conditions.

[0085] This learning process is executed at least once before the process of evaluating the degree of chronic occurrence of arrhythmia-like abnormal values, which will be described later and is shown in Fig. 5. Furthermore, this process can be executed at regular intervals as the chronic occurrence correct answer data 46 increases, and the chronic occurrence discrimination model 52 can be re-trained. As a result, a chronic occurrence discrimination model 52 with even higher discrimination accuracy can be generated.

[0086] 4A to 4F are diagrams showing an example of a mask area definition in a feature extraction method using a mask pattern used as the feature extraction model 50 in the biometric data evaluation server 1. FIG.

[0087] In this embodiment, an example of a feature extraction method using a mask pattern consisting of five patterns shown in Figures 4B to 4F will be shown, using the period A unit aggregated LP data 45 shown in Figure 4A as an example. In the feature extraction method using a mask pattern, the period A unit aggregated LP processing unit 24 extracts, as feature quantities (S26 in Figure 3), values ​​such as statistical quantities such as the average or sum of density inside and outside a defined mask region, and the number of mesh regions where the density is equal to or greater than a certain threshold.

[0088] 4A shows an example of period A aggregated LP data 45, where the density on LP1 to LP4-2 indicates the RRI distribution in each mesh area. Also, the straight dashed lines represent y=nx (n=3, 2, 1, 1 / 2, 1 / 3), respectively.

[0089] Furthermore, RRI[t] on the horizontal axis indicates the RRI at a certain time, and RRI[t+1] on the vertical axis indicates the RRI from a certain time to the next heartbeat.

[0090] 4B shows an example of a mask region (measurement error mask Mask1) that defines the range of distribution of measurement error-like abnormal values ​​during measurement instability, which is frequently observed due to factors other than failure to detect beats. Measurement errors due to measurement instability occur because the peak of the R wave cannot be properly captured, and therefore both R waves and noise are detected as R waves at intervals shorter than the average RRI that is actually measured. In this example, the mask region (Mask1) is defined by the following equation (1):

[0091]

[0092] For example, if it is assumed that the driver's RRI rarely falls below 500 ms while driving, then by setting a = b = 500 ms, the degree of abnormal values ​​assumed to be caused by measurement instability can be quantified.

[0093] 4C shows an example of a mask region (Mask2) that defines the distribution range of RRI data where the RRI is considered to fluctuate within a normal range. In this example, the mask region (Mask2) is defined by the following equation (2).

[0094]

[0095] FluctRange is the fluctuation width that RRI data can take. For example, by taking the variance σ2 of heart rate fluctuations in a resting state with eyes closed as a reference, it is assumed that RRI data is distributed widely within 2σ, and FluctRange can be set to 80 ms.

[0096] The RRI data group of LP1 shown in FIG. 4A is shown to be included in the area of ​​the normal range mask (Mask2).

[0097] Next, a mask region for separating and characterizing arrhythmia-like abnormal values ​​and measurement-like abnormal values ​​due to missed beat detection is shown. In this example, among arrhythmia-like abnormal values, a case where premature ventricular contractions (PVCs) and premature atrial contractions (PACs) occur frequently will be specifically mentioned.

[0098] Measurement failure-like abnormal values ​​due to missed beat detection are distributed near y = (n + 1) x and y = 1 / (n + 1) x if n beats are missed. On the other hand, arrhythmia-like abnormal values ​​are distributed in the region from y = x to y = 2x and y = 1 / 2x in the case of ventricular and atrial premature contraction-like RRI. Therefore, for quantitative evaluation of arrhythmia-like abnormal values, it is effective to evaluate the region from y = x to y = 2x and y = 1 / 2x so as not to include the distribution region of missed one beat detection.

[0099] 4D shows an example of a mask region (Mask3) that defines the range in which arrhythmia-like abnormal values ​​are distributed. In this example, the mask region is defined as follows:

[0100]

[0101] The PVC-like abnormal value mask (Mask 3) enables evaluation of arrhythmia-like RRI by evaluating the area between a straight line obtained by relaxing y = 2x and y = 1 / 2x by a rotation angle Δθ around the origin, with counterclockwise rotation being positive, and y = x ± FluctRange, so as not to include the distribution area of ​​one beat missed detection, as described below.

[0102] The rotation angle Δθ may be set to, for example, Δθ = 2°. Furthermore, by excluding the region equal to or greater than the RRI of the interval MaxRRI, which is not expected during driving, it becomes possible to further evaluate only arrhythmia-like abnormal values. For example, if the heart rate falls below 40 while driving, it can be assumed that the RRI data is not being measured correctly, and MaxRRI = 1500 ms can be set.

[0103] The RRI data groups of LP2-1 and LP2-2 shown in FIG. 4A are shown to be included in the region of the PVC-like abnormal value mask (Mask3).

[0104] FIG. 4E shows an example of a mask region (Mask4) that defines the range in which abnormal RRI values ​​are distributed when n=1 consecutive beats are missed for detection, and the mask region (Mask4) is defined as follows.

[0105]

[0106] The RRI data groups of LP3-1 and LP3-2 shown in FIG. 4A are included in the region of the one-beat missed detection mask (Mask 4).

[0107] Figure 4F shows an example of a mask region (Mask5) that defines the range in which RRI abnormal values ​​for consecutive n = 2 beats are distributed, and the mask region (Mask5) is defined in the same way as in Figure 4E. The RRI data groups LP4-1 and LP4-2 shown in Figure 4A are included in the region of the consecutive 2 beats missed detection mask (Mask5).

[0108] As described above, by extracting features from the period A-unit aggregated LP, it becomes possible to distinguish and evaluate the degree of arrhythmia-like abnormal values ​​and measurement error-like abnormal values. Note that the mask region is not limited to this embodiment. For example, an additional mask region for representing atrial fibrillation may be defined and used.

[0109] As described above, by calculating features that can be evaluated by separating the mask region that defines the arrhythmia-like abnormal value and the measurement error-like abnormal value, it is possible to selectively evaluate the chronic occurrence of arrhythmia-like abnormal values. Furthermore, as a secondary effect, it is possible to similarly evaluate the severity of the measurement error-like abnormal value.

[0110] 5 is a flowchart showing an example of a process for evaluating the degree of chronic occurrence of arrhythmia-like abnormal values, which is performed in the biological data evaluation server 1. Note that steps S22 to S26 in the figure are the same processes as those in the flowchart of FIG. 3, and therefore are given the same reference numerals as in FIG. 3.

[0111] First, the period B unit LP generation unit 23 reads period B unit RRI data 41 obtained by dividing the RRI data of period A into units of period B (S23). Next, the period B unit LP generation unit 23 uses the read period B unit RRI data 41 to generate an LP for each period B, and stores the LP as period B unit LP data 43 (S24).

[0112] After the period B unit LP generation unit 23 generates period B unit LP data 43 for all periods B included in period A (S22), the period A unit aggregated LP processing unit 24 performs a period A unit aggregated LP generation process (S25) to generate period A unit aggregated LP data 45 by aggregating the period B unit LP data 43 into period A units.

[0113] Then, the period A unit aggregated LP processing unit 24 performs an aggregated LP feature generation process (S26) using a feature extraction model 50, which is a model for extracting aggregated LP features representing the degree of arrhythmia-like abnormalities and measurement error-like abnormalities from the period A unit aggregated LP data 45.

[0114] Thereafter, the abnormal value chronic occurrence evaluation unit 25 performs an abnormality degree calculation process (S31) on the obtained aggregated LP feature amount data 47, using the learned chronic occurrence discrimination model 52 to calculate abnormality degree data 49.

[0115] The abnormality degree calculated in this process can be used as the abnormality degree data 49, for example, by inputting the aggregated LP feature data 47 into the chronic occurrence discrimination model 52 as described above, and calculating the probability of determining whether or not a chronic occurrence has occurred as the chronic arrhythmia-like abnormality degree 147 (see Figure 10E).

[0116] Finally, the abnormal value chronic occurrence evaluation unit 25 performs a chronic occurrence determination process (S32) using the aggregated LP feature data 47, the abnormality degree data 49, and the chronic occurrence determination model 52, determines whether or not arrhythmia-like abnormal values ​​are chronically occurring during period A, and stores the result in period A unit abnormality determination data 51.

[0117] The chronic abnormal value occurrence evaluation unit 25 acquires the chronic arrhythmia-like abnormality degree 147 from the abnormality degree data 49 of the target driver, and if the chronic arrhythmia-like abnormality degree 147 exceeds a preset abnormality judgment threshold, sets "1" to the chronic arrhythmia-like abnormality judgment result 157 (see Figure 10F) in the period A unit abnormality judgment data 51, and if it is below the abnormality judgment threshold, sets "0".

[0118] 3, when the period B data reading process (S23) additionally reads history data 44 and generates the period A unit aggregated LP from only the period B unit RRI data 41 measured in a predetermined driver state, the feature extraction model 50 used in the aggregated LP feature generation process (S26) and the chronic occurrence discrimination model 52 used in the abnormality degree calculation process S3 and the chronic occurrence discrimination process (S32) may be selected and used as models for the predetermined driver state. In this case, the occurrence status of arrhythmia-like abnormal values ​​can be evaluated with higher accuracy based on the measurement status of the RRI data.

[0119] In this embodiment, the anomaly degree calculation process (S31) and the chronic occurrence discrimination process (S32) are performed sequentially, but they may be performed simultaneously (or in parallel). In this case, the aggregated LP feature amount data 47 is input to the chronic occurrence discrimination model 52, and the obtained discrimination probability and discrimination result are stored as anomaly degree data 49 and period A unit anomaly discrimination data 51, respectively.

[0120] As a result, even for RRI data for a period A with missing data, it is possible to generate an LP for evaluating the degree of occurrence of arrhythmia-like abnormal values ​​in period A. It is also possible to determine whether the occurrence of arrhythmia-like abnormal values ​​is chronic.

[0121] Therefore, by using the obtained period A unit abnormality discrimination data 51, it becomes possible to exclude inappropriate periods from period A even in an environment with missing data, thereby improving the reliability of autonomic nervous function evaluation.

[0122] 6 is a flowchart showing an example of a process for determining whether a driver is unsuitable for an autonomic nervous function evaluation, which is performed by the biological data evaluation server 1. In this embodiment, an example is shown in which period A is one working day, but the occurrence of arrhythmia-like abnormal values ​​in a driver can change depending on the exercise load and health condition.

[0123] For this reason, it is difficult to determine that future autonomic nervous function evaluation is inappropriate for all data of the driver based solely on the chronic arrhythmia-like abnormality determination result 157 for period A. To make this determination, it is considered desirable to make the evaluation taking into account the chronic arrhythmia-like abnormality determination result 157 for period C, which is longer than period A.

[0124] Therefore, in the process of evaluating whether a driver is unsuitable for autonomic nervous function evaluation, the unsuitable driver determination unit 26 first reads out the period A unit abnormality determination data 51 that exists within period C for the most recent period C, and performs a determination result reading process for period C (S41).

[0125] Then, the unsuitable driver determination unit 26 inputs the period A unit abnormality determination data 51 within period C, and uses the unsuitable driver determination model 54 to calculate the determination result (ANF evaluation unsuitability determination 167 in Figure 10G) of whether the driver is unsuitable for autonomic nervous function evaluation based on RRI data, and stores the result in the unsuitability determination data 48 (S42).

[0126] In addition, the ANF evaluation inadequacy judgment 167 of the inadequacy judgment data 48 is set to "1" if it is inadequate for autonomic nervous function evaluation, and is set to "0" if it can be used for autonomic nervous function evaluation.

[0127] For example, if period A is one business day, period C may be five business days. The inappropriate driver determination model 54 may use a statistical model that statistically sets a determination threshold by comparing the occurrence distribution of ANF evaluation inappropriateness determinations 167 for period A when period C is the total number of cases in which arrhythmia-like abnormal values ​​are constantly exhibited and cases in which arrhythmia-like abnormal values ​​are accidentally exhibited depending on the driver's situation.

[0128] As a result, the inappropriate driver determination unit 26 can detect drivers who are considered to be consistently inappropriate for autonomic nervous function evaluation using RRI data, regardless of changes in the driver's own condition, such as health status or exercise load, thereby achieving the effect of improving the reliability of autonomic nervous function evaluation.

[0129] 7 is a flowchart showing an example of a process for calculating an autonomic nervous function index performed by the biological data evaluation server 1. In this example, an example is shown in which the autonomic nervous function index is calculated using RRI data with a window width similar to that of the period B used for generating the LP. That is, in this example, an example is shown in which the autonomic nervous function index is calculated in units of an analysis window of 2 minutes.

[0130] The calculation process of the autonomic nervous function index is performed by a known or well-known method, and therefore only an outline thereof will be described below. First, the autonomic nervous function index calculation unit 27 performs a data read process to read the period B unit RRI data 41 (S51).

[0131] Next, in order to evaluate whether the driver is considered to be consistently inappropriate in terms of autonomic nervous function evaluation based on RRI data, the autonomic nervous function index calculation unit 27 determines whether the analysis is appropriate based on the inadequacy determination data 48 (S52).

[0132] For this determination, autonomic nervous function index calculation unit 27 extracts records in which ANF evaluation inadequacy determination 167 is "0" from inadequacy determination data 48, and calculates autonomic nervous function index data 53 in steps S53 to S55 using B-unit RRI data 41 for the period from analysis start 165 to analysis end 166. This allows autonomic nervous function index calculation unit 27 to exclude records in which ANF evaluation inadequacy determination 167 is "1."

[0133] If the analysis does not identify an inappropriate driver, the autonomic nervous function index calculation unit 27 performs an analysis as needed from the RRI data to calculate the autonomic nervous function index data 53. Examples of the analysis as needed include a frequency domain analysis (S53), a time domain analysis (S54), and an RRI nonlinear domain analysis (S55).

[0134] In the frequency domain analysis (S53), the autonomic nervous function index calculation unit 27 calculates a frequency domain index from the RRI time series via a power spectral density. Because the RRI time series is irregularly spaced time series data, the power spectral density (PSD) is calculated using a known method such as an autoregressive model or a maximum entropy method after resampling at regular intervals using spline interpolation, or using the Lomb-Scargle method, which can use irregularly spaced data.

[0135] The autonomic nervous function index calculation unit 27 calculates, from the calculated PSD, for example, the integral value LF of the low frequency region of 0.05 Hz-0.15 Hz, the integral value HF of the high frequency region of 0.15 Hz-0.40 Hz, TP which is the sum of LF and HF, LF / HF which is LF divided by HF, and LFnu which is LF divided by TP as a percentage, as frequency domain indices of the autonomic nervous function index data 53.

[0136] In the time domain analysis (S54), the autonomic nervous function index calculation unit 27 calculates the time domain index by calculating statistics of the RRI time series and the ΔRRI time series, which is the difference series between adjacent RRIs.

[0137] For example, the autonomic nervous function index calculation unit 27 calculates the average heart rate, which is the reciprocal of the average value of the RRI time series, and SDNN, which is the standard deviation of the RRI data. Furthermore, from the ΔRRI time series, for example, NN50, which is the total number of data whose absolute values ​​of difference values ​​constituting the ΔRRI time series exceed 50 ms, pNN50, which is NN50 divided by the total number of data in the ΔRRI time series, and SDSD, which is the standard deviation of ΔRRI, are calculated and calculated as time domain indices of the autonomic nervous function index data 53.

[0138] In the RRI nonlinear region analysis (S55), the autonomic nervous function index calculation unit 27 calculates nonlinear feature quantities using various methods. For example, the autonomic nervous function index calculation unit 27 calculates an ellipse area S obtained by ellipsically approximating the region plotted as shown in FIG. 4A through LP analysis. The autonomic nervous function index calculation unit 27 also calculates similarity entropy, α1 and α2 using detrended fluctuation analysis, and tone and entropy based on tone-entropy analysis, and calculates these as the RRI nonlinear region index of the autonomic nervous function index data 53.

[0139] Thereafter, autonomic nervous function index calculation section 27 collectively stores the calculated autonomic nervous function indexes in autonomic nervous function index data 53 (S56).

[0140] The autonomic nervous function index calculation unit 27 may execute the above steps in parallel or sequentially.

[0141] On the other hand, in the case of a driver who is deemed to be unsuitable for analysis based on the unsuitability determination data 48, the autonomic nervous function index calculation unit 27 does not calculate the autonomic nervous function index, but instead stores an unsuitability flag in the autonomic nervous function index data 53. Note that the autonomic nervous function index may be calculated and then the unsuitability flag may be stored in the autonomic nervous function index data 53.

[0142] As a result of the above, it is possible to assign an inappropriate flag to drivers whose autonomic nervous function evaluation using RRI data is inappropriate due to steady arrhythmia, thereby reducing the possibility of misinterpretation of the obtained autonomic nervous function index and improving the reliability of the autonomic nervous function evaluation.

[0143] 8 is a diagram showing an example of an autonomic nervous function evaluation result screen 1000 that the result display unit 28 outputs to the display of the input / output device 5. When the biological data evaluation server 1 finishes measuring the RRI data for period A and generates period A unit abnormality determination data 51, the input / output device 5 displays the autonomic nervous function evaluation result screen 1000 for period A.

[0144] On the autonomic nervous function evaluation result screen 1000, a driver ID 1011, a used vehicle (ID) 1012, and an arrhythmic RRI abnormality level 1013 are displayed at the top as summary information 1010. Also, at the bottom, a time series of the autonomic nervous function index every 30 minutes is displayed in five stages as an autonomic nervous function index transition 1020. Note that the autonomic nervous function index is an example showing a range from relaxed to stressed.

[0145] During one business day in period A, which is the subject of this embodiment, data is missing for some reason, for example at 10:00, and the autonomic nervous function index cannot be calculated. In other words, this is a case where a missing RRI data occurs during period A, making it difficult to determine the degree of arrhythmia-like abnormal values ​​by applying the conventional LP.

[0146] However, in this embodiment, the degree of arrhythmia-like abnormal values ​​can be evaluated even if there is a missing section within period A, so the summary information 1010 at the top displays today's working hours (e.g., 8.5 hours) and the degree of arrhythmia-like abnormal values ​​during this working time as arrhythmia-like RRI abnormality level 1013.

[0147] For example, the arrhythmia-like RRI abnormality level 1013 may quantitatively display an evaluation of the occurrence status of arrhythmia-like abnormal values ​​by displaying a value obtained by converting the discrimination probability recorded as a percentage in the abnormality degree data 49 into a percentage display.

[0148] As a result of the above, even if there is a missing section of RRI data during period A, which can frequently occur during work, the driver can quantitatively understand whether the trend in the autonomic nervous function index displayed on the autonomic nervous function evaluation result screen 1000 is reliable.

[0149] 9 is a diagram showing an example of a detailed analysis screen 2000 of the reliability of the RRI data measured during the period A, which is output by the result display unit 28 to the display of the input / output device 5. When the details button 1014 displayed in the summary information 1010 on the autonomic nervous function evaluation result screen 1000 shown in FIG. 8 is pressed, the input / output device 5 displays the detailed analysis screen 2000 for the measurement data for the period A.

[0150] The upper left of the detailed analysis screen 2000 displays the relevant date 2001, driver ID 2002, and reliability 2003 of the autonomic nervous function index for the relevant one workday in period A.

[0151] A period A unit aggregated LP 2004 is displayed at the bottom left of the detailed analysis screen 2000. Period B unit RRI data 2011 and period B unit LP data 2012 measured before aggregation to create the period A unit aggregated LP 2004 are displayed at the bottom right, and a scroll bar 2013 at the bottom allows the user to check the change over time in the period B unit LP data.

[0152] Furthermore, a scroll bar 2013 at the bottom displays a section 2014 with low reliability in shaded areas for each period B. In the upper right corner of the detailed analysis screen 2000, a degree 2021 of arrhythmia-like RRI abnormality and degrees 2022 and 2023 of measurement-poor RRI abnormality are displayed together with the reasons for their respective degrees.

[0153] In this embodiment, for each of the abnormal RRI values ​​defined in the feature extraction method using a mask pattern used in the feature extraction model 50, such as arrhythmia-like, measurement failure-like, and R-wave detection failure-like, the area definition on the LP that serves as the basis for judgment is superimposed on the period A unit aggregated LP 2004.

[0154] Each abnormality level of the period A unit aggregated LP 2004 can be displayed as a percentage by normalizing the feature amount related to each mask by the maximum value of the feature amount. When a convolutional neural network is used as the feature extraction model 50, the basis for the determination may be visualized by displaying an attention map, which is a means for visualizing the basis for the determination.

[0155] As a result, by referring to the detailed analysis screen 2000, users of the biometric data evaluation server 1 can easily present the reasons why the reliability of autonomic nervous function evaluation due to arrhythmia-like abnormal values ​​has decreased.

[0156] Furthermore, in addition to arrhythmia-like abnormal values, information on the status of measurement-like abnormal values ​​can be presented, enabling the driver to determine whether RRI data is being measured normally. Furthermore, if it is found that the measurement status is poor only in a certain period B, the driver can consider the cause of the measurement failure by comparing it with his / her own work knowledge.

[0157] <Data Structure> Next, the characteristic structure of each data used in the biometric data evaluation system will be described.

[0158] FIG. 10A is a diagram showing an example of the data structure of the period B unit RRI data 41 stored in the storage device 4 in the biological data evaluation server 1. As shown in FIG.

[0159] The period B unit RRI data 41 typically stores a driver ID 101, a vehicle ID 102, a measurement time 103 of the RRI data, an RRI 104, and an acceleration norm 105 in one record.

[0160] The driver ID 101 stores the identifier of the driver acquired by the driver ID reader 11 of the vehicle 7. The vehicle ID 102 stores the identifier of the vehicle 7 that is set in advance in the driving data collection device 10.

[0161] The measurement time 103 stores the date and time when the heart rate sensor 14 measured the RRI data. The RRI 104 stores the value (msec) detected by the heart rate sensor 14. The acceleration norm 105 stores the vector value of the acceleration detected by the acceleration sensor 15.

[0162] 10B is a diagram showing an example of the data structure of the period B unit LP data 43 stored in the storage device 4 in the biological data evaluation server 1. The period B unit LP data 43 typically stores a driver ID 111, a vehicle ID 112, a window width 113 of period B, an analysis period 114, a period B unit LP 115, and an analysis source file name 116 in one record.

[0163] 10A, the driver ID 111 stores the identifier of the driver. The vehicle ID 112 stores the identifier of the vehicle 7, the same as in FIG. 10A, the period B 113 stores the length of the period B. The analysis period 114 stores the date and time of the start of the period B.

[0164] The period B unit LP 115 may store an array in which two-dimensional LP matrix elements within period B are flattened. Alternatively, information obtained by encoding an LP image in which the LP matrix elements are visualized as luminance may be stored in binary. Alternatively, each LP matrix element may be stored in a different column (or field) direction. The analysis source file name 118 stores the file name (or path) of the period B unit LP data 43.

[0165] 10C is a diagram showing an example of the data structure of the period A unit aggregated LP data 45 stored in the storage device 4 in the biological data evaluation server 1. The period A unit aggregated LP data 45 typically has a driver ID 121, a vehicle ID 122, a window width 123 of period A, a window width 124 of period B, a window number 125 indicating the number of sections of period B in which data actually existed within period A, an analysis period 126, a period A unit aggregated LP 127, and a method indicating an aggregation method 128 stored in one record.

[0166] The driver ID 121 and vehicle ID 122 are the same as those in FIG. 10A and store the driver's identifier and the vehicle 7's identifier. The period A 123 stores the length of the period A. The period B 124 stores the length of the period B. The analysis period 126 stores the date and time of the start of the period A. The period A unit aggregated LP 127 may store an array in which the two-dimensional LP matrix elements within the period A are flattened. Alternatively, information obtained by encoding an LP image in which the LP matrix elements are visualized as luminance into binary may be stored. Alternatively, each LP matrix element may be stored in a different column direction.

[0167] 10D is a diagram showing an example of the data structure of the period A unit aggregated LP feature amount data 47 stored in the storage device 4 in the biological data evaluation server 1. The period A unit aggregated LP feature amount data 47 typically includes a driver ID 131, a vehicle ID 132, a window width 133 of period A, a window width 134 of period B, a window number 135 indicating the number of sections of period B that actually existed within period A, an analysis period 136, and, for a group of features extracted from the period A unit aggregated LP, column names indicating the characteristic names of the features, such as arrhythmia-like or measurement error-like (e.g., arrhythmia-like feature amount 1137-1 to measurement error-like feature amount N137-N) are stored in one record.

[0168] The driver ID 131 to the analysis period 136 are the same as the driver ID 121D to the analysis period 126 in FIG. 10C.

[0169] Arrhythmia features 1 to N (137-1 to 137-N) store, for example, the features of LP included in the measurement failure mask Mask1 in FIG. 4B, the features of LP included in the PVC-like abnormal value mask Mask3, the features of LP included in the one-beat detection missed mask Mask4, and the consecutive two-beat detection missed mask Mask5.

[0170] 10E is a diagram showing an example of the data structure of the abnormality degree data 49 stored in the storage device 4 in the biological data evaluation server 1. The abnormality degree data 49 typically stores, in one record, a driver ID 141, a vehicle ID 142, a window width 143 of period A, a window width 144 of period B, a window number 145 indicating the number of sections of period B that actually existed within period A, an analysis period 146, and a chronic arrhythmia-like abnormality degree 147.

[0171] 10D . The chronic arrhythmia-like abnormality degree 147 stores, in one record, the probability of determining whether or not an arrhythmia has occurred chronically, obtained by inputting the aggregated LP feature amount data 47 into the chronic occurrence determination model 52.

[0172] 10F is a diagram showing an example of the data structure of the period A unit abnormality determination data 51 held in the storage device 4 in the biological data evaluation server 1. The period A unit abnormality determination data 51 typically stores, in one record, a driver ID 151, a vehicle ID 152, a window width 153 of period A, a window width 154 of period B, a window number 155 indicating the number of sections of period B that actually existed within period A, an analysis period 156, and a chronic arrhythmia-like abnormality determination result 157.

[0173] The driver ID 151 to the analysis period 156 are the same as the driver ID 141D to the analysis period 146 in FIG. 10E.

[0174] The chronic arrhythmia-like abnormality determination result 157 stores the result of the abnormal value chronic occurrence evaluation unit 25 determining whether or not an arrhythmia-like abnormal value has chronically occurred during period A as a value of "0" or "1." If an arrhythmia-like abnormal value has chronically occurred, the chronic arrhythmia-like abnormality determination result 157 stores "1," and if not, it stores "0."

[0175] 10G is a diagram showing an example of the data structure of the inadequacy determination data 48 stored in the storage device 4 in the biological data evaluation server 1. The inadequacy determination data 48 typically stores, in one record, a driver ID 161, a vehicle ID 162, a window width 163 of period A, a window width 164 of period C, an analysis start 165 of period A when the analysis started, an analysis end 166 of period A when the analysis ended, and an autonomic nervous function (ANF in the figure) evaluation inadequacy determination 167 evaluated for period C.

[0176] 10F. Period C 164 stores a period (window width) larger than period A. Analysis start 165 and analysis end 166 store the start date and time and end date and time of period C.

[0177] The autonomic nervous function (ANF) evaluation inappropriateness judgment 167 stores "1" if the RRI data of the driver ID 161 is not suitable for evaluating the autonomic nervous function, and stores "0" if not.

[0178] 10H is a diagram showing an example of the data structure of the autonomic nervous function index data 53 stored in the storage device 4 in the biological data evaluation server 1. The autonomic nervous function index data 53 typically includes a driver ID 171, a vehicle ID 172, a date and time 173, and various autonomic nervous function indexes calculated by the autonomic nervous function index calculation unit 27 stored in one record.

[0179] The driver ID 171 and the vehicle ID 172 are the same as the driver ID 161 and the vehicle ID 162 in Fig. 10J. The date and time 173 stores the date and time when the autonomic nerve function index is calculated.

[0180] In this embodiment, examples of autonomic nervous function indices include LF / HF 174, which is a frequency domain index, average heart rate 175, which is a time domain index, and NN50 (176) or α1 (177), which is an RRI nonlinear domain index.

[0181] 10I is a diagram showing an example of the data structure of the business status data 42 stored in the storage device 4 in the biological data evaluation server 1. The business status data 42 typically includes a driver ID 181, a vehicle ID 182, a business date 183, a measurement start date and time 184, a measurement end date and time 185, and a travel distance 186 stored in one record.

[0182] The driver ID 181 and vehicle ID 182 are the same as the driver ID 171 and vehicle ID 172 in Fig. 10H. The work date 183 stores the date on which the driver performed work. The measurement start date and time 184 and the measurement end date and time 185 store the date and time when measurement of biological data started and ended. The driving distance 186 stores the distance driven by the driver on the work day 183.

[0183] 10J is a diagram showing an example of the data structure of the history data 44 stored in the storage device 4 in the biological data evaluation server 1. The history data 44 typically includes a driver ID 191, a vehicle ID 192, a window width 193 for period B, a transmission time 194 of the period B unit RRI data, a received file name 195 of the period B unit RRI data, and a representative state 196, all of which are stored in one record.

[0184] The driver ID 191 and vehicle ID 192 are the same as the driver ID 181 and vehicle ID 182 in Fig. 10I. Period B 193 stores the length of period B. File transmission time 194 stores the date and time when the driving data collection device 10 of the vehicle 7 transmitted the RRI data. File name 195 stores the file name (or path) of the RRI data.

[0185] The representative state 196 stores the state of the driver in the period B when the period B unit RRI data 41 was measured.

[0186] 10K is a diagram showing an example of the data structure of the chronic occurrence correct answer data 46 stored in the storage device 4 in the biological data evaluation server 1. The chronic occurrence correct answer data 46 typically stores, in one record, a driver ID 201, a vehicle ID 202, a window width 203 of period A, an analysis period 204, and a chronic arrhythmia-like abnormality label 205 indicating a correct answer label as to whether or not the abnormality is a chronic arrhythmia-like abnormality.

[0187] The driver ID 201 and vehicle ID 202 are the same as the driver ID 191 and vehicle ID 192 in Fig. 10J. Period A 203 stores the length of period A. Analysis period 204 stores the start date and time of period A. The chronic arrhythmia-like abnormality label 205 stores "1" if it is a chronic arrhythmia-like abnormality, and stores "0" if it is not.

[0188] 11 is a diagram showing an example of the definitions of period A and period B and the occurrence of data loss. In this embodiment, when period A501 is set to one business day (i.e., the period from the start to the end of business on a certain date) and period B503 is set to two minutes, an example will be described in which period A501 (501-1, 501-2) is three man-days and period A501 is divided into period B503 units.

[0189] First, we will explain the period A 501 and the period B 503 when no data loss occurs. In the case of driver A 502-1 on December 1st, for the period defined by period A (driver A) 501-1, there are period B unit RRI data 504 divided by period B 503, and the number of windows is n.

[0190] On the other hand, in the case of driver B 502-3 on 12 / 1, the start and end times of work are different from those of driver A 502-1 on 12 / 1, and period B unit RRI data 504 is measured over period A (driver B) 501-2, which is different from period A (driver A) 501-1. As a result, period B unit RRI data 504 with number of windows m, which is different from the number of windows n that existed in period A 501-1 of driver A on 12 / 1, becomes the subject of analysis.

[0191] Next, we will explain the case of driver A 502-2 on December 2nd when there is missing data. In this case, since the business system has not changed for the same driver, period A 501 is also defined as period A (driver A) 501-1 in driver A 502-2, just like driver A 502-1.

[0192] On the other hand, data loss occurs in the period B unit RRI data 504 measured during the period A (driver A) 501-1 due to various factors. For example, the period B unit RRI data 505-1 has a significantly small amount of valid RRI data due to measurement failure, and is determined to have data loss.

[0193] Furthermore, the period B unit RRI data 505-2 is determined to have missing data because RRI data measurement failed in period B503 and empty period B unit RRI data exists on the biological data evaluation server 1.

[0194] Furthermore, the period B unit RRI data 505-3 is determined to have missing data because the period B unit RRI data 504 does not exist on the biological data evaluation server 1 due to an external factor 73 such as poor communication.

[0195] As a result, data loss occurred in three sections, and n-3 pieces of RRI data per period B were measured by driver A502-2 on December 2, which is three pieces of data less than the total number n of RRI data per period B for driver A502-1 on December 1. Note that the causes of data loss are not limited to the above.

[0196] As described above, the period B unit RRI data 41 measured during period A is n, n-3, m, respectively, and even if an attempt is made to measure RRI data over period A, there are cases in which the actually measured RRI data amount differs.

[0197] Assuming that the period B unit RRI data 41 read into the biometric data evaluation server 1 has very few valid RRIs or is empty, the target period B unit RRI data 41 may be inspected to determine whether or not there is missing data.

[0198] As described above, in the biometric data evaluation system of this embodiment, the biometric data evaluation server 1 calculates the period A unit aggregated LP data 45 by aggregating the period A unit using the period B unit LP data 43 group calculated from the period B unit RRI data 41 group, calculates the period A unit aggregated LP data 45 by aggregating the period A unit using the feature extraction model 50, calculates the aggregated LP feature data 47 including features representing the degree of occurrence of arrhythmia-like abnormal values ​​from the period A unit aggregated LP data 45, and inputs the aggregated LP feature data 47 into the chronic occurrence discrimination model 52, thereby discriminating whether or not arrhythmia-like abnormal values ​​are chronically occurring in the period A unit.

[0199] This makes it possible for the biological data evaluation server 1 of this embodiment to generate an aggregated LP that uses the degree of arrhythmia RRI abnormality value for evaluation even for RRI data with missing data.

[0200] In addition, the biometric data evaluation server 1 generates aggregated LP feature data 47 containing features representing the degree of occurrence of arrhythmia-like abnormal values ​​from the aggregated LP, making it possible to quantitatively evaluate the degree of occurrence of arrhythmia-like abnormal values ​​by distinguishing them from RRI abnormal values ​​caused by factors other than arrhythmia, such as measurement error-like abnormal values.

[0201] Furthermore, by using the aggregated LP feature data 47, the biometric data evaluation server 1 becomes able to determine whether the occurrence of arrhythmia-like abnormal values ​​is chronic during period A for RRI data for period A that includes missing data.

[0202] As a result of the above, the biometric data evaluation server 1 has the effect of being able to evaluate the reliability of the autonomic nervous function index obtained from the RRI data measured during period A, even when measuring RRI data in a state that is not necessarily at rest, such as during work that involves driving a vehicle 7.

[0203] In the first embodiment, the present invention is applied to the biometric data evaluation server 1 that manages the vehicle 7, but the present invention is not limited to this. For example, instead of the vehicle 7, the present invention can be applied to a moving body that requires a driver or operator, such as a railroad vehicle, a ship, or an aircraft.

[0204] Furthermore, the target is not limited to drivers, but may also be general employees who work in an environment where biometric data is measured remotely, or people who belong to an environment where biometric data is measured remotely.

[0205] In addition, in the above-mentioned Example 1, an example of generating an LP in units of period B was shown, but this is not limited to this, and an LP may be generated in real time from the RRI data received from vehicle 7, and the generation of the LP may be completed in units of period B.

[0206] Next, a description will be given of a second embodiment of the present invention. Except for the differences described below, the components of the safe driving support system of the second embodiment have the same functions as the components of the first embodiment that are assigned the same reference numerals, and therefore, the description thereof will be omitted.

[0207] FIG. 12 shows a second embodiment of the present invention, and is a block diagram showing an example of the main configuration when the biological data evaluation system also predicts the risk of a driver having a traffic accident or incident (hereinafter referred to as accident risk) using autonomic nervous function index data 53.

[0208] The vehicle 7 includes a biosensor 12 that detects the driver's biometric data, a driver ID reader 11 that identifies the driver, a driving data collection device 10 that collects the detected biometric data and driver ID and transmits them to the biometric data evaluation server 1, as well as an on-board sensor 8 that detects the operating status and driving status, and a prediction result notification device 9 that receives warnings from the biometric data evaluation server 1 according to the driver's accident risk and presents them to the driver.

[0209] In the illustrated example, the driving data collecting device 10, the prediction result notifying device 9, and the driver ID reading device 11 are configured as independent devices, but they can also be configured as a single mobile terminal. In this case, the mobile terminal functions as a driving data collecting unit, a prediction result notifying unit, and a driver ID reading unit.

[0210] The on-board sensors 8 may include a GNSS (Global Navigation Satellite System) 15 that detects the vehicle's location information, an acceleration sensor 16 that detects the behavior and speed of the vehicle 7, a camera 17 that detects the driving environment as video, and a business terminal 18 that presents or records the business information of the driver on board.

[0211] The on-board sensor 8 is not limited to the above, and may be a distance measuring sensor that detects objects and / or distances around the vehicle 7, a steering angle sensor that detects driving operations, an angular velocity sensor that detects turning operations of the vehicle 7, etc. Furthermore, the acceleration sensor is preferably a three-axis acceleration sensor.

[0212] The memory 3 of the biological data evaluation server 1 loads, as programs, functional units including a data collection unit 21, a chronic occurrence discrimination model learning unit 22, a period B unit LP generation unit 23, a period A unit aggregated LP processing unit 24, an abnormal value chronic occurrence evaluation unit 25, an inappropriate driver determination unit 26, an autonomic nervous function index calculation unit 27, a result display unit 28, as well as a danger prediction unit 29 and a warning presentation unit 30. Each program is executed by the processor 2. Details of each functional unit will be described later.

[0213] The storage device 4 of the biological data evaluation server 1 stores data used by the above-mentioned functional units. The storage device 4 stores the period B unit RRI data 41, period B unit LP data 43, period A unit aggregated LP data 45, aggregated LP feature amount data 47, abnormality degree data 49, period A unit abnormality discrimination data 51, autonomic nervous function index data 53, work status data 42, history data 44, chronic occurrence correct answer data 46, inappropriateness judgment data 48, feature extraction model 50, chronic occurrence discrimination model 52, inappropriate driver judgment model 54, as well as work / environment data 55, attribute information data 57, accident risk prediction data 56, and accident risk prediction model 58.

[0214] 13A is a flowchart showing an example of a process for predicting an accident risk during work, which is performed by the biometric data evaluation server 1. This process can be executed when biometric data is received from the vehicle 7.

[0215] The risk prediction unit 29 first inputs the RRI data acquired from the vehicle 7 to the autonomic nervous function index calculation unit 27 to calculate the autonomic nervous function index data 53 (S61).

[0216] The autonomic nervous function index calculation unit 27 performs frequency domain analysis and calculates the power spectrum density PSD as described above, and calculates LF / HF, LFnu, etc. as frequency domain indices of the autonomic nervous function index data 53 .

[0217] Thereafter, the danger prediction unit 29 selects and reads the accident risk prediction model 58 suitable for the driver of the vehicle 7 currently in motion (S62).

[0218] The accident risk prediction model 58 is a well-known or publicly known machine learning model that takes the autonomic nervous function index data 53 of the driver of a moving vehicle 7 as input and predicts and outputs the accident risk at a predetermined time later, and is a pre-trained model.

[0219] It is preferable to generate a plurality of accident risk prediction models 58 in advance according to the type of accident risk, the driving environment measured by the on-board sensor 8 of the vehicle 7, the task and environment data 55 storing predetermined task hours, etc. By generating a plurality of models in advance, it becomes possible to select and use an appropriate model in the accident risk prediction process (S63).

[0220] Furthermore, multiple models may be generated in advance according to attribute information data 57 that stores the driver's work characteristics (driving on ordinary roads, driving on highways, working continuously day and night, etc.), driving experience (years of driving, driving skills, type of license held), and health characteristics (gender, amount of sleep, etc.). When multiple models have been generated in advance, an appropriate accident risk prediction model 58 is selected based on the work and environment data 55 and the attribute information data 57 (S62).

[0221] In the accident risk prediction model selection (S62), instead of selecting only a single model, multiple accident risk prediction models 58 may be selected. In this case, it is desirable to assign a code to the accident risk prediction data 56 that allows the accident risk prediction model 58 used for the prediction to be identified.

[0222] Finally, the danger prediction unit 29 uses the selected accident risk prediction model 58, inputs the autonomic nervous function index data 53, and predicts the accident risk after a predetermined time, and stores the predicted risk in accident risk prediction data 56. The accident risk prediction data 56 can be calculated as the probability of an incident or accident occurring.

[0223] Fig. 13B is a flowchart showing an example of a process for issuing an alert to warn of an increased risk of an accident, which is performed by the biological data evaluation server 1. This process is the process performed in step 63 of Fig. 13A.

[0224] The warning presentation unit 30 performs a process (S71) of searching whether data indicating a high accident risk that is subject to alert generation has been accumulated from the accident risk prediction data 56. The warning presentation unit 30 can determine that data in which the probability of an incident or accident occurring exceeds a predetermined threshold is data indicating a high accident risk.

[0225] The warning presentation unit 30 determines whether or not there is accident risk prediction data 56 that is the subject of a report (S72), and if there is accident risk prediction data 56 that is the subject of a report, proceeds to step S73, and if there is no accident risk prediction data 56 that is the subject of a report, terminates the processing.

[0226] The warning presentation unit 30 then performs an evaluation appropriateness determination process (S73) to determine whether there are any concerns about the evaluation of the autonomic nervous function index that was used as an input to the accident risk prediction model 58. In the evaluation appropriateness determination process (S73), for example, based on the inappropriateness determination data 48, it is determined whether the driver in question regularly experiences arrhythmia-like abnormal values ​​even on different work days, and whether there is a possibility of a false alarm being issued.

[0227] Furthermore, the warning presentation unit 30 determines whether or not the driver's RRI data is likely to be significantly affected by a measurement error during measurement, for example, based on the abnormality level data 49. The determination of a measurement error can be made, for example, by generating an LP from the RRI data read by the warning presentation unit 30, and determining that a measurement error has occurred if the amount of data (density) included in the measurement error mask Mask1, the one beat detection omission mask Mask4, or the consecutive two beat detection omission mask Mask5 in FIG. 4B exceeds a predetermined threshold.

[0228] Thereafter, the warning presentation unit 30 generates (S74) a warning content to warn of an increased accident risk according to the situation based on the driver's accident risk prediction data 56, business / environment data 55, and attribute information data 57, and issues this as an alert to the driver (S75).

[0229] In this case, the warning presentation unit 30 identifies the transmission target by acquiring the vehicle ID of the transmission target from the driver ID based on the business / environment data 55. Note that if the transmission target is the driver manager instead of the driver, the warning presentation unit 30 may instead set the input / output device 5 of the biological data evaluation server 1 as the transmission target.

[0230] By the above process, a warning is sent to the vehicle of the driver whose accident risk is detected to be increased. In the vehicle 7 that receives the warning, the prediction result notification device 9 notifies the driver of the warning. In the biological data evaluation server 1, the warning presentation unit 30 displays the vehicle 7 that sent the warning on the display of the input / output device 5.

[0231] In this embodiment, after the evaluation adequacy determination process (S73) is performed, an example is shown in which notification is made regardless of the determination result. However, it is not necessary to issue an alert (S75) based on the determination result. For example, if arrhythmia-like abnormal values ​​occur regularly even on different work days and the detected high accident risk event is an event that is significantly affected by the arrhythmia-like abnormal values, it is not necessary to issue an alert (S75) to a driver who is determined to have an inadequate autonomic nervous function evaluation. As described above, it is possible to prevent a decrease in the reliability of alert issuance due to frequent false alerts.

[0232] 14 is a diagram showing an example of a warning presentation screen 3000 that is output by the prediction result notification device 9 of the vehicle 7 and that is issued to the driver when an increase in accident risk is detected. The prediction result notification device 9 has a display (not shown), and displays the warning presentation screen 3000 when it receives a warning from the biological data evaluation server 1.

[0233] The warning presentation screen 3000 includes an area 3001 that displays an accident risk alert, a comment area 3003 that displays countermeasures to resolve the increased risk of an accident, and an area 3002 that displays information regarding the possibility that the displayed alert content is incorrect.

[0234] For example, a warning message about an increased accident risk can be displayed in the area 3001 that displays the accident risk alert. Also, by presenting, for example, specific countermeasures for eliminating the increased accident risk in the comment area 3003 of the warning presentation screen 3000, the driver who receives the warning can understand and take the next action to eliminate the dangerous situation, rather than just receiving the warning and leaving it at that.

[0235] Furthermore, in the notification area 3002 of the possibility of a false alarm on the warning presentation screen 3000, information for notifying the possibility of a false alarm is displayed based on the reliability of the autonomic nervous function index measured from the driver for whom the alarm was issued.

[0236] For example, if arrhythmia-like abnormal values ​​that are inappropriate for autonomic nervous function evaluation based on RRI data are occurring chronically, the notification can be "Arrhythmia: Low." Also, if there are many measurement errors occurring regularly in the measurement of the driver's RRI data, the notification can be "Measurement Error: Low."

[0237] As a result, the driver can determine whether the alert he or she has been notified of is due to unreliable measurement data or autonomic nervous function evaluation, or whether the risk of an accident is truly increasing, thereby improving the reliability of the alert content.

[0238] Although the present embodiment shows an example of presenting a warning using the warning presentation screen 3000, the warning may be presented by other methods. For example, the warning may be presented in the form of an audio message in which a sentence having the same content as that displayed on the warning presentation screen 3000 is mechanically read aloud.

[0239] As described above, in addition to the processing described in Example 1, the biological data evaluation system of this Example inputs autonomic nervous function index data 53 calculated from RRI data into an accident risk prediction model 58 to calculate accident risk prediction data 56 after a predetermined time, and when an increased risk of an accident or incident is detected from the accident risk prediction data 56, an alert is issued to the driver to warn of the increased accident risk, taking into account the contents of the abnormality degree data 49, the inappropriateness judgment data 48, and the period A unit abnormality judgment data 51.

[0240] As a result, when the biometric data evaluation server 1 of this embodiment issues a report of an increased risk of an accident based on the autonomic nervous function index data 53 calculated from the RRI data, it is able to issue an alert that takes into account the characteristics of the driver receiving the report about events that could cause a false report, such as arrhythmia or poor measurement of the RRI data.

[0241] As a result, it becomes possible to consider canceling the issuance of an alert depending on the possibility of a false alarm, and to issue an alert that includes the possibility of a false alarm in the notification content. Therefore, it is possible to reduce false alarms in the issuance of alerts based on the autonomic nervous function index data 53 calculated from the RRI data executed by the biological data evaluation server 1, improve acceptability of the reasons for false alarms, and achieve the effect of significantly improving the reliability of the alerts that are issued.

[0242] The present invention is not limited to the above-described embodiments, but includes various modifications. For example, the above-described embodiments have been described in detail to clearly explain the present invention, and the present invention is not necessarily limited to those including all of the described configurations. Furthermore, it is possible to replace part of the configuration of one embodiment with the configuration of another embodiment, or to add the configuration of another embodiment to the configuration of one embodiment. Furthermore, it is possible to add, delete, or replace part of the configuration of each embodiment with other configurations.

[0243] The above-described configurations, functions, processing units, processing means, etc. may be partially or entirely realized in hardware by, for example, designing them as integrated circuits. The above-described configurations, functions, etc. may also be realized in software by the processor 2 interpreting and executing programs that realize the respective functions. Information such as programs, tables, and files that realize the respective functions can be stored in storage devices such as the memory 3, a hard disk drive, or an SSD (Solid State Drive), or in computer-readable non-transitory data storage media such as an IC card, an SD card, or a DVD.

[0244] The drawings show control lines and information lines that are considered necessary for explaining the embodiments, but do not necessarily show all of the control lines and information lines included in an actual product to which the present invention is applied. In reality, it can be considered that almost all components are interconnected.

[0245] <Conclusion> As described above, the biological data evaluation system of the above embodiment can be configured as follows.

[0246] (1) A biometric data evaluation server having a processor (2) and a memory (3) for evaluating biometric data, characterized in that it has a data collection unit (21) that receives heart rate interval equivalent data (period B unit RRI data 41) from the biometric data of a subject (driver), and a Lorenz plot generation unit (period B unit LP generation unit 23, period A unit aggregated LP processing unit 24) that calculates a Lorenz plot (period B unit LP data 43) for a predetermined period from the heart rate interval equivalent data (41) and outputs it as an aggregated Lorenz plot (period A unit aggregated LP data 45).

[0247] With the above configuration, an LP is generated for each period B in which no RRI data loss occurs, and these are aggregated on a period A basis, making it possible to apply knowledge about period B to period A in which RRI data loss occurs.

[0248] (2) The biological data evaluation server described in (1) above, wherein the predetermined period includes a first period (period A) and a second period (period B) shorter than the first period (period A), and the Lorenz plot generation unit (23, 24) calculates the Lorenz plot (period B unit LP data 43) from the heartbeat interval equivalent data (41) in units of the second period (period B), aggregates the Lorenz plot (43) calculated in units of the second period (period B) in units of the first period (period A), calculates the aggregated Lorenz plot (45) for the first period (period A), and outputs the aggregated Lorenz plot (45) for the first period (period A).

[0249] With the above configuration, an LP is generated for each period B in which no RRI data loss occurs, and each LP is aggregated by period A, making it possible to apply knowledge about period B that has been previously studied to period A in which RRI data loss occurs.

[0250] (3) The biological data evaluation server described in (2) above, wherein the Lorenz plot generation unit (23, 24) determines whether or not there is a loss in the heartbeat interval equivalent data (41) from the Lorenz plot (43) in units of the second period (period B), and excludes the portion of the heartbeat interval equivalent data (41) in units of the second period (period B), and then performs the aggregation process to calculate the aggregated Lorenz plot (45) in the first period (period A).

[0251] With the above configuration, in the period A unit aggregated LP generation process (S25), the chronic occurrence discrimination model learning unit 22 calls the period A unit aggregated LP processing unit 24, and the period A unit aggregated LP processing unit 24 performs an aggregation process (S25) on the period B unit LP data 43 group for period B that exists within the period A to be evaluated, i.e., that is not a data missing period, to generate period A unit aggregated LP data 45, which is an LP that quantifies the features of the RRI data for period A.

[0252] (4) A biometric data evaluation server as described in (2) above, characterized in that the Lorenz plot generation unit (23, 24) calculates statistical values ​​for each matrix element of a Lorenz plot matrix showing the plurality of Lorenz plots (43) calculated for each second period (period B) as the aggregation process, for each first period (period A).

[0253] With the above configuration, the period A unit aggregated LP processing unit 24 performs statistical processing such as averaging for each component of the LP matrix on the period B unit LP data 43 group to generate period A unit aggregated LP data 45. If there is period B unit LP data 43 in period A that has significantly different characteristics from the others, statistical processing can be added to perform aggregation processing that reduces the influence of data with different characteristics.

[0254] (5) A biometric data evaluation server as described in (2) above, characterized in that the Lorenz plot generation unit (23, 24) sets the second period (period B) to be shorter than the first period (period A) and greater than or equal to the time width required for heart rate variability analysis.

[0255] With the above configuration, the period A unit aggregated LP processing unit 24 can generate period A unit aggregated LP data 45 for performing heart rate variability analysis from period B unit LP data 43 of period B that is not a data missing period.

[0256] (6) A biometric data evaluation server as described in (2) above, characterized in that the Lorenz plot generation unit (23, 24) receives information on the time width of the loss in the heartbeat interval equivalent data (41) and determines the second period (period B) based on the information on the time width of the loss in the heartbeat interval equivalent data (41).

[0257] With the above configuration, the period B unit LP generation unit 23 determines the time width of period B based on information on the time width of missing or missing RRI data received from an input device, etc., thereby enabling generation of period B unit LP data 43 that corresponds to the measurement environment of the biometric data.

[0258] (7) A biometric data evaluation server as described in (2) above, characterized in that it further has an abnormal value chronic occurrence evaluation unit (25) that calculates features in a predefined region in the aggregated Lorenz plot (45) and calculates and outputs the degree of occurrence of arrhythmia-like abnormal values ​​as abnormality degree data based on the features.

[0259] With the above configuration, the abnormal value chronic occurrence evaluation unit 25 can input the aggregated LP feature data 47 into the chronic occurrence discrimination model 52 to calculate the probability of determining whether or not chronic occurrence exists as the chronic arrhythmia-like abnormality degree 147, and generate abnormality degree data 49.

[0260] (8) The biometric data evaluation server described in (7) above, further comprising an unsuitable person determination unit (unsuitable driver determination unit 26) that calculates the frequency of occurrence of the arrhythmia-like abnormal values ​​from the aggregated Lorenz plot (45) during a third period (period C) that is equal to or greater than the first period (period A) and determines whether the subject is suitable for autonomic nervous function evaluation.

[0261] With the above configuration, the inappropriate driver determination unit 26 can detect drivers who are considered to be consistently inappropriate for autonomic nervous function evaluation using RRI data, regardless of changes in the driver's own condition, such as health status or exercise load, thereby achieving the effect of improving the reliability of autonomic nervous function evaluation.

[0262] (9) The biometric data evaluation server described in (8) above, further comprising an autonomic nervous function index calculation unit (27) that calculates and outputs an autonomic nervous function index based on the heart rate interval equivalent data (41) of a subject suitable for the autonomic nervous function evaluation based on the judgment result of the unsuitable person judgment unit (26).

[0263] With the above configuration, the autonomic nervous function index calculation unit 27 can assign an inappropriate flag to a driver whose autonomic nervous function evaluation using RRI data is inappropriate due to steady arrhythmia, thereby reducing the possibility of misinterpreting the obtained autonomic nervous function index and improving the reliability of the autonomic nervous function evaluation.

[0264] (10) A biometric data evaluation server as described in (9) above, characterized in that it further has a warning presentation unit (30) that determines the reliability of the autonomic nervous function index based on the arrhythmia-like abnormal value and displays the reliability of the autonomic nervous function index on an output device.

[0265] With the above configuration, the warning presentation unit can prevent a decrease in reliability of alert issuance due to frequent false alerts.

[0266] (11) The biometric data evaluation server described in (10) above, further comprising a danger prediction unit (29) that calculates the probability that an accident or incident will occur to the subject within a specified time based on the autonomic nervous function index as an accident risk, and the warning presentation unit (30) issues an alert to warn of an increase in accident risk to a subject whose accident risk exceeds a specified threshold.

[0267] With the above configuration, the driver can determine whether the alert he or she has been notified of is due to low reliability of measurement data or autonomic nervous function evaluation, or whether the risk of an accident is truly increasing, thereby improving the reliability of the alert content.

Claims

1. A biometric data evaluation server having a processor and memory for evaluating biometric data, characterized in that it has a data collection unit that receives data equivalent to heartbeat intervals from the biometric data of a subject, and a Lorenz plot generation unit that calculates a Lorenz plot for a predetermined period from the data equivalent to heartbeat intervals and outputs it as an aggregated Lorenz plot.

2. A biological data evaluation server as described in claim 1, wherein the predetermined period includes a first period and a second period shorter than the first period, and the Lorenz plot generation unit calculates the Lorenz plot of the heartbeat interval equivalent data in units of the second period, aggregates the Lorenz plot calculated in units of the second period in units of the first period, calculates the aggregated Lorenz plot for the first period, and outputs the aggregated Lorenz plot for the first period.

3. A biological data evaluation server as described in claim 2, characterized in that the Lorenz plot generation unit determines whether or not there is a loss of data equivalent to the heartbeat interval from the Lorenz plot for the second period unit, excludes the portion of the data equivalent to the heartbeat interval that is lost for the second period unit, and then performs the aggregation process to calculate the aggregated Lorenz plot for the first period.

4. A biometric data evaluation server as described in claim 2, characterized in that the Lorenz plot generation unit, as the aggregation process, calculates statistical values ​​in the first period unit for each matrix element of a Lorenz plot matrix showing the multiple Lorenz plots calculated in the second period unit.

5. A biometric data evaluation server as described in claim 2, characterized in that the Lorenz plot generation unit sets the second period to be shorter than the first period and equal to or greater than the time width required for heart rate variability analysis.

6. A biometric data evaluation server as described in claim 2, characterized in that the Lorenz plot generation unit receives information on the time width of the loss of the heartbeat interval equivalent data and determines the second period based on the information on the time width of the loss of the heartbeat interval equivalent data.

7. A biometric data evaluation server as described in claim 2, further comprising an abnormal value chronic occurrence evaluation unit that calculates feature values ​​in a predefined region in the aggregated Lorenz plot, and calculates and outputs the degree of occurrence of arrhythmia-like abnormal values ​​as abnormality level data based on the feature values.

8. A biometric data evaluation server as described in claim 7, further comprising an unsuitable subject determination unit that calculates the frequency of occurrence of arrhythmia-like abnormal values ​​from the aggregated Lorenz plot during a third period equal to or greater than the first period, and determines whether the subject is suitable for autonomic nervous function evaluation.

9. A biometric data evaluation server as described in claim 8, further comprising an autonomic nervous function index calculation unit that calculates and outputs an autonomic nervous function index based on the heart rate interval equivalent data of subjects who are suitable for the autonomic nervous function evaluation, based on the judgment result of the unsuitable person judgment unit.

10. A biometric data evaluation server as described in claim 9, further comprising a warning presentation unit that determines the reliability of the autonomic nervous function index based on the arrhythmia-like abnormal value and displays the reliability of the autonomic nervous function index on an output device.

11. A biometric data evaluation server as described in claim 10, further comprising a danger prediction unit that calculates the probability that an accident or incident will occur to the subject within a specified time based on the autonomic nervous function index as an accident risk, and the warning presentation unit issues an alert to warn of an increase in accident risk to a subject whose accident risk exceeds a specified threshold.

12. A biometric data evaluation system for evaluating biometric data, comprising: a biometric data evaluation server having a processor and memory; and a mobile body having a biometric sensor, wherein the mobile body has a data collection device that detects biometric data including data equivalent to heartbeat intervals from a subject and transmits the data to the biometric data evaluation server, and the biometric data evaluation server has: a data collection unit that receives the biometric data and accepts the data equivalent to heartbeat intervals; and a Lorenz plot generation unit that calculates a Lorenz plot for a predetermined period from the data equivalent to heartbeat intervals and outputs it as an aggregated Lorenz plot.

13. A biological data evaluation system as described in claim 12, wherein the predetermined period includes a first period and a second period shorter than the first period, and the Lorenz plot generation unit calculates the Lorenz plot of the heartbeat interval equivalent data in units of the second period, aggregates the Lorenz plot calculated in units of the second period in units of the first period, calculates the aggregated Lorenz plot for the first period, and outputs the aggregated Lorenz plot for the first period.

14. A method for evaluating biological data in which a computer having a processor and memory evaluates biological data, the method comprising: a data collection step in which the computer receives data equivalent to heartbeat intervals from the biological data of a subject; and a Lorenz plot generation step in which the computer calculates a Lorenz plot for a predetermined period from the data equivalent to heartbeat intervals and outputs it as an aggregated Lorenz plot.

15. A method for evaluating biological data as described in claim 14, wherein the predetermined period includes a first period and a second period shorter than the first period, and the Lorenz plot generation step calculates the Lorenz plot of the heartbeat interval equivalent data in units of the second period, aggregates the Lorenz plot calculated in units of the second period in units of the first period, calculates the aggregated Lorenz plot for the first period, and outputs the aggregated Lorenz plot for the first period.